#include <linux/fs.h>
#include <linux/kprobes.h>
#include <linux/writeback.h>
+#include <linux/splice.h>
#include <linux/stacktrace.h>
#include <linux/ring_buffer.h>
* of the tracer is successful. But that is the only place that sets
* this back to zero.
*/
-int tracing_disabled = 1;
+static int tracing_disabled = 1;
static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
static cpumask_var_t __read_mostly tracing_buffer_mask;
+/* Define which cpu buffers are currently read in trace_pipe */
+static cpumask_var_t tracing_reader_cpumask;
+
#define for_each_tracing_cpu(cpu) \
for_each_cpu(cpu, tracing_buffer_mask)
data->rt_priority = tsk->rt_priority;
/* record this tasks comm */
- tracing_record_cmdline(current);
+ tracing_record_cmdline(tsk);
}
static void
return cnt;
}
+ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
+{
+ int len;
+ void *ret;
+
+ if (s->len <= s->readpos)
+ return -EBUSY;
+
+ len = s->len - s->readpos;
+ if (cnt > len)
+ cnt = len;
+ ret = memcpy(buf, s->buffer + s->readpos, cnt);
+ if (!ret)
+ return -EFAULT;
+
+ s->readpos += len;
+ return cnt;
+}
+
static void
trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
* Register a new plugin tracer.
*/
int register_tracer(struct tracer *type)
+__releases(kernel_lock)
+__acquires(kernel_lock)
{
struct tracer *t;
int len;
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) {
tracing_selftest_running = false;
mutex_unlock(&trace_types_lock);
- if (!ret && default_bootup_tracer) {
- if (!strncmp(default_bootup_tracer, type->name,
- BOOTUP_TRACER_SIZE)) {
- 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;
+ if (ret || !default_bootup_tracer)
+ goto out_unlock;
+
+ if (strncmp(default_bootup_tracer, type->name, BOOTUP_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);
+ printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
+ type->name);
#endif
- }
- }
+ out_unlock:
lock_kernel();
return ret;
}
found:
*t = (*t)->next;
+
+ if (type == current_trace && tracer_enabled) {
+ tracer_enabled = 0;
+ tracing_stop();
+ if (current_trace->stop)
+ current_trace->stop(&global_trace);
+ current_trace = &nop_trace;
+ }
+
if (strlen(type->name) != max_tracer_type_len)
goto out;
static DEFINE_SPINLOCK(trace_cmdline_lock);
/* temporary disable recording */
-atomic_t trace_record_cmdline_disabled __read_mostly;
+static atomic_t trace_record_cmdline_disabled __read_mostly;
static void trace_init_cmdlines(void)
{
(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
}
+struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
+ unsigned char type,
+ unsigned long len,
+ unsigned long flags, int pc)
+{
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(tr->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;
+}
+static void ftrace_trace_stack(struct trace_array *tr,
+ unsigned long flags, int skip, int pc);
+static void ftrace_trace_userstack(struct trace_array *tr,
+ unsigned long flags, int pc);
+
+void trace_buffer_unlock_commit(struct trace_array *tr,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ ring_buffer_unlock_commit(tr->buffer, event);
+
+ ftrace_trace_stack(tr, flags, 6, pc);
+ ftrace_trace_userstack(tr, flags, pc);
+ trace_wake_up();
+}
+
void
-trace_function(struct trace_array *tr, struct trace_array_cpu *data,
+trace_function(struct trace_array *tr,
unsigned long ip, unsigned long parent_ip, unsigned long flags,
int pc)
{
struct ring_buffer_event *event;
struct ftrace_entry *entry;
- unsigned long irq_flags;
/* If we are reading the ring buffer, don't trace */
if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
return;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
+ flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_FN;
entry->ip = ip;
entry->parent_ip = parent_ip;
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+ ring_buffer_unlock_commit(tr->buffer, event);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static void __trace_graph_entry(struct trace_array *tr,
- struct trace_array_cpu *data,
struct ftrace_graph_ent *trace,
unsigned long flags,
int pc)
{
struct ring_buffer_event *event;
struct ftrace_graph_ent_entry *entry;
- unsigned long irq_flags;
if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
return;
- event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_GRAPH_ENT;
entry->graph_ent = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+ ring_buffer_unlock_commit(global_trace.buffer, event);
}
static void __trace_graph_return(struct trace_array *tr,
- struct trace_array_cpu *data,
struct ftrace_graph_ret *trace,
unsigned long flags,
int pc)
{
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *entry;
- unsigned long irq_flags;
if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
return;
- event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_GRAPH_RET;
entry->ret = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+ ring_buffer_unlock_commit(global_trace.buffer, event);
}
#endif
int pc)
{
if (likely(!atomic_read(&data->disabled)))
- trace_function(tr, data, ip, parent_ip, flags, pc);
+ trace_function(tr, ip, parent_ip, flags, pc);
}
static void __ftrace_trace_stack(struct trace_array *tr,
- struct trace_array_cpu *data,
unsigned long flags,
int skip, int pc)
{
struct ring_buffer_event *event;
struct stack_entry *entry;
struct stack_trace trace;
- unsigned long irq_flags;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_STACK,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_STACK;
-
memset(&entry->caller, 0, sizeof(entry->caller));
trace.nr_entries = 0;
trace.entries = entry->caller;
save_stack_trace(&trace);
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
static void ftrace_trace_stack(struct trace_array *tr,
- struct trace_array_cpu *data,
unsigned long flags,
int skip, int pc)
{
if (!(trace_flags & TRACE_ITER_STACKTRACE))
return;
- __ftrace_trace_stack(tr, data, flags, skip, pc);
+ __ftrace_trace_stack(tr, flags, skip, pc);
}
void __trace_stack(struct trace_array *tr,
- struct trace_array_cpu *data,
unsigned long flags,
int skip, int pc)
{
- __ftrace_trace_stack(tr, data, flags, skip, pc);
+ __ftrace_trace_stack(tr, flags, skip, pc);
}
static void ftrace_trace_userstack(struct trace_array *tr,
- struct trace_array_cpu *data,
- unsigned long flags, int pc)
+ unsigned long flags, int pc)
{
#ifdef CONFIG_STACKTRACE
struct ring_buffer_event *event;
struct userstack_entry *entry;
struct stack_trace trace;
- unsigned long irq_flags;
if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_USER_STACK;
memset(&entry->caller, 0, sizeof(entry->caller));
trace.entries = entry->caller;
save_stack_trace_user(&trace);
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
-void __trace_userstack(struct trace_array *tr,
- struct trace_array_cpu *data,
- unsigned long flags)
+#ifdef UNUSED
+static void __trace_userstack(struct trace_array *tr, unsigned long flags)
{
- ftrace_trace_userstack(tr, data, flags, preempt_count());
+ ftrace_trace_userstack(tr, flags, preempt_count());
}
+#endif /* UNUSED */
static void
-ftrace_trace_special(void *__tr, void *__data,
+ftrace_trace_special(void *__tr,
unsigned long arg1, unsigned long arg2, unsigned long arg3,
int pc)
{
struct ring_buffer_event *event;
- struct trace_array_cpu *data = __data;
struct trace_array *tr = __tr;
struct special_entry *entry;
- unsigned long irq_flags;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL,
+ sizeof(*entry), 0, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, 0, pc);
- entry->ent.type = TRACE_SPECIAL;
entry->arg1 = arg1;
entry->arg2 = arg2;
entry->arg3 = arg3;
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
- ftrace_trace_stack(tr, data, irq_flags, 4, pc);
- ftrace_trace_userstack(tr, data, irq_flags, pc);
-
- trace_wake_up();
+ trace_buffer_unlock_commit(tr, event, 0, pc);
}
void
__trace_special(void *__tr, void *__data,
unsigned long arg1, unsigned long arg2, unsigned long arg3)
{
- ftrace_trace_special(__tr, __data, arg1, arg2, arg3, preempt_count());
+ ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
}
void
tracing_sched_switch_trace(struct trace_array *tr,
- struct trace_array_cpu *data,
struct task_struct *prev,
struct task_struct *next,
unsigned long flags, int pc)
{
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
- unsigned long irq_flags;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_CTX,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_CTX;
entry->prev_pid = prev->pid;
entry->prev_prio = prev->prio;
entry->prev_state = prev->state;
entry->next_prio = next->prio;
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
- ftrace_trace_stack(tr, data, flags, 5, pc);
- ftrace_trace_userstack(tr, data, flags, pc);
+ trace_buffer_unlock_commit(tr, event, flags, pc);
}
void
tracing_sched_wakeup_trace(struct trace_array *tr,
- struct trace_array_cpu *data,
struct task_struct *wakee,
struct task_struct *curr,
unsigned long flags, int pc)
{
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
- unsigned long irq_flags;
- event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
- &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
+ sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
- entry->ent.type = TRACE_WAKE;
entry->prev_pid = curr->pid;
entry->prev_prio = curr->prio;
entry->prev_state = curr->state;
entry->next_prio = wakee->prio;
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
- ftrace_trace_stack(tr, data, flags, 6, pc);
- ftrace_trace_userstack(tr, data, flags, pc);
- trace_wake_up();
+ ring_buffer_unlock_commit(tr->buffer, event);
+ ftrace_trace_stack(tr, flags, 6, pc);
+ ftrace_trace_userstack(tr, flags, pc);
}
void
data = tr->data[cpu];
if (likely(atomic_inc_return(&data->disabled) == 1))
- ftrace_trace_special(tr, data, arg1, arg2, arg3, pc);
+ ftrace_trace_special(tr, arg1, arg2, arg3, pc);
atomic_dec(&data->disabled);
local_irq_restore(flags);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
- __trace_graph_entry(tr, data, trace, flags, pc);
+ __trace_graph_entry(tr, trace, flags, pc);
}
/* Only do the atomic if it is not already set */
if (!test_tsk_trace_graph(current))
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
- __trace_graph_return(tr, data, trace, flags, pc);
+ __trace_graph_return(tr, trace, flags, pc);
}
if (!trace->depth)
clear_tsk_trace_graph(current);
{
struct ring_buffer *buffer = iter->tr->buffer;
struct trace_entry *ent, *next = NULL;
+ int cpu_file = iter->cpu_file;
u64 next_ts = 0, ts;
int next_cpu = -1;
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);
+ if (ent_cpu)
+ *ent_cpu = cpu_file;
+
+ return ent;
+ }
+
for_each_tracing_cpu(cpu) {
if (ring_buffer_empty_cpu(buffer, cpu))
return ent;
}
+/*
+ * No necessary locking here. The worst thing which can
+ * happen is loosing events consumed at the same time
+ * by a trace_pipe reader.
+ * Other than that, we don't risk to crash the ring buffer
+ * because it serializes the readers.
+ *
+ * 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 (!current_trace || current_trace != iter->trace) {
- mutex_unlock(&trace_types_lock);
- return NULL;
+ 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);
ftrace_disable_cpu();
- for_each_tracing_cpu(cpu) {
- ring_buffer_iter_reset(iter->buffer_iter[cpu]);
- }
+ if (cpu_file == TRACE_PIPE_ALL_CPU) {
+ for_each_tracing_cpu(cpu)
+ ring_buffer_iter_reset(iter->buffer_iter[cpu]);
+ } else
+ ring_buffer_iter_reset(iter->buffer_iter[cpu_file]);
+
ftrace_enable_cpu();
static void s_stop(struct seq_file *m, void *p)
{
atomic_dec(&trace_record_cmdline_disabled);
- mutex_unlock(&trace_types_lock);
}
static void print_lat_help_header(struct seq_file *m)
if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
SEQ_PUT_FIELD_RET(s, entry->pid);
- SEQ_PUT_FIELD_RET(s, entry->cpu);
+ SEQ_PUT_FIELD_RET(s, iter->cpu);
SEQ_PUT_FIELD_RET(s, iter->ts);
}
static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, int *ret)
{
+ long cpu_file = (long) inode->i_private;
struct trace_iterator *iter;
struct seq_file *m;
int cpu;
goto out;
}
+ /*
+ * 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) {
+ *ret = -ENOMEM;
+ goto fail;
+ }
+ if (current_trace)
+ *iter->trace = *current_trace;
+
if (current_trace && current_trace->print_max)
iter->tr = &max_tr;
else
- iter->tr = inode->i_private;
- iter->trace = current_trace;
+ 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)
if (ring_buffer_overruns(iter->tr->buffer))
iter->iter_flags |= TRACE_FILE_ANNOTATE;
+ if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
+ for_each_tracing_cpu(cpu) {
- for_each_tracing_cpu(cpu) {
+ iter->buffer_iter[cpu] =
+ ring_buffer_read_start(iter->tr->buffer, cpu);
+ if (!iter->buffer_iter[cpu])
+ goto fail_buffer;
+ }
+ } else {
+ cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_start(iter->tr->buffer, cpu);
+ ring_buffer_read_start(iter->tr->buffer, cpu);
if (!iter->buffer_iter[cpu])
- goto fail_buffer;
+ goto fail;
}
/* TODO stop tracer */
if (iter->buffer_iter[cpu])
ring_buffer_read_finish(iter->buffer_iter[cpu]);
}
+ fail:
mutex_unlock(&trace_types_lock);
+ kfree(iter->trace);
kfree(iter);
return ERR_PTR(-ENOMEM);
return 0;
}
-int tracing_release(struct inode *inode, struct file *file)
+static int tracing_release(struct inode *inode, struct file *file)
{
struct seq_file *m = (struct seq_file *)file->private_data;
struct trace_iterator *iter = m->private;
mutex_unlock(&trace_types_lock);
seq_release(inode, file);
+ mutex_destroy(&iter->mutex);
+ kfree(iter->trace);
kfree(iter);
return 0;
}
struct tracer_opt *trace_opts = current_trace->flags->opts;
- /* calulate max size */
+ /* calculate max size */
for (i = 0; trace_options[i]; i++) {
len += strlen(trace_options[i]);
len += 3; /* "no" and space */
{
struct trace_array *tr = filp->private_data;
char buf[64];
- long val;
+ unsigned long val;
int ret;
if (cnt >= sizeof(buf))
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
+int tracer_init(struct tracer *t, struct trace_array *tr)
+{
+ tracing_reset_online_cpus(tr);
+ return t->init(tr);
+}
+
static int tracing_set_tracer(const char *buf)
{
struct trace_array *tr = &global_trace;
current_trace = t;
if (t->init) {
- ret = t->init(tr);
+ ret = tracer_init(t, tr);
if (ret)
goto out;
}
tracing_max_lat_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- long *ptr = filp->private_data;
+ unsigned long *ptr = filp->private_data;
char buf[64];
- long val;
+ unsigned long val;
int ret;
if (cnt >= sizeof(buf))
return cnt;
}
-static atomic_t tracing_reader;
-
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
+ long cpu_file = (long) inode->i_private;
struct trace_iterator *iter;
+ int ret = 0;
if (tracing_disabled)
return -ENODEV;
- /* We only allow for reader of the pipe */
- if (atomic_inc_return(&tracing_reader) != 1) {
- atomic_dec(&tracing_reader);
- return -EBUSY;
+ mutex_lock(&trace_types_lock);
+
+ /* We only allow one reader per cpu */
+ if (cpu_file == TRACE_PIPE_ALL_CPU) {
+ if (!cpumask_empty(tracing_reader_cpumask)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ cpumask_setall(tracing_reader_cpumask);
+ } else {
+ if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
+ cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
+ else {
+ ret = -EBUSY;
+ goto out;
+ }
}
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
- if (!iter)
- return -ENOMEM;
+ if (!iter) {
+ ret = -ENOMEM;
+ goto out;
+ }
- if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
- kfree(iter);
- return -ENOMEM;
+ /*
+ * We make a copy of the current tracer to avoid concurrent
+ * changes on it while we are reading.
+ */
+ iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL);
+ if (!iter->trace) {
+ ret = -ENOMEM;
+ goto fail;
}
+ if (current_trace)
+ *iter->trace = *current_trace;
- mutex_lock(&trace_types_lock);
+ if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto fail;
+ }
/* trace pipe does not show start of buffer */
cpumask_setall(iter->started);
+ iter->cpu_file = cpu_file;
iter->tr = &global_trace;
- iter->trace = current_trace;
+ mutex_init(&iter->mutex);
filp->private_data = iter;
if (iter->trace->pipe_open)
iter->trace->pipe_open(iter);
+
+out:
mutex_unlock(&trace_types_lock);
+ return ret;
- return 0;
+fail:
+ kfree(iter->trace);
+ kfree(iter);
+ mutex_unlock(&trace_types_lock);
+ return ret;
}
static int tracing_release_pipe(struct inode *inode, struct file *file)
{
struct trace_iterator *iter = file->private_data;
+ mutex_lock(&trace_types_lock);
+
+ if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
+ cpumask_clear(tracing_reader_cpumask);
+ else
+ cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
+
+ mutex_unlock(&trace_types_lock);
+
free_cpumask_var(iter->started);
+ mutex_destroy(&iter->mutex);
+ kfree(iter->trace);
kfree(iter);
- atomic_dec(&tracing_reader);
return 0;
}
}
}
-/*
- * Consumer reader.
- */
-static ssize_t
-tracing_read_pipe(struct file *filp, char __user *ubuf,
- size_t cnt, loff_t *ppos)
+
+void default_wait_pipe(struct trace_iterator *iter)
{
- struct trace_iterator *iter = filp->private_data;
- ssize_t sret;
+ DEFINE_WAIT(wait);
- /* return any leftover data */
- sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
- if (sret != -EBUSY)
- return sret;
+ prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
- trace_seq_reset(&iter->seq);
+ if (trace_empty(iter))
+ schedule();
- mutex_lock(&trace_types_lock);
- if (iter->trace->read) {
- sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
- if (sret)
- goto out;
- }
+ finish_wait(&trace_wait, &wait);
+}
+
+/*
+ * This is a make-shift waitqueue.
+ * A tracer might use this callback on some rare cases:
+ *
+ * 1) the current tracer might hold the runqueue lock when it wakes up
+ * a reader, hence a deadlock (sched, function, and function graph tracers)
+ * 2) the function tracers, trace all functions, we don't want
+ * the overhead of calling wake_up and friends
+ * (and tracing them too)
+ *
+ * Anyway, this is really very primitive wakeup.
+ */
+void poll_wait_pipe(struct trace_iterator *iter)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* sleep for 100 msecs, and try again. */
+ schedule_timeout(HZ / 10);
+}
+
+/* Must be called with trace_types_lock mutex held. */
+static int tracing_wait_pipe(struct file *filp)
+{
+ struct trace_iterator *iter = filp->private_data;
-waitagain:
- sret = 0;
while (trace_empty(iter)) {
if ((filp->f_flags & O_NONBLOCK)) {
- sret = -EAGAIN;
- goto out;
+ return -EAGAIN;
}
- /*
- * This is a make-shift waitqueue. The reason we don't use
- * an actual wait queue is because:
- * 1) we only ever have one waiter
- * 2) the tracing, traces all functions, we don't want
- * the overhead of calling wake_up and friends
- * (and tracing them too)
- * Anyway, this is really very primitive wakeup.
- */
- set_current_state(TASK_INTERRUPTIBLE);
- iter->tr->waiter = current;
-
- mutex_unlock(&trace_types_lock);
+ mutex_unlock(&iter->mutex);
- /* sleep for 100 msecs, and try again. */
- schedule_timeout(HZ/10);
+ iter->trace->wait_pipe(iter);
- mutex_lock(&trace_types_lock);
+ mutex_lock(&iter->mutex);
- iter->tr->waiter = NULL;
-
- if (signal_pending(current)) {
- sret = -EINTR;
- goto out;
- }
-
- if (iter->trace != current_trace)
- goto out;
+ if (signal_pending(current))
+ return -EINTR;
/*
* We block until we read something and tracing is disabled.
*/
if (!tracer_enabled && iter->pos)
break;
+ }
+
+ return 1;
+}
+
+/*
+ * Consumer reader.
+ */
+static ssize_t
+tracing_read_pipe(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_iterator *iter = filp->private_data;
+ static struct tracer *old_tracer;
+ ssize_t sret;
+
+ /* return any leftover data */
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (sret != -EBUSY)
+ return sret;
+
+ trace_seq_reset(&iter->seq);
+
+ /* 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);
- continue;
+ /*
+ * Avoid more than one consumer on a single file descriptor
+ * This is just a matter of traces coherency, the ring buffer itself
+ * is protected.
+ */
+ mutex_lock(&iter->mutex);
+ if (iter->trace->read) {
+ sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
+ if (sret)
+ goto out;
}
+waitagain:
+ sret = tracing_wait_pipe(filp);
+ if (sret <= 0)
+ goto out;
+
/* stop when tracing is finished */
- if (trace_empty(iter))
+ if (trace_empty(iter)) {
+ sret = 0;
goto out;
+ }
if (cnt >= PAGE_SIZE)
cnt = PAGE_SIZE - 1;
iter->seq.len = len;
break;
}
-
- trace_consume(iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(iter);
if (iter->seq.len >= cnt)
break;
goto waitagain;
out:
- mutex_unlock(&trace_types_lock);
+ mutex_unlock(&iter->mutex);
return sret;
}
+static void tracing_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ __free_page(buf->page);
+}
+
+static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
+ unsigned int idx)
+{
+ __free_page(spd->pages[idx]);
+}
+
+static 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 = tracing_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+static size_t
+tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
+{
+ size_t count;
+ int ret;
+
+ /* Seq buffer is page-sized, exactly what we need. */
+ for (;;) {
+ count = iter->seq.len;
+ ret = print_trace_line(iter);
+ count = iter->seq.len - count;
+ if (rem < count) {
+ rem = 0;
+ iter->seq.len -= count;
+ break;
+ }
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ iter->seq.len -= count;
+ break;
+ }
+
+ trace_consume(iter);
+ rem -= count;
+ if (!find_next_entry_inc(iter)) {
+ rem = 0;
+ iter->ent = NULL;
+ break;
+ }
+ }
+
+ return rem;
+}
+
+static ssize_t tracing_splice_read_pipe(struct file *filp,
+ loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len,
+ unsigned int flags)
+{
+ struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial[PIPE_BUFFERS];
+ struct trace_iterator *iter = filp->private_data;
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .nr_pages = 0, /* This gets updated below. */
+ .flags = flags,
+ .ops = &tracing_pipe_buf_ops,
+ .spd_release = tracing_spd_release_pipe,
+ };
+ static struct tracer *old_tracer;
+ ssize_t ret;
+ size_t rem;
+ unsigned int i;
+
+ /* 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);
+
+ mutex_lock(&iter->mutex);
+
+ if (iter->trace->splice_read) {
+ ret = iter->trace->splice_read(iter, filp,
+ ppos, pipe, len, flags);
+ if (ret)
+ goto out_err;
+ }
+
+ ret = tracing_wait_pipe(filp);
+ if (ret <= 0)
+ goto out_err;
+
+ if (!iter->ent && !find_next_entry_inc(iter)) {
+ ret = -EFAULT;
+ goto out_err;
+ }
+
+ /* Fill as many pages as possible. */
+ for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
+ pages[i] = alloc_page(GFP_KERNEL);
+ if (!pages[i])
+ break;
+
+ rem = tracing_fill_pipe_page(rem, iter);
+
+ /* Copy the data into the page, so we can start over. */
+ ret = trace_seq_to_buffer(&iter->seq,
+ page_address(pages[i]),
+ iter->seq.len);
+ if (ret < 0) {
+ __free_page(pages[i]);
+ break;
+ }
+ partial[i].offset = 0;
+ partial[i].len = iter->seq.len;
+
+ trace_seq_reset(&iter->seq);
+ }
+
+ mutex_unlock(&iter->mutex);
+
+ spd.nr_pages = i;
+
+ return splice_to_pipe(pipe, &spd);
+
+out_err:
+ mutex_unlock(&iter->mutex);
+
+ return ret;
+}
+
static ssize_t
tracing_entries_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
.open = tracing_open_pipe,
.poll = tracing_poll_pipe,
.read = tracing_read_pipe,
+ .splice_read = tracing_splice_read_pipe,
.release = tracing_release_pipe,
};
return d_tracer;
}
+static struct dentry *d_percpu;
+
+struct dentry *tracing_dentry_percpu(void)
+{
+ static int once;
+ struct dentry *d_tracer;
+
+ if (d_percpu)
+ return d_percpu;
+
+ d_tracer = tracing_init_dentry();
+
+ if (!d_tracer)
+ return NULL;
+
+ d_percpu = debugfs_create_dir("per_cpu", d_tracer);
+
+ if (!d_percpu && !once) {
+ once = 1;
+ pr_warning("Could not create debugfs directory 'per_cpu'\n");
+ return NULL;
+ }
+
+ return d_percpu;
+}
+
+static void tracing_init_debugfs_percpu(long cpu)
+{
+ struct dentry *d_percpu = tracing_dentry_percpu();
+ struct dentry *entry;
+ /* strlen(trace_pipe) + MAX(log10(cpu)) + '\0' */
+ char filename[17];
+
+ if (cpu > 999 || cpu < 0)
+ return;
+
+ /* per cpu trace_pipe */
+ sprintf(filename, "trace_pipe%ld", cpu);
+
+ entry = debugfs_create_file(filename, 0444, d_percpu,
+ (void *) cpu, &tracing_pipe_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs '%s' entry\n", filename);
+
+ /* per cpu trace */
+ sprintf(filename, "trace%ld", cpu);
+
+ entry = debugfs_create_file(filename, 0444, d_percpu,
+ (void *) cpu, &tracing_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs '%s' entry\n", filename);
+}
+
#ifdef CONFIG_FTRACE_SELFTEST
/* Let selftest have access to static functions in this file */
#include "trace_selftest.c"
{
struct dentry *d_tracer;
struct dentry *entry;
+ int cpu;
d_tracer = tracing_init_dentry();
if (!entry)
pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
- entry = debugfs_create_file("latency_trace", 0444, d_tracer,
- &global_trace, &tracing_lt_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'latency_trace' entry\n");
-
entry = debugfs_create_file("trace", 0444, d_tracer,
- &global_trace, &tracing_fops);
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
if (!entry)
pr_warning("Could not create debugfs 'trace' entry\n");
if (!entry)
pr_warning("Could not create debugfs 'README' entry\n");
- entry = debugfs_create_file("trace_pipe", 0644, d_tracer,
- NULL, &tracing_pipe_fops);
+ entry = debugfs_create_file("trace_pipe", 0444, d_tracer,
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'trace_pipe' entry\n");
#ifdef CONFIG_SYSPROF_TRACER
init_tracer_sysprof_debugfs(d_tracer);
#endif
+
+ for_each_tracing_cpu(cpu)
+ tracing_init_debugfs_percpu(cpu);
+
return 0;
}
trace_buf[len] = 0;
size = sizeof(*entry) + len + 1;
- event = ring_buffer_lock_reserve(tr->buffer, size, &irq_flags);
+ event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, irq_flags, pc);
- entry->ent.type = TRACE_PRINT;
entry->ip = ip;
entry->depth = depth;
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = 0;
- ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+ ring_buffer_unlock_commit(tr->buffer, event);
out_unlock:
spin_unlock_irqrestore(&trace_buf_lock, irq_flags);
if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
goto out_free_buffer_mask;
+ if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+ goto out_free_tracing_cpumask;
+
cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
cpumask_copy(tracing_cpumask, cpu_all_mask);
+ cpumask_clear(tracing_reader_cpumask);
/* TODO: make the number of buffers hot pluggable with CPUS */
global_trace.buffer = ring_buffer_alloc(trace_buf_size,
ret = 0;
out_free_cpumask:
+ free_cpumask_var(tracing_reader_cpumask);
+out_free_tracing_cpumask:
free_cpumask_var(tracing_cpumask);
out_free_buffer_mask:
free_cpumask_var(tracing_buffer_mask);