/* * ring buffer based function tracer * * Copyright (C) 2007-2008 Steven Rostedt * Copyright (C) 2008 Ingo Molnar * * Originally taken from the RT patch by: * Arnaldo Carvalho de Melo * * Based on code from the latency_tracer, that is: * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 Nadia Yvette Chambers */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "trace.h" #include "trace_output.h" /* * On boot up, the ring buffer is set to the minimum size, so that * we do not waste memory on systems that are not using tracing. */ int ring_buffer_expanded; /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the * entries inserted during the selftest although some concurrent * insertions into the ring-buffer such as trace_printk could occurred * at the same time, giving false positive or negative results. */ static bool __read_mostly tracing_selftest_running; /* * If a tracer is running, we do not want to run SELFTEST. */ bool __read_mostly tracing_selftest_disabled; /* For tracers that don't implement custom flags */ static struct tracer_opt dummy_tracer_opt[] = { { } }; static struct tracer_flags dummy_tracer_flags = { .val = 0, .opts = dummy_tracer_opt }; static int dummy_set_flag(u32 old_flags, u32 bit, int set) { return 0; } /* * To prevent the comm cache from being overwritten when no * tracing is active, only save the comm when a trace event * occurred. */ static DEFINE_PER_CPU(bool, trace_cmdline_save); /* * When a reader is waiting for data, then this variable is * set to true. */ static bool trace_wakeup_needed; static struct irq_work trace_work_wakeup; /* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets * this back to zero. */ static int tracing_disabled = 1; DEFINE_PER_CPU(int, ftrace_cpu_disabled); cpumask_var_t __read_mostly tracing_buffer_mask; /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops * * If there is an oops (or kernel panic) and the ftrace_dump_on_oops * is set, then ftrace_dump is called. This will output the contents * of the ftrace buffers to the console. This is very useful for * capturing traces that lead to crashes and outputing it to a * serial console. * * It is default off, but you can enable it with either specifying * "ftrace_dump_on_oops" in the kernel command line, or setting * /proc/sys/kernel/ftrace_dump_on_oops * Set 1 if you want to dump buffers of all CPUs * Set 2 if you want to dump the buffer of the CPU that triggered oops */ enum ftrace_dump_mode ftrace_dump_on_oops; static int tracing_set_tracer(const char *buf); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static int __init set_cmdline_ftrace(char *str) { strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ ring_buffer_expanded = 1; return 1; } __setup("ftrace=", set_cmdline_ftrace); static int __init set_ftrace_dump_on_oops(char *str) { if (*str++ != '=' || !*str) { ftrace_dump_on_oops = DUMP_ALL; return 1; } if (!strcmp("orig_cpu", str)) { ftrace_dump_on_oops = DUMP_ORIG; return 1; } return 0; } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static char *trace_boot_options __initdata; static int __init set_trace_boot_options(char *str) { strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); trace_boot_options = trace_boot_options_buf; return 0; } __setup("trace_options=", set_trace_boot_options); unsigned long long ns2usecs(cycle_t nsec) { nsec += 500; do_div(nsec, 1000); return nsec; } /* * The global_trace is the descriptor that holds the tracing * buffers for the live tracing. For each CPU, it contains * a link list of pages that will store trace entries. The * page descriptor of the pages in the memory is used to hold * the link list by linking the lru item in the page descriptor * to each of the pages in the buffer per CPU. * * For each active CPU there is a data field that holds the * pages for the buffer for that CPU. Each CPU has the same number * of pages allocated for its buffer. */ static struct trace_array global_trace; static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); int filter_current_check_discard(struct ring_buffer *buffer, struct ftrace_event_call *call, void *rec, struct ring_buffer_event *event) { return filter_check_discard(call, rec, buffer, event); } EXPORT_SYMBOL_GPL(filter_current_check_discard); cycle_t ftrace_now(int cpu) { u64 ts; /* Early boot up does not have a buffer yet */ if (!global_trace.buffer) return trace_clock_local(); ts = ring_buffer_time_stamp(global_trace.buffer, cpu); ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts); return ts; } /* * The max_tr is used to snapshot the global_trace when a maximum * latency is reached. Some tracers will use this to store a maximum * trace while it continues examining live traces. * * The buffers for the max_tr are set up the same as the global_trace. * When a snapshot is taken, the link list of the max_tr is swapped * with the link list of the global_trace and the buffers are reset for * the global_trace so the tracing can continue. */ static struct trace_array max_tr; static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data); int tracing_is_enabled(void) { return tracing_is_on(); } /* * trace_buf_size is the size in bytes that is allocated * for a buffer. Note, the number of bytes is always rounded * to page size. * * This number is purposely set to a low number of 16384. * If the dump on oops happens, it will be much appreciated * to not have to wait for all that output. Anyway this can be * boot time and run time configurable. */ #define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; /* current_trace points to the tracer that is currently active */ static struct tracer *current_trace __read_mostly; /* * trace_types_lock is used to protect the trace_types list. */ static DEFINE_MUTEX(trace_types_lock); /* * serialize the access of the ring buffer * * ring buffer serializes readers, but it is low level protection. * The validity of the events (which returns by ring_buffer_peek() ..etc) * are not protected by ring buffer. * * The content of events may become garbage if we allow other process consumes * these events concurrently: * A) the page of the consumed events may become a normal page * (not reader page) in ring buffer, and this page will be rewrited * by events producer. * B) The page of the consumed events may become a page for splice_read, * and this page will be returned to system. * * These primitives allow multi process access to different cpu ring buffer * concurrently. * * These primitives don't distinguish read-only and read-consume access. * Multi read-only access are also serialized. */ #ifdef CONFIG_SMP static DECLARE_RWSEM(all_cpu_access_lock); static DEFINE_PER_CPU(struct mutex, cpu_access_lock); static inline void trace_access_lock(int cpu) { if (cpu == TRACE_PIPE_ALL_CPU) { /* gain it for accessing the whole ring buffer. */ down_write(&all_cpu_access_lock); } else { /* gain it for accessing a cpu ring buffer. */ /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */ down_read(&all_cpu_access_lock); /* Secondly block other access to this @cpu ring buffer. */ mutex_lock(&per_cpu(cpu_access_lock, cpu)); } } static inline void trace_access_unlock(int cpu) { if (cpu == TRACE_PIPE_ALL_CPU) { up_write(&all_cpu_access_lock); } else { mutex_unlock(&per_cpu(cpu_access_lock, cpu)); up_read(&all_cpu_access_lock); } } static inline void trace_access_lock_init(void) { int cpu; for_each_possible_cpu(cpu) mutex_init(&per_cpu(cpu_access_lock, cpu)); } #else static DEFINE_MUTEX(access_lock); static inline void trace_access_lock(int cpu) { (void)cpu; mutex_lock(&access_lock); } static inline void trace_access_unlock(int cpu) { (void)cpu; mutex_unlock(&access_lock); } static inline void trace_access_lock_init(void) { } #endif /* trace_wait is a waitqueue for tasks blocked on trace_poll */ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); /* trace_flags holds trace_options default values */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); /** * trace_wake_up - wake up tasks waiting for trace input * * Schedules a delayed work to wake up any task that is blocked on the * trace_wait queue. These is used with trace_poll for tasks polling the * trace. */ static void trace_wake_up(struct irq_work *work) { wake_up_all(&trace_wait); } /** * tracing_on - enable tracing buffers * * This function enables tracing buffers that may have been * disabled with tracing_off. */ void tracing_on(void) { if (global_trace.buffer) ring_buffer_record_on(global_trace.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race * between setting this flag and actually turning * on the buffer. */ global_trace.buffer_disabled = 0; } EXPORT_SYMBOL_GPL(tracing_on); /** * tracing_off - turn off tracing buffers * * This function stops the tracing buffers from recording data. * It does not disable any overhead the tracers themselves may * be causing. This function simply causes all recording to * the ring buffers to fail. */ void tracing_off(void) { if (global_trace.buffer) ring_buffer_record_off(global_trace.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race * between setting this flag and actually turning * on the buffer. */ global_trace.buffer_disabled = 1; } EXPORT_SYMBOL_GPL(tracing_off); /** * tracing_is_on - show state of ring buffers enabled */ int tracing_is_on(void) { if (global_trace.buffer) return ring_buffer_record_is_on(global_trace.buffer); return !global_trace.buffer_disabled; } EXPORT_SYMBOL_GPL(tracing_is_on); static int __init set_buf_size(char *str) { unsigned long buf_size; if (!str) return 0; buf_size = memparse(str, &str); /* nr_entries can not be zero */ if (buf_size == 0) return 0; trace_buf_size = buf_size; return 1; } __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { unsigned long threshold; int ret; if (!str) return 0; ret = kstrtoul(str, 0, &threshold); if (ret < 0) return 0; tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); unsigned long nsecs_to_usecs(unsigned long nsecs) { return nsecs / 1000; } /* These must match the bit postions in trace_iterator_flags */ static const char *trace_options[] = { "print-parent", "sym-offset", "sym-addr", "verbose", "raw", "hex", "bin", "block", "stacktrace", "trace_printk", "ftrace_preempt", "branch", "annotate", "userstacktrace", "sym-userobj", "printk-msg-only", "context-info", "latency-format", "sleep-time", "graph-time", "record-cmd", "overwrite", "disable_on_free", "irq-info", "markers", NULL }; static struct { u64 (*func)(void); const char *name; int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, ARCH_TRACE_CLOCKS }; int trace_clock_id; /* * trace_parser_get_init - gets the buffer for trace parser */ int trace_parser_get_init(struct trace_parser *parser, int size) { memset(parser, 0, sizeof(*parser)); parser->buffer = kmalloc(size, GFP_KERNEL); if (!parser->buffer) return 1; parser->size = size; return 0; } /* * trace_parser_put - frees the buffer for trace parser */ void trace_parser_put(struct trace_parser *parser) { kfree(parser->buffer); } /* * trace_get_user - reads the user input string separated by space * (matched by isspace(ch)) * * For each string found the 'struct trace_parser' is updated, * and the function returns. * * Returns number of bytes read. * * See kernel/trace/trace.h for 'struct trace_parser' details. */ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, size_t cnt, loff_t *ppos) { char ch; size_t read = 0; ssize_t ret; if (!*ppos) trace_parser_clear(parser); ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; /* * The parser is not finished with the last write, * continue reading the user input without skipping spaces. */ if (!parser->cont) { /* skip white space */ while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; } /* only spaces were written */ if (isspace(ch)) { *ppos += read; ret = read; goto out; } parser->idx = 0; } /* read the non-space input */ while (cnt && !isspace(ch)) { if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; goto out; } ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; } /* We either got finished input or we have to wait for another call. */ if (isspace(ch)) { parser->buffer[parser->idx] = 0; parser->cont = false; } else { parser->cont = true; parser->buffer[parser->idx++] = ch; } *ppos += read; ret = read; out: return ret; } ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) { int len; int ret; if (!cnt) return 0; if (s->len <= s->readpos) return -EBUSY; len = s->len - s->readpos; if (cnt > len) cnt = len; ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); if (ret == cnt) return -EFAULT; cnt -= ret; s->readpos += cnt; return cnt; } static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; if (s->len <= s->readpos) return -EBUSY; len = s->len - s->readpos; if (cnt > len) cnt = len; memcpy(buf, s->buffer + s->readpos, cnt); s->readpos += cnt; return cnt; } /* * ftrace_max_lock is used to protect the swapping of buffers * when taking a max snapshot. The buffers themselves are * protected by per_cpu spinlocks. But the action of the swap * needs its own lock. * * This is defined as a arch_spinlock_t in order to help * with performance when lockdep debugging is enabled. * * It is also used in other places outside the update_max_tr * so it needs to be defined outside of the * CONFIG_TRACER_MAX_TRACE. */ static arch_spinlock_t ftrace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; unsigned long __read_mostly tracing_thresh; #ifdef CONFIG_TRACER_MAX_TRACE unsigned long __read_mostly tracing_max_latency; /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, * for later retrieval via /sys/kernel/debug/tracing/latency_trace) */ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct trace_array_cpu *data = tr->data[cpu]; struct trace_array_cpu *max_data; max_tr.cpu = cpu; max_tr.time_start = data->preempt_timestamp; max_data = max_tr.data[cpu]; max_data->saved_latency = tracing_max_latency; max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); max_data->pid = tsk->pid; max_data->uid = task_uid(tsk); max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; max_data->policy = tsk->policy; max_data->rt_priority = tsk->rt_priority; /* record this tasks comm */ tracing_record_cmdline(tsk); } /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer * @tsk: the task with the latency * @cpu: The cpu that initiated the trace. * * Flip the buffers between the @tr and the max_tr and record information * about which task was the cause of this latency. */ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct ring_buffer *buf = tr->buffer; if (trace_stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!current_trace->use_max_tr) { WARN_ON_ONCE(1); return; } arch_spin_lock(&ftrace_max_lock); tr->buffer = max_tr.buffer; max_tr.buffer = buf; __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&ftrace_max_lock); } /** * update_max_tr_single - only copy one trace over, and reset the rest * @tr - tracer * @tsk - task with the latency * @cpu - the cpu of the buffer to copy. * * Flip the trace of a single CPU buffer between the @tr and the max_tr. */ void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; if (trace_stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!current_trace->use_max_tr) { WARN_ON_ONCE(1); return; } arch_spin_lock(&ftrace_max_lock); ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); if (ret == -EBUSY) { /* * We failed to swap the buffer due to a commit taking * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. */ trace_array_printk(&max_tr, _THIS_IP_, "Failed to swap buffers due to commit in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&ftrace_max_lock); } #endif /* CONFIG_TRACER_MAX_TRACE */ static void default_wait_pipe(struct trace_iterator *iter) { DEFINE_WAIT(wait); prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); /* * The events can happen in critical sections where * checking a work queue can cause deadlocks. * After adding a task to the queue, this flag is set * only to notify events to try to wake up the queue * using irq_work. * * We don't clear it even if the buffer is no longer * empty. The flag only causes the next event to run * irq_work to do the work queue wake up. The worse * that can happen if we race with !trace_empty() is that * an event will cause an irq_work to try to wake up * an empty queue. * * There's no reason to protect this flag either, as * the work queue and irq_work logic will do the necessary * synchronization for the wake ups. The only thing * that is necessary is that the wake up happens after * a task has been queued. It's OK for spurious wake ups. */ trace_wakeup_needed = true; if (trace_empty(iter)) schedule(); finish_wait(&trace_wait, &wait); } /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer * * Register a new plugin tracer. */ int register_tracer(struct tracer *type) { struct tracer *t; int ret = 0; if (!type->name) { pr_info("Tracer must have a name\n"); return -1; } if (strlen(type->name) >= MAX_TRACER_SIZE) { pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); return -1; } mutex_lock(&trace_types_lock); tracing_selftest_running = true; for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ pr_info("Tracer %s already registered\n", type->name); ret = -1; goto out; } } if (!type->set_flag) type->set_flag = &dummy_set_flag; if (!type->flags) type->flags = &dummy_tracer_flags; else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; if (!type->wait_pipe) type->wait_pipe = default_wait_pipe; #ifdef CONFIG_FTRACE_STARTUP_TEST if (type->selftest && !tracing_selftest_disabled) { struct tracer *saved_tracer = current_trace; struct trace_array *tr = &global_trace; /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current * tracer to be this tracer. The tracer can then run some * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ tracing_reset_online_cpus(tr); current_trace = type; /* If we expanded the buffers, make sure the max is expanded too */ if (ring_buffer_expanded && type->use_max_tr) ring_buffer_resize(max_tr.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); /* the test is responsible for resetting too */ current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); /* Add the warning after printing 'FAILED' */ WARN_ON(1); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(tr); /* Shrink the max buffer again */ if (ring_buffer_expanded && type->use_max_tr) ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); printk(KERN_CONT "PASSED\n"); } #endif type->next = trace_types; trace_types = type; out: tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) goto out_unlock; if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) goto out_unlock; printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ tracing_set_tracer(type->name); default_bootup_tracer = NULL; /* disable other selftests, since this will break it. */ tracing_selftest_disabled = 1; #ifdef CONFIG_FTRACE_STARTUP_TEST printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", type->name); #endif out_unlock: return ret; } void tracing_reset(struct trace_array *tr, int cpu) { struct ring_buffer *buffer = tr->buffer; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_sched(); ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } void tracing_reset_online_cpus(struct trace_array *tr) { struct ring_buffer *buffer = tr->buffer; int cpu; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_sched(); tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } void tracing_reset_current(int cpu) { tracing_reset(&global_trace, cpu); } void tracing_reset_current_online_cpus(void) { tracing_reset_online_cpus(&global_trace); } #define SAVED_CMDLINES 128 #define NO_CMDLINE_MAP UINT_MAX static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; static int cmdline_idx; static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; /* temporary disable recording */ static atomic_t trace_record_cmdline_disabled __read_mostly; static void trace_init_cmdlines(void) { memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline)); memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid)); cmdline_idx = 0; } int is_tracing_stopped(void) { return trace_stop_count; } /** * ftrace_off_permanent - disable all ftrace code permanently * * This should only be called when a serious anomally has * been detected. This will turn off the function tracing, * ring buffers, and other tracing utilites. It takes no * locks and can be called from any context. */ void ftrace_off_permanent(void) { tracing_disabled = 1; ftrace_stop(); tracing_off_permanent(); } /** * tracing_start - quick start of the tracer * * If tracing is enabled but was stopped by tracing_stop, * this will start the tracer back up. */ void tracing_start(void) { struct ring_buffer *buffer; unsigned long flags; if (tracing_disabled) return; raw_spin_lock_irqsave(&tracing_start_lock, flags); if (--trace_stop_count) { if (trace_stop_count < 0) { /* Someone screwed up their debugging */ WARN_ON_ONCE(1); trace_stop_count = 0; } goto out; } /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); buffer = global_trace.buffer; if (buffer) ring_buffer_record_enable(buffer); buffer = max_tr.buffer; if (buffer) ring_buffer_record_enable(buffer); arch_spin_unlock(&ftrace_max_lock); ftrace_start(); out: raw_spin_unlock_irqrestore(&tracing_start_lock, flags); } /** * tracing_stop - quick stop of the tracer * * Light weight way to stop tracing. Use in conjunction with * tracing_start. */ void tracing_stop(void) { struct ring_buffer *buffer; unsigned long flags; ftrace_stop(); raw_spin_lock_irqsave(&tracing_start_lock, flags); if (trace_stop_count++) goto out; /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); buffer = global_trace.buffer; if (buffer) ring_buffer_record_disable(buffer); buffer = max_tr.buffer; if (buffer) ring_buffer_record_disable(buffer); arch_spin_unlock(&ftrace_max_lock); out: raw_spin_unlock_irqrestore(&tracing_start_lock, flags); } void trace_stop_cmdline_recording(void); static void trace_save_cmdline(struct task_struct *tsk) { unsigned pid, idx; if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) return; /* * It's not the end of the world if we don't get * the lock, but we also don't want to spin * nor do we want to disable interrupts, * so if we miss here, then better luck next time. */ if (!arch_spin_trylock(&trace_cmdline_lock)) return; idx = map_pid_to_cmdline[tsk->pid]; if (idx == NO_CMDLINE_MAP) { idx = (cmdline_idx + 1) % SAVED_CMDLINES; /* * Check whether the cmdline buffer at idx has a pid * mapped. We are going to overwrite that entry so we * need to clear the map_pid_to_cmdline. Otherwise we * would read the new comm for the old pid. */ pid = map_cmdline_to_pid[idx]; if (pid != NO_CMDLINE_MAP) map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; map_cmdline_to_pid[idx] = tsk->pid; map_pid_to_cmdline[tsk->pid] = idx; cmdline_idx = idx; } memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); arch_spin_unlock(&trace_cmdline_lock); } void trace_find_cmdline(int pid, char comm[]) { unsigned map; if (!pid) { strcpy(comm, ""); return; } if (WARN_ON_ONCE(pid < 0)) { strcpy(comm, ""); return; } if (pid > PID_MAX_DEFAULT) { strcpy(comm, "<...>"); return; } preempt_disable(); arch_spin_lock(&trace_cmdline_lock); map = map_pid_to_cmdline[pid]; if (map != NO_CMDLINE_MAP) strcpy(comm, saved_cmdlines[map]); else strcpy(comm, "<...>"); arch_spin_unlock(&trace_cmdline_lock); preempt_enable(); } void tracing_record_cmdline(struct task_struct *tsk) { if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) return; if (!__this_cpu_read(trace_cmdline_save)) return; __this_cpu_write(trace_cmdline_save, false); trace_save_cmdline(tsk); } void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc) { struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; entry->padding = 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | #else TRACE_FLAG_IRQS_NOSUPPORT | #endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); struct ring_buffer_event * trace_buffer_lock_reserve(struct ring_buffer *buffer, int type, unsigned long len, unsigned long flags, int pc) { struct ring_buffer_event *event; event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) { struct trace_entry *ent = ring_buffer_event_data(event); tracing_generic_entry_update(ent, flags, pc); ent->type = type; } return event; } void __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_cmdline_save, true); if (trace_wakeup_needed) { trace_wakeup_needed = false; /* irq_work_queue() supplies it's own memory barriers */ irq_work_queue(&trace_work_wakeup); } ring_buffer_unlock_commit(buffer, event); } static inline void __trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); ftrace_trace_userstack(buffer, flags, pc); } void trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { __trace_buffer_unlock_commit(buffer, event, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, int type, unsigned long len, unsigned long flags, int pc) { *current_rb = global_trace.buffer; return trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); } EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve); void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { __trace_buffer_unlock_commit(buffer, event, flags, pc); } EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit); void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc, struct pt_regs *regs) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack_regs(buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); void trace_current_buffer_discard_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { ring_buffer_discard_commit(buffer, event); } EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit); void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc) { struct ftrace_event_call *call = &event_function; struct ring_buffer *buffer = tr->buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; /* If we are reading the ring buffer, don't trace */ if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return; event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); entry->ip = ip; entry->parent_ip = parent_ip; if (!filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); } void ftrace(struct trace_array *tr, struct trace_array_cpu *data, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc) { if (likely(!atomic_read(&data->disabled))) trace_function(tr, ip, parent_ip, flags, pc); } #ifdef CONFIG_STACKTRACE #define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) struct ftrace_stack { unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; }; static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { struct ftrace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; struct stack_entry *entry; struct stack_trace trace; int use_stack; int size = FTRACE_STACK_ENTRIES; trace.nr_entries = 0; trace.skip = skip; /* * Since events can happen in NMIs there's no safe way to * use the per cpu ftrace_stacks. We reserve it and if an interrupt * or NMI comes in, it will just have to use the default * FTRACE_STACK_SIZE. */ preempt_disable_notrace(); use_stack = ++__get_cpu_var(ftrace_stack_reserve); /* * We don't need any atomic variables, just a barrier. * If an interrupt comes in, we don't care, because it would * have exited and put the counter back to what we want. * We just need a barrier to keep gcc from moving things * around. */ barrier(); if (use_stack == 1) { trace.entries = &__get_cpu_var(ftrace_stack).calls[0]; trace.max_entries = FTRACE_STACK_MAX_ENTRIES; if (regs) save_stack_trace_regs(regs, &trace); else save_stack_trace(&trace); if (trace.nr_entries > size) size = trace.nr_entries; } else /* From now on, use_stack is a boolean */ use_stack = 0; size *= sizeof(unsigned long); event = trace_buffer_lock_reserve(buffer, TRACE_STACK, sizeof(*entry) + size, flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); memset(&entry->caller, 0, size); if (use_stack) memcpy(&entry->caller, trace.entries, trace.nr_entries * sizeof(unsigned long)); else { trace.max_entries = FTRACE_STACK_ENTRIES; trace.entries = entry->caller; if (regs) save_stack_trace_regs(regs, &trace); else save_stack_trace(&trace); } entry->size = trace.nr_entries; if (!filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ barrier(); __get_cpu_var(ftrace_stack_reserve)--; preempt_enable_notrace(); } void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { if (!(trace_flags & TRACE_ITER_STACKTRACE)) return; __ftrace_trace_stack(buffer, flags, skip, pc, regs); } void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, int skip, int pc) { if (!(trace_flags & TRACE_ITER_STACKTRACE)) return; __ftrace_trace_stack(buffer, flags, skip, pc, NULL); } void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL); } /** * trace_dump_stack - record a stack back trace in the trace buffer */ void trace_dump_stack(void) { unsigned long flags; if (tracing_disabled || tracing_selftest_running) return; local_save_flags(flags); /* skipping 3 traces, seems to get us at the caller of this function */ __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL); } static DEFINE_PER_CPU(int, user_stack_count); void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { struct ftrace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; struct stack_trace trace; if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* * NMIs can not handle page faults, even with fix ups. * The save user stack can (and often does) fault. */ if (unlikely(in_nmi())) return; /* * prevent recursion, since the user stack tracing may * trigger other kernel events. */ preempt_disable(); if (__this_cpu_read(user_stack_count)) goto out; __this_cpu_inc(user_stack_count); event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, sizeof(*entry), flags, pc); if (!event) goto out_drop_count; entry = ring_buffer_event_data(event); entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); trace.nr_entries = 0; trace.max_entries = FTRACE_STACK_ENTRIES; trace.skip = 0; trace.entries = entry->caller; save_stack_trace_user(&trace); if (!filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); out: preempt_enable(); } #ifdef UNUSED static void __trace_userstack(struct trace_array *tr, unsigned long flags) { ftrace_trace_userstack(tr, flags, preempt_count()); } #endif /* UNUSED */ #endif /* CONFIG_STACKTRACE */ /* created for use with alloc_percpu */ struct trace_buffer_struct { char buffer[TRACE_BUF_SIZE]; }; static struct trace_buffer_struct *trace_percpu_buffer; static struct trace_buffer_struct *trace_percpu_sirq_buffer; static struct trace_buffer_struct *trace_percpu_irq_buffer; static struct trace_buffer_struct *trace_percpu_nmi_buffer; /* * The buffer used is dependent on the context. There is a per cpu * buffer for normal context, softirq contex, hard irq context and * for NMI context. Thise allows for lockless recording. * * Note, if the buffers failed to be allocated, then this returns NULL */ static char *get_trace_buf(void) { struct trace_buffer_struct *percpu_buffer; struct trace_buffer_struct *buffer; /* * If we have allocated per cpu buffers, then we do not * need to do any locking. */ if (in_nmi()) percpu_buffer = trace_percpu_nmi_buffer; else if (in_irq()) percpu_buffer = trace_percpu_irq_buffer; else if (in_softirq()) percpu_buffer = trace_percpu_sirq_buffer; else percpu_buffer = trace_percpu_buffer; if (!percpu_buffer) return NULL; buffer = per_cpu_ptr(percpu_buffer, smp_processor_id()); return buffer->buffer; } static int alloc_percpu_trace_buffer(void) { struct trace_buffer_struct *buffers; struct trace_buffer_struct *sirq_buffers; struct trace_buffer_struct *irq_buffers; struct trace_buffer_struct *nmi_buffers; buffers = alloc_percpu(struct trace_buffer_struct); if (!buffers) goto err_warn; sirq_buffers = alloc_percpu(struct trace_buffer_struct); if (!sirq_buffers) goto err_sirq; irq_buffers = alloc_percpu(struct trace_buffer_struct); if (!irq_buffers) goto err_irq; nmi_buffers = alloc_percpu(struct trace_buffer_struct); if (!nmi_buffers) goto err_nmi; trace_percpu_buffer = buffers; trace_percpu_sirq_buffer = sirq_buffers; trace_percpu_irq_buffer = irq_buffers; trace_percpu_nmi_buffer = nmi_buffers; return 0; err_nmi: free_percpu(irq_buffers); err_irq: free_percpu(sirq_buffers); err_sirq: free_percpu(buffers); err_warn: WARN(1, "Could not allocate percpu trace_printk buffer"); return -ENOMEM; } static int buffers_allocated; void trace_printk_init_buffers(void) { if (buffers_allocated) return; if (alloc_percpu_trace_buffer()) return; pr_info("ftrace: Allocated trace_printk buffers\n"); /* Expand the buffers to set size */ tracing_update_buffers(); buffers_allocated = 1; /* * trace_printk_init_buffers() can be called by modules. * If that happens, then we need to start cmdline recording * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ if (global_trace.buffer) tracing_start_cmdline_record(); } void trace_printk_start_comm(void) { /* Start tracing comms if trace printk is set */ if (!buffers_allocated) return; tracing_start_cmdline_record(); } static void trace_printk_start_stop_comm(int enabled) { if (!buffers_allocated) return; if (enabled) tracing_start_cmdline_record(); else tracing_stop_cmdline_record(); } /** * trace_vbprintk - write binary msg to tracing buffer * */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { struct ftrace_event_call *call = &event_bprint; struct ring_buffer_event *event; struct ring_buffer *buffer; struct trace_array *tr = &global_trace; struct bprint_entry *entry; unsigned long flags; char *tbuffer; int len = 0, size, pc; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); pc = preempt_count(); preempt_disable_notrace(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out; } len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) goto out; local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->fmt = fmt; memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } out: preempt_enable_notrace(); unpause_graph_tracing(); return len; } EXPORT_SYMBOL_GPL(trace_vbprintk); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; if (!(trace_flags & TRACE_ITER_PRINTK)) return 0; va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); return ret; } int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { struct ftrace_event_call *call = &event_print; struct ring_buffer_event *event; struct ring_buffer *buffer; int len = 0, size, pc; struct print_entry *entry; unsigned long flags; char *tbuffer; if (tracing_disabled || tracing_selftest_running) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); pc = preempt_count(); preempt_disable_notrace(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out; } len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); if (len > TRACE_BUF_SIZE) goto out; local_save_flags(flags); size = sizeof(*entry) + len + 1; buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } out: preempt_enable_notrace(); unpause_graph_tracing(); return len; } int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(&global_trace, ip, fmt, args); } EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); iter->idx++; if (buf_iter) ring_buffer_read(buf_iter, NULL); } static struct trace_entry * peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); else event = ring_buffer_peek(iter->tr->buffer, cpu, ts, lost_events); if (event) { iter->ent_size = ring_buffer_event_length(event); return ring_buffer_event_data(event); } iter->ent_size = 0; return NULL; } static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { struct ring_buffer *buffer = iter->tr->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; int next_size = 0; int cpu; /* * If we are in a per_cpu trace file, don't bother by iterating over * all cpu and peek directly. */ if (cpu_file > TRACE_PIPE_ALL_CPU) { if (ring_buffer_empty_cpu(buffer, cpu_file)) return NULL; ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); if (ent_cpu) *ent_cpu = cpu_file; return ent; } for_each_tracing_cpu(cpu) { if (ring_buffer_empty_cpu(buffer, cpu)) continue; ent = peek_next_entry(iter, cpu, &ts, &lost_events); /* * Pick the entry with the smallest timestamp: */ if (ent && (!next || ts < next_ts)) { next = ent; next_cpu = cpu; next_ts = ts; next_lost = lost_events; next_size = iter->ent_size; } } iter->ent_size = next_size; if (ent_cpu) *ent_cpu = next_cpu; if (ent_ts) *ent_ts = next_ts; if (missing_events) *missing_events = next_lost; return next; } /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { return __find_next_entry(iter, ent_cpu, NULL, ent_ts); } /* Find the next real entry, and increment the iterator to the next entry */ void *trace_find_next_entry_inc(struct trace_iterator *iter) { iter->ent = __find_next_entry(iter, &iter->cpu, &iter->lost_events, &iter->ts); if (iter->ent) trace_iterator_increment(iter); return iter->ent ? iter : NULL; } static void trace_consume(struct trace_iterator *iter) { ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, &iter->lost_events); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_iterator *iter = m->private; int i = (int)*pos; void *ent; WARN_ON_ONCE(iter->leftover); (*pos)++; /* can't go backwards */ if (iter->idx > i) return NULL; if (iter->idx < 0) ent = trace_find_next_entry_inc(iter); else ent = iter; while (ent && iter->idx < i) ent = trace_find_next_entry_inc(iter); iter->pos = *pos; return ent; } void tracing_iter_reset(struct trace_iterator *iter, int cpu) { struct trace_array *tr = iter->tr; struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter; unsigned long entries = 0; u64 ts; tr->data[cpu]->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) return; ring_buffer_iter_reset(buf_iter); /* * We could have the case with the max latency tracers * that a reset never took place on a cpu. This is evident * by the timestamp being before the start of the buffer. */ while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { if (ts >= iter->tr->time_start) break; entries++; ring_buffer_read(buf_iter, NULL); } tr->data[cpu]->skipped_entries = entries; } /* * The current tracer is copied to avoid a global locking * all around. */ static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; static struct tracer *old_tracer; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); if (unlikely(old_tracer != current_trace && current_trace)) { old_tracer = current_trace; *iter->trace = *current_trace; } mutex_unlock(&trace_types_lock); atomic_inc(&trace_record_cmdline_disabled); if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; iter->idx = -1; if (cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else tracing_iter_reset(iter, cpu_file); iter->leftover = 0; for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; } else { /* * If we overflowed the seq_file before, then we want * to just reuse the trace_seq buffer again. */ if (iter->leftover) p = iter; else { l = *pos - 1; p = s_next(m, p, &l); } } trace_event_read_lock(); trace_access_lock(cpu_file); return p; } static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; atomic_dec(&trace_record_cmdline_disabled); trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries) { unsigned long count; int cpu; *total = 0; *entries = 0; for_each_tracing_cpu(cpu) { count = ring_buffer_entries_cpu(tr->buffer, cpu); /* * If this buffer has skipped entries, then we hold all * entries for the trace and we need to ignore the * ones before the time stamp. */ if (tr->data[cpu]->skipped_entries) { count -= tr->data[cpu]->skipped_entries; /* total is the same as the entries */ *total += count; } else *total += count + ring_buffer_overrun_cpu(tr->buffer, cpu); *entries += count; } } static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n"); seq_puts(m, "# / _-----=> irqs-off \n"); seq_puts(m, "# | / _----=> need-resched \n"); seq_puts(m, "# || / _---=> hardirq/softirq \n"); seq_puts(m, "# ||| / _--=> preempt-depth \n"); seq_puts(m, "# |||| / delay \n"); seq_puts(m, "# cmd pid ||||| time | caller \n"); seq_puts(m, "# \\ / ||||| \\ | / \n"); } static void print_event_info(struct trace_array *tr, struct seq_file *m) { unsigned long total; unsigned long entries; get_total_entries(tr, &total, &entries); seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", entries, total, num_online_cpus()); seq_puts(m, "#\n"); } static void print_func_help_header(struct trace_array *tr, struct seq_file *m) { print_event_info(tr, m); seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); seq_puts(m, "# | | | | |\n"); } static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m) { print_event_info(tr, m); seq_puts(m, "# _-----=> irqs-off\n"); seq_puts(m, "# / _----=> need-resched\n"); seq_puts(m, "# | / _---=> hardirq/softirq\n"); seq_puts(m, "# || / _--=> preempt-depth\n"); seq_puts(m, "# ||| / delay\n"); seq_puts(m, "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"); seq_puts(m, "# | | | |||| | |\n"); } void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_array *tr = iter->tr; struct trace_array_cpu *data = tr->data[tr->cpu]; struct tracer *type = current_trace; unsigned long entries; unsigned long total; const char *name = "preemption"; if (type) name = type->name; get_total_entries(tr, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); seq_puts(m, "# -----------------------------------" "---------------------------------\n"); seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" " (M:%s VP:%d, KP:%d, SP:%d HP:%d", nsecs_to_usecs(data->saved_latency), entries, total, tr->cpu, #if defined(CONFIG_PREEMPT_NONE) "server", #elif defined(CONFIG_PREEMPT_VOLUNTARY) "desktop", #elif defined(CONFIG_PREEMPT) "preempt", #else "unknown", #endif /* These are reserved for later use */ 0, 0, 0, 0); #ifdef CONFIG_SMP seq_printf(m, " #P:%d)\n", num_online_cpus()); #else seq_puts(m, ")\n"); #endif seq_puts(m, "# -----------------\n"); seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", data->comm, data->pid, from_kuid_munged(seq_user_ns(m), data->uid), data->nice, data->policy, data->rt_priority); seq_puts(m, "# -----------------\n"); if (data->critical_start) { seq_puts(m, "# => started at: "); seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n# => ended at: "); seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n#\n"); } seq_puts(m, "#\n"); } static void test_cpu_buff_start(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; if (!(trace_flags & TRACE_ITER_ANNOTATE)) return; if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) return; if (cpumask_test_cpu(iter->cpu, iter->started)) return; if (iter->tr->data[iter->cpu]->skipped_entries) return; cpumask_set_cpu(iter->cpu, iter->started); /* Don't print started cpu buffer for the first entry of the trace */ if (iter->idx > 1) trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu); } static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *entry; struct trace_event *event; entry = iter->ent; test_cpu_buff_start(iter); event = ftrace_find_event(entry->type); if (trace_flags & TRACE_ITER_CONTEXT_INFO) { if (iter->iter_flags & TRACE_FILE_LAT_FMT) { if (!trace_print_lat_context(iter)) goto partial; } else { if (!trace_print_context(iter)) goto partial; } } if (event) return event->funcs->trace(iter, sym_flags, event); if (!trace_seq_printf(s, "Unknown type %d\n", entry->type)) goto partial; return TRACE_TYPE_HANDLED; partial: return TRACE_TYPE_PARTIAL_LINE; } static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (trace_flags & TRACE_ITER_CONTEXT_INFO) { if (!trace_seq_printf(s, "%d %d %llu ", entry->pid, iter->cpu, iter->ts)) goto partial; } event = ftrace_find_event(entry->type); if (event) return event->funcs->raw(iter, 0, event); if (!trace_seq_printf(s, "%d ?\n", entry->type)) goto partial; return TRACE_TYPE_HANDLED; partial: return TRACE_TYPE_PARTIAL_LINE; } static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_HEX_FIELD_RET(s, entry->pid); SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); SEQ_PUT_HEX_FIELD_RET(s, iter->ts); } event = ftrace_find_event(entry->type); if (event) { enum print_line_t ret = event->funcs->hex(iter, 0, event); if (ret != TRACE_TYPE_HANDLED) return ret; } SEQ_PUT_FIELD_RET(s, newline); return TRACE_TYPE_HANDLED; } static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_FIELD_RET(s, entry->pid); SEQ_PUT_FIELD_RET(s, iter->cpu); SEQ_PUT_FIELD_RET(s, iter->ts); } event = ftrace_find_event(entry->type); return event ? event->funcs->binary(iter, 0, event) : TRACE_TYPE_HANDLED; } int trace_empty(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { cpu = iter->cpu_file; buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) return 0; } return 1; } for_each_tracing_cpu(cpu) { buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) return 0; } } return 1; } /* Called with trace_event_read_lock() held. */ enum print_line_t print_trace_line(struct trace_iterator *iter) { enum print_line_t ret; if (iter->lost_events && !trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", iter->cpu, iter->lost_events)) return TRACE_TYPE_PARTIAL_LINE; if (iter->trace && iter->trace->print_line) { ret = iter->trace->print_line(iter); if (ret != TRACE_TYPE_UNHANDLED) return ret; } if (iter->ent->type == TRACE_BPRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_bprintk_msg_only(iter); if (iter->ent->type == TRACE_PRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_printk_msg_only(iter); if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); if (trace_flags & TRACE_ITER_HEX) return print_hex_fmt(iter); if (trace_flags & TRACE_ITER_RAW) return print_raw_fmt(iter); return print_trace_fmt(iter); } void trace_latency_header(struct seq_file *m) { struct trace_iterator *iter = m->private; /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) print_trace_header(m, iter); if (!(trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } void trace_default_header(struct seq_file *m) { struct trace_iterator *iter = m->private; if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; print_trace_header(m, iter); if (!(trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) print_func_help_header_irq(iter->tr, m); else print_func_help_header(iter->tr, m); } } } static void test_ftrace_alive(struct seq_file *m) { if (!ftrace_is_dead()) return; seq_printf(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n"); seq_printf(m, "# MAY BE MISSING FUNCTION EVENTS\n"); } static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; int ret; if (iter->ent == NULL) { if (iter->tr) { seq_printf(m, "# tracer: %s\n", iter->trace->name); seq_puts(m, "#\n"); test_ftrace_alive(m); } if (iter->trace && iter->trace->print_header) iter->trace->print_header(m); else trace_default_header(m); } else if (iter->leftover) { /* * If we filled the seq_file buffer earlier, we * want to just show it now. */ ret = trace_print_seq(m, &iter->seq); /* ret should this time be zero, but you never know */ iter->leftover = ret; } else { print_trace_line(iter); ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will * ask us for this data again at start up. * Use that instead. * ret is 0 if seq_file write succeeded. * -1 otherwise. */ iter->leftover = ret; } return 0; } static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file) { long cpu_file = (long) inode->i_private; struct trace_iterator *iter; int cpu; if (tracing_disabled) return ERR_PTR(-ENODEV); iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); if (!iter) return ERR_PTR(-ENOMEM); iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), GFP_KERNEL); if (!iter->buffer_iter) goto release; /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. */ mutex_lock(&trace_types_lock); iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL); if (!iter->trace) goto fail; if (current_trace) *iter->trace = *current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; if (current_trace && current_trace->print_max) iter->tr = &max_tr; else iter->tr = &global_trace; iter->pos = -1; mutex_init(&iter->mutex); iter->cpu_file = cpu_file; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ if (ring_buffer_overruns(iter->tr->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[trace_clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* stop the trace while dumping */ tracing_stop(); if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = ring_buffer_read_prepare(iter->tr->buffer, cpu); } ring_buffer_read_prepare_sync(); for_each_tracing_cpu(cpu) { ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); } } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = ring_buffer_read_prepare(iter->tr->buffer, cpu); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); } mutex_unlock(&trace_types_lock); return iter; fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); kfree(iter->buffer_iter); release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) { if (tracing_disabled) return -ENODEV; filp->private_data = inode->i_private; return 0; } static int tracing_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct trace_iterator *iter; int cpu; if (!(file->f_mode & FMODE_READ)) return 0; iter = m->private; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); } if (iter->trace && iter->trace->close) iter->trace->close(iter); /* reenable tracing if it was previously enabled */ tracing_start(); mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); kfree(iter->buffer_iter); seq_release_private(inode, file); return 0; } static int tracing_open(struct inode *inode, struct file *file) { struct trace_iterator *iter; int ret = 0; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { long cpu = (long) inode->i_private; if (cpu == TRACE_PIPE_ALL_CPU) tracing_reset_online_cpus(&global_trace); else tracing_reset(&global_trace, cpu); } if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; } return ret; } static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct tracer *t = v; (*pos)++; if (t) t = t->next; return t; } static void *t_start(struct seq_file *m, loff_t *pos) { 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)) ; return t; } static void t_stop(struct seq_file *m, void *p) { mutex_unlock(&trace_types_lock); } static int t_show(struct seq_file *m, void *v) { struct tracer *t = v; if (!t) return 0; seq_printf(m, "%s", t->name); if (t->next) seq_putc(m, ' '); else seq_putc(m, '\n'); return 0; } static const struct seq_operations show_traces_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, .show = t_show, }; static int show_traces_open(struct inode *inode, struct file *file) { if (tracing_disabled) return -ENODEV; return seq_open(file, &show_traces_seq_ops); } static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { return count; } static loff_t tracing_seek(struct file *file, loff_t offset, int origin) { if (file->f_mode & FMODE_READ) return seq_lseek(file, offset, origin); else return 0; } static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, .write = tracing_write_stub, .llseek = tracing_seek, .release = tracing_release, }; static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, .release = seq_release, .llseek = seq_lseek, }; /* * Only trace on a CPU if the bitmask is set: */ static cpumask_var_t tracing_cpumask; /* * The tracer itself will not take this lock, but still we want * to provide a consistent cpumask to user-space: */ static DEFINE_MUTEX(tracing_cpumask_update_lock); /* * Temporary storage for the character representation of the * CPU bitmask (and one more byte for the newline): */ static char ma