diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 7024b7d1126f1369d72453eab91fddb3b50c7a4e..ee8a8411b05503869c94ca0adbfa7f43414e6c4b 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -70,18 +70,25 @@ struct trace_iterator { }; +struct trace_event; + typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, - int flags); -struct trace_event { - struct hlist_node node; - struct list_head list; - int type; + int flags, struct trace_event *event); + +struct trace_event_functions { trace_print_func trace; trace_print_func raw; trace_print_func hex; trace_print_func binary; }; +struct trace_event { + struct hlist_node node; + struct list_head list; + int type; + struct trace_event_functions *funcs; +}; + extern int register_ftrace_event(struct trace_event *event); extern int unregister_ftrace_event(struct trace_event *event); @@ -113,29 +120,70 @@ void tracing_record_cmdline(struct task_struct *tsk); struct event_filter; +enum trace_reg { + TRACE_REG_REGISTER, + TRACE_REG_UNREGISTER, + TRACE_REG_PERF_REGISTER, + TRACE_REG_PERF_UNREGISTER, +}; + +struct ftrace_event_call; + +struct ftrace_event_class { + char *system; + void *probe; +#ifdef CONFIG_PERF_EVENTS + void *perf_probe; +#endif + int (*reg)(struct ftrace_event_call *event, + enum trace_reg type); + int (*define_fields)(struct ftrace_event_call *); + struct list_head *(*get_fields)(struct ftrace_event_call *); + struct list_head fields; + int (*raw_init)(struct ftrace_event_call *); +}; + +enum { + TRACE_EVENT_FL_ENABLED_BIT, + TRACE_EVENT_FL_FILTERED_BIT, +}; + +enum { + TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), + TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), +}; + struct ftrace_event_call { struct list_head list; + struct ftrace_event_class *class; char *name; - char *system; struct dentry *dir; - struct trace_event *event; - int enabled; - int (*regfunc)(struct ftrace_event_call *); - void (*unregfunc)(struct ftrace_event_call *); - int id; + struct trace_event event; const char *print_fmt; - int (*raw_init)(struct ftrace_event_call *); - int (*define_fields)(struct ftrace_event_call *); - struct list_head fields; - int filter_active; struct event_filter *filter; void *mod; void *data; + /* + * 32 bit flags: + * bit 1: enabled + * bit 2: filter_active + * + * Changes to flags must hold the event_mutex. + * + * Note: Reads of flags do not hold the event_mutex since + * they occur in critical sections. But the way flags + * is currently used, these changes do no affect the code + * except that when a change is made, it may have a slight + * delay in propagating the changes to other CPUs due to + * caching and such. + */ + unsigned int flags; + +#ifdef CONFIG_PERF_EVENTS int perf_refcount; struct hlist_head *perf_events; - int (*perf_event_enable)(struct ftrace_event_call *); - void (*perf_event_disable)(struct ftrace_event_call *); +#endif }; #define PERF_MAX_TRACE_SIZE 2048 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 057929b0a6514963b66098e9f3ff58129937ffa5..a1a86a53bc735c13cdda531309aa6c8158231909 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -103,22 +103,6 @@ struct perf_event_attr; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) -#ifdef CONFIG_PERF_EVENTS - -#define TRACE_SYS_ENTER_PERF_INIT(sname) \ - .perf_event_enable = perf_sysenter_enable, \ - .perf_event_disable = perf_sysenter_disable, - -#define TRACE_SYS_EXIT_PERF_INIT(sname) \ - .perf_event_enable = perf_sysexit_enable, \ - .perf_event_disable = perf_sysexit_disable, -#else -#define TRACE_SYS_ENTER_PERF(sname) -#define TRACE_SYS_ENTER_PERF_INIT(sname) -#define TRACE_SYS_EXIT_PERF(sname) -#define TRACE_SYS_EXIT_PERF_INIT(sname) -#endif /* CONFIG_PERF_EVENTS */ - #ifdef CONFIG_FTRACE_SYSCALLS #define __SC_STR_ADECL1(t, a) #a #define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) @@ -134,54 +118,43 @@ struct perf_event_attr; #define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) #define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) +extern struct ftrace_event_class event_class_syscall_enter; +extern struct ftrace_event_class event_class_syscall_exit; +extern struct trace_event_functions enter_syscall_print_funcs; +extern struct trace_event_functions exit_syscall_print_funcs; + #define SYSCALL_TRACE_ENTER_EVENT(sname) \ - static const struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_enter_##sname; \ - static struct trace_event enter_syscall_print_##sname = { \ - .trace = print_syscall_enter, \ - }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ - .system = "syscalls", \ - .event = &enter_syscall_print_##sname, \ - .raw_init = init_syscall_trace, \ - .define_fields = syscall_enter_define_fields, \ - .regfunc = reg_event_syscall_enter, \ - .unregfunc = unreg_event_syscall_enter, \ + .class = &event_class_syscall_enter, \ + .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_ENTER_PERF_INIT(sname) \ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ - static const struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_exit_##sname; \ - static struct trace_event exit_syscall_print_##sname = { \ - .trace = print_syscall_exit, \ - }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ - .system = "syscalls", \ - .event = &exit_syscall_print_##sname, \ - .raw_init = init_syscall_trace, \ - .define_fields = syscall_exit_define_fields, \ - .regfunc = reg_event_syscall_exit, \ - .unregfunc = unreg_event_syscall_exit, \ + .class = &event_class_syscall_exit, \ + .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_EXIT_PERF_INIT(sname) \ } #define SYSCALL_METADATA(sname, nb) \ SYSCALL_TRACE_ENTER_EVENT(sname); \ SYSCALL_TRACE_EXIT_EVENT(sname); \ - static const struct syscall_metadata __used \ + static struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ __syscall_meta_##sname = { \ @@ -191,12 +164,14 @@ struct perf_event_attr; .args = args_##sname, \ .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ + .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ + .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \ }; #define SYSCALL_DEFINE0(sname) \ SYSCALL_TRACE_ENTER_EVENT(_##sname); \ SYSCALL_TRACE_EXIT_EVENT(_##sname); \ - static const struct syscall_metadata __used \ + static struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ __syscall_meta__##sname = { \ @@ -204,6 +179,8 @@ struct perf_event_attr; .nb_args = 0, \ .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ + .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ + .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \ }; \ asmlinkage long sys_##sname(void) #else diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1d85f9a6a19926af57cfe58081822109d99a98f0..9a59d1f98cd4114948129d8e9ad95b77da27ec6d 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -20,12 +20,17 @@ struct module; struct tracepoint; +struct tracepoint_func { + void *func; + void *data; +}; + struct tracepoint { const char *name; /* Tracepoint name */ int state; /* State. */ void (*regfunc)(void); void (*unregfunc)(void); - void **funcs; + struct tracepoint_func *funcs; } __attribute__((aligned(32))); /* * Aligned on 32 bytes because it is * globally visible and gcc happily @@ -37,16 +42,19 @@ struct tracepoint { * Connect a probe to a tracepoint. * Internal API, should not be used directly. */ -extern int tracepoint_probe_register(const char *name, void *probe); +extern int tracepoint_probe_register(const char *name, void *probe, void *data); /* * Disconnect a probe from a tracepoint. * Internal API, should not be used directly. */ -extern int tracepoint_probe_unregister(const char *name, void *probe); +extern int +tracepoint_probe_unregister(const char *name, void *probe, void *data); -extern int tracepoint_probe_register_noupdate(const char *name, void *probe); -extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe); +extern int tracepoint_probe_register_noupdate(const char *name, void *probe, + void *data); +extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe, + void *data); extern void tracepoint_probe_update_all(void); struct tracepoint_iter { @@ -102,17 +110,27 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. + * + * Note, the proto and args passed in includes "__data" as the first parameter. + * The reason for this is to handle the "void" prototype. If a tracepoint + * has a "void" prototype, then it is invalid to declare a function + * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just + * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ #define __DO_TRACE(tp, proto, args) \ do { \ - void **it_func; \ + struct tracepoint_func *it_func_ptr; \ + void *it_func; \ + void *__data; \ \ rcu_read_lock_sched_notrace(); \ - it_func = rcu_dereference_sched((tp)->funcs); \ - if (it_func) { \ + it_func_ptr = rcu_dereference_sched((tp)->funcs); \ + if (it_func_ptr) { \ do { \ - ((void(*)(proto))(*it_func))(args); \ - } while (*(++it_func)); \ + it_func = (it_func_ptr)->func; \ + __data = (it_func_ptr)->data; \ + ((void(*)(proto))(it_func))(args); \ + } while ((++it_func_ptr)->func); \ } \ rcu_read_unlock_sched_notrace(); \ } while (0) @@ -122,24 +140,32 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define DECLARE_TRACE(name, proto, args) \ +#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ if (unlikely(__tracepoint_##name.state)) \ __DO_TRACE(&__tracepoint_##name, \ - TP_PROTO(proto), TP_ARGS(args)); \ + TP_PROTO(data_proto), \ + TP_ARGS(data_args)); \ + } \ + static inline int \ + register_trace_##name(void (*probe)(data_proto), void *data) \ + { \ + return tracepoint_probe_register(#name, (void *)probe, \ + data); \ } \ - static inline int register_trace_##name(void (*probe)(proto)) \ + static inline int \ + unregister_trace_##name(void (*probe)(data_proto), void *data) \ { \ - return tracepoint_probe_register(#name, (void *)probe); \ + return tracepoint_probe_unregister(#name, (void *)probe, \ + data); \ } \ - static inline int unregister_trace_##name(void (*probe)(proto)) \ + static inline void \ + check_trace_callback_type_##name(void (*cb)(data_proto)) \ { \ - return tracepoint_probe_unregister(#name, (void *)probe);\ } - #define DEFINE_TRACE_FN(name, reg, unreg) \ static const char __tpstrtab_##name[] \ __attribute__((section("__tracepoints_strings"))) = #name; \ @@ -156,18 +182,23 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, EXPORT_SYMBOL(__tracepoint_##name) #else /* !CONFIG_TRACEPOINTS */ -#define DECLARE_TRACE(name, proto, args) \ - static inline void _do_trace_##name(struct tracepoint *tp, proto) \ - { } \ +#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ - static inline int register_trace_##name(void (*probe)(proto)) \ + static inline int \ + register_trace_##name(void (*probe)(data_proto), \ + void *data) \ { \ return -ENOSYS; \ } \ - static inline int unregister_trace_##name(void (*probe)(proto)) \ + static inline int \ + unregister_trace_##name(void (*probe)(data_proto), \ + void *data) \ { \ return -ENOSYS; \ + } \ + static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \ + { \ } #define DEFINE_TRACE_FN(name, reg, unreg) @@ -176,6 +207,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, #define EXPORT_TRACEPOINT_SYMBOL(name) #endif /* CONFIG_TRACEPOINTS */ + +/* + * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype + * (void). "void" is a special value in a function prototype and can + * not be combined with other arguments. Since the DECLARE_TRACE() + * macro adds a data element at the beginning of the prototype, + * we need a way to differentiate "(void *data, proto)" from + * "(void *data, void)". The second prototype is invalid. + * + * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype + * and "void *__data" as the callback prototype. + * + * DECLARE_TRACE() passes "proto" as the tracepoint protoype and + * "void *__data, proto" as the callback prototype. + */ +#define DECLARE_TRACE_NOARGS(name) \ + __DECLARE_TRACE(name, void, , void *__data, __data) + +#define DECLARE_TRACE(name, proto, args) \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 4eb2148f13216b0d06c15b28891a76460812fbef..0152b8673bd7a35517980b5a040ae4b000182d91 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -62,7 +62,10 @@ struct trace_entry ent; \ tstruct \ char __data[0]; \ - }; + }; \ + \ + static struct ftrace_event_class event_class_##name; + #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) \ static struct ftrace_event_call \ @@ -147,7 +150,7 @@ * * entry = iter->ent; * - * if (entry->type != event_.id) { + * if (entry->type != event_->event.type) { * WARN_ON_ONCE(1); * return TRACE_TYPE_UNHANDLED; * } @@ -203,18 +206,22 @@ #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace enum print_line_t \ -ftrace_raw_output_id_##call(int event_id, const char *name, \ - struct trace_iterator *iter, int flags) \ +ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ + struct trace_event *trace_event) \ { \ + struct ftrace_event_call *event; \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##call *field; \ struct trace_entry *entry; \ struct trace_seq *p; \ int ret; \ \ + event = container_of(trace_event, struct ftrace_event_call, \ + event); \ + \ entry = iter->ent; \ \ - if (entry->type != event_id) { \ + if (entry->type != event->event.type) { \ WARN_ON_ONCE(1); \ return TRACE_TYPE_UNHANDLED; \ } \ @@ -223,7 +230,7 @@ ftrace_raw_output_id_##call(int event_id, const char *name, \ \ p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ - ret = trace_seq_printf(s, "%s: ", name); \ + ret = trace_seq_printf(s, "%s: ", event->name); \ if (ret) \ ret = trace_seq_printf(s, print); \ put_cpu(); \ @@ -231,21 +238,16 @@ ftrace_raw_output_id_##call(int event_id, const char *name, \ return TRACE_TYPE_PARTIAL_LINE; \ \ return TRACE_TYPE_HANDLED; \ -} - -#undef DEFINE_EVENT -#define DEFINE_EVENT(template, name, proto, args) \ -static notrace enum print_line_t \ -ftrace_raw_output_##name(struct trace_iterator *iter, int flags) \ -{ \ - return ftrace_raw_output_id_##template(event_##name.id, \ - #name, iter, flags); \ -} +} \ +static struct trace_event_functions ftrace_event_type_funcs_##call = { \ + .trace = ftrace_raw_output_##call, \ +}; #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ static notrace enum print_line_t \ -ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ +ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ + struct trace_event *event) \ { \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##template *field; \ @@ -255,7 +257,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ \ entry = iter->ent; \ \ - if (entry->type != event_##call.id) { \ + if (entry->type != event_##call.event.type) { \ WARN_ON_ONCE(1); \ return TRACE_TYPE_UNHANDLED; \ } \ @@ -272,7 +274,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ return TRACE_TYPE_PARTIAL_LINE; \ \ return TRACE_TYPE_HANDLED; \ -} +} \ +static struct trace_event_functions ftrace_event_type_funcs_##call = { \ + .trace = ftrace_raw_output_##call, \ +}; #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -378,80 +383,18 @@ static inline notrace int ftrace_get_offsets_##call( \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#ifdef CONFIG_PERF_EVENTS - -/* - * Generate the functions needed for tracepoint perf_event support. - * - * NOTE: The insertion profile callback (ftrace_profile_) is defined later - * - * static int ftrace_profile_enable_(void) - * { - * return register_trace_(ftrace_profile_); - * } - * - * static void ftrace_profile_disable_(void) - * { - * unregister_trace_(ftrace_profile_); - * } - * - */ - -#undef DECLARE_EVENT_CLASS -#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) - -#undef DEFINE_EVENT -#define DEFINE_EVENT(template, name, proto, args) \ - \ -static void perf_trace_##name(proto); \ - \ -static notrace int \ -perf_trace_enable_##name(struct ftrace_event_call *unused) \ -{ \ - return register_trace_##name(perf_trace_##name); \ -} \ - \ -static notrace void \ -perf_trace_disable_##name(struct ftrace_event_call *unused) \ -{ \ - unregister_trace_##name(perf_trace_##name); \ -} - -#undef DEFINE_EVENT_PRINT -#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ - DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) - -#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) - -#endif /* CONFIG_PERF_EVENTS */ - /* * Stage 4 of the trace events. * * Override the macros in to include the following: * - * static void ftrace_event_(proto) - * { - * event_trace_printk(_RET_IP_, ": " ); - * } - * - * static int ftrace_reg_event_(struct ftrace_event_call *unused) - * { - * return register_trace_(ftrace_event_); - * } - * - * static void ftrace_unreg_event_(struct ftrace_event_call *unused) - * { - * unregister_trace_(ftrace_event_); - * } - * - * * For those macros defined with TRACE_EVENT: * * static struct ftrace_event_call event_; * - * static void ftrace_raw_event_(proto) + * static void ftrace_raw_event_(void *__data, proto) * { + * struct ftrace_event_call *event_call = __data; * struct ftrace_data_offsets_ __maybe_unused __data_offsets; * struct ring_buffer_event *event; * struct ftrace_raw_ *entry; <-- defined in stage 1 @@ -466,7 +409,7 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \ * __data_size = ftrace_get_offsets_(&__data_offsets, args); * * event = trace_current_buffer_lock_reserve(&buffer, - * event_.id, + * event_->event.type, * sizeof(*entry) + __data_size, * irq_flags, pc); * if (!event) @@ -481,43 +424,42 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \ * event, irq_flags, pc); * } * - * static int ftrace_raw_reg_event_(struct ftrace_event_call *unused) - * { - * return register_trace_(ftrace_raw_event_); - * } - * - * static void ftrace_unreg_event_(struct ftrace_event_call *unused) - * { - * unregister_trace_(ftrace_raw_event_); - * } - * * static struct trace_event ftrace_event_type_ = { * .trace = ftrace_raw_output_, <-- stage 2 * }; * * static const char print_fmt_[] = ; * + * static struct ftrace_event_class __used event_class_