yuezonghe | 824eb0c | 2024-06-27 02:32:26 -0700 | [diff] [blame] | 1 | #include <trace/syscall.h> |
| 2 | #include <trace/events/syscalls.h> |
| 3 | #include <linux/slab.h> |
| 4 | #include <linux/kernel.h> |
| 5 | #include <linux/module.h> /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */ |
| 6 | #include <linux/ftrace.h> |
| 7 | #include <linux/perf_event.h> |
| 8 | #include <asm/syscall.h> |
| 9 | |
| 10 | #include "trace_output.h" |
| 11 | #include "trace.h" |
| 12 | |
| 13 | static DEFINE_MUTEX(syscall_trace_lock); |
| 14 | static int sys_refcount_enter; |
| 15 | static int sys_refcount_exit; |
| 16 | static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); |
| 17 | static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); |
| 18 | |
| 19 | static int syscall_enter_register(struct ftrace_event_call *event, |
| 20 | enum trace_reg type, void *data); |
| 21 | static int syscall_exit_register(struct ftrace_event_call *event, |
| 22 | enum trace_reg type, void *data); |
| 23 | |
| 24 | static int syscall_enter_define_fields(struct ftrace_event_call *call); |
| 25 | static int syscall_exit_define_fields(struct ftrace_event_call *call); |
| 26 | |
| 27 | static struct list_head * |
| 28 | syscall_get_enter_fields(struct ftrace_event_call *call) |
| 29 | { |
| 30 | struct syscall_metadata *entry = call->data; |
| 31 | |
| 32 | return &entry->enter_fields; |
| 33 | } |
| 34 | |
| 35 | struct trace_event_functions enter_syscall_print_funcs = { |
| 36 | .trace = print_syscall_enter, |
| 37 | }; |
| 38 | |
| 39 | struct trace_event_functions exit_syscall_print_funcs = { |
| 40 | .trace = print_syscall_exit, |
| 41 | }; |
| 42 | |
| 43 | struct ftrace_event_class event_class_syscall_enter = { |
| 44 | .system = "syscalls", |
| 45 | .reg = syscall_enter_register, |
| 46 | .define_fields = syscall_enter_define_fields, |
| 47 | .get_fields = syscall_get_enter_fields, |
| 48 | .raw_init = init_syscall_trace, |
| 49 | }; |
| 50 | |
| 51 | struct ftrace_event_class event_class_syscall_exit = { |
| 52 | .system = "syscalls", |
| 53 | .reg = syscall_exit_register, |
| 54 | .define_fields = syscall_exit_define_fields, |
| 55 | .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), |
| 56 | .raw_init = init_syscall_trace, |
| 57 | }; |
| 58 | |
| 59 | extern struct syscall_metadata *__start_syscalls_metadata[]; |
| 60 | extern struct syscall_metadata *__stop_syscalls_metadata[]; |
| 61 | |
| 62 | static struct syscall_metadata **syscalls_metadata; |
| 63 | |
| 64 | #ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME |
| 65 | static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) |
| 66 | { |
| 67 | /* |
| 68 | * Only compare after the "sys" prefix. Archs that use |
| 69 | * syscall wrappers may have syscalls symbols aliases prefixed |
| 70 | * with "SyS" instead of "sys", leading to an unwanted |
| 71 | * mismatch. |
| 72 | */ |
| 73 | return !strcmp(sym + 3, name + 3); |
| 74 | } |
| 75 | #endif |
| 76 | |
| 77 | static __init struct syscall_metadata * |
| 78 | find_syscall_meta(unsigned long syscall) |
| 79 | { |
| 80 | struct syscall_metadata **start; |
| 81 | struct syscall_metadata **stop; |
| 82 | char str[KSYM_SYMBOL_LEN]; |
| 83 | |
| 84 | |
| 85 | start = __start_syscalls_metadata; |
| 86 | stop = __stop_syscalls_metadata; |
| 87 | kallsyms_lookup(syscall, NULL, NULL, NULL, str); |
| 88 | |
| 89 | if (arch_syscall_match_sym_name(str, "sys_ni_syscall")) |
| 90 | return NULL; |
| 91 | |
| 92 | for ( ; start < stop; start++) { |
| 93 | if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name)) |
| 94 | return *start; |
| 95 | } |
| 96 | return NULL; |
| 97 | } |
| 98 | |
| 99 | static struct syscall_metadata *syscall_nr_to_meta(int nr) |
| 100 | { |
| 101 | if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) |
| 102 | return NULL; |
| 103 | |
| 104 | return syscalls_metadata[nr]; |
| 105 | } |
| 106 | |
| 107 | enum print_line_t |
| 108 | print_syscall_enter(struct trace_iterator *iter, int flags, |
| 109 | struct trace_event *event) |
| 110 | { |
| 111 | struct trace_seq *s = &iter->seq; |
| 112 | struct trace_entry *ent = iter->ent; |
| 113 | struct syscall_trace_enter *trace; |
| 114 | struct syscall_metadata *entry; |
| 115 | int i, ret, syscall; |
| 116 | |
| 117 | trace = (typeof(trace))ent; |
| 118 | syscall = trace->nr; |
| 119 | entry = syscall_nr_to_meta(syscall); |
| 120 | |
| 121 | if (!entry) |
| 122 | goto end; |
| 123 | |
| 124 | if (entry->enter_event->event.type != ent->type) { |
| 125 | WARN_ON_ONCE(1); |
| 126 | goto end; |
| 127 | } |
| 128 | |
| 129 | ret = trace_seq_printf(s, "%s(", entry->name); |
| 130 | if (!ret) |
| 131 | return TRACE_TYPE_PARTIAL_LINE; |
| 132 | |
| 133 | for (i = 0; i < entry->nb_args; i++) { |
| 134 | /* parameter types */ |
| 135 | if (trace_flags & TRACE_ITER_VERBOSE) { |
| 136 | ret = trace_seq_printf(s, "%s ", entry->types[i]); |
| 137 | if (!ret) |
| 138 | return TRACE_TYPE_PARTIAL_LINE; |
| 139 | } |
| 140 | /* parameter values */ |
| 141 | ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i], |
| 142 | trace->args[i], |
| 143 | i == entry->nb_args - 1 ? "" : ", "); |
| 144 | if (!ret) |
| 145 | return TRACE_TYPE_PARTIAL_LINE; |
| 146 | } |
| 147 | |
| 148 | ret = trace_seq_putc(s, ')'); |
| 149 | if (!ret) |
| 150 | return TRACE_TYPE_PARTIAL_LINE; |
| 151 | |
| 152 | end: |
| 153 | ret = trace_seq_putc(s, '\n'); |
| 154 | if (!ret) |
| 155 | return TRACE_TYPE_PARTIAL_LINE; |
| 156 | |
| 157 | return TRACE_TYPE_HANDLED; |
| 158 | } |
| 159 | |
| 160 | enum print_line_t |
| 161 | print_syscall_exit(struct trace_iterator *iter, int flags, |
| 162 | struct trace_event *event) |
| 163 | { |
| 164 | struct trace_seq *s = &iter->seq; |
| 165 | struct trace_entry *ent = iter->ent; |
| 166 | struct syscall_trace_exit *trace; |
| 167 | int syscall; |
| 168 | struct syscall_metadata *entry; |
| 169 | int ret; |
| 170 | |
| 171 | trace = (typeof(trace))ent; |
| 172 | syscall = trace->nr; |
| 173 | entry = syscall_nr_to_meta(syscall); |
| 174 | |
| 175 | if (!entry) { |
| 176 | trace_seq_printf(s, "\n"); |
| 177 | return TRACE_TYPE_HANDLED; |
| 178 | } |
| 179 | |
| 180 | if (entry->exit_event->event.type != ent->type) { |
| 181 | WARN_ON_ONCE(1); |
| 182 | return TRACE_TYPE_UNHANDLED; |
| 183 | } |
| 184 | |
| 185 | ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name, |
| 186 | trace->ret); |
| 187 | if (!ret) |
| 188 | return TRACE_TYPE_PARTIAL_LINE; |
| 189 | |
| 190 | return TRACE_TYPE_HANDLED; |
| 191 | } |
| 192 | |
| 193 | extern char *__bad_type_size(void); |
| 194 | |
| 195 | #define SYSCALL_FIELD(type, name) \ |
| 196 | sizeof(type) != sizeof(trace.name) ? \ |
| 197 | __bad_type_size() : \ |
| 198 | #type, #name, offsetof(typeof(trace), name), \ |
| 199 | sizeof(trace.name), is_signed_type(type) |
| 200 | |
| 201 | static |
| 202 | int __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) |
| 203 | { |
| 204 | int i; |
| 205 | int pos = 0; |
| 206 | |
| 207 | /* When len=0, we just calculate the needed length */ |
| 208 | #define LEN_OR_ZERO (len ? len - pos : 0) |
| 209 | |
| 210 | pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); |
| 211 | for (i = 0; i < entry->nb_args; i++) { |
| 212 | pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s", |
| 213 | entry->args[i], sizeof(unsigned long), |
| 214 | i == entry->nb_args - 1 ? "" : ", "); |
| 215 | } |
| 216 | pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); |
| 217 | |
| 218 | for (i = 0; i < entry->nb_args; i++) { |
| 219 | pos += snprintf(buf + pos, LEN_OR_ZERO, |
| 220 | ", ((unsigned long)(REC->%s))", entry->args[i]); |
| 221 | } |
| 222 | |
| 223 | #undef LEN_OR_ZERO |
| 224 | |
| 225 | /* return the length of print_fmt */ |
| 226 | return pos; |
| 227 | } |
| 228 | |
| 229 | static int set_syscall_print_fmt(struct ftrace_event_call *call) |
| 230 | { |
| 231 | char *print_fmt; |
| 232 | int len; |
| 233 | struct syscall_metadata *entry = call->data; |
| 234 | |
| 235 | if (entry->enter_event != call) { |
| 236 | call->print_fmt = "\"0x%lx\", REC->ret"; |
| 237 | return 0; |
| 238 | } |
| 239 | |
| 240 | /* First: called with 0 length to calculate the needed length */ |
| 241 | len = __set_enter_print_fmt(entry, NULL, 0); |
| 242 | |
| 243 | print_fmt = kmalloc(len + 1, GFP_KERNEL); |
| 244 | if (!print_fmt) |
| 245 | return -ENOMEM; |
| 246 | |
| 247 | /* Second: actually write the @print_fmt */ |
| 248 | __set_enter_print_fmt(entry, print_fmt, len + 1); |
| 249 | call->print_fmt = print_fmt; |
| 250 | |
| 251 | return 0; |
| 252 | } |
| 253 | |
| 254 | static void free_syscall_print_fmt(struct ftrace_event_call *call) |
| 255 | { |
| 256 | struct syscall_metadata *entry = call->data; |
| 257 | |
| 258 | if (entry->enter_event == call) |
| 259 | kfree(call->print_fmt); |
| 260 | } |
| 261 | |
| 262 | static int syscall_enter_define_fields(struct ftrace_event_call *call) |
| 263 | { |
| 264 | struct syscall_trace_enter trace; |
| 265 | struct syscall_metadata *meta = call->data; |
| 266 | int ret; |
| 267 | int i; |
| 268 | int offset = offsetof(typeof(trace), args); |
| 269 | |
| 270 | ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); |
| 271 | if (ret) |
| 272 | return ret; |
| 273 | |
| 274 | for (i = 0; i < meta->nb_args; i++) { |
| 275 | ret = trace_define_field(call, meta->types[i], |
| 276 | meta->args[i], offset, |
| 277 | sizeof(unsigned long), 0, |
| 278 | FILTER_OTHER); |
| 279 | offset += sizeof(unsigned long); |
| 280 | } |
| 281 | |
| 282 | return ret; |
| 283 | } |
| 284 | |
| 285 | static int syscall_exit_define_fields(struct ftrace_event_call *call) |
| 286 | { |
| 287 | struct syscall_trace_exit trace; |
| 288 | int ret; |
| 289 | |
| 290 | ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); |
| 291 | if (ret) |
| 292 | return ret; |
| 293 | |
| 294 | ret = trace_define_field(call, SYSCALL_FIELD(long, ret), |
| 295 | FILTER_OTHER); |
| 296 | |
| 297 | return ret; |
| 298 | } |
| 299 | |
| 300 | void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) |
| 301 | { |
| 302 | struct syscall_trace_enter *entry; |
| 303 | struct syscall_metadata *sys_data; |
| 304 | struct ring_buffer_event *event; |
| 305 | struct ring_buffer *buffer; |
| 306 | int size; |
| 307 | int syscall_nr; |
| 308 | unsigned long irq_flags; |
| 309 | int pc; |
| 310 | |
| 311 | syscall_nr = syscall_get_nr(current, regs); |
| 312 | if (syscall_nr < 0 || syscall_nr >= NR_syscalls) |
| 313 | return; |
| 314 | if (!test_bit(syscall_nr, enabled_enter_syscalls)) |
| 315 | return; |
| 316 | |
| 317 | sys_data = syscall_nr_to_meta(syscall_nr); |
| 318 | if (!sys_data) |
| 319 | return; |
| 320 | |
| 321 | size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; |
| 322 | |
| 323 | local_save_flags(irq_flags); |
| 324 | pc = preempt_count(); |
| 325 | |
| 326 | event = trace_current_buffer_lock_reserve(&buffer, |
| 327 | sys_data->enter_event->event.type, size, irq_flags, pc); |
| 328 | if (!event) |
| 329 | return; |
| 330 | |
| 331 | entry = ring_buffer_event_data(event); |
| 332 | entry->nr = syscall_nr; |
| 333 | syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); |
| 334 | |
| 335 | if (!filter_current_check_discard(buffer, sys_data->enter_event, |
| 336 | entry, event)) |
| 337 | trace_current_buffer_unlock_commit(buffer, event, |
| 338 | irq_flags, pc); |
| 339 | } |
| 340 | |
| 341 | void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) |
| 342 | { |
| 343 | struct syscall_trace_exit *entry; |
| 344 | struct syscall_metadata *sys_data; |
| 345 | struct ring_buffer_event *event; |
| 346 | struct ring_buffer *buffer; |
| 347 | int syscall_nr; |
| 348 | unsigned long irq_flags; |
| 349 | int pc; |
| 350 | |
| 351 | syscall_nr = syscall_get_nr(current, regs); |
| 352 | if (syscall_nr < 0 || syscall_nr >= NR_syscalls) |
| 353 | return; |
| 354 | if (!test_bit(syscall_nr, enabled_exit_syscalls)) |
| 355 | return; |
| 356 | |
| 357 | sys_data = syscall_nr_to_meta(syscall_nr); |
| 358 | if (!sys_data) |
| 359 | return; |
| 360 | |
| 361 | local_save_flags(irq_flags); |
| 362 | pc = preempt_count(); |
| 363 | |
| 364 | event = trace_current_buffer_lock_reserve(&buffer, |
| 365 | sys_data->exit_event->event.type, sizeof(*entry), |
| 366 | irq_flags, pc); |
| 367 | if (!event) |
| 368 | return; |
| 369 | |
| 370 | entry = ring_buffer_event_data(event); |
| 371 | entry->nr = syscall_nr; |
| 372 | entry->ret = syscall_get_return_value(current, regs); |
| 373 | |
| 374 | if (!filter_current_check_discard(buffer, sys_data->exit_event, |
| 375 | entry, event)) |
| 376 | trace_current_buffer_unlock_commit(buffer, event, |
| 377 | irq_flags, pc); |
| 378 | } |
| 379 | |
| 380 | int reg_event_syscall_enter(struct ftrace_event_call *call) |
| 381 | { |
| 382 | int ret = 0; |
| 383 | int num; |
| 384 | |
| 385 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 386 | if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) |
| 387 | return -ENOSYS; |
| 388 | mutex_lock(&syscall_trace_lock); |
| 389 | if (!sys_refcount_enter) |
| 390 | ret = register_trace_sys_enter(ftrace_syscall_enter, NULL); |
| 391 | if (!ret) { |
| 392 | set_bit(num, enabled_enter_syscalls); |
| 393 | sys_refcount_enter++; |
| 394 | } |
| 395 | mutex_unlock(&syscall_trace_lock); |
| 396 | return ret; |
| 397 | } |
| 398 | |
| 399 | void unreg_event_syscall_enter(struct ftrace_event_call *call) |
| 400 | { |
| 401 | int num; |
| 402 | |
| 403 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 404 | if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) |
| 405 | return; |
| 406 | mutex_lock(&syscall_trace_lock); |
| 407 | sys_refcount_enter--; |
| 408 | clear_bit(num, enabled_enter_syscalls); |
| 409 | if (!sys_refcount_enter) |
| 410 | unregister_trace_sys_enter(ftrace_syscall_enter, NULL); |
| 411 | mutex_unlock(&syscall_trace_lock); |
| 412 | } |
| 413 | |
| 414 | int reg_event_syscall_exit(struct ftrace_event_call *call) |
| 415 | { |
| 416 | int ret = 0; |
| 417 | int num; |
| 418 | |
| 419 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 420 | if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) |
| 421 | return -ENOSYS; |
| 422 | mutex_lock(&syscall_trace_lock); |
| 423 | if (!sys_refcount_exit) |
| 424 | ret = register_trace_sys_exit(ftrace_syscall_exit, NULL); |
| 425 | if (!ret) { |
| 426 | set_bit(num, enabled_exit_syscalls); |
| 427 | sys_refcount_exit++; |
| 428 | } |
| 429 | mutex_unlock(&syscall_trace_lock); |
| 430 | return ret; |
| 431 | } |
| 432 | |
| 433 | void unreg_event_syscall_exit(struct ftrace_event_call *call) |
| 434 | { |
| 435 | int num; |
| 436 | |
| 437 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 438 | if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) |
| 439 | return; |
| 440 | mutex_lock(&syscall_trace_lock); |
| 441 | sys_refcount_exit--; |
| 442 | clear_bit(num, enabled_exit_syscalls); |
| 443 | if (!sys_refcount_exit) |
| 444 | unregister_trace_sys_exit(ftrace_syscall_exit, NULL); |
| 445 | mutex_unlock(&syscall_trace_lock); |
| 446 | } |
| 447 | |
| 448 | int init_syscall_trace(struct ftrace_event_call *call) |
| 449 | { |
| 450 | int id; |
| 451 | int num; |
| 452 | |
| 453 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 454 | if (num < 0 || num >= NR_syscalls) { |
| 455 | pr_debug("syscall %s metadata not mapped, disabling ftrace event\n", |
| 456 | ((struct syscall_metadata *)call->data)->name); |
| 457 | return -ENOSYS; |
| 458 | } |
| 459 | |
| 460 | if (set_syscall_print_fmt(call) < 0) |
| 461 | return -ENOMEM; |
| 462 | |
| 463 | id = trace_event_raw_init(call); |
| 464 | |
| 465 | if (id < 0) { |
| 466 | free_syscall_print_fmt(call); |
| 467 | return id; |
| 468 | } |
| 469 | |
| 470 | return id; |
| 471 | } |
| 472 | |
| 473 | unsigned long __init __weak arch_syscall_addr(int nr) |
| 474 | { |
| 475 | return (unsigned long)sys_call_table[nr]; |
| 476 | } |
| 477 | |
| 478 | int __init init_ftrace_syscalls(void) |
| 479 | { |
| 480 | struct syscall_metadata *meta; |
| 481 | unsigned long addr; |
| 482 | int i; |
| 483 | |
| 484 | syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata), |
| 485 | GFP_KERNEL); |
| 486 | if (!syscalls_metadata) { |
| 487 | WARN_ON(1); |
| 488 | return -ENOMEM; |
| 489 | } |
| 490 | |
| 491 | for (i = 0; i < NR_syscalls; i++) { |
| 492 | addr = arch_syscall_addr(i); |
| 493 | meta = find_syscall_meta(addr); |
| 494 | if (!meta) |
| 495 | continue; |
| 496 | |
| 497 | meta->syscall_nr = i; |
| 498 | syscalls_metadata[i] = meta; |
| 499 | } |
| 500 | |
| 501 | return 0; |
| 502 | } |
| 503 | core_initcall(init_ftrace_syscalls); |
| 504 | |
| 505 | #ifdef CONFIG_PERF_EVENTS |
| 506 | |
| 507 | static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls); |
| 508 | static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); |
| 509 | static int sys_perf_refcount_enter; |
| 510 | static int sys_perf_refcount_exit; |
| 511 | |
| 512 | static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) |
| 513 | { |
| 514 | struct syscall_metadata *sys_data; |
| 515 | struct syscall_trace_enter *rec; |
| 516 | struct hlist_head *head; |
| 517 | int syscall_nr; |
| 518 | int rctx; |
| 519 | int size; |
| 520 | |
| 521 | syscall_nr = syscall_get_nr(current, regs); |
| 522 | if (syscall_nr < 0 || syscall_nr >= NR_syscalls) |
| 523 | return; |
| 524 | if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) |
| 525 | return; |
| 526 | |
| 527 | sys_data = syscall_nr_to_meta(syscall_nr); |
| 528 | if (!sys_data) |
| 529 | return; |
| 530 | |
| 531 | /* get the size after alignment with the u32 buffer size field */ |
| 532 | size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec); |
| 533 | size = ALIGN(size + sizeof(u32), sizeof(u64)); |
| 534 | size -= sizeof(u32); |
| 535 | |
| 536 | if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, |
| 537 | "perf buffer not large enough")) |
| 538 | return; |
| 539 | |
| 540 | rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, |
| 541 | sys_data->enter_event->event.type, regs, &rctx); |
| 542 | if (!rec) |
| 543 | return; |
| 544 | |
| 545 | rec->nr = syscall_nr; |
| 546 | syscall_get_arguments(current, regs, 0, sys_data->nb_args, |
| 547 | (unsigned long *)&rec->args); |
| 548 | |
| 549 | head = this_cpu_ptr(sys_data->enter_event->perf_events); |
| 550 | perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); |
| 551 | } |
| 552 | |
| 553 | int perf_sysenter_enable(struct ftrace_event_call *call) |
| 554 | { |
| 555 | int ret = 0; |
| 556 | int num; |
| 557 | |
| 558 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 559 | |
| 560 | mutex_lock(&syscall_trace_lock); |
| 561 | if (!sys_perf_refcount_enter) |
| 562 | ret = register_trace_sys_enter(perf_syscall_enter, NULL); |
| 563 | if (ret) { |
| 564 | pr_info("event trace: Could not activate" |
| 565 | "syscall entry trace point"); |
| 566 | } else { |
| 567 | set_bit(num, enabled_perf_enter_syscalls); |
| 568 | sys_perf_refcount_enter++; |
| 569 | } |
| 570 | mutex_unlock(&syscall_trace_lock); |
| 571 | return ret; |
| 572 | } |
| 573 | |
| 574 | void perf_sysenter_disable(struct ftrace_event_call *call) |
| 575 | { |
| 576 | int num; |
| 577 | |
| 578 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 579 | |
| 580 | mutex_lock(&syscall_trace_lock); |
| 581 | sys_perf_refcount_enter--; |
| 582 | clear_bit(num, enabled_perf_enter_syscalls); |
| 583 | if (!sys_perf_refcount_enter) |
| 584 | unregister_trace_sys_enter(perf_syscall_enter, NULL); |
| 585 | mutex_unlock(&syscall_trace_lock); |
| 586 | } |
| 587 | |
| 588 | static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) |
| 589 | { |
| 590 | struct syscall_metadata *sys_data; |
| 591 | struct syscall_trace_exit *rec; |
| 592 | struct hlist_head *head; |
| 593 | int syscall_nr; |
| 594 | int rctx; |
| 595 | int size; |
| 596 | |
| 597 | syscall_nr = syscall_get_nr(current, regs); |
| 598 | if (syscall_nr < 0 || syscall_nr >= NR_syscalls) |
| 599 | return; |
| 600 | if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) |
| 601 | return; |
| 602 | |
| 603 | sys_data = syscall_nr_to_meta(syscall_nr); |
| 604 | if (!sys_data) |
| 605 | return; |
| 606 | |
| 607 | /* We can probably do that at build time */ |
| 608 | size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); |
| 609 | size -= sizeof(u32); |
| 610 | |
| 611 | /* |
| 612 | * Impossible, but be paranoid with the future |
| 613 | * How to put this check outside runtime? |
| 614 | */ |
| 615 | if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, |
| 616 | "exit event has grown above perf buffer size")) |
| 617 | return; |
| 618 | |
| 619 | rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, |
| 620 | sys_data->exit_event->event.type, regs, &rctx); |
| 621 | if (!rec) |
| 622 | return; |
| 623 | |
| 624 | rec->nr = syscall_nr; |
| 625 | rec->ret = syscall_get_return_value(current, regs); |
| 626 | |
| 627 | head = this_cpu_ptr(sys_data->exit_event->perf_events); |
| 628 | perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); |
| 629 | } |
| 630 | |
| 631 | int perf_sysexit_enable(struct ftrace_event_call *call) |
| 632 | { |
| 633 | int ret = 0; |
| 634 | int num; |
| 635 | |
| 636 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 637 | |
| 638 | mutex_lock(&syscall_trace_lock); |
| 639 | if (!sys_perf_refcount_exit) |
| 640 | ret = register_trace_sys_exit(perf_syscall_exit, NULL); |
| 641 | if (ret) { |
| 642 | pr_info("event trace: Could not activate" |
| 643 | "syscall exit trace point"); |
| 644 | } else { |
| 645 | set_bit(num, enabled_perf_exit_syscalls); |
| 646 | sys_perf_refcount_exit++; |
| 647 | } |
| 648 | mutex_unlock(&syscall_trace_lock); |
| 649 | return ret; |
| 650 | } |
| 651 | |
| 652 | void perf_sysexit_disable(struct ftrace_event_call *call) |
| 653 | { |
| 654 | int num; |
| 655 | |
| 656 | num = ((struct syscall_metadata *)call->data)->syscall_nr; |
| 657 | |
| 658 | mutex_lock(&syscall_trace_lock); |
| 659 | sys_perf_refcount_exit--; |
| 660 | clear_bit(num, enabled_perf_exit_syscalls); |
| 661 | if (!sys_perf_refcount_exit) |
| 662 | unregister_trace_sys_exit(perf_syscall_exit, NULL); |
| 663 | mutex_unlock(&syscall_trace_lock); |
| 664 | } |
| 665 | |
| 666 | #endif /* CONFIG_PERF_EVENTS */ |
| 667 | |
| 668 | static int syscall_enter_register(struct ftrace_event_call *event, |
| 669 | enum trace_reg type, void *data) |
| 670 | { |
| 671 | switch (type) { |
| 672 | case TRACE_REG_REGISTER: |
| 673 | return reg_event_syscall_enter(event); |
| 674 | case TRACE_REG_UNREGISTER: |
| 675 | unreg_event_syscall_enter(event); |
| 676 | return 0; |
| 677 | |
| 678 | #ifdef CONFIG_PERF_EVENTS |
| 679 | case TRACE_REG_PERF_REGISTER: |
| 680 | return perf_sysenter_enable(event); |
| 681 | case TRACE_REG_PERF_UNREGISTER: |
| 682 | perf_sysenter_disable(event); |
| 683 | return 0; |
| 684 | case TRACE_REG_PERF_OPEN: |
| 685 | case TRACE_REG_PERF_CLOSE: |
| 686 | case TRACE_REG_PERF_ADD: |
| 687 | case TRACE_REG_PERF_DEL: |
| 688 | return 0; |
| 689 | #endif |
| 690 | } |
| 691 | return 0; |
| 692 | } |
| 693 | |
| 694 | static int syscall_exit_register(struct ftrace_event_call *event, |
| 695 | enum trace_reg type, void *data) |
| 696 | { |
| 697 | switch (type) { |
| 698 | case TRACE_REG_REGISTER: |
| 699 | return reg_event_syscall_exit(event); |
| 700 | case TRACE_REG_UNREGISTER: |
| 701 | unreg_event_syscall_exit(event); |
| 702 | return 0; |
| 703 | |
| 704 | #ifdef CONFIG_PERF_EVENTS |
| 705 | case TRACE_REG_PERF_REGISTER: |
| 706 | return perf_sysexit_enable(event); |
| 707 | case TRACE_REG_PERF_UNREGISTER: |
| 708 | perf_sysexit_disable(event); |
| 709 | return 0; |
| 710 | case TRACE_REG_PERF_OPEN: |
| 711 | case TRACE_REG_PERF_CLOSE: |
| 712 | case TRACE_REG_PERF_ADD: |
| 713 | case TRACE_REG_PERF_DEL: |
| 714 | return 0; |
| 715 | #endif |
| 716 | } |
| 717 | return 0; |
| 718 | } |