diff options
Diffstat (limited to 'kernel/trace')
-rw-r--r-- | kernel/trace/Kconfig | 1 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 23 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 189 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 19 | ||||
-rw-r--r-- | kernel/trace/ring_buffer_benchmark.c | 6 | ||||
-rw-r--r-- | kernel/trace/trace.c | 197 | ||||
-rw-r--r-- | kernel/trace/trace.h | 41 | ||||
-rw-r--r-- | kernel/trace/trace_event_perf.c | 22 | ||||
-rw-r--r-- | kernel/trace/trace_events.c | 85 | ||||
-rw-r--r-- | kernel/trace/trace_events_trigger.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_export.c | 6 | ||||
-rw-r--r-- | kernel/trace/trace_functions.c | 147 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace_irqsoff.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 38 | ||||
-rw-r--r-- | kernel/trace/trace_nop.c | 5 | ||||
-rw-r--r-- | kernel/trace/trace_output.c | 33 | ||||
-rw-r--r-- | kernel/trace/trace_probe.h | 17 | ||||
-rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace_uprobe.c | 217 |
21 files changed, 736 insertions, 344 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 015f85aaca0..8639819f6ce 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -424,6 +424,7 @@ config UPROBE_EVENT bool "Enable uprobes-based dynamic events" depends on ARCH_SUPPORTS_UPROBES depends on MMU + depends on PERF_EVENTS select UPROBES select PROBE_EVENTS select TRACING diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b418cb0d724..c1bd4ada2a0 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q) * blk_add_trace_rq - Add a trace for a request oriented action * @q: queue the io is for * @rq: the source request + * @nr_bytes: number of completed bytes * @what: the action * * Description: @@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q) * **/ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, - u32 what) + unsigned int nr_bytes, u32 what) { struct blk_trace *bt = q->blk_trace; @@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); - __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags, + __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags, what, rq->errors, rq->cmd_len, rq->cmd); } else { what |= BLK_TC_ACT(BLK_TC_FS); - __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, rq->cmd_flags, what, rq->errors, 0, NULL); } } @@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, static void blk_add_trace_rq_abort(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_ABORT); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT); } static void blk_add_trace_rq_insert(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_INSERT); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT); } static void blk_add_trace_rq_issue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_ISSUE); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE); } static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE); } static void blk_add_trace_rq_complete(void *ignore, struct request_queue *q, - struct request *rq) + struct request *rq, + unsigned int nr_bytes) { - blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); + blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE); } /** @@ -1427,7 +1429,8 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) return print_one_line(iter, true); } -static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set) +static int +blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* don't output context-info for blk_classic output */ if (bit == TRACE_BLK_OPT_CLASSIC) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cd7f76d1eb8..4a54a25afa2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -237,14 +237,13 @@ static int control_ops_alloc(struct ftrace_ops *ops) return 0; } -static void control_ops_free(struct ftrace_ops *ops) -{ - free_percpu(ops->disabled); -} - static void update_global_ops(void) { - ftrace_func_t func; + ftrace_func_t func = ftrace_global_list_func; + void *private = NULL; + + /* The list has its own recursion protection. */ + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; /* * If there's only one function registered, then call that @@ -254,23 +253,17 @@ static void update_global_ops(void) if (ftrace_global_list == &ftrace_list_end || ftrace_global_list->next == &ftrace_list_end) { func = ftrace_global_list->func; + private = ftrace_global_list->private; /* * As we are calling the function directly. * If it does not have recursion protection, * the function_trace_op needs to be updated * accordingly. */ - if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) - global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; - else + if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)) global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE; - } else { - func = ftrace_global_list_func; - /* The list has its own recursion protection. */ - global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; } - /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); @@ -278,6 +271,7 @@ static void update_global_ops(void) } global_ops.func = func; + global_ops.private = private; } static void ftrace_sync(struct work_struct *work) @@ -437,6 +431,9 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { + if (ops->flags & FTRACE_OPS_FL_DELETED) + return -EINVAL; + if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; @@ -1172,8 +1169,6 @@ struct ftrace_page { int size; }; -static struct ftrace_page *ftrace_new_pgs; - #define ENTRY_SIZE sizeof(struct dyn_ftrace) #define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) @@ -1560,7 +1555,7 @@ unsigned long ftrace_location(unsigned long ip) * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. */ -int ftrace_text_reserved(void *start, void *end) +int ftrace_text_reserved(const void *start, const void *end) { unsigned long ret; @@ -1994,6 +1989,7 @@ int __weak ftrace_arch_code_modify_post_process(void) void ftrace_modify_all_code(int command) { int update = command & FTRACE_UPDATE_TRACE_FUNC; + int err = 0; /* * If the ftrace_caller calls a ftrace_ops func directly, @@ -2005,8 +2001,11 @@ void ftrace_modify_all_code(int command) * to make sure the ops are having the right functions * traced. */ - if (update) - ftrace_update_ftrace_func(ftrace_ops_list_func); + if (update) { + err = ftrace_update_ftrace_func(ftrace_ops_list_func); + if (FTRACE_WARN_ON(err)) + return; + } if (command & FTRACE_UPDATE_CALLS) ftrace_replace_code(1); @@ -2019,13 +2018,16 @@ void ftrace_modify_all_code(int command) /* If irqs are disabled, we are in stop machine */ if (!irqs_disabled()) smp_call_function(ftrace_sync_ipi, NULL, 1); - ftrace_update_ftrace_func(ftrace_trace_function); + err = ftrace_update_ftrace_func(ftrace_trace_function); + if (FTRACE_WARN_ON(err)) + return; } if (command & FTRACE_START_FUNC_RET) - ftrace_enable_ftrace_graph_caller(); + err = ftrace_enable_ftrace_graph_caller(); else if (command & FTRACE_STOP_FUNC_RET) - ftrace_disable_ftrace_graph_caller(); + err = ftrace_disable_ftrace_graph_caller(); + FTRACE_WARN_ON(err); } static int __ftrace_modify_code(void *data) @@ -2093,6 +2095,11 @@ static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; static int global_start_up; +static void control_ops_free(struct ftrace_ops *ops) +{ + free_percpu(ops->disabled); +} + static void ftrace_startup_enable(int command) { if (saved_ftrace_func != ftrace_trace_function) { @@ -2244,7 +2251,6 @@ static void ftrace_shutdown_sysctl(void) } static cycle_t ftrace_update_time; -static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; static inline int ops_traces_mod(struct ftrace_ops *ops) @@ -2300,11 +2306,12 @@ static int referenced_filters(struct dyn_ftrace *rec) return cnt; } -static int ftrace_update_code(struct module *mod) +static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) { struct ftrace_page *pg; struct dyn_ftrace *p; cycle_t start, stop; + unsigned long update_cnt = 0; unsigned long ref = 0; bool test = false; int i; @@ -2330,9 +2337,8 @@ static int ftrace_update_code(struct module *mod) } start = ftrace_now(raw_smp_processor_id()); - ftrace_update_cnt = 0; - for (pg = ftrace_new_pgs; pg; pg = pg->next) { + for (pg = new_pgs; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { int cnt = ref; @@ -2353,7 +2359,7 @@ static int ftrace_update_code(struct module *mod) if (!ftrace_code_disable(mod, p)) break; - ftrace_update_cnt++; + update_cnt++; /* * If the tracing is enabled, go ahead and enable the record. @@ -2372,11 +2378,9 @@ static int ftrace_update_code(struct module *mod) } } - ftrace_new_pgs = NULL; - stop = ftrace_now(raw_smp_processor_id()); ftrace_update_time = stop - start; - ftrace_update_tot_cnt += ftrace_update_cnt; + ftrace_update_tot_cnt += update_cnt; return 0; } @@ -2468,22 +2472,6 @@ ftrace_allocate_pages(unsigned long num_to_init) return NULL; } -static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) -{ - int cnt; - - if (!num_to_init) { - pr_info("ftrace: No functions to be traced?\n"); - return -1; - } - - cnt = num_to_init / ENTRIES_PER_PAGE; - pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt + 1); - - return 0; -} - #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { @@ -2871,7 +2859,9 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&global_ops, + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH, inode, file); } @@ -2879,7 +2869,9 @@ ftrace_filter_open(struct inode *inode, struct file *file) static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE, + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -4109,6 +4101,36 @@ static const struct file_operations ftrace_graph_notrace_fops = { }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent) +{ + + trace_create_file("set_ftrace_filter", 0644, parent, + ops, &ftrace_filter_fops); + + trace_create_file("set_ftrace_notrace", 0644, parent, + ops, &ftrace_notrace_fops); +} + +/* + * The name "destroy_filter_files" is really a misnomer. Although + * in the future, it may actualy delete the files, but this is + * really intended to make sure the ops passed in are disabled + * and that when this function returns, the caller is free to + * free the ops. + * + * The "destroy" name is only to match the "create" name that this + * should be paired with. + */ +void ftrace_destroy_filter_files(struct ftrace_ops *ops) +{ + mutex_lock(&ftrace_lock); + if (ops->flags & FTRACE_OPS_FL_ENABLED) + ftrace_shutdown(ops, 0); + ops->flags |= FTRACE_OPS_FL_DELETED; + mutex_unlock(&ftrace_lock); +} + static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { @@ -4118,11 +4140,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("enabled_functions", 0444, d_tracer, NULL, &ftrace_enabled_fops); - trace_create_file("set_ftrace_filter", 0644, d_tracer, - NULL, &ftrace_filter_fops); - - trace_create_file("set_ftrace_notrace", 0644, d_tracer, - NULL, &ftrace_notrace_fops); + ftrace_create_filter_files(&global_ops, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER trace_create_file("set_graph_function", 0444, d_tracer, @@ -4238,9 +4256,6 @@ static int ftrace_process_locs(struct module *mod, /* Assign the last page to ftrace_pages */ ftrace_pages = pg; - /* These new locations need to be initialized */ - ftrace_new_pgs = start_pg; - /* * We only need to disable interrupts on start up * because we are modifying code that an interrupt @@ -4251,7 +4266,7 @@ static int ftrace_process_locs(struct module *mod, */ if (!mod) local_irq_save(flags); - ftrace_update_code(mod); + ftrace_update_code(mod, start_pg); if (!mod) local_irq_restore(flags); ret = 0; @@ -4315,16 +4330,11 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) +void ftrace_module_init(struct module *mod) { - struct module *mod = data; - - if (val == MODULE_STATE_COMING) - ftrace_init_module(mod, mod->ftrace_callsites, - mod->ftrace_callsites + - mod->num_ftrace_callsites); - return 0; + ftrace_init_module(mod, mod->ftrace_callsites, + mod->ftrace_callsites + + mod->num_ftrace_callsites); } static int ftrace_module_notify_exit(struct notifier_block *self, @@ -4338,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, return 0; } #else -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} static int ftrace_module_notify_exit(struct notifier_block *self, unsigned long val, void *data) { @@ -4350,40 +4355,32 @@ static int ftrace_module_notify_exit(struct notifier_block *self, } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_enter_nb = { - .notifier_call = ftrace_module_notify_enter, - .priority = INT_MAX, /* Run before anything that can use kprobes */ -}; - struct notifier_block ftrace_module_exit_nb = { .notifier_call = ftrace_module_notify_exit, .priority = INT_MIN, /* Run after anything that can remove kprobes */ }; -extern unsigned long __start_mcount_loc[]; -extern unsigned long __stop_mcount_loc[]; - void __init ftrace_init(void) { - unsigned long count, addr, flags; + extern unsigned long __start_mcount_loc[]; + extern unsigned long __stop_mcount_loc[]; + unsigned long count, flags; int ret; - /* Keep the ftrace pointer to the stub */ - addr = (unsigned long)ftrace_stub; - local_irq_save(flags); - ftrace_dyn_arch_init(&addr); + ret = ftrace_dyn_arch_init(); local_irq_restore(flags); - - /* ftrace_dyn_arch_init places the return code in addr */ - if (addr) + if (ret) goto failed; count = __stop_mcount_loc - __start_mcount_loc; - - ret = ftrace_dyn_table_alloc(count); - if (ret) + if (!count) { + pr_info("ftrace: No functions to be traced?\n"); goto failed; + } + + pr_info("ftrace: allocating %ld entries in %ld pages\n", + count, count / ENTRIES_PER_PAGE + 1); last_ftrace_enabled = ftrace_enabled = 1; @@ -4391,10 +4388,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_enter_nb); - if (ret) - pr_warning("Failed to register trace ftrace module enter notifier\n"); - ret = register_module_notifier(&ftrace_module_exit_nb); if (ret) pr_warning("Failed to register trace ftrace module exit notifier\n"); @@ -4431,7 +4424,13 @@ static inline void ftrace_startup_enable(int command) { } (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ ___ret; \ }) -# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops) +# define ftrace_shutdown(ops, command) \ + ({ \ + int ___ret = __unregister_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fc4da2d97f9..c634868c292 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1301,7 +1301,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, * In that off case, we need to allocate for all possible cpus. */ #ifdef CONFIG_HOTPLUG_CPU - get_online_cpus(); + cpu_notifier_register_begin(); cpumask_copy(buffer->cpumask, cpu_online_mask); #else cpumask_copy(buffer->cpumask, cpu_possible_mask); @@ -1324,10 +1324,10 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, #ifdef CONFIG_HOTPLUG_CPU buffer->cpu_notify.notifier_call = rb_cpu_notify; buffer->cpu_notify.priority = 0; - register_cpu_notifier(&buffer->cpu_notify); + __register_cpu_notifier(&buffer->cpu_notify); + cpu_notifier_register_done(); #endif - put_online_cpus(); mutex_init(&buffer->mutex); return buffer; @@ -1341,7 +1341,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, fail_free_cpumask: free_cpumask_var(buffer->cpumask); - put_online_cpus(); +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif fail_free_buffer: kfree(buffer); @@ -1358,16 +1360,17 @@ ring_buffer_free(struct ring_buffer *buffer) { int cpu; - get_online_cpus(); - #ifdef CONFIG_HOTPLUG_CPU - unregister_cpu_notifier(&buffer->cpu_notify); + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&buffer->cpu_notify); #endif for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); - put_online_cpus(); +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif kfree(buffer->buffers); free_cpumask_var(buffer->cpumask); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index a5457d577b9..0434ff1b808 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -40,8 +40,8 @@ static int write_iteration = 50; module_param(write_iteration, uint, 0644); MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings"); -static int producer_nice = 19; -static int consumer_nice = 19; +static int producer_nice = MAX_NICE; +static int consumer_nice = MAX_NICE; static int producer_fifo = -1; static int consumer_fifo = -1; @@ -308,7 +308,7 @@ static void ring_buffer_producer(void) /* Let the user know that the test is running at low priority */ if (producer_fifo < 0 && consumer_fifo < 0 && - producer_nice == 19 && consumer_nice == 19) + producer_nice == MAX_NICE && consumer_nice == MAX_NICE) trace_printk("WARNING!!! This test is running at lowest priority.\n"); trace_printk("Time: %lld (usecs)\n", time); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 24c1f238255..737b0efa1a6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -73,7 +73,8 @@ static struct tracer_flags dummy_tracer_flags = { .opts = dummy_tracer_opt }; -static int dummy_set_flag(u32 old_flags, u32 bit, int set) +static int +dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return 0; } @@ -118,7 +119,7 @@ enum ftrace_dump_mode ftrace_dump_on_oops; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; -static int tracing_set_tracer(const char *buf); +static int tracing_set_tracer(struct trace_array *tr, const char *buf); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; @@ -180,6 +181,17 @@ static int __init set_trace_boot_options(char *str) } __setup("trace_options=", set_trace_boot_options); +static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_clock __initdata; + +static int __init set_trace_boot_clock(char *str) +{ + strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); + trace_boot_clock = trace_boot_clock_buf; + return 0; +} +__setup("trace_clock=", set_trace_boot_clock); + unsigned long long ns2usecs(cycle_t nsec) { @@ -1230,7 +1242,7 @@ int register_tracer(struct tracer *type) printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ - tracing_set_tracer(type->name); + tracing_set_tracer(&global_trace, type->name); default_bootup_tracer = NULL; /* disable other selftests, since this will break it. */ tracing_selftest_disabled = true; @@ -3137,27 +3149,52 @@ static int tracing_open(struct inode *inode, struct file *file) return ret; } +/* + * Some tracers are not suitable for instance buffers. + * A tracer is always available for the global array (toplevel) + * or if it explicitly states that it is. + */ +static bool +trace_ok_for_array(struct tracer *t, struct trace_array *tr) +{ + return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; +} + +/* Find the next tracer that this trace array may use */ +static struct tracer * +get_tracer_for_array(struct trace_array *tr, struct tracer *t) +{ + while (t && !trace_ok_for_array(t, tr)) + t = t->next; + + return t; +} + static void * t_next(struct seq_file *m, void *v, loff_t *pos) { + struct trace_array *tr = m->private; struct tracer *t = v; (*pos)++; if (t) - t = t->next; + t = get_tracer_for_array(tr, t->next); return t; } static void *t_start(struct seq_file *m, loff_t *pos) { + struct trace_array *tr = m->private; struct tracer *t; loff_t l = 0; mutex_lock(&trace_types_lock); - for (t = trace_types; t && l < *pos; t = t_next(m, t, &l)) - ; + + t = get_tracer_for_array(tr, trace_types); + for (; t && l < *pos; t = t_next(m, t, &l)) + ; return t; } @@ -3192,10 +3229,21 @@ static const struct seq_operations show_traces_seq_ops = { static int show_traces_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + struct seq_file *m; + int ret; + if (tracing_disabled) return -ENODEV; - return seq_open(file, &show_traces_seq_ops); + ret = seq_open(file, &show_traces_seq_ops); + if (ret) + return ret; + + m = file->private_data; + m->private = tr; + + return 0; } static ssize_t @@ -3355,13 +3403,14 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) return 0; } -static int __set_tracer_option(struct tracer *trace, +static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { + struct tracer *trace = tr->current_trace; int ret; - ret = trace->set_flag(tracer_flags->val, opts->bit, !neg); + ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); if (ret) return ret; @@ -3373,8 +3422,9 @@ static int __set_tracer_option(struct tracer *trace, } /* Try to assign a tracer specific option */ -static int set_tracer_option(struct tracer *trace, char *cmp, int neg) +static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) { + struct tracer *trace = tr->current_trace; struct tracer_flags *tracer_flags = trace->flags; struct tracer_opt *opts = NULL; int i; @@ -3383,8 +3433,7 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) opts = &tracer_flags->opts[i]; if (strcmp(cmp, opts->name) == 0) - return __set_tracer_option(trace, trace->flags, - opts, neg); + return __set_tracer_option(tr, trace->flags, opts, neg); } return -EINVAL; @@ -3407,7 +3456,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) /* Give the tracer a chance to approve the change */ if (tr->current_trace->flag_changed) - if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled)) + if (tr->current_trace->flag_changed(tr, mask, !!enabled)) return -EINVAL; if (enabled) @@ -3456,7 +3505,7 @@ static int trace_set_options(struct trace_array *tr, char *option) /* If no option could be set, test the specific tracer options */ if (!trace_options[i]) - ret = set_tracer_option(tr->current_trace, cmp, neg); + ret = set_tracer_option(tr, cmp, neg); mutex_unlock(&trace_types_lock); @@ -3562,6 +3611,8 @@ static const char readme_msg[] = #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif + "\t\t dump\n" + "\t\t cpudump\n" "\t example: echo do_fault:traceoff > set_ftrace_filter\n" "\t echo do_trap:traceoff:3 > set_ftrace_filter\n" "\t The first one will disable tracing every time do_fault is hit\n" @@ -3885,10 +3936,26 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer); static void destroy_trace_option_files(struct trace_option_dentry *topts); -static int tracing_set_tracer(const char *buf) +/* + * Used to clear out the tracer before deletion of an instance. + * Must have trace_types_lock held. + */ +static void tracing_set_nop(struct trace_array *tr) +{ + if (tr->current_trace == &nop_trace) + return; + + tr->current_trace->enabled--; + + if (tr->current_trace->reset) + tr->current_trace->reset(tr); + + tr->current_trace = &nop_trace; +} + +static int tracing_set_tracer(struct trace_array *tr, const char *buf) { static struct trace_option_dentry *topts; - struct trace_array *tr = &global_trace; struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; @@ -3916,9 +3983,15 @@ static int tracing_set_tracer(const char *buf) if (t == tr->current_trace) goto out; + /* Some tracers are only allowed for the top level buffer */ + if (!trace_ok_for_array(t, tr)) { + ret = -EINVAL; + goto out; + } + trace_branch_disable(); - tr->current_trace->enabled = false; + tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); @@ -3941,9 +4014,11 @@ static int tracing_set_tracer(const char *buf) free_snapshot(tr); } #endif - destroy_trace_option_files(topts); - - topts = create_trace_option_files(tr, t); + /* Currently, only the top instance has options */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { + destroy_trace_option_files(topts); + topts = create_trace_option_files(tr, t); + } #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { @@ -3960,7 +4035,7 @@ static int tracing_set_tracer(const char *buf) } tr->current_trace = t; - tr->current_trace->enabled = true; + tr->current_trace->enabled++; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3972,6 +4047,7 @@ static ssize_t tracing_set_trace_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; int i; size_t ret; @@ -3991,7 +4067,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) buf[i] = 0; - err = tracing_set_tracer(buf); + err = tracing_set_tracer(tr, buf); if (err) return err; @@ -4316,8 +4392,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, static const struct pipe_buf_operations tracing_pipe_buf_ops = { .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -4412,7 +4486,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, trace_access_lock(iter->cpu_file); /* Fill as many pages as possible. */ - for (i = 0, rem = len; i < pipe->buffers && rem; i++) { + for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) { spd.pages[i] = alloc_page(GFP_KERNEL); if (!spd.pages[i]) break; @@ -4699,25 +4773,10 @@ static int tracing_clock_show(struct seq_file *m, void *v) return 0; } -static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *fpos) +static int tracing_set_clock(struct trace_array *tr, const char *clockstr) { - struct seq_file *m = filp->private_data; - struct trace_array *tr = m->private; - char buf[64]; - const char *clockstr; int i; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - clockstr = strstrip(buf); - for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { if (strcmp(trace_clocks[i].name, clockstr) == 0) break; @@ -4745,6 +4804,32 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, mutex_unlock(&trace_types_lock); + return 0; +} + +static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + char buf[64]; + const char *clockstr; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + clockstr = strstrip(buf); + + ret = tracing_set_clock(tr, clockstr); + if (ret) + return ret; + *fpos += cnt; return cnt; @@ -5194,8 +5279,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -5271,7 +5354,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); - for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) { + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { struct page *page; int r; @@ -5705,7 +5788,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); - ret = __set_tracer_option(topt->tr->current_trace, topt->flags, + ret = __set_tracer_option(topt->tr, topt->flags, topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) @@ -6112,7 +6195,9 @@ static int instance_delete(const char *name) list_del(&tr->list); + tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_destroy_function_files(tr); debugfs_remove_recursive(tr->dir); free_percpu(tr->trace_buffer.data); ring_buffer_free(tr->trace_buffer.buffer); @@ -6207,6 +6292,12 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) { int cpu; + trace_create_file("available_tracers", 0444, d_tracer, + tr, &show_traces_fops); + + trace_create_file("current_tracer", 0644, d_tracer, + tr, &set_tracer_fops); + trace_create_file("tracing_cpumask", 0644, d_tracer, tr, &tracing_cpumask_fops); @@ -6237,6 +6328,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("tracing_on", 0644, d_tracer, tr, &rb_simple_fops); + if (ftrace_create_function_files(tr, d_tracer)) + WARN(1, "Could not allocate function filter files"); + #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, tr, &snapshot_fops); @@ -6259,12 +6353,6 @@ static __init int tracer_init_debugfs(void) init_tracer_debugfs(&global_trace, d_tracer); - trace_create_file("available_tracers", 0444, d_tracer, - &global_trace, &show_traces_fops); - - trace_create_file("current_tracer", 0644, d_tracer, - &global_trace, &set_tracer_fops); - #ifdef CONFIG_TRACER_MAX_TRACE trace_create_file("tracing_max_latency", 0644, d_tracer, &tracing_max_latency, &tracing_max_lat_fops); @@ -6527,6 +6615,13 @@ __init static int tracer_alloc_buffers(void) trace_init_cmdlines(); + if (trace_boot_clock) { + ret = tracing_set_clock(&global_trace, trace_boot_clock); + if (ret < 0) + pr_warning("Trace clock %s not defined, going back to default\n", + trace_boot_clock); + } + /* * register_tracer() might reference current_trace, so it * needs to be set before we register anything. This is diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 02b592f2d4b..2e29d7ba5a5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -13,6 +13,7 @@ #include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/ftrace_event.h> +#include <linux/compiler.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ @@ -210,6 +211,11 @@ struct trace_array { struct list_head events; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; +#ifdef CONFIG_FUNCTION_TRACER + struct ftrace_ops *ops; + /* function tracing enabled */ + int function_enabled; +#endif }; enum { @@ -355,14 +361,16 @@ struct tracer { void (*print_header)(struct seq_file *m); enum print_line_t (*print_line)(struct trace_iterator *iter); /* If you handled the flag setting, return 0 */ - int (*set_flag)(u32 old_flags, u32 bit, int set); + int (*set_flag)(struct trace_array *tr, + u32 old_flags, u32 bit, int set); /* Return 0 if OK with change, else return non-zero */ - int (*flag_changed)(struct tracer *tracer, + int (*flag_changed)(struct trace_array *tr, u32 mask, int set); struct tracer *next; struct tracer_flags *flags; + int enabled; bool print_max; - bool enabled; + bool allow_instances; #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif @@ -812,13 +820,36 @@ static inline int ftrace_trace_task(struct task_struct *task) return test_tsk_trace_trace(task); } extern int ftrace_is_dead(void); +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent); +void ftrace_destroy_function_files(struct trace_array *tr); #else static inline int ftrace_trace_task(struct task_struct *task) { return 1; } static inline int ftrace_is_dead(void) { return 0; } -#endif +static inline int +ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + return 0; +} +static inline void ftrace_destroy_function_files(struct trace_array *tr) { } +#endif /* CONFIG_FUNCTION_TRACER */ + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent); +void ftrace_destroy_filter_files(struct ftrace_ops *ops); +#else +/* + * The ops parameter passed in is usually undefined. + * This must be a macro. + */ +#define ftrace_create_filter_files(ops, parent) do { } while (0) +#define ftrace_destroy_filter_files(ops) do { } while (0) +#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */ int ftrace_event_is_function(struct ftrace_event_call *call); @@ -1249,7 +1280,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_##call; + __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index e854f420e03..c894614de14 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, } /* The ftrace function trace is allowed only for root. */ - if (ftrace_event_is_function(tp_event) && - perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + if (ftrace_event_is_function(tp_event)) { + if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (!p_event->attr.exclude_callchain_user) + return -EINVAL; + + /* + * Same reason to disable user stack dump as for user space + * callchains above. + */ + if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER) + return -EINVAL; + } /* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7b16d40bd64..3ddfd8f62c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -188,29 +188,60 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); +void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer, + struct ftrace_event_file *ftrace_file, + unsigned long len) +{ + struct ftrace_event_call *event_call = ftrace_file->event_call; + + local_save_flags(fbuffer->flags); + fbuffer->pc = preempt_count(); + fbuffer->ftrace_file = ftrace_file; + + fbuffer->event = + trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file, + event_call->event.type, len, + fbuffer->flags, fbuffer->pc); + if (!fbuffer->event) + return NULL; + + fbuffer->entry = ring_buffer_event_data(fbuffer->event); + return fbuffer->entry; +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve); + +void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer) +{ + event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer, + fbuffer->event, fbuffer->entry, + fbuffer->flags, fbuffer->pc); +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit); + int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type, void *data) { struct ftrace_event_file *file = data; + WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT)); switch (type) { case TRACE_REG_REGISTER: - return tracepoint_probe_register(call->name, + return tracepoint_probe_register(call->tp, call->class->probe, file); case TRACE_REG_UNREGISTER: - tracepoint_probe_unregister(call->name, + tracepoint_probe_unregister(call->tp, call->class->probe, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return tracepoint_probe_register(call->name, + return tracepoint_probe_register(call->tp, call->class->perf_probe, call); case TRACE_REG_PERF_UNREGISTER: - tracepoint_probe_unregister(call->name, + tracepoint_probe_unregister(call->tp, call->class->perf_probe, call); return 0; @@ -322,7 +353,7 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file, if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " - "%s\n", call->name); + "%s\n", ftrace_event_name(call)); break; } set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); @@ -451,27 +482,29 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, { struct ftrace_event_file *file; struct ftrace_event_call *call; + const char *name; int ret = -EINVAL; list_for_each_entry(file, &tr->events, list) { call = file->event_call; + name = ftrace_event_name(call); - if (!call->name || !call->class || !call->class->reg) + if (!name || !call->class || !call->class->reg) continue; if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) continue; if (match && - strcmp(match, call->name) != 0 && + strcmp(match, name) != 0 && strcmp(match, call->class->system) != 0) continue; if (sub && strcmp(sub, call->class->system) != 0) continue; - if (event && strcmp(event, call->name) != 0) + if (event && strcmp(event, name) != 0) continue; ftrace_event_enable_disable(file, set); @@ -669,7 +702,7 @@ static int t_show(struct seq_file *m, void *v) if (strcmp(call->class->system, TRACE_SYSTEM) != 0) seq_printf(m, "%s:", call->class->system); - seq_printf(m, "%s\n", call->name); + seq_printf(m, "%s\n", ftrace_event_name(call)); return 0; } @@ -762,7 +795,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; - if (!call->name || !call->class || !call->class->reg) + if (!ftrace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) @@ -877,7 +910,7 @@ static int f_show(struct seq_file *m, void *v) switch ((unsigned long)v) { case FORMAT_HEADER: - seq_printf(m, "name: %s\n", call->name); + seq_printf(m, "name: %s\n", ftrace_event_name(call)); seq_printf(m, "ID: %d\n", call->event.type); seq_printf(m, "format:\n"); return 0; @@ -1497,6 +1530,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) struct trace_array *tr = file->tr; struct list_head *head; struct dentry *d_events; + const char *name; int ret; /* @@ -1510,10 +1544,11 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) } else d_events = parent; - file->dir = debugfs_create_dir(call->name, d_events); + name = ftrace_event_name(call); + file->dir = debugfs_create_dir(name, d_events); if (!file->dir) { pr_warning("Could not create debugfs '%s' directory\n", - call->name); + name); return -1; } @@ -1537,7 +1572,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) ret = call->class->define_fields(call); if (ret < 0) { pr_warning("Could not initialize trace point" - " events/%s\n", call->name); + " events/%s\n", name); return -1; } } @@ -1601,15 +1636,17 @@ static void event_remove(struct ftrace_event_call *call) static int event_init(struct ftrace_event_call *call) { int ret = 0; + const char *name; - if (WARN_ON(!call->name)) + name = ftrace_event_name(call); + if (WARN_ON(!name)) return -EINVAL; if (call->class->raw_init) { ret = call->class->raw_init(call); if (ret < 0 && ret != -ENOSYS) pr_warn("Could not initialize trace events/%s\n", - call->name); + name); } return ret; @@ -1855,7 +1892,7 @@ __trace_add_event_dirs(struct trace_array *tr) ret = __trace_add_new_event(call, tr); if (ret < 0) pr_warning("Could not create directory for event %s\n", - call->name); + ftrace_event_name(call)); } } @@ -1864,18 +1901,20 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) { struct ftrace_event_file *file; struct ftrace_event_call *call; + const char *name; list_for_each_entry(file, &tr->events, list) { call = file->event_call; + name = ftrace_event_name(call); - if (!call->name || !call->class || !call->class->reg) + if (!name || !call->class || !call->class->reg) continue; if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) continue; - if (strcmp(event, call->name) == 0 && + if (strcmp(event, name) == 0 && strcmp(system, call->class->system) == 0) return file; } @@ -1943,7 +1982,7 @@ event_enable_print(struct seq_file *m, unsigned long ip, seq_printf(m, "%s:%s:%s", data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, data->file->event_call->class->system, - data->file->event_call->name); + ftrace_event_name(data->file->event_call)); if (data->count == -1) seq_printf(m, ":unlimited\n"); @@ -2163,7 +2202,7 @@ __trace_early_add_event_dirs(struct trace_array *tr) ret = event_create_dir(tr->event_dir, file); if (ret < 0) pr_warning("Could not create directory for event %s\n", - file->event_call->name); + ftrace_event_name(file->event_call)); } } @@ -2187,7 +2226,7 @@ __trace_early_add_events(struct trace_array *tr) ret = __trace_early_add_new_event(call, tr); if (ret < 0) pr_warning("Could not create early event %s\n", - call->name); + ftrace_event_name(call)); } } @@ -2519,7 +2558,7 @@ static __init void event_trace_self_tests(void) continue; #endif - pr_info("Testing event %s: ", call->name); + pr_info("Testing event %s: ", ftrace_event_name(call)); /* * If an event is already enabled, someone is using diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8efbb69b04f..4747b476a03 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec) data->ops->func(data); continue; } - filter = rcu_dereference(data->filter); + filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; if (data->cmd_ops->post_trigger) { @@ -1095,7 +1095,7 @@ event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, seq_printf(m, "%s:%s:%s", enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, enable_data->file->event_call->class->system, - enable_data->file->event_call->name); + ftrace_event_name(enable_data->file->event_call)); if (data->count == -1) seq_puts(m, ":unlimited"); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index ee0a5098ac4..d4ddde28a81 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -173,9 +173,11 @@ struct ftrace_event_class __refdata event_class_ftrace_##call = { \ }; \ \ struct ftrace_event_call __used event_##call = { \ - .name = #call, \ - .event.type = etype, \ .class = &event_class_ftrace_##call, \ + { \ + .name = #call, \ + }, \ + .event.type = etype, \ .print_fmt = print, \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ }; \ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 38fe1483c50..ffd56351b52 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -13,32 +13,110 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/slab.h> #include <linux/fs.h> #include "trace.h" -/* function tracing enabled */ -static int ftrace_function_enabled; +static void tracing_start_function_trace(struct trace_array *tr); +static void tracing_stop_function_trace(struct trace_array *tr); +static void +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static struct ftrace_ops trace_ops; +static struct ftrace_ops trace_stack_ops; +static struct tracer_flags func_flags; + +/* Our option */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, +}; + +static int allocate_ftrace_ops(struct trace_array *tr) +{ + struct ftrace_ops *ops; + + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + /* Currently only the non stack verision is supported */ + ops->func = function_trace_call; + ops->flags = FTRACE_OPS_FL_RECURSION_SAFE; -static struct trace_array *func_trace; + tr->ops = ops; + ops->private = tr; + return 0; +} + + +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + int ret; + + /* + * The top level array uses the "global_ops", and the files are + * created on boot up. + */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; -static void tracing_start_function_trace(void); -static void tracing_stop_function_trace(void); + ret = allocate_ftrace_ops(tr); + if (ret) + return ret; + + ftrace_create_filter_files(tr->ops, parent); + + return 0; +} + +void ftrace_destroy_function_files(struct trace_array *tr) +{ + ftrace_destroy_filter_files(tr->ops); + kfree(tr->ops); + tr->ops = NULL; +} static int function_trace_init(struct trace_array *tr) { - func_trace = tr; + struct ftrace_ops *ops; + + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { + /* There's only one global tr */ + if (!trace_ops.private) { + trace_ops.private = tr; + trace_stack_ops.private = tr; + } + + if (func_flags.val & TRACE_FUNC_OPT_STACK) + ops = &trace_stack_ops; + else + ops = &trace_ops; + tr->ops = ops; + } else if (!tr->ops) { + /* + * Instance trace_arrays get their ops allocated + * at instance creation. Unless it failed + * the allocation. + */ + return -ENOMEM; + } + tr->trace_buffer.cpu = get_cpu(); put_cpu(); tracing_start_cmdline_record(); - tracing_start_function_trace(); + tracing_start_function_trace(tr); return 0; } static void function_trace_reset(struct trace_array *tr) { - tracing_stop_function_trace(); + tracing_stop_function_trace(tr); tracing_stop_cmdline_record(); } @@ -47,25 +125,18 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->trace_buffer); } -/* Our option */ -enum { - TRACE_FUNC_OPT_STACK = 0x1, -}; - -static struct tracer_flags func_flags; - static void function_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { - struct trace_array *tr = func_trace; + struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned long flags; int bit; int cpu; int pc; - if (unlikely(!ftrace_function_enabled)) + if (unlikely(!tr->function_enabled)) return; pc = preempt_count(); @@ -91,14 +162,14 @@ static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { - struct trace_array *tr = func_trace; + struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned long flags; long disabled; int cpu; int pc; - if (unlikely(!ftrace_function_enabled)) + if (unlikely(!tr->function_enabled)) return; /* @@ -128,7 +199,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, local_irq_restore(flags); } - static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, @@ -153,29 +223,21 @@ static struct tracer_flags func_flags = { .opts = func_opts }; -static void tracing_start_function_trace(void) +static void tracing_start_function_trace(struct trace_array *tr) { - ftrace_function_enabled = 0; - - if (func_flags.val & TRACE_FUNC_OPT_STACK) - register_ftrace_function(&trace_stack_ops); - else - register_ftrace_function(&trace_ops); - - ftrace_function_enabled = 1; + tr->function_enabled = 0; + register_ftrace_function(tr->ops); + tr->function_enabled = 1; } -static void tracing_stop_function_trace(void) +static void tracing_stop_function_trace(struct trace_array *tr) { - ftrace_function_enabled = 0; - - if (func_flags.val & TRACE_FUNC_OPT_STACK) - unregister_ftrace_function(&trace_stack_ops); - else - unregister_ftrace_function(&trace_ops); + tr->function_enabled = 0; + unregister_ftrace_function(tr->ops); } -static int func_set_flag(u32 old_flags, u32 bit, int set) +static int +func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { switch (bit) { case TRACE_FUNC_OPT_STACK: @@ -183,12 +245,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) break; + unregister_ftrace_function(tr->ops); + if (set) { - unregister_ftrace_function(&trace_ops); - register_ftrace_function(&trace_stack_ops); + tr->ops = &trace_stack_ops; + register_ftrace_function(tr->ops); } else { - unregister_ftrace_function(&trace_stack_ops); - register_ftrace_function(&trace_ops); + tr->ops = &trace_ops; + register_ftrace_function(tr->ops); } break; @@ -208,6 +272,7 @@ static struct tracer function_trace __tracer_data = .wait_pipe = poll_wait_pipe, .flags = &func_flags, .set_flag = func_set_flag, + .allow_instances = true, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_function, #endif diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 0b99120d395..deff1120026 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1476,7 +1476,8 @@ void graph_trace_close(struct trace_iterator *iter) } } -static int func_graph_set_flag(u32 old_flags, u32 bit, int set) +static int +func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { if (bit == TRACE_GRAPH_PRINT_IRQS) ftrace_graph_skip_irqs = !set; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 2aefbee93a6..8ff02cbb892 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -160,7 +160,8 @@ static struct ftrace_ops trace_ops __read_mostly = #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { int cpu; @@ -266,7 +267,8 @@ __trace_function(struct trace_array *tr, #else #define __trace_function trace_function -static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return -EINVAL; } @@ -498,14 +500,14 @@ void trace_hardirqs_off(void) } EXPORT_SYMBOL(trace_hardirqs_off); -void trace_hardirqs_on_caller(unsigned long caller_addr) +__visible void trace_hardirqs_on_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); -void trace_hardirqs_off_caller(unsigned long caller_addr) +__visible void trace_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); @@ -570,8 +572,10 @@ static void irqsoff_function_set(int set) unregister_irqsoff_function(is_graph()); } -static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set) +static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set) { + struct tracer *tracer = tr->current_trace; + if (mask & TRACE_ITER_FUNCTION) irqsoff_function_set(set); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index bdbae450c13..903ae28962b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,11 +35,6 @@ struct trace_kprobe { struct trace_probe tp; }; -struct event_file_link { - struct ftrace_event_file *file; - struct list_head list; -}; - #define SIZEOF_TRACE_KPROBE(n) \ (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) @@ -346,7 +341,7 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, struct trace_kprobe *tk; list_for_each_entry(tk, &probe_list, list) - if (strcmp(tk->tp.call.name, event) == 0 && + if (strcmp(ftrace_event_name(&tk->tp.call), event) == 0 && strcmp(tk->tp.call.class->system, group) == 0) return tk; return NULL; @@ -387,18 +382,6 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file) return ret; } -static struct event_file_link * -find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) -{ - struct event_file_link *link; - - list_for_each_entry(link, &tp->files, list) - if (link->file == file) - return link; - - return NULL; -} - /* * Disable trace_probe * if the file is NULL, disable "perf" handler, or disable "trace" handler. @@ -533,7 +516,8 @@ static int register_trace_kprobe(struct trace_kprobe *tk) mutex_lock(&probe_lock); /* Delete old (same name) event if exist */ - old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system); + old_tk = find_trace_kprobe(ftrace_event_name(&tk->tp.call), + tk->tp.call.class->system); if (old_tk) { ret = unregister_trace_kprobe(old_tk); if (ret < 0) @@ -581,7 +565,8 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, if (ret) pr_warning("Failed to re-register probe %s on" "%s: %d\n", - tk->tp.call.name, mod->name, ret); + ftrace_event_name(&tk->tp.call), + mod->name, ret); } } mutex_unlock(&probe_lock); @@ -835,7 +820,8 @@ static int probes_seq_show(struct seq_file *m, void *v) int i; seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p'); - seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name); + seq_printf(m, ":%s/%s", tk->tp.call.class->system, + ftrace_event_name(&tk->tp.call)); if (!tk->symbol) seq_printf(m, " 0x%p", tk->rp.kp.addr); @@ -893,7 +879,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_kprobe *tk = v; - seq_printf(m, " %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit, + seq_printf(m, " %-44s %15lu %15lu\n", + ftrace_event_name(&tk->tp.call), tk->nhit, tk->rp.kp.nmissed); return 0; @@ -1028,7 +1015,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, field = (struct kprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - if (!trace_seq_printf(s, "%s: (", tp->call.name)) + if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call))) goto partial; if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) @@ -1064,7 +1051,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, field = (struct kretprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - if (!trace_seq_printf(s, "%s: (", tp->call.name)) + if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call))) goto partial; if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET)) @@ -1303,7 +1290,8 @@ static int register_kprobe_event(struct trace_kprobe *tk) call->data = tk; ret = trace_add_event_call(call); if (ret) { - pr_info("Failed to register kprobe event: %s\n", call->name); + pr_info("Failed to register kprobe event: %s\n", + ftrace_event_name(call)); kfree(call->print_fmt); unregister_ftrace_event(&call->event); } diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 394f94417e2..69a5cc94c01 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -62,7 +62,7 @@ static void nop_trace_reset(struct trace_array *tr) * If you don't implement it, then the flag setting will be * automatically accepted. */ -static int nop_set_flag(u32 old_flags, u32 bit, int set) +static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* * Note that you don't need to update nop_flags.val yourself. @@ -96,6 +96,7 @@ struct tracer nop_trace __read_mostly = .selftest = trace_selftest_startup_nop, #endif .flags = &nop_flags, - .set_flag = nop_set_flag + .set_flag = nop_set_flag, + .allow_instances = true, }; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index ed32284fbe3..a436de18aa9 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -431,7 +431,7 @@ int ftrace_raw_output_prep(struct trace_iterator *iter, } trace_seq_init(p); - ret = trace_seq_printf(s, "%s: ", event->name); + ret = trace_seq_printf(s, "%s: ", ftrace_event_name(event)); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter, } EXPORT_SYMBOL(ftrace_raw_output_prep); +static int ftrace_output_raw(struct trace_iterator *iter, char *name, + char *fmt, va_list ap) +{ + struct trace_seq *s = &iter->seq; + int ret; + + ret = trace_seq_printf(s, "%s: ", name); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_vprintf(s, fmt, ap); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...) +{ + va_list ap; + int ret; + + va_start(ap, fmt); + ret = ftrace_output_raw(iter, name, fmt, ap); + va_end(ap); + + return ret; +} +EXPORT_SYMBOL_GPL(ftrace_output_call); + #ifdef CONFIG_KRETPROBES static inline const char *kretprobed(const char *name) { diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index b73574a5f42..fb1ab5dfbd4 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -288,6 +288,11 @@ struct trace_probe { struct probe_arg args[]; }; +struct event_file_link { + struct ftrace_event_file *file; + struct list_head list; +}; + static inline bool trace_probe_is_enabled(struct trace_probe *tp) { return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE)); @@ -316,6 +321,18 @@ static inline int is_good_name(const char *name) return 1; } +static inline struct event_file_link * +find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) +{ + struct event_file_link *link; + + list_for_each_entry(link, &tp->files, list) + if (link->file == file) + return link; + + return NULL; +} + extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, struct probe_arg *parg, bool is_return, bool is_kprobe); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 6e32635e5e5..e14da5e97a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -179,8 +179,10 @@ static void wakeup_function_set(int set) unregister_wakeup_function(is_graph()); } -static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set) +static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) { + struct tracer *tracer = tr->current_trace; + if (mask & TRACE_ITER_FUNCTION) wakeup_function_set(set); @@ -209,7 +211,8 @@ static void stop_func_tracer(int graph) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int wakeup_set_flag(u32 old_flags, u32 bit, int set) +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { if (!(bit & TRACE_DISPLAY_GRAPH)) @@ -311,7 +314,8 @@ __trace_function(struct trace_array *tr, #else #define __trace_function trace_function -static int wakeup_set_flag(u32 old_flags, u32 bit, int set) +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return -EINVAL; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index e6be585cf06..21b320e5d16 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -13,6 +13,7 @@ #include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/magic.h> #include <asm/setup.h> @@ -144,6 +145,8 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } + BUG_ON(current != &init_task && + *(end_of_stack(current)) != STACK_END_MAGIC); out: arch_spin_unlock(&max_stack_lock); local_irq_restore(flags); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 79e52d93860..c082a744134 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -260,6 +260,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) goto error; INIT_LIST_HEAD(&tu->list); + INIT_LIST_HEAD(&tu->tp.files); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; @@ -293,7 +294,7 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou struct trace_uprobe *tu; list_for_each_entry(tu, &uprobe_list, list) - if (strcmp(tu->tp.call.name, event) == 0 && + if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 && strcmp(tu->tp.call.class->system, group) == 0) return tu; @@ -323,7 +324,8 @@ static int register_trace_uprobe(struct trace_uprobe *tu) mutex_lock(&uprobe_lock); /* register as an event */ - old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system); + old_tu = find_probe_event(ftrace_event_name(&tu->tp.call), + tu->tp.call.class->system); if (old_tu) { /* delete old event */ ret = unregister_trace_uprobe(old_tu); @@ -598,7 +600,8 @@ static int probes_seq_show(struct seq_file *m, void *v) char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name); + seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, + ftrace_event_name(&tu->tp.call)); seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); for (i = 0; i < tu->tp.nr_args; i++) @@ -648,7 +651,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_uprobe *tu = v; - seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit); + seq_printf(m, " %s %-44s %15lu\n", tu->filename, + ftrace_event_name(&tu->tp.call), tu->nhit); return 0; } @@ -728,9 +732,15 @@ static int uprobe_buffer_enable(void) static void uprobe_buffer_disable(void) { + int cpu; + BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } @@ -758,31 +768,32 @@ static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) mutex_unlock(&ucb->mutex); } -static void uprobe_trace_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +static void __uprobe_trace_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize, + struct ftrace_event_file *ftrace_file) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - struct uprobe_cpu_buffer *ucb; void *data; - int size, dsize, esize; + int size, esize; struct ftrace_event_call *call = &tu->tp.call; - dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + WARN_ON(call != ftrace_file->event_call); - if (WARN_ON_ONCE(!uprobe_cpu_buffer || tu->tp.size + dsize > PAGE_SIZE)) + if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) return; - ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; - event = trace_current_buffer_lock_reserve(&buffer, call->event.type, - size, 0, 0); + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, size, 0, 0); if (!event) - goto out; + return; entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { @@ -796,25 +807,36 @@ static void uprobe_trace_print(struct trace_uprobe *tu, memcpy(data, ucb->buf, tu->tp.size + dsize); - if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - -out: - uprobe_buffer_put(ucb); + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0); } /* uprobe handler */ -static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - if (!is_ret_probe(tu)) - uprobe_trace_print(tu, 0, regs); + struct event_file_link *link; + + if (is_ret_probe(tu)) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + rcu_read_unlock(); + return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - uprobe_trace_print(tu, func, regs); + struct event_file_link *link; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + rcu_read_unlock(); } /* Event entry printers */ @@ -831,12 +853,14 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e tu = container_of(event, struct trace_uprobe, tp.call.event); if (is_ret_probe(tu)) { - if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name, + if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", + ftrace_event_name(&tu->tp.call), entry->vaddr[1], entry->vaddr[0])) goto partial; data = DATAOF_TRACE_ENTRY(entry, true); } else { - if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name, + if (!trace_seq_printf(s, "%s: (0x%lx)", + ftrace_event_name(&tu->tp.call), entry->vaddr[0])) goto partial; data = DATAOF_TRACE_ENTRY(entry, false); @@ -861,12 +885,24 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm); static int -probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) +probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, + filter_func_t filter) { - int ret = 0; + bool enabled = trace_probe_is_enabled(&tu->tp); + struct event_file_link *link = NULL; + int ret; + + if (file) { + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; - if (trace_probe_is_enabled(&tu->tp)) - return -EINTR; + link->file = file; + list_add_tail_rcu(&link->list, &tu->tp.files); + + tu->tp.flags |= TP_FLAG_TRACE; + } else + tu->tp.flags |= TP_FLAG_PROFILE; ret = uprobe_buffer_enable(); if (ret < 0) @@ -874,24 +910,49 @@ probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - tu->tp.flags |= flag; + if (enabled) + return 0; + tu->consumer.filter = filter; ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - if (ret) - tu->tp.flags &= ~flag; + if (ret) { + if (file) { + list_del(&link->list); + kfree(link); + tu->tp.flags &= ~TP_FLAG_TRACE; + } else + tu->tp.flags &= ~TP_FLAG_PROFILE; + } return ret; } -static void probe_event_disable(struct trace_uprobe *tu, int flag) +static void +probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file) { if (!trace_probe_is_enabled(&tu->tp)) return; + if (file) { + struct event_file_link *link; + + link = find_event_file_link(&tu->tp, file); + if (!link) + return; + + list_del_rcu(&link->list); + /* synchronize with u{,ret}probe_trace_func */ + synchronize_sched(); + kfree(link); + + if (!list_empty(&tu->tp.files)) + return; + } + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->tp.flags &= ~flag; + tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); } @@ -1014,31 +1075,24 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, return ret; } -static void uprobe_perf_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +static void __uprobe_perf_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { struct ftrace_event_call *call = &tu->tp.call; struct uprobe_trace_entry_head *entry; struct hlist_head *head; - struct uprobe_cpu_buffer *ucb; void *data; - int size, dsize, esize; + int size, esize; int rctx; - dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - if (WARN_ON_ONCE(!uprobe_cpu_buffer)) - return; - size = esize + tu->tp.size + dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; - ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); - preempt_disable(); head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) @@ -1068,46 +1122,49 @@ static void uprobe_perf_print(struct trace_uprobe *tu, perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); out: preempt_enable(); - uprobe_buffer_put(ucb); } /* uprobe profile handler */ -static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) - uprobe_perf_print(tu, 0, regs); + __uprobe_perf_func(tu, 0, regs, ucb, dsize); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - uprobe_perf_print(tu, func, regs); + __uprobe_perf_func(tu, func, regs, ucb, dsize); } #endif /* CONFIG_PERF_EVENTS */ -static -int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) +static int +trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, + void *data) { struct trace_uprobe *tu = event->data; + struct ftrace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE, NULL); + return probe_event_enable(tu, file, NULL); case TRACE_REG_UNREGISTER: - probe_event_disable(tu, TP_FLAG_TRACE); + probe_event_disable(tu, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); + return probe_event_enable(tu, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: - probe_event_disable(tu, TP_FLAG_PROFILE); + probe_event_disable(tu, NULL); return 0; case TRACE_REG_PERF_OPEN: @@ -1127,8 +1184,11 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; int ret = 0; + tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; @@ -1137,13 +1197,29 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) current->utask->vaddr = (unsigned long) &udd; +#ifdef CONFIG_PERF_EVENTS + if ((tu->tp.flags & TP_FLAG_TRACE) == 0 && + !uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; +#endif + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (tu->tp.flags & TP_FLAG_TRACE) - ret |= uprobe_trace_func(tu, regs); + ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (tu->tp.flags & TP_FLAG_PROFILE) - ret |= uprobe_perf_func(tu, regs); + ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif + uprobe_buffer_put(ucb); return ret; } @@ -1152,6 +1228,8 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; tu = container_of(con, struct trace_uprobe, consumer); @@ -1160,13 +1238,23 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, current->utask->vaddr = (unsigned long) &udd; + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (tu->tp.flags & TP_FLAG_TRACE) - uretprobe_trace_func(tu, func, regs); + uretprobe_trace_func(tu, func, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (tu->tp.flags & TP_FLAG_PROFILE) - uretprobe_perf_func(tu, func, regs); + uretprobe_perf_func(tu, func, regs, ucb, dsize); #endif + uprobe_buffer_put(ucb); return 0; } @@ -1198,7 +1286,8 @@ static int register_uprobe_event(struct trace_uprobe *tu) ret = trace_add_event_call(call); if (ret) { - pr_info("Failed to register uprobe event: %s\n", call->name); + pr_info("Failed to register uprobe event: %s\n", + ftrace_event_name(call)); kfree(call->print_fmt); unregister_ftrace_event(&call->event); } |