* Copyright (C) 2004 William Lee Irwin III
*/
#include <linux/ring_buffer.h>
-#include <linux/utsrelease.h>
+#include <generated/utsrelease.h>
#include <linux/stacktrace.h>
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
-#include <linux/gfp.h>
#include <linux/fs.h>
#include "trace.h"
*/
static int tracing_disabled = 1;
-DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
{
preempt_disable();
- local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_inc(ftrace_cpu_disabled);
}
static inline void ftrace_enable_cpu(void)
{
- local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_dec(ftrace_cpu_disabled);
preempt_enable();
}
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)
*
* 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 to true.
+ * /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
*/
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
static int tracing_set_tracer(const char *buf);
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
{
strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
ring_buffer_expanded = 1;
return 1;
}
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
static int __init set_ftrace_dump_on_oops(char *str)
{
- ftrace_dump_on_oops = 1;
- return 1;
+ 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 struct trace_array max_tr;
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
/* tracer_enabled is used to toggle activation of a tracer */
static int tracer_enabled = 1;
/*
* trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
*/
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);
}
__setup("trace_buf_size=", set_buf_size);
+static int __init set_tracing_thresh(char *str)
+{
+ unsigned long threshhold;
+ int ret;
+
+ if (!str)
+ return 0;
+ ret = strict_strtoul(str, 0, &threshhold);
+ if (ret < 0)
+ return 0;
+ tracing_thresh = threshhold * 1000;
+ return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
unsigned long nsecs_to_usecs(unsigned long nsecs)
{
return nsecs / 1000;
"bin",
"block",
"stacktrace",
- "sched-tree",
"trace_printk",
"ftrace_preempt",
"branch",
* protected by per_cpu spinlocks. But the action of the swap
* needs its own lock.
*
- * This is defined as a raw_spinlock_t in order to help
+ * 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 raw_spinlock_t ftrace_max_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+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;
-unsigned long __read_mostly tracing_thresh;
/*
* Copy the new maximum trace into the separate maximum-trace
__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 = tr->data[cpu];
+ struct trace_array_cpu *max_data;
max_tr.cpu = cpu;
max_tr.time_start = data->preempt_timestamp;
max_data->critical_start = data->critical_start;
max_data->critical_end = data->critical_end;
- memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+ 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;
return;
WARN_ON_ONCE(!irqs_disabled());
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
tr->buffer = max_tr.buffer;
max_tr.buffer = buf;
__update_max_tr(tr, tsk, cpu);
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
}
/**
return;
WARN_ON_ONCE(!irqs_disabled());
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
ftrace_disable_cpu();
WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
__update_max_tr(tr, tsk, cpu);
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
}
#endif /* CONFIG_TRACER_MAX_TRACE */
mutex_unlock(&trace_types_lock);
}
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
{
ftrace_disable_cpu();
- ring_buffer_reset_cpu(tr->buffer, cpu);
+ ring_buffer_reset_cpu(buffer, cpu);
ftrace_enable_cpu();
}
/* Make sure all commits have finished */
synchronize_sched();
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
tr->time_start = ftrace_now(tr->cpu);
for_each_online_cpu(cpu)
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
static int cmdline_idx;
-static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
/* temporary disable recording */
static atomic_t trace_record_cmdline_disabled __read_mostly;
goto out;
}
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
buffer = global_trace.buffer;
if (buffer)
if (buffer)
ring_buffer_record_enable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
ftrace_start();
out:
spin_unlock_irqrestore(&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);
if (buffer)
ring_buffer_record_disable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
out:
spin_unlock_irqrestore(&tracing_start_lock, flags);
}
* nor do we want to disable interrupts,
* so if we miss here, then better luck next time.
*/
- if (!__raw_spin_trylock(&trace_cmdline_lock))
+ if (!arch_spin_trylock(&trace_cmdline_lock))
return;
idx = map_pid_to_cmdline[tsk->pid];
memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
- __raw_spin_unlock(&trace_cmdline_lock);
+ arch_spin_unlock(&trace_cmdline_lock);
}
void trace_find_cmdline(int pid, char comm[])
return;
}
+ if (WARN_ON_ONCE(pid < 0)) {
+ strcpy(comm, "<XXX>");
+ return;
+ }
+
if (pid > PID_MAX_DEFAULT) {
strcpy(comm, "<...>");
return;
}
preempt_disable();
- __raw_spin_lock(&trace_cmdline_lock);
+ 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, "<...>");
- __raw_spin_unlock(&trace_cmdline_lock);
+ arch_spin_unlock(&trace_cmdline_lock);
preempt_enable();
}
struct ftrace_entry *entry;
/* If we are reading the ring buffer, don't trace */
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
__ftrace_trace_stack(tr->buffer, flags, skip, pc);
}
+/**
+ * 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());
+}
+
void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
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;
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
*/
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
- static raw_spinlock_t trace_buf_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t trace_buf_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static u32 trace_buf[TRACE_BUF_SIZE];
struct ftrace_event_call *call = &event_bprint;
/* Lockdep uses trace_printk for lock tracing */
local_irq_save(flags);
- __raw_spin_lock(&trace_buf_lock);
+ arch_spin_lock(&trace_buf_lock);
len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
if (len > TRACE_BUF_SIZE || len < 0)
entry->fmt = fmt;
memcpy(entry->buf, trace_buf, sizeof(u32) * len);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, flags, 6, pc);
+ }
out_unlock:
- __raw_spin_unlock(&trace_buf_lock);
+ arch_spin_unlock(&trace_buf_lock);
local_irq_restore(flags);
out:
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
- static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
static char trace_buf[TRACE_BUF_SIZE];
struct ftrace_event_call *call = &event_print;
pause_graph_tracing();
raw_local_irq_save(irq_flags);
- __raw_spin_lock(&trace_buf_lock);
+ arch_spin_lock(&trace_buf_lock);
len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
- len = min(len, TRACE_BUF_SIZE-1);
- trace_buf[len] = 0;
-
size = sizeof(*entry) + len + 1;
buffer = tr->buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- entry->ip = ip;
+ entry->ip = ip;
memcpy(&entry->buf, trace_buf, len);
- entry->buf[len] = 0;
- if (!filter_check_discard(call, entry, buffer, event))
+ entry->buf[len] = '\0';
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, irq_flags, 6, pc);
+ }
out_unlock:
- __raw_spin_unlock(&trace_buf_lock);
+ arch_spin_unlock(&trace_buf_lock);
raw_local_irq_restore(irq_flags);
unpause_graph_tracing();
out:
}
static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+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 = iter->buffer_iter[cpu];
if (buf_iter)
event = ring_buffer_iter_peek(buf_iter, ts);
else
- event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+ event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+ lost_events);
ftrace_enable_cpu();
}
static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__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;
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);
+ ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
if (ent_cpu)
*ent_cpu = cpu_file;
if (ring_buffer_empty_cpu(buffer, cpu))
continue;
- ent = peek_next_entry(iter, cpu, &ts);
+ ent = peek_next_entry(iter, cpu, &ts, &lost_events);
/*
* Pick the entry with the smallest timestamp:
next = ent;
next_cpu = cpu;
next_ts = ts;
+ next_lost = lost_events;
}
}
if (ent_ts)
*ent_ts = next_ts;
+ if (missing_events)
+ *missing_events = next_lost;
+
return next;
}
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
int *ent_cpu, u64 *ent_ts)
{
- return __find_next_entry(iter, ent_cpu, 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 */
static void *find_next_entry_inc(struct trace_iterator *iter)
{
- iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+ iter->ent = __find_next_entry(iter, &iter->cpu,
+ &iter->lost_events, &iter->ts);
if (iter->ent)
trace_iterator_increment(iter);
{
/* Don't allow ftrace to trace into the ring buffers */
ftrace_disable_cpu();
- ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+ &iter->lost_events);
ftrace_enable_cpu();
}
int i = (int)*pos;
void *ent;
+ WARN_ON_ONCE(iter->leftover);
+
(*pos)++;
/* can't go backwards */
}
/*
- * 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.
*/
ftrace_enable_cpu();
+ iter->leftover = 0;
for (p = iter; p && l < *pos; p = s_next(m, p, &l))
;
} else {
- l = *pos - 1;
- p = s_next(m, p, &l);
+ /*
+ * 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
+void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
}
if (event)
- return event->trace(iter, sym_flags);
+ return event->funcs->trace(iter, sym_flags, event);
if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
goto partial;
event = ftrace_find_event(entry->type);
if (event)
- return event->raw(iter, 0);
+ return event->funcs->raw(iter, 0, event);
if (!trace_seq_printf(s, "%d ?\n", entry->type))
goto partial;
event = ftrace_find_event(entry->type);
if (event) {
- enum print_line_t ret = event->hex(iter, 0);
+ enum print_line_t ret = event->funcs->hex(iter, 0, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
}
event = ftrace_find_event(entry->type);
- return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+ return event ? event->funcs->binary(iter, 0, event) :
+ TRACE_TYPE_HANDLED;
}
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
{
int cpu;
{
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);
+
if (iter->trace && iter->trace->print_line) {
ret = iter->trace->print_line(iter);
if (ret != TRACE_TYPE_UNHANDLED)
return print_trace_fmt(iter);
}
+void trace_default_header(struct seq_file *m)
+{
+ struct trace_iterator *iter = m->private;
+
+ 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))
+ print_func_help_header(m);
+ }
+}
+
static int s_show(struct seq_file *m, void *v)
{
struct trace_iterator *iter = v;
+ int ret;
if (iter->ent == NULL) {
if (iter->tr) {
}
if (iter->trace && iter->trace->print_header)
iter->trace->print_header(m);
- else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
- /* print nothing if the buffers are empty */
- if (trace_empty(iter))
- return 0;
- print_trace_header(m, iter);
- if (!(trace_flags & TRACE_ITER_VERBOSE))
- print_lat_help_header(m);
- } else {
- if (!(trace_flags & TRACE_ITER_VERBOSE))
- print_func_help_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);
- trace_print_seq(m, &iter->seq);
+ 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;
if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
for_each_tracing_cpu(cpu) {
-
iter->buffer_iter[cpu] =
- ring_buffer_read_start(iter->tr->buffer, 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_start(iter->tr->buffer, 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_lock(&tracing_cpumask_update_lock);
local_irq_disable();
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
for_each_tracing_cpu(cpu) {
/*
* Increase/decrease the disabled counter if we are
atomic_dec(&global_trace.data[cpu]->disabled);
}
}
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
local_irq_enable();
cpumask_copy(tracing_cpumask, tracing_cpumask_new);
.write = tracing_cpumask_write,
};
-static ssize_t
-tracing_trace_options_read(struct file *filp, char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int tracing_trace_options_show(struct seq_file *m, void *v)
{
struct tracer_opt *trace_opts;
u32 tracer_flags;
- int len = 0;
- char *buf;
- int r = 0;
int i;
-
- /* calculate max size */
- for (i = 0; trace_options[i]; i++) {
- len += strlen(trace_options[i]);
- len += 3; /* "no" and newline */
- }
-
mutex_lock(&trace_types_lock);
tracer_flags = current_trace->flags->val;
trace_opts = current_trace->flags->opts;
- /*
- * Increase the size with names of options specific
- * of the current tracer.
- */
- for (i = 0; trace_opts[i].name; i++) {
- len += strlen(trace_opts[i].name);
- len += 3; /* "no" and newline */
- }
-
- /* +1 for \0 */
- buf = kmalloc(len + 1, GFP_KERNEL);
- if (!buf) {
- mutex_unlock(&trace_types_lock);
- return -ENOMEM;
- }
-
for (i = 0; trace_options[i]; i++) {
if (trace_flags & (1 << i))
- r += sprintf(buf + r, "%s\n", trace_options[i]);
+ seq_printf(m, "%s\n", trace_options[i]);
else
- r += sprintf(buf + r, "no%s\n", trace_options[i]);
+ seq_printf(m, "no%s\n", trace_options[i]);
}
for (i = 0; trace_opts[i].name; i++) {
if (tracer_flags & trace_opts[i].bit)
- r += sprintf(buf + r, "%s\n",
- trace_opts[i].name);
+ seq_printf(m, "%s\n", trace_opts[i].name);
else
- r += sprintf(buf + r, "no%s\n",
- trace_opts[i].name);
+ seq_printf(m, "no%s\n", trace_opts[i].name);
}
mutex_unlock(&trace_types_lock);
- WARN_ON(r >= len + 1);
+ return 0;
+}
+
+static int __set_tracer_option(struct tracer *trace,
+ struct tracer_flags *tracer_flags,
+ struct tracer_opt *opts, int neg)
+{
+ int ret;
- r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+ ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+ if (ret)
+ return ret;
- kfree(buf);
- return r;
+ if (neg)
+ tracer_flags->val &= ~opts->bit;
+ else
+ tracer_flags->val |= opts->bit;
+ return 0;
}
/* Try to assign a tracer specific option */
{
struct tracer_flags *tracer_flags = trace->flags;
struct tracer_opt *opts = NULL;
- int ret = 0, i = 0;
- int len;
+ int i;
for (i = 0; tracer_flags->opts[i].name; i++) {
opts = &tracer_flags->opts[i];
- len = strlen(opts->name);
- if (strncmp(cmp, opts->name, len) == 0) {
- ret = trace->set_flag(tracer_flags->val,
- opts->bit, !neg);
- break;
- }
+ if (strcmp(cmp, opts->name) == 0)
+ return __set_tracer_option(trace, trace->flags,
+ opts, neg);
}
- /* Not found */
- if (!tracer_flags->opts[i].name)
- return -EINVAL;
-
- /* Refused to handle */
- if (ret)
- return ret;
-
- if (neg)
- tracer_flags->val &= ~opts->bit;
- else
- tracer_flags->val |= opts->bit;
- return 0;
+ return -EINVAL;
}
static void set_tracer_flags(unsigned int mask, int enabled)
size_t cnt, loff_t *ppos)
{
char buf[64];
- char *cmp = buf;
+ char *cmp;
int neg = 0;
int ret;
int i;
return -EFAULT;
buf[cnt] = 0;
+ cmp = strstrip(buf);
- if (strncmp(buf, "no", 2) == 0) {
+ if (strncmp(cmp, "no", 2) == 0) {
neg = 1;
cmp += 2;
}
for (i = 0; trace_options[i]; i++) {
- int len = strlen(trace_options[i]);
-
- if (strncmp(cmp, trace_options[i], len) == 0) {
+ if (strcmp(cmp, trace_options[i]) == 0) {
set_tracer_flags(1 << i, !neg);
break;
}
return cnt;
}
+static int tracing_trace_options_open(struct inode *inode, struct file *file)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+ return single_open(file, tracing_trace_options_show, NULL);
+}
+
static const struct file_operations tracing_iter_fops = {
- .open = tracing_open_generic,
- .read = tracing_trace_options_read,
+ .open = tracing_trace_options_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
.write = tracing_trace_options_write,
};
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) {
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);
+ if (iter->trace->pipe_close)
+ iter->trace->pipe_close(iter);
mutex_unlock(&trace_types_lock);
iter->pos = -1;
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
while (find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
int len = iter->seq.len;
if (iter->seq.len >= cnt)
break;
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
/* Now copy what we have to the user */
__free_page(spd->pages[idx]);
}
-static struct pipe_buf_operations tracing_pipe_buf_ops = {
+static const struct pipe_buf_operations tracing_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
size_t len,
unsigned int flags)
{
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct trace_iterator *iter = filp->private_data;
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
.flags = flags,
.ops = &tracing_pipe_buf_ops,
size_t rem;
unsigned int i;
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
/* copy the tracer to avoid using a global lock all around */
mutex_lock(&trace_types_lock);
if (unlikely(old_tracer != current_trace && current_trace)) {
}
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
/* 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])
+ for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+ spd.pages[i] = alloc_page(GFP_KERNEL);
+ if (!spd.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]),
+ page_address(spd.pages[i]),
iter->seq.len);
if (ret < 0) {
- __free_page(pages[i]);
+ __free_page(spd.pages[i]);
break;
}
- partial[i].offset = 0;
- partial[i].len = iter->seq.len;
+ spd.partial[i].offset = 0;
+ spd.partial[i].len = iter->seq.len;
trace_seq_init(&iter->seq);
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
mutex_unlock(&iter->mutex);
spd.nr_pages = i;
- return splice_to_pipe(pipe, &spd);
+ ret = splice_to_pipe(pipe, &spd);
+out:
+ splice_shrink_spd(pipe, &spd);
+ return ret;
out_err:
mutex_unlock(&iter->mutex);
-
- return ret;
+ goto out;
}
static ssize_t
size_t cnt, loff_t *fpos)
{
char *buf;
- char *end;
if (tracing_disabled)
return -EINVAL;
if (cnt > TRACE_BUF_SIZE)
cnt = TRACE_BUF_SIZE;
- buf = kmalloc(cnt + 1, GFP_KERNEL);
+ buf = kmalloc(cnt + 2, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
kfree(buf);
return -EFAULT;
}
+ if (buf[cnt-1] != '\n') {
+ buf[cnt] = '\n';
+ buf[cnt+1] = '\0';
+ } else
+ buf[cnt] = '\0';
- /* Cut from the first nil or newline. */
- buf[cnt] = '\0';
- end = strchr(buf, '\n');
- if (end)
- *end = '\0';
-
- cnt = mark_printk("%s\n", buf);
+ cnt = mark_printk("%s", buf);
kfree(buf);
*fpos += cnt;
return cnt;
}
-static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int tracing_clock_show(struct seq_file *m, void *v)
{
- char buf[64];
- int bufiter = 0;
int i;
for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
- bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter,
+ seq_printf(m,
"%s%s%s%s", i ? " " : "",
i == trace_clock_id ? "[" : "", trace_clocks[i].name,
i == trace_clock_id ? "]" : "");
- bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n");
+ seq_putc(m, '\n');
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter);
+ return 0;
}
static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
return cnt;
}
+static int tracing_clock_open(struct inode *inode, struct file *file)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+ return single_open(file, tracing_clock_show, NULL);
+}
+
static const struct file_operations tracing_max_lat_fops = {
.open = tracing_open_generic,
.read = tracing_max_lat_read,
};
static const struct file_operations trace_clock_fops = {
- .open = tracing_open_generic,
- .read = tracing_clock_read,
+ .open = tracing_clock_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
.write = tracing_clock_write,
};
size_t count, loff_t *ppos)
{
struct ftrace_buffer_info *info = filp->private_data;
- unsigned int pos;
ssize_t ret;
size_t size;
info->read = 0;
+ trace_access_lock(info->cpu);
ret = ring_buffer_read_page(info->tr->buffer,
&info->spare,
count,
info->cpu, 0);
+ trace_access_unlock(info->cpu);
if (ret < 0)
return 0;
- pos = ring_buffer_page_len(info->spare);
-
- if (pos < PAGE_SIZE)
- memset(info->spare + pos, 0, PAGE_SIZE - pos);
-
read:
size = PAGE_SIZE - info->read;
if (size > count)
}
/* Pipe buffer operations for a buffer. */
-static struct pipe_buf_operations buffer_pipe_buf_ops = {
+static const struct pipe_buf_operations buffer_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
unsigned int flags)
{
struct ftrace_buffer_info *info = file->private_data;
- struct partial_page partial[PIPE_BUFFERS];
- struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
int entries, size, i;
size_t ret;
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
if (*ppos & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: previous read must page-align\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
if (len & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
- if (len < PAGE_SIZE)
- return -EINVAL;
+ if (len < PAGE_SIZE) {
+ ret = -EINVAL;
+ goto out;
+ }
len &= PAGE_MASK;
}
+ trace_access_lock(info->cpu);
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
- for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+ for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
int r;
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
}
+ trace_access_unlock(info->cpu);
spd.nr_pages = i;
/* did we read anything? */
else
ret = 0;
/* TODO: block */
- return ret;
+ goto out;
}
ret = splice_to_pipe(pipe, &spd);
-
+ splice_shrink_spd(pipe, &spd);
+out:
return ret;
}
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
- return ENOMEM;
+ return -ENOMEM;
trace_seq_init(s);
if (ret < 0)
return ret;
- ret = 0;
- switch (val) {
- case 0:
- /* do nothing if already cleared */
- if (!(topt->flags->val & topt->opt->bit))
- break;
-
- mutex_lock(&trace_types_lock);
- if (current_trace->set_flag)
- ret = current_trace->set_flag(topt->flags->val,
- topt->opt->bit, 0);
- mutex_unlock(&trace_types_lock);
- if (ret)
- return ret;
- topt->flags->val &= ~topt->opt->bit;
- break;
- case 1:
- /* do nothing if already set */
- if (topt->flags->val & topt->opt->bit)
- break;
+ if (val != 0 && val != 1)
+ return -EINVAL;
+ if (!!(topt->flags->val & topt->opt->bit) != val) {
mutex_lock(&trace_types_lock);
- if (current_trace->set_flag)
- ret = current_trace->set_flag(topt->flags->val,
- topt->opt->bit, 1);
+ ret = __set_tracer_option(current_trace, topt->flags,
+ topt->opt, !val);
mutex_unlock(&trace_types_lock);
if (ret)
return ret;
- topt->flags->val |= topt->opt->bit;
- break;
-
- default:
- return -EINVAL;
}
*ppos += cnt;
struct dentry *d_tracer;
int cpu;
+ trace_access_lock_init();
+
d_tracer = tracing_init_dentry();
trace_create_file("tracing_enabled", 0644, d_tracer,
#ifdef CONFIG_TRACER_MAX_TRACE
trace_create_file("tracing_max_latency", 0644, d_tracer,
&tracing_max_latency, &tracing_max_lat_fops);
+#endif
trace_create_file("tracing_thresh", 0644, d_tracer,
&tracing_thresh, &tracing_max_lat_fops);
-#endif
trace_create_file("README", 0444, d_tracer,
NULL, &tracing_readme_fops);
unsigned long event, void *unused)
{
if (ftrace_dump_on_oops)
- ftrace_dump();
+ ftrace_dump(ftrace_dump_on_oops);
return NOTIFY_OK;
}
switch (val) {
case DIE_OOPS:
if (ftrace_dump_on_oops)
- ftrace_dump();
+ ftrace_dump(ftrace_dump_on_oops);
break;
default:
break;
trace_seq_init(s);
}
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
{
- static raw_spinlock_t ftrace_dump_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t ftrace_dump_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
unsigned int old_userobj;
/* only one dump */
local_irq_save(flags);
- __raw_spin_lock(&ftrace_dump_lock);
+ arch_spin_lock(&ftrace_dump_lock);
if (dump_ran)
goto out;
/* don't look at user memory in panic mode */
trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
- printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
/* Simulate the iterator */
iter.tr = &global_trace;
iter.trace = current_trace;
- iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+ switch (oops_dump_mode) {
+ case DUMP_ALL:
+ iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ break;
+ case DUMP_ORIG:
+ iter.cpu_file = raw_smp_processor_id();
+ break;
+ case DUMP_NONE:
+ goto out_enable;
+ default:
+ printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+ iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ }
+
+ printk(KERN_TRACE "Dumping ftrace buffer:\n");
/*
* We need to stop all tracing on all CPUS to read the
else
printk(KERN_TRACE "---------------------------------\n");
+ out_enable:
/* Re-enable tracing if requested */
if (!disable_tracing) {
trace_flags |= old_userobj;
}
out:
- __raw_spin_unlock(&ftrace_dump_lock);
+ arch_spin_unlock(&ftrace_dump_lock);
local_irq_restore(flags);
}
/* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
{
- __ftrace_dump(true);
+ __ftrace_dump(true, oops_dump_mode);
}
__init static int tracer_alloc_buffers(void)
if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
goto out_free_buffer_mask;
- if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
- goto out_free_tracing_cpumask;
-
/* To save memory, keep the ring buffer size to its minimum */
if (ring_buffer_expanded)
ring_buf_size = trace_buf_size;
/* Allocate the first page for all buffers */
for_each_tracing_cpu(i) {
global_trace.data[i] = &per_cpu(global_trace_cpu, i);
- max_tr.data[i] = &per_cpu(max_data, i);
+ max_tr.data[i] = &per_cpu(max_tr_data, i);
}
trace_init_cmdlines();
return 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);