38516ab59f
This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
300 lines
7.4 KiB
C
300 lines
7.4 KiB
C
/*
|
|
* Workqueue statistical tracer.
|
|
*
|
|
* Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
|
|
*
|
|
*/
|
|
|
|
|
|
#include <trace/events/workqueue.h>
|
|
#include <linux/list.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/kref.h>
|
|
#include "trace_stat.h"
|
|
#include "trace.h"
|
|
|
|
|
|
/* A cpu workqueue thread */
|
|
struct cpu_workqueue_stats {
|
|
struct list_head list;
|
|
struct kref kref;
|
|
int cpu;
|
|
pid_t pid;
|
|
/* Can be inserted from interrupt or user context, need to be atomic */
|
|
atomic_t inserted;
|
|
/*
|
|
* Don't need to be atomic, works are serialized in a single workqueue thread
|
|
* on a single CPU.
|
|
*/
|
|
unsigned int executed;
|
|
};
|
|
|
|
/* List of workqueue threads on one cpu */
|
|
struct workqueue_global_stats {
|
|
struct list_head list;
|
|
spinlock_t lock;
|
|
};
|
|
|
|
/* Don't need a global lock because allocated before the workqueues, and
|
|
* never freed.
|
|
*/
|
|
static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
|
|
#define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
|
|
|
|
static void cpu_workqueue_stat_free(struct kref *kref)
|
|
{
|
|
kfree(container_of(kref, struct cpu_workqueue_stats, kref));
|
|
}
|
|
|
|
/* Insertion of a work */
|
|
static void
|
|
probe_workqueue_insertion(void *ignore,
|
|
struct task_struct *wq_thread,
|
|
struct work_struct *work)
|
|
{
|
|
int cpu = cpumask_first(&wq_thread->cpus_allowed);
|
|
struct cpu_workqueue_stats *node;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
|
|
if (node->pid == wq_thread->pid) {
|
|
atomic_inc(&node->inserted);
|
|
goto found;
|
|
}
|
|
}
|
|
pr_debug("trace_workqueue: entry not found\n");
|
|
found:
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
}
|
|
|
|
/* Execution of a work */
|
|
static void
|
|
probe_workqueue_execution(void *ignore,
|
|
struct task_struct *wq_thread,
|
|
struct work_struct *work)
|
|
{
|
|
int cpu = cpumask_first(&wq_thread->cpus_allowed);
|
|
struct cpu_workqueue_stats *node;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
|
|
if (node->pid == wq_thread->pid) {
|
|
node->executed++;
|
|
goto found;
|
|
}
|
|
}
|
|
pr_debug("trace_workqueue: entry not found\n");
|
|
found:
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
}
|
|
|
|
/* Creation of a cpu workqueue thread */
|
|
static void probe_workqueue_creation(void *ignore,
|
|
struct task_struct *wq_thread, int cpu)
|
|
{
|
|
struct cpu_workqueue_stats *cws;
|
|
unsigned long flags;
|
|
|
|
WARN_ON(cpu < 0);
|
|
|
|
/* Workqueues are sometimes created in atomic context */
|
|
cws = kzalloc(sizeof(struct cpu_workqueue_stats), GFP_ATOMIC);
|
|
if (!cws) {
|
|
pr_warning("trace_workqueue: not enough memory\n");
|
|
return;
|
|
}
|
|
INIT_LIST_HEAD(&cws->list);
|
|
kref_init(&cws->kref);
|
|
cws->cpu = cpu;
|
|
cws->pid = wq_thread->pid;
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list);
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
}
|
|
|
|
/* Destruction of a cpu workqueue thread */
|
|
static void
|
|
probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
|
|
{
|
|
/* Workqueue only execute on one cpu */
|
|
int cpu = cpumask_first(&wq_thread->cpus_allowed);
|
|
struct cpu_workqueue_stats *node, *next;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
|
|
list) {
|
|
if (node->pid == wq_thread->pid) {
|
|
list_del(&node->list);
|
|
kref_put(&node->kref, cpu_workqueue_stat_free);
|
|
goto found;
|
|
}
|
|
}
|
|
|
|
pr_debug("trace_workqueue: don't find workqueue to destroy\n");
|
|
found:
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
|
|
}
|
|
|
|
static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
|
|
{
|
|
unsigned long flags;
|
|
struct cpu_workqueue_stats *ret = NULL;
|
|
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
|
|
if (!list_empty(&workqueue_cpu_stat(cpu)->list)) {
|
|
ret = list_entry(workqueue_cpu_stat(cpu)->list.next,
|
|
struct cpu_workqueue_stats, list);
|
|
kref_get(&ret->kref);
|
|
}
|
|
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void *workqueue_stat_start(struct tracer_stat *trace)
|
|
{
|
|
int cpu;
|
|
void *ret = NULL;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
ret = workqueue_stat_start_cpu(cpu);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static void *workqueue_stat_next(void *prev, int idx)
|
|
{
|
|
struct cpu_workqueue_stats *prev_cws = prev;
|
|
struct cpu_workqueue_stats *ret;
|
|
int cpu = prev_cws->cpu;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) {
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
do {
|
|
cpu = cpumask_next(cpu, cpu_possible_mask);
|
|
if (cpu >= nr_cpu_ids)
|
|
return NULL;
|
|
} while (!(ret = workqueue_stat_start_cpu(cpu)));
|
|
return ret;
|
|
} else {
|
|
ret = list_entry(prev_cws->list.next,
|
|
struct cpu_workqueue_stats, list);
|
|
kref_get(&ret->kref);
|
|
}
|
|
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int workqueue_stat_show(struct seq_file *s, void *p)
|
|
{
|
|
struct cpu_workqueue_stats *cws = p;
|
|
struct pid *pid;
|
|
struct task_struct *tsk;
|
|
|
|
pid = find_get_pid(cws->pid);
|
|
if (pid) {
|
|
tsk = get_pid_task(pid, PIDTYPE_PID);
|
|
if (tsk) {
|
|
seq_printf(s, "%3d %6d %6u %s\n", cws->cpu,
|
|
atomic_read(&cws->inserted), cws->executed,
|
|
tsk->comm);
|
|
put_task_struct(tsk);
|
|
}
|
|
put_pid(pid);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void workqueue_stat_release(void *stat)
|
|
{
|
|
struct cpu_workqueue_stats *node = stat;
|
|
|
|
kref_put(&node->kref, cpu_workqueue_stat_free);
|
|
}
|
|
|
|
static int workqueue_stat_headers(struct seq_file *s)
|
|
{
|
|
seq_printf(s, "# CPU INSERTED EXECUTED NAME\n");
|
|
seq_printf(s, "# | | | |\n");
|
|
return 0;
|
|
}
|
|
|
|
struct tracer_stat workqueue_stats __read_mostly = {
|
|
.name = "workqueues",
|
|
.stat_start = workqueue_stat_start,
|
|
.stat_next = workqueue_stat_next,
|
|
.stat_show = workqueue_stat_show,
|
|
.stat_release = workqueue_stat_release,
|
|
.stat_headers = workqueue_stat_headers
|
|
};
|
|
|
|
|
|
int __init stat_workqueue_init(void)
|
|
{
|
|
if (register_stat_tracer(&workqueue_stats)) {
|
|
pr_warning("Unable to register workqueue stat tracer\n");
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
fs_initcall(stat_workqueue_init);
|
|
|
|
/*
|
|
* Workqueues are created very early, just after pre-smp initcalls.
|
|
* So we must register our tracepoints at this stage.
|
|
*/
|
|
int __init trace_workqueue_early_init(void)
|
|
{
|
|
int ret, cpu;
|
|
|
|
ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
|
|
if (ret)
|
|
goto out;
|
|
|
|
ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
|
|
if (ret)
|
|
goto no_insertion;
|
|
|
|
ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
|
|
if (ret)
|
|
goto no_execution;
|
|
|
|
ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
|
|
if (ret)
|
|
goto no_creation;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
|
|
INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
|
|
}
|
|
|
|
return 0;
|
|
|
|
no_creation:
|
|
unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
|
|
no_execution:
|
|
unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
|
|
no_insertion:
|
|
unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
|
|
out:
|
|
pr_warning("trace_workqueue: unable to trace workqueues\n");
|
|
|
|
return 1;
|
|
}
|
|
early_initcall(trace_workqueue_early_init);
|