summaryrefslogtreecommitdiff
path: root/kernel/trace/trace.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/trace.c')
-rw-r--r--kernel/trace/trace.c277
1 files changed, 228 insertions, 49 deletions
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 059233abcfcf..5814e7386109 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -890,6 +890,7 @@ static struct {
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
+ { ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};
@@ -1088,6 +1089,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
buf = tr->trace_buffer.buffer;
tr->trace_buffer.buffer = tr->max_buffer.buffer;
tr->max_buffer.buffer = buf;
@@ -1356,6 +1363,7 @@ static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
unsigned *map_cmdline_to_pid;
+ unsigned *map_cmdline_to_tgid;
unsigned cmdline_num;
int cmdline_idx;
char *saved_cmdlines;
@@ -1389,12 +1397,23 @@ static int allocate_cmdlines_buffer(unsigned int val,
return -ENOMEM;
}
+ s->map_cmdline_to_tgid = kmalloc_array(val,
+ sizeof(*s->map_cmdline_to_tgid),
+ GFP_KERNEL);
+ if (!s->map_cmdline_to_tgid) {
+ kfree(s->map_cmdline_to_pid);
+ kfree(s->saved_cmdlines);
+ return -ENOMEM;
+ }
+
s->cmdline_idx = 0;
s->cmdline_num = val;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
sizeof(s->map_pid_to_cmdline));
memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
val * sizeof(*s->map_cmdline_to_pid));
+ memset(s->map_cmdline_to_tgid, NO_CMDLINE_MAP,
+ val * sizeof(*s->map_cmdline_to_tgid));
return 0;
}
@@ -1560,14 +1579,17 @@ static int trace_save_cmdline(struct task_struct *tsk)
if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
return 0;
+ preempt_disable();
/*
* 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))
+ if (!arch_spin_trylock(&trace_cmdline_lock)) {
+ preempt_enable();
return 0;
+ }
idx = savedcmd->map_pid_to_cmdline[tsk->pid];
if (idx == NO_CMDLINE_MAP) {
@@ -1590,8 +1612,9 @@ static int trace_save_cmdline(struct task_struct *tsk)
}
set_cmdline(idx, tsk->comm);
-
+ savedcmd->map_cmdline_to_tgid[idx] = tsk->tgid;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
return 1;
}
@@ -1633,6 +1656,35 @@ void trace_find_cmdline(int pid, char comm[])
preempt_enable();
}
+static int __find_tgid_locked(int pid)
+{
+ unsigned map;
+ int tgid;
+
+ map = savedcmd->map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ tgid = savedcmd->map_cmdline_to_tgid[map];
+ else
+ tgid = -1;
+
+ return tgid;
+}
+
+int trace_find_tgid(int pid)
+{
+ int tgid;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ tgid = __find_tgid_locked(pid);
+
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ return tgid;
+}
+
void tracing_record_cmdline(struct task_struct *tsk)
{
if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
@@ -1660,7 +1712,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
TRACE_FLAG_IRQS_NOSUPPORT |
#endif
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
- ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+ ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
}
@@ -1751,7 +1803,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
{
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
+ /*
+ * If regs is not set, then skip the following callers:
+ * trace_buffer_unlock_commit_regs
+ * event_trigger_unlock_commit
+ * trace_event_buffer_commit
+ * trace_event_raw_event_sched_switch
+ * Note, we can still get here via blktrace, wakeup tracer
+ * and mmiotrace, but that's ok if they lose a function or
+ * two. They are that meaningful.
+ */
+ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
ftrace_trace_userstack(buffer, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
@@ -1810,6 +1872,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
trace.skip = skip;
/*
+ * Add two, for this function and the call to save_stack_trace()
+ * If regs is set, then these functions will not be in the way.
+ */
+ if (!regs)
+ trace.skip += 2;
+
+ /*
* 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
@@ -2180,6 +2249,7 @@ out:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
+__printf(3, 0)
static int
__trace_array_vprintk(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, va_list args)
@@ -2230,12 +2300,14 @@ __trace_array_vprintk(struct ring_buffer *buffer,
return len;
}
+__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}
+__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
@@ -2251,6 +2323,7 @@ int trace_array_printk(struct trace_array *tr,
return ret;
}
+__printf(3, 4)
int trace_array_printk_buf(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
@@ -2266,6 +2339,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
return ret;
}
+__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -2583,6 +2657,13 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
"# | | | | |\n");
}
+static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# TASK-PID TGID CPU# TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | | |\n");
+}
+
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
print_event_info(buf, m);
@@ -2595,6 +2676,18 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
"# | | | |||| | |\n");
}
+static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, 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 TGID CPU# |||| TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | |||| | |\n");
+}
+
void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
@@ -2668,13 +2761,14 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
return;
- if (iter->started && cpumask_test_cpu(iter->cpu, iter->started))
+ if (cpumask_available(iter->started) &&
+ cpumask_test_cpu(iter->cpu, iter->started))
return;
if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
return;
- if (iter->started)
+ if (cpumask_available(iter->started))
cpumask_set_cpu(iter->cpu, iter->started);
/* Don't print started cpu buffer for the first entry of the trace */
@@ -2907,9 +3001,15 @@ void trace_default_header(struct seq_file *m)
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_irq_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header_irq(iter->trace_buffer, m);
else
- print_func_help_header(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header(iter->trace_buffer, m);
}
}
}
@@ -3094,7 +3194,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
}
ring_buffer_read_prepare_sync();
for_each_tracing_cpu(cpu) {
@@ -3104,7 +3205,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
ring_buffer_read_prepare_sync();
ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
@@ -3226,11 +3328,17 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
int cpu = tracing_get_cpu(inode);
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->current_trace->print_max)
+ trace_buf = &tr->max_buffer;
+#endif
if (cpu == RING_BUFFER_ALL_CPUS)
- tracing_reset_online_cpus(&tr->trace_buffer);
+ tracing_reset_online_cpus(trace_buf);
else
- tracing_reset(&tr->trace_buffer, cpu);
+ tracing_reset(trace_buf, cpu);
}
if (file->f_mode & FMODE_READ) {
@@ -3378,37 +3486,30 @@ static const struct file_operations show_traces_fops = {
.llseek = seq_lseek,
};
-/*
- * 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 mask_str[NR_CPUS + 1];
-
static ssize_t
tracing_cpumask_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct trace_array *tr = file_inode(filp)->i_private;
+ char *mask_str;
int len;
- mutex_lock(&tracing_cpumask_update_lock);
+ len = snprintf(NULL, 0, "%*pb\n",
+ cpumask_pr_args(tr->tracing_cpumask)) + 1;
+ mask_str = kmalloc(len, GFP_KERNEL);
+ if (!mask_str)
+ return -ENOMEM;
- len = snprintf(mask_str, count, "%*pb\n",
+ len = snprintf(mask_str, len, "%*pb\n",
cpumask_pr_args(tr->tracing_cpumask));
if (len >= count) {
count = -EINVAL;
goto out_err;
}
- count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+ count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
out_err:
- mutex_unlock(&tracing_cpumask_update_lock);
+ kfree(mask_str);
return count;
}
@@ -3428,8 +3529,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (err)
goto err_unlock;
- mutex_lock(&tracing_cpumask_update_lock);
-
local_irq_disable();
arch_spin_lock(&tr->max_lock);
for_each_tracing_cpu(cpu) {
@@ -3452,8 +3551,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
local_irq_enable();
cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
- mutex_unlock(&tracing_cpumask_update_lock);
free_cpumask_var(tracing_cpumask_new);
return count;
@@ -3917,10 +4014,15 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
{
char buf[64];
int r;
+ unsigned int n;
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
- r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
+ n = savedcmd->cmdline_num;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ r = scnprintf(buf, sizeof(buf), "%u\n", n);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -3929,6 +4031,7 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
{
kfree(s->saved_cmdlines);
kfree(s->map_cmdline_to_pid);
+ kfree(s->map_cmdline_to_tgid);
kfree(s);
}
@@ -3945,10 +4048,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
return -ENOMEM;
}
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
savedcmd = s;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
free_saved_cmdlines_buffer(savedcmd_temp);
return 0;
@@ -4161,6 +4266,78 @@ static void trace_insert_enum_map(struct module *mod,
}
static ssize_t
+tracing_saved_tgids_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int i;
+ int *pids;
+ int n = 0;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ pids = kmalloc_array(savedcmd->cmdline_num, 2*sizeof(int), GFP_KERNEL);
+ if (!pids) {
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < savedcmd->cmdline_num; i++) {
+ int pid;
+
+ pid = savedcmd->map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ pids[n] = pid;
+ pids[n+1] = __find_tgid_locked(pid);
+ n += 2;
+ }
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ if (n == 0) {
+ kfree(pids);
+ return 0;
+ }
+
+ /* enough to hold max pair of pids + space, lr and nul */
+ len = n * 12;
+ file_buf = kmalloc(len, GFP_KERNEL);
+ if (!file_buf) {
+ kfree(pids);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+ for (i = 0; i < n && len > 0; i += 2) {
+ int r;
+
+ r = snprintf(buf, len, "%d %d\n", pids[i], pids[i+1]);
+ buf += r;
+ len -= r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, buf - file_buf);
+
+ kfree(file_buf);
+ kfree(pids);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_tgids_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_tgids_read,
+ .llseek = generic_file_llseek,
+};
+
+static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
@@ -4623,7 +4800,6 @@ out:
return ret;
fail:
- kfree(iter->trace);
kfree(iter);
__trace_array_put(tr);
mutex_unlock(&trace_types_lock);
@@ -4701,7 +4877,7 @@ static int tracing_wait_pipe(struct file *filp)
*
* iter->pos will be 0 if we haven't read anything.
*/
- if (!tracing_is_on() && iter->pos)
+ if (!tracer_tracing_is_on(iter->tr) && iter->pos)
break;
mutex_unlock(&iter->mutex);
@@ -5237,7 +5413,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
tracing_reset_online_cpus(&tr->trace_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
+ if (tr->max_buffer.buffer)
ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
tracing_reset_online_cpus(&tr->max_buffer);
#endif
@@ -5759,7 +5935,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5810,14 +5986,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -6060,11 +6228,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
return ret;
out_reg:
- ret = register_ftrace_function_probe(glob, ops, count);
+ ret = alloc_snapshot(&global_trace);
+ if (ret < 0)
+ goto out;
- if (ret >= 0)
- alloc_snapshot(&global_trace);
+ ret = register_ftrace_function_probe(glob, ops, count);
+ out:
return ret < 0 ? ret : 0;
}
@@ -6496,7 +6666,9 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
if (buffer) {
mutex_lock(&trace_types_lock);
- if (val) {
+ if (!!val == tracer_tracing_is_on(tr)) {
+ val = 0; /* do nothing */
+ } else if (val) {
tracer_tracing_on(tr);
if (tr->current_trace->start)
tr->current_trace->start(tr);
@@ -6542,6 +6714,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -6565,7 +6738,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
@@ -6735,6 +6910,7 @@ static int instance_rmdir(const char *name)
}
kfree(tr->topts);
+ free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -6790,6 +6966,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
+ trace_create_file("saved_tgids", 0444, d_tracer,
+ tr, &tracing_saved_tgids_fops);
+
trace_create_file("trace_clock", 0644, d_tracer, tr,
&trace_clock_fops);
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-23 17:11:48 +0000