aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace/trace.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/trace.c')
-rw-r--r--kernel/trace/trace.c244
1 files changed, 120 insertions, 124 deletions
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8a76339a9e6..dc53ecb8058 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@@ -101,10 +100,7 @@ static inline void ftrace_enable_cpu(void)
preempt_enable();
}
-static cpumask_var_t __read_mostly tracing_buffer_mask;
-
-#define for_each_tracing_cpu(cpu) \
- for_each_cpu(cpu, tracing_buffer_mask)
+cpumask_var_t __read_mostly tracing_buffer_mask;
/*
* ftrace_dump_on_oops - variable to dump ftrace buffer on oops
@@ -344,7 +340,7 @@ 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_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
static int trace_stop_count;
static DEFINE_SPINLOCK(tracing_start_lock);
@@ -428,6 +424,7 @@ static const char *trace_options[] = {
"latency-format",
"sleep-time",
"graph-time",
+ "record-cmd",
NULL
};
@@ -659,6 +656,10 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
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;
@@ -685,6 +686,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
return;
WARN_ON_ONCE(!irqs_disabled());
+ if (!current_trace->use_max_tr) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
arch_spin_lock(&ftrace_max_lock);
ftrace_disable_cpu();
@@ -729,18 +735,11 @@ __acquires(kernel_lock)
return -1;
}
- if (strlen(type->name) > MAX_TRACER_SIZE) {
+ if (strlen(type->name) >= MAX_TRACER_SIZE) {
pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
return -1;
}
- /*
- * When this gets called we hold the BKL which means that
- * preemption is disabled. Various trace selftests however
- * need to disable and enable preemption for successful tests.
- * So we drop the BKL here and grab it after the tests again.
- */
- unlock_kernel();
mutex_lock(&trace_types_lock);
tracing_selftest_running = true;
@@ -822,7 +821,6 @@ __acquires(kernel_lock)
#endif
out_unlock:
- lock_kernel();
return ret;
}
@@ -1285,6 +1283,8 @@ void trace_dump_stack(void)
__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
}
+static DEFINE_PER_CPU(int, user_stack_count);
+
void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
@@ -1303,10 +1303,20 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
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)
- return;
+ goto out_drop_count;
entry = ring_buffer_event_data(event);
entry->tgid = current->tgid;
@@ -1320,6 +1330,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
save_stack_trace_user(&trace);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
+
+ out_drop_count:
+ __this_cpu_dec(user_stack_count);
+ out:
+ preempt_enable();
}
#ifdef UNUSED
@@ -1331,61 +1346,6 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
#endif /* CONFIG_STACKTRACE */
-static void
-ftrace_trace_special(void *__tr,
- unsigned long arg1, unsigned long arg2, unsigned long arg3,
- int pc)
-{
- struct ftrace_event_call *call = &event_special;
- struct ring_buffer_event *event;
- struct trace_array *tr = __tr;
- struct ring_buffer *buffer = tr->buffer;
- struct special_entry *entry;
-
- event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
- sizeof(*entry), 0, pc);
- if (!event)
- return;
- entry = ring_buffer_event_data(event);
- entry->arg1 = arg1;
- entry->arg2 = arg2;
- entry->arg3 = arg3;
-
- if (!filter_check_discard(call, entry, buffer, event))
- trace_buffer_unlock_commit(buffer, event, 0, pc);
-}
-
-void
-__trace_special(void *__tr, void *__data,
- unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
- ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
-}
-
-void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
- struct trace_array *tr = &global_trace;
- struct trace_array_cpu *data;
- unsigned long flags;
- int cpu;
- int pc;
-
- if (tracing_disabled)
- return;
-
- pc = preempt_count();
- local_irq_save(flags);
- cpu = raw_smp_processor_id();
- data = tr->data[cpu];
-
- if (likely(atomic_inc_return(&data->disabled) == 1))
- ftrace_trace_special(tr, arg1, arg2, arg3, pc);
-
- atomic_dec(&data->disabled);
- local_irq_restore(flags);
-}
-
/**
* trace_vbprintk - write binary msg to tracing buffer
*
@@ -1404,7 +1364,6 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
struct bprint_entry *entry;
unsigned long flags;
int disable;
- int resched;
int cpu, len = 0, size, pc;
if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -1414,7 +1373,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
pause_graph_tracing();
pc = preempt_count();
- resched = ftrace_preempt_disable();
+ preempt_disable_notrace();
cpu = raw_smp_processor_id();
data = tr->data[cpu];
@@ -1452,7 +1411,7 @@ out_unlock:
out:
atomic_dec_return(&data->disabled);
- ftrace_preempt_enable(resched);
+ preempt_enable_notrace();
unpause_graph_tracing();
return len;
@@ -1539,11 +1498,6 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
}
EXPORT_SYMBOL_GPL(trace_vprintk);
-enum trace_file_type {
- TRACE_FILE_LAT_FMT = 1,
- TRACE_FILE_ANNOTATE = 2,
-};
-
static void trace_iterator_increment(struct trace_iterator *iter)
{
/* Don't allow ftrace to trace into the ring buffers */
@@ -1641,7 +1595,7 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
}
/* Find the next real entry, and increment the iterator to the next entry */
-static void *find_next_entry_inc(struct trace_iterator *iter)
+void *trace_find_next_entry_inc(struct trace_iterator *iter)
{
iter->ent = __find_next_entry(iter, &iter->cpu,
&iter->lost_events, &iter->ts);
@@ -1676,19 +1630,19 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
return NULL;
if (iter->idx < 0)
- ent = find_next_entry_inc(iter);
+ ent = trace_find_next_entry_inc(iter);
else
ent = iter;
while (ent && iter->idx < i)
- ent = find_next_entry_inc(iter);
+ ent = trace_find_next_entry_inc(iter);
iter->pos = *pos;
return ent;
}
-static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+void tracing_iter_reset(struct trace_iterator *iter, int cpu)
{
struct trace_array *tr = iter->tr;
struct ring_buffer_event *event;
@@ -1936,7 +1890,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
}
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;
@@ -1962,7 +1916,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
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;
@@ -1989,7 +1943,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
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;
}
@@ -2014,7 +1968,8 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
}
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;
}
int trace_empty(struct trace_iterator *iter)
@@ -2048,7 +2003,7 @@ int trace_empty(struct trace_iterator *iter)
}
/* Called with trace_event_read_lock() held. */
-static enum print_line_t print_trace_line(struct trace_iterator *iter)
+enum print_line_t print_trace_line(struct trace_iterator *iter)
{
enum print_line_t ret;
@@ -2257,7 +2212,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
static int tracing_release(struct inode *inode, struct file *file)
{
- struct seq_file *m = (struct seq_file *)file->private_data;
+ struct seq_file *m = file->private_data;
struct trace_iterator *iter;
int cpu;
@@ -2381,11 +2336,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
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 = seq_lseek,
+ .llseek = tracing_seek,
.release = tracing_release,
};
@@ -2393,6 +2356,7 @@ static const struct file_operations show_traces_fops = {
.open = show_traces_open,
.read = seq_read,
.release = seq_release,
+ .llseek = seq_lseek,
};
/*
@@ -2486,6 +2450,7 @@ static const struct file_operations tracing_cpumask_fops = {
.open = tracing_open_generic,
.read = tracing_cpumask_read,
.write = tracing_cpumask_write,
+ .llseek = generic_file_llseek,
};
static int tracing_trace_options_show(struct seq_file *m, void *v)
@@ -2561,6 +2526,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
trace_flags |= mask;
else
trace_flags &= ~mask;
+
+ if (mask == TRACE_ITER_RECORD_CMD)
+ trace_event_enable_cmd_record(enabled);
}
static ssize_t
@@ -2652,6 +2620,7 @@ tracing_readme_read(struct file *filp, char __user *ubuf,
static const struct file_operations tracing_readme_fops = {
.open = tracing_open_generic,
.read = tracing_readme_read,
+ .llseek = generic_file_llseek,
};
static ssize_t
@@ -2702,6 +2671,7 @@ tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
static const struct file_operations tracing_saved_cmdlines_fops = {
.open = tracing_open_generic,
.read = tracing_saved_cmdlines_read,
+ .llseek = generic_file_llseek,
};
static ssize_t
@@ -2797,6 +2767,9 @@ static int tracing_resize_ring_buffer(unsigned long size)
if (ret < 0)
return ret;
+ if (!current_trace->use_max_tr)
+ goto out;
+
ret = ring_buffer_resize(max_tr.buffer, size);
if (ret < 0) {
int r;
@@ -2824,11 +2797,14 @@ static int tracing_resize_ring_buffer(unsigned long size)
return ret;
}
+ max_tr.entries = size;
+ out:
global_trace.entries = size;
return ret;
}
+
/**
* tracing_update_buffers - used by tracing facility to expand ring buffers
*
@@ -2889,12 +2865,26 @@ static int tracing_set_tracer(const char *buf)
trace_branch_disable();
if (current_trace && current_trace->reset)
current_trace->reset(tr);
-
+ if (current_trace && current_trace->use_max_tr) {
+ /*
+ * We don't free the ring buffer. instead, resize it because
+ * The max_tr ring buffer has some state (e.g. ring->clock) and
+ * we want preserve it.
+ */
+ ring_buffer_resize(max_tr.buffer, 1);
+ max_tr.entries = 1;
+ }
destroy_trace_option_files(topts);
current_trace = t;
topts = create_trace_option_files(current_trace);
+ if (current_trace->use_max_tr) {
+ ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
+ if (ret < 0)
+ goto out;
+ max_tr.entries = global_trace.entries;
+ }
if (t->init) {
ret = tracer_init(t, tr);
@@ -3031,6 +3021,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
if (iter->trace->pipe_open)
iter->trace->pipe_open(iter);
+ nonseekable_open(inode, filp);
out:
mutex_unlock(&trace_types_lock);
return ret;
@@ -3210,7 +3201,7 @@ waitagain:
trace_event_read_lock();
trace_access_lock(iter->cpu_file);
- while (find_next_entry_inc(iter) != NULL) {
+ while (trace_find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
int len = iter->seq.len;
@@ -3293,7 +3284,7 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
if (ret != TRACE_TYPE_NO_CONSUME)
trace_consume(iter);
rem -= count;
- if (!find_next_entry_inc(iter)) {
+ if (!trace_find_next_entry_inc(iter)) {
rem = 0;
iter->ent = NULL;
break;
@@ -3349,7 +3340,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
if (ret <= 0)
goto out_err;
- if (!iter->ent && !find_next_entry_inc(iter)) {
+ if (!iter->ent && !trace_find_next_entry_inc(iter)) {
ret = -EFAULT;
goto out_err;
}
@@ -3476,7 +3467,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
}
tracing_start();
- max_tr.entries = global_trace.entries;
mutex_unlock(&trace_types_lock);
return cnt;
@@ -3497,6 +3487,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
{
char *buf;
+ size_t written;
if (tracing_disabled)
return -EINVAL;
@@ -3518,11 +3509,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
} else
buf[cnt] = '\0';
- cnt = mark_printk("%s", buf);
+ written = mark_printk("%s", buf);
kfree(buf);
- *fpos += cnt;
+ *fpos += written;
- return cnt;
+ /* don't tell userspace we wrote more - it might confuse them */
+ if (written > cnt)
+ written = cnt;
+
+ return written;
}
static int tracing_clock_show(struct seq_file *m, void *v)
@@ -3589,18 +3584,21 @@ static const struct file_operations tracing_max_lat_fops = {
.open = tracing_open_generic,
.read = tracing_max_lat_read,
.write = tracing_max_lat_write,
+ .llseek = generic_file_llseek,
};
static const struct file_operations tracing_ctrl_fops = {
.open = tracing_open_generic,
.read = tracing_ctrl_read,
.write = tracing_ctrl_write,
+ .llseek = generic_file_llseek,
};
static const struct file_operations set_tracer_fops = {
.open = tracing_open_generic,
.read = tracing_set_trace_read,
.write = tracing_set_trace_write,
+ .llseek = generic_file_llseek,
};
static const struct file_operations tracing_pipe_fops = {
@@ -3609,17 +3607,20 @@ static const struct file_operations tracing_pipe_fops = {
.read = tracing_read_pipe,
.splice_read = tracing_splice_read_pipe,
.release = tracing_release_pipe,
+ .llseek = no_llseek,
};
static const struct file_operations tracing_entries_fops = {
.open = tracing_open_generic,
.read = tracing_entries_read,
.write = tracing_entries_write,
+ .llseek = generic_file_llseek,
};
static const struct file_operations tracing_mark_fops = {
.open = tracing_open_generic,
.write = tracing_mark_write,
+ .llseek = generic_file_llseek,
};
static const struct file_operations trace_clock_fops = {
@@ -3665,7 +3666,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct ftrace_buffer_info *info = filp->private_data;
- unsigned int pos;
ssize_t ret;
size_t size;
@@ -3692,11 +3692,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
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)
@@ -3931,6 +3926,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
static const struct file_operations tracing_stats_fops = {
.open = tracing_open_generic,
.read = tracing_stats_read,
+ .llseek = generic_file_llseek,
};
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -3967,6 +3963,7 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf,
static const struct file_operations tracing_dyn_info_fops = {
.open = tracing_open_generic,
.read = tracing_read_dyn_info,
+ .llseek = generic_file_llseek,
};
#endif
@@ -4023,13 +4020,9 @@ static void tracing_init_debugfs_percpu(long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu();
struct dentry *d_cpu;
- /* strlen(cpu) + MAX(log10(cpu)) + '\0' */
- char cpu_dir[7];
+ char cpu_dir[30]; /* 30 characters should be more than enough */
- if (cpu > 999 || cpu < 0)
- return;
-
- sprintf(cpu_dir, "cpu%ld", cpu);
+ snprintf(cpu_dir, 30, "cpu%ld", cpu);
d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
if (!d_cpu) {
pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
@@ -4120,6 +4113,7 @@ static const struct file_operations trace_options_fops = {
.open = tracing_open_generic,
.read = trace_options_read,
.write = trace_options_write,
+ .llseek = generic_file_llseek,
};
static ssize_t
@@ -4171,6 +4165,7 @@ static const struct file_operations trace_options_core_fops = {
.open = tracing_open_generic,
.read = trace_options_core_read,
.write = trace_options_core_write,
+ .llseek = generic_file_llseek,
};
struct dentry *trace_create_file(const char *name,
@@ -4360,9 +4355,6 @@ static __init int tracer_init_debugfs(void)
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
#endif
-#ifdef CONFIG_SYSPROF_TRACER
- init_tracer_sysprof_debugfs(d_tracer);
-#endif
create_trace_options_dir();
@@ -4419,7 +4411,7 @@ static struct notifier_block trace_die_notifier = {
*/
#define KERN_TRACE KERN_EMERG
-static void
+void
trace_printk_seq(struct trace_seq *s)
{
/* Probably should print a warning here. */
@@ -4434,6 +4426,13 @@ trace_printk_seq(struct trace_seq *s)
trace_seq_init(s);
}
+void trace_init_global_iter(struct trace_iterator *iter)
+{
+ iter->tr = &global_trace;
+ iter->trace = current_trace;
+ iter->cpu_file = TRACE_PIPE_ALL_CPU;
+}
+
static void
__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
{
@@ -4459,8 +4458,10 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
if (disable_tracing)
ftrace_kill();
+ trace_init_global_iter(&iter);
+
for_each_tracing_cpu(cpu) {
- atomic_inc(&global_trace.data[cpu]->disabled);
+ atomic_inc(&iter.tr->data[cpu]->disabled);
}
old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
@@ -4509,7 +4510,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
iter.iter_flags |= TRACE_FILE_LAT_FMT;
iter.pos = -1;
- if (find_next_entry_inc(&iter) != NULL) {
+ if (trace_find_next_entry_inc(&iter) != NULL) {
int ret;
ret = print_trace_line(&iter);
@@ -4531,7 +4532,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
trace_flags |= old_userobj;
for_each_tracing_cpu(cpu) {
- atomic_dec(&global_trace.data[cpu]->disabled);
+ atomic_dec(&iter.tr->data[cpu]->disabled);
}
tracing_on();
}
@@ -4580,16 +4581,14 @@ __init static int tracer_alloc_buffers(void)
#ifdef CONFIG_TRACER_MAX_TRACE
- max_tr.buffer = ring_buffer_alloc(ring_buf_size,
- TRACE_BUFFER_FLAGS);
+ max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
if (!max_tr.buffer) {
printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
WARN_ON(1);
ring_buffer_free(global_trace.buffer);
goto out_free_cpumask;
}
- max_tr.entries = ring_buffer_size(max_tr.buffer);
- WARN_ON(max_tr.entries != global_trace.entries);
+ max_tr.entries = 1;
#endif
/* Allocate the first page for all buffers */
@@ -4602,9 +4601,6 @@ __init static int tracer_alloc_buffers(void)
register_tracer(&nop_trace);
current_trace = &nop_trace;
-#ifdef CONFIG_BOOT_TRACER
- register_tracer(&boot_tracer);
-#endif
/* All seems OK, enable tracing */
tracing_disabled = 0;