/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_TRACEPOINT_H #define _LINUX_TRACEPOINT_H /* * Kernel Tracepoint API. * * See Documentation/trace/tracepoints.rst. * * Copyright (C) 2008-2014 Mathieu Desnoyers <[email protected]> * * Heavily inspired from the Linux Kernel Markers. */ #include <linux/smp.h> #include <linux/srcu.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/tracepoint-defs.h> #include <linux/static_call.h> struct module; struct tracepoint; struct notifier_block; struct trace_eval_map { … }; #define TRACEPOINT_DEFAULT_PRIO … extern struct srcu_struct tracepoint_srcu; extern int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data); extern int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data, int prio); extern int tracepoint_probe_register_prio_may_exist(struct tracepoint *tp, void *probe, void *data, int prio); extern int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data); static inline int tracepoint_probe_register_may_exist(struct tracepoint *tp, void *probe, void *data) { … } extern void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), void *priv); #ifdef CONFIG_MODULES struct tp_module { … }; bool trace_module_has_bad_taint(struct module *mod); extern int register_tracepoint_module_notifier(struct notifier_block *nb); extern int unregister_tracepoint_module_notifier(struct notifier_block *nb); void for_each_module_tracepoint(void (*fct)(struct tracepoint *, struct module *, void *), void *priv); void for_each_tracepoint_in_module(struct module *, void (*fct)(struct tracepoint *, struct module *, void *), void *priv); #else static inline bool trace_module_has_bad_taint(struct module *mod) { return false; } static inline int register_tracepoint_module_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_tracepoint_module_notifier(struct notifier_block *nb) { return 0; } static inline void for_each_module_tracepoint(void (*fct)(struct tracepoint *, struct module *, void *), void *priv) { } static inline void for_each_tracepoint_in_module(struct module *mod, void (*fct)(struct tracepoint *, struct module *, void *), void *priv) { } #endif /* CONFIG_MODULES */ /* * tracepoint_synchronize_unregister must be called between the last tracepoint * probe unregistration and the end of module exit to make sure there is no * caller executing a probe when it is freed. */ #ifdef CONFIG_TRACEPOINTS static inline void tracepoint_synchronize_unregister(void) { … } #else static inline void tracepoint_synchronize_unregister(void) { } #endif #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS extern int syscall_regfunc(void); extern void syscall_unregfunc(void); #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */ #ifndef PARAMS #define PARAMS(args...) … #endif #define TRACE_DEFINE_ENUM(x) … #define TRACE_DEFINE_SIZEOF(x) … #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { … } #define __TRACEPOINT_ENTRY(name) … #else static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { return *p; } #define __TRACEPOINT_ENTRY … #endif #endif /* _LINUX_TRACEPOINT_H */ /* * Note: we keep the TRACE_EVENT and DECLARE_TRACE outside the include * file ifdef protection. * This is due to the way trace events work. If a file includes two * trace event headers under one "CREATE_TRACE_POINTS" the first include * will override the TRACE_EVENT and break the second include. */ #ifndef DECLARE_TRACE #define TP_PROTO(args...) … #define TP_ARGS(args...) … #define TP_CONDITION(args...) … /* * Individual subsystem my have a separate configuration to * enable their tracepoints. By default, this file will create * the tracepoints if CONFIG_TRACEPOINTS is defined. If a subsystem * wants to be able to disable its tracepoints from being created * it can define NOTRACE before including the tracepoint headers. */ #if defined(CONFIG_TRACEPOINTS) && !defined(NOTRACE) #define TRACEPOINTS_ENABLED #endif #ifdef TRACEPOINTS_ENABLED #ifdef CONFIG_HAVE_STATIC_CALL #define __DO_TRACE_CALL(name, args) … #else #define __DO_TRACE_CALL … #endif /* CONFIG_HAVE_STATIC_CALL */ /* * ARCH_WANTS_NO_INSTR archs are expected to have sanitized entry and idle * code that disallow any/all tracing/instrumentation when RCU isn't watching. */ #ifdef CONFIG_ARCH_WANTS_NO_INSTR #define RCUIDLE_COND(rcuidle) … #else /* srcu can't be used from NMI */ #define RCUIDLE_COND … #endif /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. */ #define __DO_TRACE(name, args, cond, rcuidle) … #ifndef MODULE #define __DECLARE_TRACE_RCU(name, proto, args, cond) … #else #define __DECLARE_TRACE_RCU … #endif /* * Make sure the alignment of the structure in the __tracepoints section will * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * * When lockdep is enabled, we make sure to always test if RCU is * "watching" regardless if the tracepoint is enabled or not. Tracepoints * require RCU to be active, and it should always warn at the tracepoint * site if it is not watching, as it will need to be active when the * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) … /* * We have no guarantee that gcc and the linker won't up-align the tracepoint * structures, so we create an array of pointers that will be used for iteration * on the tracepoints. */ #define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args) … #define DEFINE_TRACE(name, proto, args) … #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) … #define EXPORT_TRACEPOINT_SYMBOL(name) … #else /* !TRACEPOINTS_ENABLED */ #define __DECLARE_TRACE … #define DEFINE_TRACE_FN … #define DEFINE_TRACE … #define EXPORT_TRACEPOINT_SYMBOL_GPL … #define EXPORT_TRACEPOINT_SYMBOL … #endif /* TRACEPOINTS_ENABLED */ #ifdef CONFIG_TRACING /** * tracepoint_string - register constant persistent string to trace system * @str - a constant persistent string that will be referenced in tracepoints * * If constant strings are being used in tracepoints, it is faster and * more efficient to just save the pointer to the string and reference * that with a printf "%s" instead of saving the string in the ring buffer * and wasting space and time. * * The problem with the above approach is that userspace tools that read * the binary output of the trace buffers do not have access to the string. * Instead they just show the address of the string which is not very * useful to users. * * With tracepoint_string(), the string will be registered to the tracing * system and exported to userspace via the debugfs/tracing/printk_formats * file that maps the string address to the string text. This way userspace * tools that read the binary buffers have a way to map the pointers to * the ASCII strings they represent. * * The @str used must be a constant string and persistent as it would not * make sense to show a string that no longer exists. But it is still fine * to be used with modules, because when modules are unloaded, if they * had tracepoints, the ring buffers are cleared too. As long as the string * does not change during the life of the module, it is fine to use * tracepoint_string() within a module. */ #define tracepoint_string(str) … #define __tracepoint_string … #else /* * tracepoint_string() is used to save the string address for userspace * tracing tools. When tracing isn't configured, there's no need to save * anything. */ #define tracepoint_string … #define __tracepoint_string #endif #define DECLARE_TRACE(name, proto, args) … #define DECLARE_TRACE_CONDITION(name, proto, args, cond) … #define TRACE_EVENT_FLAGS(event, flag) … #define TRACE_EVENT_PERF_PERM(event, expr...) … #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT /* * For use with the TRACE_EVENT macro: * * We define a tracepoint, its arguments, its printk format * and its 'fast binary record' layout. * * Firstly, name your tracepoint via TRACE_EVENT(name : the * 'subsystem_event' notation is fine. * * Think about this whole construct as the * 'trace_sched_switch() function' from now on. * * * TRACE_EVENT(sched_switch, * * * * * A function has a regular function arguments * * prototype, declare it via TP_PROTO(): * * * * TP_PROTO(struct rq *rq, struct task_struct *prev, * struct task_struct *next), * * * * * Define the call signature of the 'function'. * * (Design sidenote: we use this instead of a * * TP_PROTO1/TP_PROTO2/TP_PROTO3 ugliness.) * * * * TP_ARGS(rq, prev, next), * * * * * Fast binary tracing: define the trace record via * * TP_STRUCT__entry(). You can think about it like a * * regular C structure local variable definition. * * * * This is how the trace record is structured and will * * be saved into the ring buffer. These are the fields * * that will be exposed to user-space in * * /sys/kernel/tracing/events/<*>/format. * * * * The declared 'local variable' is called '__entry' * * * * __field(pid_t, prev_pid) is equivalent to a standard declaration: * * * * pid_t prev_pid; * * * * __array(char, prev_comm, TASK_COMM_LEN) is equivalent to: * * * * char prev_comm[TASK_COMM_LEN]; * * * * TP_STRUCT__entry( * __array( char, prev_comm, TASK_COMM_LEN ) * __field( pid_t, prev_pid ) * __field( int, prev_prio ) * __array( char, next_comm, TASK_COMM_LEN ) * __field( pid_t, next_pid ) * __field( int, next_prio ) * ), * * * * * Assign the entry into the trace record, by embedding * * a full C statement block into TP_fast_assign(). You * * can refer to the trace record as '__entry' - * * otherwise you can put arbitrary C code in here. * * * * Note: this C code will execute every time a trace event * * happens, on an active tracepoint. * * * * TP_fast_assign( * memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); * __entry->prev_pid = prev->pid; * __entry->prev_prio = prev->prio; * memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); * __entry->next_pid = next->pid; * __entry->next_prio = next->prio; * ), * * * * * Formatted output of a trace record via TP_printk(). * * This is how the tracepoint will appear under ftrace * * plugins that make use of this tracepoint. * * * * (raw-binary tracing wont actually perform this step.) * * * * TP_printk("task %s:%d [%d] ==> %s:%d [%d]", * __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, * __entry->next_comm, __entry->next_pid, __entry->next_prio), * * ); * * This macro construct is thus used for the regular printk format * tracing setup, it is used to construct a function pointer based * tracepoint callback (this is used by programmatic plugins and * can also by used by generic instrumentation like SystemTap), and * it is also used to expose a structured trace record in * /sys/kernel/tracing/events/. * * A set of (un)registration functions can be passed to the variant * TRACE_EVENT_FN to perform any (un)registration work. */ #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) … #define DEFINE_EVENT(template, name, proto, args) … #define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) … #define DEFINE_EVENT_PRINT(template, name, proto, args, print) … #define DEFINE_EVENT_CONDITION(template, name, proto, \ args, cond) … #define TRACE_EVENT(name, proto, args, struct, assign, print) … #define TRACE_EVENT_FN(name, proto, args, struct, \ assign, print, reg, unreg) … #define TRACE_EVENT_FN_COND(name, proto, args, cond, struct, \ assign, print, reg, unreg) … #define TRACE_EVENT_CONDITION(name, proto, args, cond, \ struct, assign, print) … #define TRACE_EVENT_FLAGS(event, flag) … #define TRACE_EVENT_PERF_PERM(event, expr...) … #define DECLARE_EVENT_NOP(name, proto, args) … #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print) … #define DECLARE_EVENT_CLASS_NOP(name, proto, args, tstruct, assign, print) … #define DEFINE_EVENT_NOP(template, name, proto, args) … #endif /* ifdef TRACE_EVENT (see note above) */