aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c6
-rw-r--r--kernel/fork.c5
-rw-r--r--kernel/irq/handle.c7
-rw-r--r--kernel/irq/manage.c5
-rw-r--r--kernel/kthread.c5
-rw-r--r--kernel/lockdep.c38
-rw-r--r--kernel/module.c26
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/posix-cpu-timers.c8
-rw-r--r--kernel/power/disk.c51
-rw-r--r--kernel/ptrace.c4
-rw-r--r--kernel/sched.c14
-rw-r--r--kernel/signal.c4
-rw-r--r--kernel/slow-work.c4
-rw-r--r--kernel/softirq.c7
-rw-r--r--kernel/sysctl.c5
-rw-r--r--kernel/time/tick-common.c12
-rw-r--r--kernel/trace/Kconfig89
-rw-r--r--kernel/trace/Makefile8
-rw-r--r--kernel/trace/blktrace.c193
-rw-r--r--kernel/trace/events.c14
-rw-r--r--kernel/trace/ftrace.c726
-rw-r--r--kernel/trace/kmemtrace.c10
-rw-r--r--kernel/trace/ring_buffer.c657
-rw-r--r--kernel/trace/ring_buffer_benchmark.c413
-rw-r--r--kernel/trace/trace.c371
-rw-r--r--kernel/trace/trace.h241
-rw-r--r--kernel/trace/trace_boot.c5
-rw-r--r--kernel/trace/trace_branch.c8
-rw-r--r--kernel/trace/trace_event_profile.c24
-rw-r--r--kernel/trace/trace_event_types.h12
-rw-r--r--kernel/trace/trace_events.c830
-rw-r--r--kernel/trace/trace_events_filter.c1200
-rw-r--r--kernel/trace/trace_events_stage_1.h39
-rw-r--r--kernel/trace/trace_events_stage_2.h176
-rw-r--r--kernel/trace/trace_events_stage_3.h281
-rw-r--r--kernel/trace/trace_export.c110
-rw-r--r--kernel/trace/trace_functions_graph.c25
-rw-r--r--kernel/trace/trace_hw_branches.c4
-rw-r--r--kernel/trace/trace_mmiotrace.c6
-rw-r--r--kernel/trace/trace_output.c82
-rw-r--r--kernel/trace/trace_output.h28
-rw-r--r--kernel/trace/trace_power.c8
-rw-r--r--kernel/trace/trace_printk.c6
-rw-r--r--kernel/trace/trace_sched_switch.c12
-rw-r--r--kernel/trace/trace_sched_wakeup.c8
-rw-r--r--kernel/trace/trace_stack.c13
-rw-r--r--kernel/trace/trace_stat.c2
-rw-r--r--kernel/trace/trace_stat.h2
-rw-r--r--kernel/trace/trace_sysprof.c6
-rw-r--r--kernel/trace/trace_workqueue.c2
51 files changed, 4123 insertions, 1691 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index abf9cf3b95c..cab535c427b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -48,7 +48,7 @@
#include <linux/tracehook.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -56,10 +56,6 @@
#include <asm/mmu_context.h>
#include "cred-internals.h"
-DEFINE_TRACE(sched_process_free);
-DEFINE_TRACE(sched_process_exit);
-DEFINE_TRACE(sched_process_wait);
-
static void exit_mm(struct task_struct * tsk);
static void __unhash_process(struct task_struct *p)
diff --git a/kernel/fork.c b/kernel/fork.c
index 7d10c46cbb4..711468f3db2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,7 +61,6 @@
#include <linux/proc_fs.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
-#include <trace/sched.h>
#include <linux/magic.h>
#include <asm/pgtable.h>
@@ -71,6 +70,8 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#include <trace/events/sched.h>
+
/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
@@ -83,8 +84,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
-DEFINE_TRACE(sched_process_fork);
-
int nr_processes(void)
{
int cpu;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d82142be8dd..5dd2572993c 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,8 +17,8 @@
#include <linux/kernel_stat.h>
#include <linux/rculist.h>
#include <linux/hash.h>
-#include <trace/irq.h>
#include <linux/bootmem.h>
+#include <trace/events/irq.h>
#include "internals.h"
@@ -348,9 +348,6 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
"but no thread function available.", irq, action->name);
}
-DEFINE_TRACE(irq_handler_entry);
-DEFINE_TRACE(irq_handler_exit);
-
/**
* handle_IRQ_event - irq action chain handler
* @irq: the interrupt number
@@ -363,8 +360,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
irqreturn_t ret, retval = IRQ_NONE;
unsigned int status = 0;
- WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!");
-
if (!(action->flags & IRQF_DISABLED))
local_irq_enable_in_hardirq();
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7e2e7dd4cd2..2734eca5924 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -109,10 +109,9 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
spin_lock_irqsave(&desc->lock, flags);
#ifdef CONFIG_GENERIC_PENDING_IRQ
- if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
- cpumask_copy(desc->affinity, cpumask);
+ if (desc->status & IRQ_MOVE_PCNTXT)
desc->chip->set_affinity(irq, cpumask);
- } else {
+ else {
desc->status |= IRQ_MOVE_PENDING;
cpumask_copy(desc->pending_mask, cpumask);
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4ebaf8519ab..41c88fe4050 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,7 +13,7 @@
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mutex.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#define KTHREAD_NICE_LEVEL (-5)
@@ -21,9 +21,6 @@ static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
-DEFINE_TRACE(sched_kthread_stop);
-DEFINE_TRACE(sched_kthread_stop_ret);
-
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index b0f01186696..8bbeef996c7 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -42,12 +42,14 @@
#include <linux/hash.h>
#include <linux/ftrace.h>
#include <linux/stringify.h>
-#include <trace/lockdep.h>
#include <asm/sections.h>
#include "lockdep_internals.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/lockdep.h>
+
#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
module_param(prove_locking, int, 0644);
@@ -2490,13 +2492,20 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
- if (unlikely(!debug_locks))
+ lock->class_cache = NULL;
+#ifdef CONFIG_LOCK_STAT
+ lock->cpu = raw_smp_processor_id();
+#endif
+
+ if (DEBUG_LOCKS_WARN_ON(!name)) {
+ lock->name = "NULL";
return;
+ }
+
+ lock->name = name;
if (DEBUG_LOCKS_WARN_ON(!key))
return;
- if (DEBUG_LOCKS_WARN_ON(!name))
- return;
/*
* Sanity check, the lock-class key must be persistent:
*/
@@ -2505,12 +2514,11 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
DEBUG_LOCKS_WARN_ON(1);
return;
}
- lock->name = name;
lock->key = key;
- lock->class_cache = NULL;
-#ifdef CONFIG_LOCK_STAT
- lock->cpu = raw_smp_processor_id();
-#endif
+
+ if (unlikely(!debug_locks))
+ return;
+
if (subclass)
register_lock_class(lock, subclass, 1);
}
@@ -2929,8 +2937,6 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
}
EXPORT_SYMBOL_GPL(lock_set_class);
-DEFINE_TRACE(lock_acquire);
-
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
@@ -2957,8 +2963,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
}
EXPORT_SYMBOL_GPL(lock_acquire);
-DEFINE_TRACE(lock_release);
-
void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip)
{
@@ -3099,6 +3103,8 @@ found_it:
hlock->holdtime_stamp = now;
}
+ trace_lock_acquired(lock, ip, waittime);
+
stats = get_lock_stats(hlock_class(hlock));
if (waittime) {
if (hlock->read)
@@ -3114,8 +3120,6 @@ found_it:
lock->ip = ip;
}
-DEFINE_TRACE(lock_contended);
-
void lock_contended(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
@@ -3137,14 +3141,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
}
EXPORT_SYMBOL_GPL(lock_contended);
-DEFINE_TRACE(lock_acquired);
-
void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- trace_lock_acquired(lock, ip);
-
if (unlikely(!lock_stat))
return;
diff --git a/kernel/module.c b/kernel/module.c
index e797812a4d9..2383e60fcf3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -18,6 +18,7 @@
*/
#include <linux/module.h>
#include <linux/moduleloader.h>
+#include <linux/ftrace_event.h>
#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/fs.h>
@@ -1489,9 +1490,6 @@ static void free_module(struct module *mod)
/* Free any allocated parameters. */
destroy_params(mod->kp, mod->num_kp);
- /* release any pointers to mcount in this module */
- ftrace_release(mod->module_core, mod->core_size);
-
/* This may be NULL, but that's OK */
module_free(mod, mod->module_init);
kfree(mod->args);
@@ -1892,11 +1890,9 @@ static noinline struct module *load_module(void __user *umod,
unsigned int symindex = 0;
unsigned int strindex = 0;
unsigned int modindex, versindex, infoindex, pcpuindex;
- unsigned int num_mcount;
struct module *mod;
long err = 0;
void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
- unsigned long *mseg;
mm_segment_t old_fs;
DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2172,7 +2168,19 @@ static noinline struct module *load_module(void __user *umod,
sizeof(*mod->tracepoints),
&mod->num_tracepoints);
#endif
-
+#ifdef CONFIG_EVENT_TRACING
+ mod->trace_events = section_objs(hdr, sechdrs, secstrings,
+ "_ftrace_events",
+ sizeof(*mod->trace_events),
+ &mod->num_trace_events);
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ /* sechdrs[0].sh_size is always zero */
+ mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings,
+ "__mcount_loc",
+ sizeof(*mod->ftrace_callsites),
+ &mod->num_ftrace_callsites);
+#endif
#ifdef CONFIG_MODVERSIONS
if ((mod->num_syms && !mod->crcs)
|| (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -2237,11 +2245,6 @@ static noinline struct module *load_module(void __user *umod,
dynamic_debug_setup(debug, num_debug);
}
- /* sechdrs[0].sh_size is always zero */
- mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
- sizeof(*mseg), &num_mcount);
- ftrace_init_module(mod, mseg, mseg + num_mcount);
-
err = module_finalize(hdr, sechdrs, mod);
if (err < 0)
goto cleanup;
@@ -2302,7 +2305,6 @@ static noinline struct module *load_module(void __user *umod,
cleanup:
kobject_del(&mod->mkobj.kobj);
kobject_put(&mod->mkobj.kobj);
- ftrace_release(mod->module_core, mod->core_size);
free_unload:
module_unload_free(mod);
#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
diff --git a/kernel/panic.c b/kernel/panic.c
index 934fb377f4b..3dcaa166135 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -221,7 +221,7 @@ void add_taint(unsigned flag)
* post-warning case.
*/
if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off())
- printk(KERN_WARNING "Disabling lockdep due to kernel taint\n");
+ printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n");
set_bit(flag, &tainted_mask);
}
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c9dcf98b446..bece7c0b67b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1420,19 +1420,19 @@ void run_posix_cpu_timers(struct task_struct *tsk)
* timer call will interfere.
*/
list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
- int firing;
+ int cpu_firing;
+
spin_lock(&timer->it_lock);
list_del_init(&timer->it.cpu.entry);
- firing = timer->it.cpu.firing;
+ cpu_firing = timer->it.cpu.firing;
timer->it.cpu.firing = 0;
/*
* The firing flag is -1 if we collided with a reset
* of the timer, which already reported this
* almost-firing as an overrun. So don't generate an event.
*/
- if (likely(firing >= 0)) {
+ if (likely(cpu_firing >= 0))
cpu_timer_fire(timer);
- }
spin_unlock(&timer->it_lock);
}
}
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 0854770b63b..e71ca9cd81b 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -646,13 +646,6 @@ static int software_resume(void)
return 0;
/*
- * We can't depend on SCSI devices being available after loading one of
- * their modules if scsi_complete_async_scans() is not called and the
- * resume device usually is a SCSI one.
- */
- scsi_complete_async_scans();
-
- /*
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
@@ -663,32 +656,42 @@ static int software_resume(void)
* here to avoid lockdep complaining.
*/
mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+
+ if (swsusp_resume_device)
+ goto Check_image;
+
+ if (!strlen(resume_file)) {
+ error = -ENOENT;
+ goto Unlock;
+ }
+
+ pr_debug("PM: Checking image partition %s\n", resume_file);
+
+ /* Check if the device is there */
+ swsusp_resume_device = name_to_dev_t(resume_file);
if (!swsusp_resume_device) {
- if (!strlen(resume_file)) {
- mutex_unlock(&pm_mutex);
- return -ENOENT;
- }
/*
* Some device discovery might still be in progress; we need
* to wait for this to finish.
*/
wait_for_device_probe();
+ /*
+ * We can't depend on SCSI devices being available after loading
+ * one of their modules until scsi_complete_async_scans() is
+ * called and the resume device usually is a SCSI one.
+ */
+ scsi_complete_async_scans();
+
swsusp_resume_device = name_to_dev_t(resume_file);
- pr_debug("PM: Resume from partition %s\n", resume_file);
- } else {
- pr_debug("PM: Resume from partition %d:%d\n",
- MAJOR(swsusp_resume_device),
- MINOR(swsusp_resume_device));
+ if (!swsusp_resume_device) {
+ error = -ENODEV;
+ goto Unlock;
+ }
}
- if (noresume) {
- /**
- * FIXME: If noresume is specified, we need to find the
- * partition and reset it back to normal swap space.
- */
- mutex_unlock(&pm_mutex);
- return 0;
- }
+ Check_image:
+ pr_debug("PM: Resume from partition %d:%d\n",
+ MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
pr_debug("PM: Checking hibernation image.\n");
error = swsusp_check();
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4559e84f4b8..e950805f863 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -178,7 +178,7 @@ int ptrace_attach(struct task_struct *task)
/* Protect exec's credential calculations against our interference;
* SUID, SGID and LSM creds get determined differently under ptrace.
*/
- retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+ retval = mutex_lock_interruptible(&task->cred_exec_mutex);
if (retval < 0)
goto out;
@@ -222,7 +222,7 @@ repeat:
bad:
write_unlock_irqrestore(&tasklist_lock, flags);
task_unlock(task);
- mutex_unlock(&current->cred_exec_mutex);
+ mutex_unlock(&task->cred_exec_mutex);
out:
return retval;
}
diff --git a/kernel/sched.c b/kernel/sched.c
index 36322e8682c..6530a27052f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -72,13 +72,15 @@
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
#include "sched_cpupri.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -118,12 +120,6 @@
*/
#define RUNTIME_INF ((u64)~0ULL)
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
#ifdef CONFIG_SMP
static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -1958,7 +1954,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
clock_offset = old_rq->clock - new_rq->clock;
- trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+ trace_sched_migrate_task(p, new_cpu);
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
@@ -4775,7 +4771,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
if (user_tick)
account_user_time(p, one_jiffy, one_jiffy_scaled);
- else if (p != rq->idle)
+ else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
one_jiffy_scaled);
else
diff --git a/kernel/signal.c b/kernel/signal.c
index d8034737db4..94ec0a4dde0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -27,7 +27,7 @@
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/param.h>
#include <asm/uaccess.h>
@@ -41,8 +41,6 @@
static struct kmem_cache *sigqueue_cachep;
-DEFINE_TRACE(sched_signal_send);
-
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index cf2bc01186e..b28d19135f4 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -609,14 +609,14 @@ void slow_work_unregister_user(void)
if (slow_work_user_count == 0) {
printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
slow_work_threads_should_exit = true;
+ del_timer_sync(&slow_work_cull_timer);
+ del_timer_sync(&slow_work_oom_timer);
wake_up_all(&slow_work_thread_wq);
wait_for_completion(&slow_work_last_thread_exited);
printk(KERN_NOTICE "Slow work thread pool:"
" Shut down complete\n");
}
- del_timer_sync(&slow_work_cull_timer);
-
mutex_unlock(&slow_work_user_lock);
}
EXPORT_SYMBOL(slow_work_unregister_user);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b525dd34851..dc4d0cfdcb2 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -24,7 +24,9 @@
#include <linux/ftrace.h>
#include <linux/smp.h>
#include <linux/tick.h>
-#include <trace/irq.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq.h>
#include <asm/irq.h>
/*
@@ -186,9 +188,6 @@ EXPORT_SYMBOL(local_bh_enable_ip);
*/
#define MAX_SOFTIRQ_RESTART 10
-DEFINE_TRACE(softirq_entry);
-DEFINE_TRACE(softirq_exit);
-
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e3d2c7dd59b..ea78fa101ad 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -103,6 +103,9 @@ static unsigned long one_ul = 1;
static int one_hundred = 100;
static int one_thousand = 1000;
+/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
+static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
+
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
static int minolduid;
@@ -1006,7 +1009,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &dirty_bytes_handler,
.strategy = &sysctl_intvec,
- .extra1 = &one_ul,
+ .extra1 = &dirty_bytes_min,
},
{
.procname = "dirty_writeback_centisecs",
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 21a5ca84951..83c4417b6a3 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -93,7 +93,17 @@ void tick_handle_periodic(struct clock_event_device *dev)
for (;;) {
if (!clockevents_program_event(dev, next, ktime_get()))
return;
- tick_periodic(cpu);
+ /*
+ * Have to be careful here. If we're in oneshot mode,
+ * before we call tick_periodic() in a loop, we need
+ * to be sure we're using a real hardware clocksource.
+ * Otherwise we could get trapped in an infinite
+ * loop, as the tick_periodic() increments jiffies,
+ * when then will increment time, posibly causing
+ * the loop to trigger again and again.
+ */
+ if (timekeeping_valid_for_hres())
+ tick_periodic(cpu);
next = ktime_add(next, tick_period);
}
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 417d1985e29..50f62a296e1 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -48,6 +48,9 @@ config FTRACE_NMI_ENTER
depends on HAVE_FTRACE_NMI_ENTER
default y
+config EVENT_TRACING
+ bool
+
config TRACING
bool
select DEBUG_FS
@@ -56,6 +59,7 @@ config TRACING
select TRACEPOINTS
select NOP_TRACER
select BINARY_PRINTF
+ select EVENT_TRACING
#
# Minimum requirements an architecture has to meet for us to
@@ -73,7 +77,12 @@ config TRACING_SUPPORT
if TRACING_SUPPORT
-menu "Tracers"
+menuconfig FTRACE
+ bool "Tracers"
+ help
+ Enable the kernel tracing infrastructure.
+
+if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
@@ -104,6 +113,7 @@ config FUNCTION_GRAPH_TRACER
the return value. This is done by setting the current return
address on the current task structure into a stack of calls.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
default n
@@ -173,7 +183,7 @@ config CONTEXT_SWITCH_TRACER
This tracer gets called from the context switch and records
all switching of tasks.
-config EVENT_TRACER
+config ENABLE_EVENT_TRACING
bool "Trace various events in the kernel"
select TRACING
help
@@ -181,6 +191,10 @@ config EVENT_TRACER
allowing the user to pick and choose which trace point they
want to trace.
+ Note, all tracers enable event tracing. This option is
+ only a convenience to enable event tracing when no other
+ tracers are selected.
+
config FTRACE_SYSCALLS
bool "Trace syscalls"
depends on HAVE_FTRACE_SYSCALLS
@@ -207,8 +221,36 @@ config BOOT_TRACER
to enable this on bootup.
config TRACE_BRANCH_PROFILING
- bool "Trace likely/unlikely profiler"
+ bool
select TRACING
+
+choice
+ prompt "Branch Profiling"
+ default BRANCH_PROFILE_NONE
+ help
+ The branch profiling is a software profiler. It will add hooks
+ into the C conditionals to test which path a branch takes.
+
+ The likely/unlikely profiler only looks at the conditions that
+ are annotated with a likely or unlikely macro.
+
+ The "all branch" profiler will profile every if statement in the
+ kernel. This profiler will also enable the likely/unlikely
+ profiler as well.
+
+ Either of the above profilers add a bit of overhead to the system.
+ If unsure choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+ bool "No branch profiling"
+ help
+ No branch profiling. Branch profiling adds a bit of overhead.
+ Only enable it if you want to analyse the branching behavior.
+ Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
+ bool "Trace likely/unlikely profiler"
+ select TRACE_BRANCH_PROFILING
help
This tracer profiles all the the likely and unlikely macros
in the kernel. It will display the results in:
@@ -218,11 +260,9 @@ config TRACE_BRANCH_PROFILING
Note: this will add a significant overhead, only turn this
on if you need to profile the system's use of these macros.
- Say N if unsure.
-
config PROFILE_ALL_BRANCHES
bool "Profile all if conditionals"
- depends on TRACE_BRANCH_PROFILING
+ select TRACE_BRANCH_PROFILING
help
This tracer profiles all branch conditions. Every if ()
taken in the kernel is recorded whether it hit or miss.
@@ -230,11 +270,12 @@ config PROFILE_ALL_BRANCHES
/debugfs/tracing/profile_branch
+ This option also enables the likely/unlikely profiler.
+
This configuration, when enabled, will impose a great overhead
on the system. This should only be enabled when the system
is to be analyzed
-
- Say N if unsure.
+endchoice
config TRACING_BRANCHES
bool
@@ -375,6 +416,20 @@ config DYNAMIC_FTRACE
were made. If so, it runs stop_machine (stops all CPUS)
and modifies the code to jump over the call to ftrace.
+config FUNCTION_PROFILER
+ bool "Kernel function profiler"
+ depends on FUNCTION_TRACER
+ default n
+ help
+ This option enables the kernel function profiler. A file is created
+ in debugfs called function_profile_enabled which defaults to zero.
+ When a 1 is echoed into this file profiling begins, and when a
+ zero is entered, profiling stops. A file in the trace_stats
+ directory called functions, that show the list of functions that
+ have been hit and their counters.
+
+ If in doubt, say N
+
config FTRACE_MCOUNT_RECORD
def_bool y
depends on DYNAMIC_FTRACE
@@ -416,7 +471,23 @@ config MMIOTRACE_TEST
Say N, unless you absolutely know what you are doing.
-endmenu
+config RING_BUFFER_BENCHMARK
+ tristate "Ring buffer benchmark stress tester"
+ depends on RING_BUFFER
+ help
+ This option creates a test to stress the ring buffer and bench mark it.
+ It creates its own ring buffer such that it will not interfer with
+ any other users of the ring buffer (such as ftrace). It then creates
+ a producer and consumer that will run for 10 seconds and sleep for
+ 10 seconds. Each interval it will print out the number of events
+ it recorded and give a rough estimate of how long each iteration took.
+
+ It does not disable interrupts or raise its priority, so it may be
+ affected by processes that are running.
+
+ If unsure, say N
+
+endif # FTRACE
endif # TRACING_SUPPORT
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index ecc671e9f14..06b85850fab 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -23,6 +23,7 @@ obj-y += trace_clock.o
obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
obj-$(CONFIG_TRACING) += trace.o
obj-$(CONFIG_TRACING) += trace_output.o
@@ -45,11 +46,10 @@ obj-$(CONFIG_POWER_TRACER) += trace_power.o
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events.o
-obj-$(CONFIG_EVENT_TRACER) += events.o
-obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 921ef5d1f0b..e099f8cc1d1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -147,7 +147,7 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
{
if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
return 1;
- if (sector < bt->start_lba || sector > bt->end_lba)
+ if (sector && (sector < bt->start_lba || sector > bt->end_lba))
return 1;
if (bt->pid && pid != bt->pid)
return 1;
@@ -192,7 +192,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
what |= MASK_TC_BIT(rw, DISCARD);
pid = tsk->pid;
- if (unlikely(act_log_check(bt, what, sector, pid)))
+ if (act_log_check(bt, what, sector, pid))
return;
cpu = raw_smp_processor_id();
@@ -403,11 +403,29 @@ static struct rchan_callbacks blk_relay_callbacks = {
.remove_buf_file = blk_remove_buf_file_callback,
};
+static void blk_trace_setup_lba(struct blk_trace *bt,
+ struct block_device *bdev)
+{
+ struct hd_struct *part = NULL;
+
+ if (bdev)
+ part = bdev->bd_part;
+
+ if (part) {
+ bt->start_lba = part->start_sect;
+ bt->end_lba = part->start_sect + part->nr_sects;
+ } else {
+ bt->start_lba = 0;
+ bt->end_lba = -1ULL;
+ }
+}
+
/*
* Setup everything required to start tracing
*/
int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
- struct blk_user_trace_setup *buts)
+ struct block_device *bdev,
+ struct blk_user_trace_setup *buts)
{
struct blk_trace *old_bt, *bt = NULL;
struct dentry *dir = NULL;
@@ -480,10 +498,13 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (!bt->act_mask)
bt->act_mask = (u16) -1;
- bt->start_lba = buts->start_lba;
- bt->end_lba = buts->end_lba;
- if (!bt->end_lba)
- bt->end_lba = -1ULL;
+ blk_trace_setup_lba(bt, bdev);
+
+ /* overwrite with user settings */
+ if (buts->start_lba)
+ bt->start_lba = buts->start_lba;
+ if (buts->end_lba)
+ bt->end_lba = buts->end_lba;
bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
@@ -505,6 +526,7 @@ err:
}
int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
char __user *arg)
{
struct blk_user_trace_setup buts;
@@ -514,7 +536,7 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (ret)
return -EFAULT;
- ret = do_blk_trace_setup(q, name, dev, &buts);
+ ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
if (ret)
return ret;
@@ -582,7 +604,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
switch (cmd) {
case BLKTRACESETUP:
bdevname(bdev, b);
- ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
+ ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
case BLKTRACESTART:
start = 1;
@@ -809,7 +831,6 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
* @bio: the source bio
* @dev: target device
* @from: source sector
- * @to: target sector
*
* Description:
* Device mapper or raid target sometimes need to split a bio because
@@ -817,7 +838,7 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
*
**/
static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from, sector_t to)
+ dev_t dev, sector_t from)
{
struct blk_trace *bt = q->blk_trace;
struct blk_io_trace_remap r;
@@ -825,12 +846,13 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
if (likely(!bt))
return;
- r.device = cpu_to_be32(dev);
- r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
- r.sector = cpu_to_be64(to);
+ r.device_from = cpu_to_be32(dev);
+ r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev);
+ r.sector_from = cpu_to_be64(from);
- __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
- !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+ BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
+ sizeof(r), &r);
}
/**
@@ -971,6 +993,16 @@ static inline const void *pdu_start(const struct trace_entry *ent)
return te_blk_io_trace(ent) + 1;
}
+static inline u32 t_action(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->action;
+}
+
+static inline u32 t_bytes(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->bytes;
+}
+
static inline u32 t_sec(const struct trace_entry *ent)
{
return te_blk_io_trace(ent)->bytes >> 9;
@@ -996,11 +1028,11 @@ static void get_pdu_remap(const struct trace_entry *ent,
struct blk_io_trace_remap *r)
{
const struct blk_io_trace_remap *__r = pdu_start(ent);
- __u64 sector = __r->sector;
+ __u64 sector_from = __r->sector_from;
- r->device = be32_to_cpu(__r->device);
r->device_from = be32_to_cpu(__r->device_from);
- r->sector = be64_to_cpu(sector);
+ r->device_to = be32_to_cpu(__r->device_to);
+ r->sector_from = be64_to_cpu(sector_from);
}
typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
@@ -1031,36 +1063,98 @@ static int blk_log_action(struct trace_iterator *iter, const char *act)
MAJOR(t->device), MINOR(t->device), act, rwbs);
}
+static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+{
+ const char *pdu_buf;
+ int pdu_len;
+ int i, end, ret;
+
+ pdu_buf = pdu_start(ent);
+ pdu_len = te_blk_io_trace(ent)->pdu_len;
+
+ if (!pdu_len)
+ return 1;
+
+ /* find the last zero that needs to be printed */
+ for (end = pdu_len - 1; end >= 0; end--)
+ if (pdu_buf[end])
+ break;
+ end++;
+
+ if (!trace_seq_putc(s, '('))
+ return 0;
+
+ for (i = 0; i < pdu_len; i++) {
+
+ ret = trace_seq_printf(s, "%s%02x",
+ i == 0 ? "" : " ", pdu_buf[i]);
+ if (!ret)
+ return ret;
+
+ /*
+ * stop when the rest is just zeroes and indicate so
+ * with a ".." appended
+ */
+ if (i == end && end != pdu_len - 1)
+ return trace_seq_puts(s, " ..) ");
+ }
+
+ return trace_seq_puts(s, ") ");
+}
+
static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
- if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%s]\n",
- t_sector(ent), t_sec(ent), cmd);
- return trace_seq_printf(s, "[%s]\n", cmd);
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = trace_seq_printf(s, "%u ", t_bytes(ent));
+ if (!ret)
+ return 0;
+ ret = blk_log_dump_pdu(s, ent);
+ if (!ret)
+ return 0;
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%s]\n",
+ t_sector(ent), t_sec(ent), cmd);
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ }
}
static int blk_log_with_error(struct trace_seq *s,
const struct trace_entry *ent)
{
- if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent),
- t_sec(ent), t_error(ent));
- return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent));
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = blk_log_dump_pdu(s, ent);
+ if (ret)
+ return trace_seq_printf(s, "[%d]\n", t_error(ent));
+ return 0;
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%d]\n",
+ t_sector(ent),
+ t_sec(ent), t_error(ent));
+ return trace_seq_printf(s, "%llu [%d]\n",
+ t_sector(ent), t_error(ent));
+ }
}
static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
{
- struct blk_io_trace_remap r = { .device = 0, };
+ struct blk_io_trace_remap r = { .device_from = 0, };
get_pdu_remap(ent, &r);
return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
- t_sector(ent),
- t_sec(ent), MAJOR(r.device), MINOR(r.device),
- (unsigned long long)r.sector);
+ t_sector(ent), t_sec(ent),
+ MAJOR(r.device_from), MINOR(r.device_from),
+ (unsigned long long)r.sector_from);
}
static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
@@ -1117,7 +1211,6 @@ static void blk_tracer_print_header(struct seq_file *m)
static void blk_tracer_start(struct trace_array *tr)
{
blk_tracer_enabled = true;
- trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
}
static int blk_tracer_init(struct trace_array *tr)
@@ -1130,7 +1223,6 @@ static int blk_tracer_init(struct trace_array *tr)
static void blk_tracer_stop(struct trace_array *tr)
{
blk_tracer_enabled = false;
- trace_flags |= TRACE_ITER_CONTEXT_INFO;
}
static void blk_tracer_reset(struct trace_array *tr)
@@ -1182,7 +1274,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
}
if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
- ret = trace_seq_printf(s, "Bad pc action %x\n", what);
+ ret = trace_seq_printf(s, "Unknown action %x\n", what);
else {
ret = log_action(iter, what2act[what].act[long_act]);
if (ret)
@@ -1195,9 +1287,6 @@ out:
static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
int flags)
{
- if (!trace_print_context(iter))
- return TRACE_TYPE_PARTIAL_LINE;
-
return print_one_line(iter, false);
}
@@ -1232,6 +1321,18 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
return print_one_line(iter, true);
}
+static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+{
+ /* don't output context-info for blk_classic output */
+ if (bit == TRACE_BLK_OPT_CLASSIC) {
+ if (set)
+ trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+ else
+ trace_flags |= TRACE_ITER_CONTEXT_INFO;
+ }
+ return 0;
+}
+
static struct tracer blk_tracer __read_mostly = {
.name = "blk",
.init = blk_tracer_init,
@@ -1241,6 +1342,7 @@ static struct tracer blk_tracer __read_mostly = {
.print_header = blk_tracer_print_header,
.print_line = blk_tracer_print_line,
.flags = &blk_tracer_flags,
+ .set_flag = blk_tracer_set_flag,
};
static struct trace_event trace_blk_event = {
@@ -1285,7 +1387,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
/*
* Setup everything required to start tracing
*/
-static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
+static int blk_trace_setup_queue(struct request_queue *q,
+ struct block_device *bdev)
{
struct blk_trace *old_bt, *bt = NULL;
int ret = -ENOMEM;
@@ -1298,9 +1401,10 @@ static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
if (!bt->msg_data)
goto free_bt;
- bt->dev = dev;
+ bt->dev = bdev->bd_dev;
bt->act_mask = (u16)-1;
- bt->end_lba = -1ULL;
+
+ blk_trace_setup_lba(bt, bdev);
old_bt = xchg(&q->blk_trace, bt);
if (old_bt != NULL) {
@@ -1517,7 +1621,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
if (attr == &dev_attr_enable) {
if (value)
- ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ ret = blk_trace_setup_queue(q, bdev);
else
ret = blk_trace_remove_queue(q);
goto out_unlock_bdev;
@@ -1525,7 +1629,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
ret = 0;
if (q->blk_trace == NULL)
- ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ ret = blk_trace_setup_queue(q, bdev);
if (ret == 0) {
if (attr == &dev_attr_act_mask)
@@ -1548,3 +1652,8 @@ out:
return ret ? ret : count;
}
+int blk_trace_init_sysfs(struct device *dev)
+{
+ return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
+}
+
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
deleted file mode 100644
index 246f2aa6dc4..00000000000
--- a/kernel/trace/events.c
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * This is the place to register all trace points as events.
- */
-
-#include <linux/stringify.h>
-
-#include <trace/trace_events.h>
-
-#include "trace_output.h"
-
-#include "trace_events_stage_1.h"
-#include "trace_events_stage_2.h"
-#include "trace_events_stage_3.h"
-
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f1ed080406c..5b606f45b6c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -29,11 +29,12 @@
#include <linux/list.h>
#include <linux/hash.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/ftrace.h>
-#include "trace.h"
+#include "trace_output.h"
+#include "trace_stat.h"
#define FTRACE_WARN_ON(cond) \
do { \
@@ -68,7 +69,7 @@ static DEFINE_MUTEX(ftrace_lock);
static struct ftrace_ops ftrace_list_end __read_mostly =
{
- .func = ftrace_stub,
+ .func = ftrace_stub,
};
static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
@@ -240,6 +241,576 @@ static void ftrace_update_pid_func(void)
#endif
}
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+ struct hlist_node node;
+ unsigned long ip;
+ unsigned long counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ unsigned long long time;
+#endif
+};
+
+struct ftrace_profile_page {
+ struct ftrace_profile_page *next;
+ unsigned long index;
+ struct ftrace_profile records[];
+};
+
+struct ftrace_profile_stat {
+ atomic_t disabled;
+ struct hlist_head *hash;
+ struct ftrace_profile_page *pages;
+ struct ftrace_profile_page *start;
+ struct tracer_stat stat;
+};
+
+#define PROFILE_RECORDS_SIZE \
+ (PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE \
+ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+ struct ftrace_profile *rec = v;
+ struct ftrace_profile_page *pg;
+
+ pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+ rec++;
+ if ((void *)rec >= (void *)&pg->records[pg->index]) {
+ pg = pg->next;
+ if (!pg)
+ return NULL;
+ rec = &pg->records[0];
+ if (!rec->counter)
+ goto again;
+ }
+
+ return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+ struct ftrace_profile_stat *stat =
+ container_of(trace, struct ftrace_profile_stat, stat);
+
+ if (!stat || !stat->start)
+ return NULL;
+
+ return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->time < b->time)
+ return -1;
+ if (a->time > b->time)
+ return 1;
+ else
+ return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->counter < b->counter)
+ return -1;
+ if (a->counter > b->counter)
+ return 1;
+ else
+ return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " Function "
+ "Hit Time Avg\n"
+ " -------- "
+ "--- ---- ---\n");
+#else
+ seq_printf(m, " Function Hit\n"
+ " -------- ---\n");
+#endif
+ return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+ struct ftrace_profile *rec = v;
+ char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ static DEFINE_MUTEX(mutex);
+ static struct trace_seq s;
+ unsigned long long avg;
+#endif
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ seq_printf(m, " %-30.30s %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " ");
+ avg = rec->time;
+ do_div(avg, rec->counter);
+
+ mutex_lock(&mutex);
+ trace_seq_init(&s);
+ trace_print_graph_duration(rec->time, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(avg, &s);
+ trace_print_seq(m, &s);
+ mutex_unlock(&mutex);
+#endif
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+
+ pg = stat->pages = stat->start;
+
+ while (pg) {
+ memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+ pg->index = 0;
+ pg = pg->next;
+ }
+
+ memset(stat->hash, 0,
+ FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+ int functions;
+ int pages;
+ int i;
+
+ /* If we already allocated, do nothing */
+ if (stat->pages)
+ return 0;
+
+ stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!stat->pages)
+ return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ functions = ftrace_update_tot_cnt;
+#else
+ /*
+ * We do not know the number of functions that exist because
+ * dynamic tracing is what counts them. With past experience
+ * we have around 20K functions. That should be more than enough.
+ * It is highly unlikely we will execute every function in
+ * the kernel.
+ */
+ functions = 20000;
+#endif
+
+ pg = stat->start = stat->pages;
+
+ pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+ for (i = 0; i < pages; i++) {
+ pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!pg->next)
+ goto out_free;
+ pg = pg->next;
+ }
+
+ return 0;
+
+ out_free:
+ pg = stat->start;
+ while (pg) {
+ unsigned long tmp = (unsigned long)pg;
+
+ pg = pg->next;
+ free_page(tmp);
+ }
+
+ free_page((unsigned long)stat->pages);
+ stat->pages = NULL;
+ stat->start = NULL;
+
+ return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+ struct ftrace_profile_stat *stat;
+ int size;
+
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ if (stat->hash) {
+ /* If the profile is already created, simply reset it */
+ ftrace_profile_reset(stat);
+ return 0;
+ }
+
+ /*
+ * We are profiling all functions, but usually only a few thousand
+ * functions are hit. We'll make a hash of 1024 items.
+ */
+ size = FTRACE_PROFILE_HASH_SIZE;
+
+ stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+ if (!stat->hash)
+ return -ENOMEM;
+
+ if (!ftrace_profile_bits) {
+ size--;
+
+ for (; size; size >>= 1)
+ ftrace_profile_bits++;
+ }
+
+ /* Preallocate the function profiling pages */
+ if (ftrace_profile_pages_init(stat) < 0) {
+ kfree(stat->hash);
+ stat->hash = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+ int cpu;
+ int ret = 0;
+
+ for_each_online_cpu(cpu) {
+ ret = ftrace_profile_init_cpu(cpu);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec;
+ struct hlist_head *hhd;
+ struct hlist_node *n;
+ unsigned long key;
+
+ key = hash_long(ip, ftrace_profile_bits);
+ hhd = &stat->hash[key];
+
+ if (hlist_empty(hhd))
+ return NULL;
+
+ hlist_for_each_entry_rcu(rec, n, hhd, node) {
+ if (rec->ip == ip)
+ return rec;
+ }
+
+ return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+ struct ftrace_profile *rec)
+{
+ unsigned long key;
+
+ key = hash_long(rec->ip, ftrace_profile_bits);
+ hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec = NULL;
+
+ /* prevent recursion (from NMIs) */
+ if (atomic_inc_return(&stat->disabled) != 1)
+ goto out;
+
+ /*
+ * Try to find the function again since an NMI
+ * could have added it
+ */
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (rec)
+ goto out;
+
+ if (stat->pages->index == PROFILES_PER_PAGE) {
+ if (!stat->pages->next)
+ goto out;
+ stat->pages = stat->pages->next;
+ }
+
+ rec = &stat->pages->records[stat->pages->index++];
+ rec->ip = ip;
+ ftrace_add_profile(stat, rec);
+
+ out:
+ atomic_dec(&stat->disabled);
+
+ return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_profile_stat *stat;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ if (!ftrace_profile_enabled)
+ return;
+
+ local_irq_save(flags);
+
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash)
+ goto out;
+
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (!rec) {
+ rec = ftrace_profile_alloc(stat, ip);
+ if (!rec)
+ goto out;
+ }
+
+ rec->counter++;
+ out:
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+ function_profile_call(trace->func, 0);
+ return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct ftrace_profile_stat *stat;
+ unsigned long long calltime;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash)
+ goto out;
+
+ calltime = trace->rettime - trace->calltime;
+
+ if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+ int index;
+
+ index = trace->depth;
+
+ /* Append this call time to the parent time to subtract */
+ if (index)
+ current->ret_stack[index - 1].subtime += calltime;
+
+ if (current->ret_stack[index].subtime < calltime)
+ calltime -= current->ret_stack[index].subtime;
+ else
+ calltime = 0;
+ }
+
+ rec = ftrace_find_profiled_func(stat, trace->func);
+ if (rec)
+ rec->time += calltime;
+
+ out:
+ local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_graph(&profile_graph_return,
+ &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+ .func = function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long val;
+ char buf[64]; /* big enough to hold a number */
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ val = !!val;
+
+ mutex_lock(&ftrace_profile_lock);
+ if (ftrace_profile_enabled ^ val) {
+ if (val) {
+ ret = ftrace_profile_init();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+
+ ret = register_ftrace_profiler();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+ ftrace_profile_enabled = 1;
+ } else {
+ ftrace_profile_enabled = 0;
+ unregister_ftrace_profiler();
+ }
+ }
+ out:
+ mutex_unlock(&ftrace_profile_lock);
+
+ filp->f_pos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64]; /* big enough to hold a number */
+ int r;
+
+ r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+ .open = tracing_open_generic,
+ .read = ftrace_profile_read,
+ .write = ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+ .name = "functions",
+ .stat_start = function_stat_start,
+ .stat_next = function_stat_next,
+ .stat_cmp = function_stat_cmp,
+ .stat_headers = function_stat_headers,
+ .stat_show = function_stat_show
+};
+
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+ struct ftrace_profile_stat *stat;
+ struct dentry *entry;
+ char *name;
+ int ret;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ /* allocate enough for function name + cpu number */
+ name = kmalloc(32, GFP_KERNEL);
+ if (!name) {
+ /*
+ * The files created are permanent, if something happens
+ * we still do not free memory.
+ */
+ kfree(stat);
+ WARN(1,
+ "Could not allocate stat file for cpu %d\n",
+ cpu);
+ return;
+ }
+ stat->stat = function_stats;
+ snprintf(name, 32, "function%d", cpu);
+ stat->stat.name = name;
+ ret = register_stat_tracer(&stat->stat);
+ if (ret) {
+ WARN(1,
+ "Could not register function stat for cpu %d\n",
+ cpu);
+ kfree(name);
+ return;
+ }
+ }
+
+ entry = debugfs_create_file("function_profile_enabled", 0644,
+ d_tracer, NULL, &ftrace_profile_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
/* set when tracing only a pid */
struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
@@ -261,7 +832,6 @@ struct ftrace_func_probe {
struct rcu_head rcu;
};
-
enum {
FTRACE_ENABLE_CALLS = (1 << 0),
FTRACE_DISABLE_CALLS = (1 << 1),
@@ -346,30 +916,6 @@ static void ftrace_free_rec(struct dyn_ftrace *rec)
rec->flags |= FTRACE_FL_FREE;
}
-void ftrace_release(void *start, unsigned long size)
-{
- struct dyn_ftrace *rec;
- struct ftrace_page *pg;
- unsigned long s = (unsigned long)start;
- unsigned long e = s + size;
-
- if (ftrace_disabled || !start)
- return;
-
- mutex_lock(&ftrace_lock);
- do_for_each_ftrace_rec(pg, rec) {
- if ((rec->ip >= s) && (rec->ip < e)) {
- /*
- * rec->ip is changed in ftrace_free_rec()
- * It should not between s and e if record was freed.
- */
- FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
- ftrace_free_rec(rec);
- }
- } while_for_each_ftrace_rec();
- mutex_unlock(&ftrace_lock);
-}
-
static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
{
struct dyn_ftrace *rec;
@@ -1408,7 +1954,7 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
static struct ftrace_ops trace_probe_ops __read_mostly =
{
- .func = function_trace_probe_call,
+ .func = function_trace_probe_call,
};
static int ftrace_probe_registered;
@@ -2128,38 +2674,23 @@ static const struct file_operations ftrace_graph_fops = {
static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
{
- struct dentry *entry;
- entry = debugfs_create_file("available_filter_functions", 0444,
- d_tracer, NULL, &ftrace_avail_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'available_filter_functions' entry\n");
+ trace_create_file("available_filter_functions", 0444,
+ d_tracer, NULL, &ftrace_avail_fops);
- entry = debugfs_create_file("failures", 0444,
- d_tracer, NULL, &ftrace_failures_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'failures' entry\n");
+ trace_create_file("failures", 0444,
+ d_tracer, NULL, &ftrace_failures_fops);
- entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
- NULL, &ftrace_filter_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_filter' entry\n");
+ trace_create_file("set_ftrace_filter", 0644, d_tracer,
+ NULL, &ftrace_filter_fops);
- entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer,
+ trace_create_file("set_ftrace_notrace", 0644, d_tracer,
NULL, &ftrace_notrace_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_notrace' entry\n");
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- entry = debugfs_create_file("set_graph_function", 0444, d_tracer,
+ trace_create_file("set_graph_function", 0444, d_tracer,
NULL,
&ftrace_graph_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_graph_function' entry\n");
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
return 0;
@@ -2197,14 +2728,72 @@ static int ftrace_convert_nops(struct module *mod,
return 0;
}
-void ftrace_init_module(struct module *mod,
- unsigned long *start, unsigned long *end)
+#ifdef CONFIG_MODULES
+void ftrace_release(void *start, void *end)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+ unsigned long s = (unsigned long)start;
+ unsigned long e = (unsigned long)end;
+
+ if (ftrace_disabled || !start || start == end)
+ return;
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+ if ((rec->ip >= s) && (rec->ip < e)) {
+ /*
+ * rec->ip is changed in ftrace_free_rec()
+ * It should not between s and e if record was freed.
+ */
+ FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
+ ftrace_free_rec(rec);
+ }
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+}
+
+static void ftrace_init_module(struct module *mod,
+ unsigned long *start, unsigned long *end)
{
if (ftrace_disabled || start == end)
return;
ftrace_convert_nops(mod, start, end);
}
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ ftrace_init_module(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
+ break;
+ case MODULE_STATE_GOING:
+ ftrace_release(mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
+ break;
+ }
+
+ return 0;
+}
+#else
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block ftrace_module_nb = {
+ .notifier_call = ftrace_module_notify,
+ .priority = 0,
+};
+
extern unsigned long __start_mcount_loc[];
extern unsigned long __stop_mcount_loc[];
@@ -2236,6 +2825,10 @@ void __init ftrace_init(void)
__start_mcount_loc,
__stop_mcount_loc);
+ ret = register_module_notifier(&ftrace_module_nb);
+ if (!ret)
+ pr_warning("Failed to register trace ftrace module notifier\n");
+
return;
failed:
ftrace_disabled = 1;
@@ -2417,7 +3010,6 @@ static const struct file_operations ftrace_pid_fops = {
static __init int ftrace_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
if (!d_tracer)
@@ -2425,11 +3017,11 @@ static __init int ftrace_init_debugfs(void)
ftrace_init_dyn_debugfs(d_tracer);
- entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
- NULL, &ftrace_pid_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_pid' entry\n");
+ trace_create_file("set_ftrace_pid", 0644, d_tracer,
+ NULL, &ftrace_pid_fops);
+
+ ftrace_profile_debugfs(d_tracer);
+
return 0;
}
fs_initcall(ftrace_init_debugfs);
@@ -2538,7 +3130,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static atomic_t ftrace_graph_active;
+static int ftrace_graph_active;
static struct notifier_block ftrace_suspend_notifier;
int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
@@ -2690,7 +3282,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
mutex_lock(&ftrace_lock);
/* we currently allow only one tracer registered at a time */
- if (atomic_read(&ftrace_graph_active)) {
+ if (ftrace_graph_active) {
ret = -EBUSY;
goto out;
}
@@ -2698,10 +3290,10 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
register_pm_notifier(&ftrace_suspend_notifier);
- atomic_inc(&ftrace_graph_active);
+ ftrace_graph_active++;
ret = start_graph_tracing();
if (ret) {
- atomic_dec(&ftrace_graph_active);
+ ftrace_graph_active--;
goto out;
}
@@ -2719,10 +3311,10 @@ void unregister_ftrace_graph(void)
{
mutex_lock(&ftrace_lock);
- if (!unlikely(atomic_read(&ftrace_graph_active)))
+ if (unlikely(!ftrace_graph_active))
goto out;
- atomic_dec(&ftrace_graph_active);
+ ftrace_graph_active--;
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
@@ -2736,7 +3328,7 @@ void unregister_ftrace_graph(void)
/* Allocate a return stack for newly created task */
void ftrace_graph_init_task(struct task_struct *t)
{
- if (atomic_read(&ftrace_graph_active)) {
+ if (ftrace_graph_active) {
t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
* sizeof(struct ftrace_ret_stack),
GFP_KERNEL);
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 5011f4d91e3..86cdf671d7e 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -12,7 +12,7 @@
#include <linux/dcache.h>
#include <linux/fs.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include "trace_output.h"
#include "trace.h"
@@ -42,6 +42,7 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
gfp_t gfp_flags,
int node)
{
+ struct ftrace_event_call *call = &event_kmem_alloc;
struct trace_array *tr = kmemtrace_array;
struct kmemtrace_alloc_entry *entry;
struct ring_buffer_event *event;
@@ -62,7 +63,8 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
entry->gfp_flags = gfp_flags;
entry->node = node;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
trace_wake_up();
}
@@ -71,6 +73,7 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
unsigned long call_site,
const void *ptr)
{
+ struct ftrace_event_call *call = &event_kmem_free;
struct trace_array *tr = kmemtrace_array;
struct kmemtrace_free_entry *entry;
struct ring_buffer_event *event;
@@ -86,7 +89,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
entry->call_site = call_site;
entry->ptr = ptr;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
trace_wake_up();
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 960cbf44c84..3ae5ccf2c0f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -22,6 +22,28 @@
#include "trace.h"
/*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_seq_printf(s, "# compressed entry header\n");
+ ret = trace_seq_printf(s, "\ttype_len : 5 bits\n");
+ ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n");
+ ret = trace_seq_printf(s, "\tarray : 32 bits\n");
+ ret = trace_seq_printf(s, "\n");
+ ret = trace_seq_printf(s, "\tpadding : type == %d\n",
+ RINGBUF_TYPE_PADDING);
+ ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+ RINGBUF_TYPE_TIME_EXTEND);
+ ret = trace_seq_printf(s, "\tdata max type_len == %d\n",
+ RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+ return ret;
+}
+
+/*
* The ring buffer is made up of a list of pages. A separate list of pages is
* allocated for each CPU. A writer may only write to a buffer that is
* associated with the CPU it is currently executing on. A reader may read
@@ -182,7 +204,10 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
#define RB_ALIGNMENT 4U
-#define RB_MAX_SMALL_DATA 28
+#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
enum {
RB_LEN_TIME_EXTEND = 8,
@@ -191,48 +216,28 @@ enum {
static inline int rb_null_event(struct ring_buffer_event *event)
{
- return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+ return event->type_len == RINGBUF_TYPE_PADDING
+ && event->time_delta == 0;
}
static inline int rb_discarded_event(struct ring_buffer_event *event)
{
- return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+ return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
}
static void rb_event_set_padding(struct ring_buffer_event *event)
{
- event->type = RINGBUF_TYPE_PADDING;
+ event->type_len = RINGBUF_TYPE_PADDING;
event->time_delta = 0;
}
-/**
- * ring_buffer_event_discard - discard an event in the ring buffer
- * @buffer: the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
-{
- event->type = RINGBUF_TYPE_PADDING;
- /* time delta must be non zero */
- if (!event->time_delta)
- event->time_delta = 1;
-}
-
static unsigned
rb_event_data_length(struct ring_buffer_event *event)
{
unsigned length;
- if (event->len)
- length = event->len * RB_ALIGNMENT;
+ if (event->type_len)
+ length = event->type_len * RB_ALIGNMENT;
else
length = event->array[0];
return length + RB_EVNT_HDR_SIZE;
@@ -242,12 +247,12 @@ rb_event_data_length(struct ring_buffer_event *event)
static unsigned
rb_event_length(struct ring_buffer_event *event)
{
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event))
/* undefined */
return -1;
- return rb_event_data_length(event);
+ return event->array[0] + RB_EVNT_HDR_SIZE;
case RINGBUF_TYPE_TIME_EXTEND:
return RB_LEN_TIME_EXTEND;
@@ -271,7 +276,7 @@ rb_event_length(struct ring_buffer_event *event)
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
unsigned length = rb_event_length(event);
- if (event->type != RINGBUF_TYPE_DATA)
+ if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
return length;
length -= RB_EVNT_HDR_SIZE;
if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
@@ -284,9 +289,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
static void *
rb_event_data(struct ring_buffer_event *event)
{
- BUG_ON(event->type != RINGBUF_TYPE_DATA);
+ BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
- if (event->len)
+ if (event->type_len)
return (void *)&event->array[0];
/* Otherwise length is in array[0] and array[1] has the data */
return (void *)&event->array[1];
@@ -316,9 +321,10 @@ struct buffer_data_page {
};
struct buffer_page {
+ struct list_head list; /* list of buffer pages */
local_t write; /* index for next write */
unsigned read; /* index for next read */
- struct list_head list; /* list of free pages */
+ local_t entries; /* entries on this page */
struct buffer_data_page *page; /* Actual data page */
};
@@ -361,6 +367,28 @@ static inline int test_time_stamp(u64 delta)
#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+ struct buffer_data_page field;
+ int ret;
+
+ ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+ "offset:0;\tsize:%u;\n",
+ (unsigned int)sizeof(field.time_stamp));
+
+ ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ (unsigned int)sizeof(field.commit));
+
+ ret = trace_seq_printf(s, "\tfield: char data;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), data),
+ (unsigned int)BUF_PAGE_SIZE);
+
+ return ret;
+}
+
/*
* head_page == tail_page && head == tail then buffer is empty.
*/
@@ -375,8 +403,11 @@ struct ring_buffer_per_cpu {
struct buffer_page *tail_page; /* write to tail */
struct buffer_page *commit_page; /* committed pages */
struct buffer_page *reader_page;
+ unsigned long nmi_dropped;
+ unsigned long commit_overrun;
unsigned long overrun;
- unsigned long entries;
+ unsigned long read;
+ local_t entries;
u64 write_stamp;
u64 read_stamp;
atomic_t record_disabled;
@@ -947,31 +978,6 @@ static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
return rb_page_commit(cpu_buffer->head_page);
}
-/*
- * When the tail hits the head and the buffer is in overwrite mode,
- * the head jumps to the next page and all content on the previous
- * page is discarded. But before doing so, we update the overrun
- * variable of the buffer.
- */
-static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
-{
- struct ring_buffer_event *event;
- unsigned long head;
-
- for (head = 0; head < rb_head_size(cpu_buffer);
- head += rb_event_length(event)) {
-
- event = __rb_page_index(cpu_buffer->head_page, head);
- if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
- return;
- /* Only count data entries */
- if (event->type != RINGBUF_TYPE_DATA)
- continue;
- cpu_buffer->overrun++;
- cpu_buffer->entries--;
- }
-}
-
static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
struct buffer_page **bpage)
{
@@ -1110,28 +1116,21 @@ static void
rb_update_event(struct ring_buffer_event *event,
unsigned type, unsigned length)
{
- event->type = type;
+ event->type_len = type;
switch (type) {
case RINGBUF_TYPE_PADDING:
- break;
-
case RINGBUF_TYPE_TIME_EXTEND:
- event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT);
- break;
-
case RINGBUF_TYPE_TIME_STAMP:
- event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT);
break;
- case RINGBUF_TYPE_DATA:
+ case 0:
length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA) {
- event->len = 0;
+ if (length > RB_MAX_SMALL_DATA)
event->array[0] = length;
- } else
- event->len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+ else
+ event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
break;
default:
BUG();
@@ -1155,131 +1154,156 @@ static unsigned rb_calculate_event_length(unsigned length)
return length;
}
+
static struct ring_buffer_event *
-__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length, u64 *ts)
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length, unsigned long tail,
+ struct buffer_page *commit_page,
+ struct buffer_page *tail_page, u64 *ts)
{
- struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
- unsigned long tail, write;
+ struct buffer_page *next_page, *head_page, *reader_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
- unsigned long flags;
bool lock_taken = false;
+ unsigned long flags;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
- tail_page = cpu_buffer->tail_page;
- write = local_add_return(length, &tail_page->write);
- tail = write - length;
+ next_page = tail_page;
- /* See if we shot pass the end of this buffer page */
- if (write > BUF_PAGE_SIZE) {
- struct buffer_page *next_page = tail_page;
+ local_irq_save(flags);
+ /*
+ * Since the write to the buffer is still not
+ * fully lockless, we must be careful with NMIs.
+ * The locks in the writers are taken when a write
+ * crosses to a new page. The locks protect against
+ * races with the readers (this will soon be fixed
+ * with a lockless solution).
+ *
+ * Because we can not protect against NMIs, and we
+ * want to keep traces reentrant, we need to manage
+ * what happens when we are in an NMI.
+ *
+ * NMIs can happen after we take the lock.
+ * If we are in an NMI, only take the lock
+ * if it is not already taken. Otherwise
+ * simply fail.
+ */
+ if (unlikely(in_nmi())) {
+ if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+ cpu_buffer->nmi_dropped++;
+ goto out_reset;
+ }
+ } else
+ __raw_spin_lock(&cpu_buffer->lock);
- local_irq_save(flags);
- /*
- * Since the write to the buffer is still not
- * fully lockless, we must be careful with NMIs.
- * The locks in the writers are taken when a write
- * crosses to a new page. The locks protect against
- * races with the readers (this will soon be fixed
- * with a lockless solution).
- *
- * Because we can not protect against NMIs, and we
- * want to keep traces reentrant, we need to manage
- * what happens when we are in an NMI.
- *
- * NMIs can happen after we take the lock.
- * If we are in an NMI, only take the lock
- * if it is not already taken. Otherwise
- * simply fail.
- */
- if (unlikely(in_nmi())) {
- if (!__raw_spin_trylock(&cpu_buffer->lock))
- goto out_reset;
- } else
- __raw_spin_lock(&cpu_buffer->lock);
+ lock_taken = true;
- lock_taken = true;
+ rb_inc_page(cpu_buffer, &next_page);
- rb_inc_page(cpu_buffer, &next_page);
+ head_page = cpu_buffer->head_page;
+ reader_page = cpu_buffer->reader_page;
- head_page = cpu_buffer->head_page;
- reader_page = cpu_buffer->reader_page;
+ /* we grabbed the lock before incrementing */
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_reset;
- /* we grabbed the lock before incrementing */
- if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
- goto out_reset;
+ /*
+ * If for some reason, we had an interrupt storm that made
+ * it all the way around the buffer, bail, and warn
+ * about it.
+ */
+ if (unlikely(next_page == commit_page)) {
+ cpu_buffer->commit_overrun++;
+ goto out_reset;
+ }
- /*
- * If for some reason, we had an interrupt storm that made
- * it all the way around the buffer, bail, and warn
- * about it.
- */
- if (unlikely(next_page == commit_page)) {
- WARN_ON_ONCE(1);
+ if (next_page == head_page) {
+ if (!(buffer->flags & RB_FL_OVERWRITE))
goto out_reset;
- }
-
- if (next_page == head_page) {
- if (!(buffer->flags & RB_FL_OVERWRITE))
- goto out_reset;
- /* tail_page has not moved yet? */
- if (tail_page == cpu_buffer->tail_page) {
- /* count overflows */
- rb_update_overflow(cpu_buffer);
+ /* tail_page has not moved yet? */
+ if (tail_page == cpu_buffer->tail_page) {
+ /* count overflows */
+ cpu_buffer->overrun +=
+ local_read(&head_page->entries);
- rb_inc_page(cpu_buffer, &head_page);
- cpu_buffer->head_page = head_page;
- cpu_buffer->head_page->read = 0;
- }
+ rb_inc_page(cpu_buffer, &head_page);
+ cpu_buffer->head_page = head_page;
+ cpu_buffer->head_page->read = 0;
}
+ }
- /*
- * If the tail page is still the same as what we think
- * it is, then it is up to us to update the tail
- * pointer.
- */
- if (tail_page == cpu_buffer->tail_page) {
- local_set(&next_page->write, 0);
- local_set(&next_page->page->commit, 0);
- cpu_buffer->tail_page = next_page;
+ /*
+ * If the tail page is still the same as what we think
+ * it is, then it is up to us to update the tail
+ * pointer.
+ */
+ if (tail_page == cpu_buffer->tail_page) {
+ local_set(&next_page->write, 0);
+ local_set(&next_page->entries, 0);
+ local_set(&next_page->page->commit, 0);
+ cpu_buffer->tail_page = next_page;
+
+ /* reread the time stamp */
+ *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
+ cpu_buffer->tail_page->page->time_stamp = *ts;
+ }
- /* reread the time stamp */
- *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
- cpu_buffer->tail_page->page->time_stamp = *ts;
- }
+ /*
+ * The actual tail page has moved forward.
+ */
+ if (tail < BUF_PAGE_SIZE) {
+ /* Mark the rest of the page with padding */
+ event = __rb_page_index(tail_page, tail);
+ rb_event_set_padding(event);
+ }
- /*
- * The actual tail page has moved forward.
- */
- if (tail < BUF_PAGE_SIZE) {
- /* Mark the rest of the page with padding */
- event = __rb_page_index(tail_page, tail);
- rb_event_set_padding(event);
- }
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
- if (tail <= BUF_PAGE_SIZE)
- /* Set the write back to the previous setting */
- local_set(&tail_page->write, tail);
+ /*
+ * If this was a commit entry that failed,
+ * increment that too
+ */
+ if (tail_page == cpu_buffer->commit_page &&
+ tail == rb_commit_index(cpu_buffer)) {
+ rb_set_commit_to_write(cpu_buffer);
+ }
- /*
- * If this was a commit entry that failed,
- * increment that too
- */
- if (tail_page == cpu_buffer->commit_page &&
- tail == rb_commit_index(cpu_buffer)) {
- rb_set_commit_to_write(cpu_buffer);
- }
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ /* fail and let the caller try again */
+ return ERR_PTR(-EAGAIN);
+
+ out_reset:
+ /* reset write */
+ local_sub(length, &tail_page->write);
+ if (likely(lock_taken))
__raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ local_irq_restore(flags);
+ return NULL;
+}
- /* fail and let the caller try again */
- return ERR_PTR(-EAGAIN);
- }
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned type, unsigned long length, u64 *ts)
+{
+ struct buffer_page *tail_page, *commit_page;
+ struct ring_buffer_event *event;
+ unsigned long tail, write;
+
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
+ tail_page = cpu_buffer->tail_page;
+ write = local_add_return(length, &tail_page->write);
+ tail = write - length;
+
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE)
+ return rb_move_tail(cpu_buffer, length, tail,
+ commit_page, tail_page, ts);
/* We reserved something on the buffer */
@@ -1289,6 +1313,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
rb_update_event(event, type, length);
+ /* The passed in type is zero for DATA */
+ if (likely(!type))
+ local_inc(&tail_page->entries);
+
/*
* If this is a commit and the tail is zero, then update
* this page's time stamp.
@@ -1297,16 +1325,6 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
cpu_buffer->commit_page->page->time_stamp = *ts;
return event;
-
- out_reset:
- /* reset write */
- if (tail <= BUF_PAGE_SIZE)
- local_set(&tail_page->write, tail);
-
- if (likely(lock_taken))
- __raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
- return NULL;
}
static int
@@ -1458,6 +1476,36 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
return event;
}
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+ current->trace_recursion++;
+
+ if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+ return 0;
+
+ /* Disable all tracing before we do anything else */
+ tracing_off_permanent();
+
+ printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+ "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+ current->trace_recursion,
+ hardirq_count() >> HARDIRQ_SHIFT,
+ softirq_count() >> SOFTIRQ_SHIFT,
+ in_nmi());
+
+ WARN_ON_ONCE(1);
+ return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+ WARN_ON_ONCE(!current->trace_recursion);
+
+ current->trace_recursion--;
+}
+
static DEFINE_PER_CPU(int, rb_need_resched);
/**
@@ -1491,6 +1539,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
/* If we are tracing schedule, we don't want to recurse */
resched = ftrace_preempt_disable();
+ if (trace_recursive_lock())
+ goto out_nocheck;
+
cpu = raw_smp_processor_id();
if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -1505,7 +1556,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
if (length > BUF_PAGE_SIZE)
goto out;
- event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+ event = rb_reserve_next_event(cpu_buffer, 0, length);
if (!event)
goto out;
@@ -1520,6 +1571,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
return event;
out:
+ trace_recursive_unlock();
+
+ out_nocheck:
ftrace_preempt_enable(resched);
return NULL;
}
@@ -1528,7 +1582,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
- cpu_buffer->entries++;
+ local_inc(&cpu_buffer->entries);
/* Only process further if we own the commit */
if (!rb_is_commit(cpu_buffer, event))
@@ -1558,6 +1612,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
rb_commit(cpu_buffer, event);
+ trace_recursive_unlock();
+
/*
* Only the last preempt count needs to restore preemption.
*/
@@ -1570,6 +1626,119 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+ /* array[0] holds the actual length for the discarded event */
+ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ if (!event->time_delta)
+ event->time_delta = 1;
+}
+
+/**
+ * ring_buffer_event_discard - discard any event in the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+ rb_event_discard(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * This is similar to ring_buffer_event_discard but must only be
+ * performed on an event that has not been committed yet. The difference
+ * is that this will also try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long new_index, old_index;
+ struct buffer_page *bpage;
+ unsigned long index;
+ unsigned long addr;
+ int cpu;
+
+ /* The event is discarded regardless */
+ rb_event_discard(event);
+
+ /*
+ * This must only be called if the event has not been
+ * committed yet. Thus we can assume that preemption
+ * is still disabled.
+ */
+ RB_WARN_ON(buffer, !preempt_count());
+
+ cpu = smp_processor_id();
+ cpu_buffer = buffer->buffers[cpu];
+
+ new_index = rb_event_index(event);
+ old_index = new_index + rb_event_length(event);
+ addr = (unsigned long)event;
+ addr &= PAGE_MASK;
+
+ bpage = cpu_buffer->tail_page;
+
+ if (bpage == (void *)addr && rb_page_write(bpage) == old_index) {
+ /*
+ * This is on the tail page. It is possible that
+ * a write could come in and move the tail page
+ * and write to the next page. That is fine
+ * because we just shorten what is on this page.
+ */
+ index = local_cmpxchg(&bpage->write, old_index, new_index);
+ if (index == old_index)
+ goto out;
+ }
+
+ /*
+ * The commit is still visible by the reader, so we
+ * must increment entries.
+ */
+ local_inc(&cpu_buffer->entries);
+ out:
+ /*
+ * If a write came in and pushed the tail page
+ * we still need to update the commit pointer
+ * if we were the commit.
+ */
+ if (rb_is_commit(cpu_buffer, event))
+ rb_set_commit_to_write(cpu_buffer);
+
+ trace_recursive_unlock();
+
+ /*
+ * Only the last preempt count needs to restore preemption.
+ */
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
+ preempt_enable_no_resched_notrace();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
+
/**
* ring_buffer_write - write data to the buffer without reserving
* @buffer: The ring buffer to write to.
@@ -1613,8 +1782,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
goto out;
event_length = rb_calculate_event_length(length);
- event = rb_reserve_next_event(cpu_buffer,
- RINGBUF_TYPE_DATA, event_length);
+ event = rb_reserve_next_event(cpu_buffer, 0, event_length);
if (!event)
goto out;
@@ -1728,7 +1896,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
return 0;
cpu_buffer = buffer->buffers[cpu];
- ret = cpu_buffer->entries;
+ ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+ - cpu_buffer->read;
return ret;
}
@@ -1755,6 +1924,47 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
/**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->nmi_dropped;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->commit_overrun;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
+/**
* ring_buffer_entries - get the number of entries in a buffer
* @buffer: The ring buffer
*
@@ -1770,7 +1980,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
/* if you care about this being correct, lock the buffer */
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
- entries += cpu_buffer->entries;
+ entries += (local_read(&cpu_buffer->entries) -
+ cpu_buffer->overrun) - cpu_buffer->read;
}
return entries;
@@ -1862,7 +2073,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
@@ -1893,7 +2104,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
@@ -1966,6 +2177,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->list.prev = reader->list.prev;
local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
local_set(&cpu_buffer->reader_page->page->commit, 0);
/* Make the reader page now replace the head */
@@ -2008,8 +2220,9 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
event = rb_reader_event(cpu_buffer);
- if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
- cpu_buffer->entries--;
+ if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+ || rb_discarded_event(event))
+ cpu_buffer->read++;
rb_update_read_stamp(cpu_buffer, event);
@@ -2089,7 +2302,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
event = rb_reader_event(cpu_buffer);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event))
RB_WARN_ON(cpu_buffer, 1);
@@ -2161,7 +2374,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
event = rb_iter_head_event(iter);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event)) {
rb_inc_iter(iter);
@@ -2220,7 +2433,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
event = rb_buffer_peek(buffer, cpu, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
@@ -2248,7 +2461,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
event = rb_iter_peek(iter, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
@@ -2293,7 +2506,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
out:
preempt_enable();
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
@@ -2386,7 +2599,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
out:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
@@ -2411,6 +2624,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->head_page
= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
local_set(&cpu_buffer->head_page->write, 0);
+ local_set(&cpu_buffer->head_page->entries, 0);
local_set(&cpu_buffer->head_page->page->commit, 0);
cpu_buffer->head_page->read = 0;
@@ -2420,11 +2634,15 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
local_set(&cpu_buffer->reader_page->page->commit, 0);
cpu_buffer->reader_page->read = 0;
+ cpu_buffer->nmi_dropped = 0;
+ cpu_buffer->commit_overrun = 0;
cpu_buffer->overrun = 0;
- cpu_buffer->entries = 0;
+ cpu_buffer->read = 0;
+ local_set(&cpu_buffer->entries, 0);
cpu_buffer->write_stamp = 0;
cpu_buffer->read_stamp = 0;
@@ -2443,6 +2661,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
+ atomic_inc(&cpu_buffer->record_disabled);
+
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
__raw_spin_lock(&cpu_buffer->lock);
@@ -2452,6 +2672,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
__raw_spin_unlock(&cpu_buffer->lock);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ atomic_dec(&cpu_buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
@@ -2578,28 +2800,6 @@ out:
}
EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
-static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
- struct buffer_data_page *bpage,
- unsigned int offset)
-{
- struct ring_buffer_event *event;
- unsigned long head;
-
- __raw_spin_lock(&cpu_buffer->lock);
- for (head = offset; head < local_read(&bpage->commit);
- head += rb_event_length(event)) {
-
- event = __rb_data_page_index(bpage, head);
- if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
- return;
- /* Only count data entries */
- if (event->type != RINGBUF_TYPE_DATA)
- continue;
- cpu_buffer->entries--;
- }
- __raw_spin_unlock(&cpu_buffer->lock);
-}
-
/**
* ring_buffer_alloc_read_page - allocate a page to read from buffer
* @buffer: the buffer to allocate for.
@@ -2630,6 +2830,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
return bpage;
}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
/**
* ring_buffer_free_read_page - free an allocated read page
@@ -2642,6 +2843,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
{
free_page((unsigned long)data);
}
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
/**
* ring_buffer_read_page - extract a page from the ring buffer
@@ -2768,16 +2970,17 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
/* we copied everything to the beginning */
read = 0;
} else {
+ /* update the entry counter */
+ cpu_buffer->read += local_read(&reader->entries);
+
/* swap the pages */
rb_init_page(bpage);
bpage = reader->page;
reader->page = *data_page;
local_set(&reader->write, 0);
+ local_set(&reader->entries, 0);
reader->read = 0;
*data_page = bpage;
-
- /* update the entry counter */
- rb_remove_entries(cpu_buffer, bpage, read);
}
ret = read;
@@ -2787,6 +2990,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
out:
return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
@@ -2845,14 +3049,11 @@ static const struct file_operations rb_simple_fops = {
static __init int rb_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("tracing_on", 0644, d_tracer,
- &ring_buffer_flags, &rb_simple_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_on' entry\n");
+ trace_create_file("tracing_on", 0644, d_tracer,
+ &ring_buffer_flags, &rb_simple_fops);
return 0;
}
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
new file mode 100644
index 00000000000..a26fc67b63b
--- /dev/null
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -0,0 +1,413 @@
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/time.h>
+
+struct rb_page {
+ u64 ts;
+ local_t commit;
+ char data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME 10
+#define SLEEP_TIME 10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static struct completion read_start;
+static struct completion read_done;
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static int read_events;
+
+static int kill_test;
+
+#define KILL_TEST() \
+ do { \
+ if (!kill_test) { \
+ kill_test = 1; \
+ WARN_ON(1); \
+ } \
+ } while (0)
+
+enum event_status {
+ EVENT_FOUND,
+ EVENT_DROPPED,
+};
+
+static enum event_status read_event(int cpu)
+{
+ struct ring_buffer_event *event;
+ int *entry;
+ u64 ts;
+
+ event = ring_buffer_consume(buffer, cpu, &ts);
+ if (!event)
+ return EVENT_DROPPED;
+
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ return EVENT_DROPPED;
+ }
+
+ read++;
+ return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+ struct ring_buffer_event *event;
+ struct rb_page *rpage;
+ unsigned long commit;
+ void *bpage;
+ int *entry;
+ int ret;
+ int inc;
+ int i;
+
+ bpage = ring_buffer_alloc_read_page(buffer);
+ if (!bpage)
+ return EVENT_DROPPED;
+
+ ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+ if (ret >= 0) {
+ rpage = bpage;
+ commit = local_read(&rpage->commit);
+ for (i = 0; i < commit && !kill_test; i += inc) {
+
+ if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+ KILL_TEST();
+ break;
+ }
+
+ inc = -1;
+ event = (void *)&rpage->data[i];
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ /* We don't expect any padding */
+ KILL_TEST();
+ break;
+ case RINGBUF_TYPE_TIME_EXTEND:
+ inc = 8;
+ break;
+ case 0:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ if (!event->array[0]) {
+ KILL_TEST();
+ break;
+ }
+ inc = event->array[0];
+ break;
+ default:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ inc = ((event->type_len + 1) * 4);
+ }
+ if (kill_test)
+ break;
+
+ if (inc <= 0) {
+ KILL_TEST();
+ break;
+ }
+ }
+ }
+ ring_buffer_free_read_page(buffer, bpage);
+
+ if (ret < 0)
+ return EVENT_DROPPED;
+ return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+ /* toggle between reading pages and events */
+ read_events ^= 1;
+
+ read = 0;
+ while (!reader_finish && !kill_test) {
+ int found;
+
+ do {
+ int cpu;
+
+ found = 0;
+ for_each_online_cpu(cpu) {
+ enum event_status stat;
+
+ if (read_events)
+ stat = read_event(cpu);
+ else
+ stat = read_page(cpu);
+
+ if (kill_test)
+ break;
+ if (stat == EVENT_FOUND)
+ found = 1;
+ }
+ } while (found && !kill_test);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (reader_finish)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ reader_finish = 0;
+ complete(&read_done);
+}
+
+/*
+ * If we are a non preempt kernel, the 10 second run will
+ * stop everything while it runs. Instead, we will call cond_resched
+ * and also add any time that was lost by a rescedule.
+ */
+#ifdef CONFIG_PREEMPT
+static void sched_if_needed(struct timeval *start_tv, struct timeval *end_tv)
+{
+}
+#else
+static void sched_if_needed(struct timeval *start_tv, struct timeval *end_tv)
+{
+ struct timeval tv;
+
+ cond_resched();
+ do_gettimeofday(&tv);
+ if (tv.tv_usec < end_tv->tv_usec) {
+ tv.tv_usec += 1000000;
+ tv.tv_sec--;
+ }
+ start_tv->tv_sec += tv.tv_sec - end_tv->tv_sec;
+ start_tv->tv_usec += tv.tv_usec - end_tv->tv_usec;
+ if (start_tv->tv_usec > 1000000) {
+ start_tv->tv_usec -= 1000000;
+ start_tv->tv_sec++;
+ }
+}
+#endif
+
+static void ring_buffer_producer(void)
+{
+ struct timeval start_tv;
+ struct timeval end_tv;
+ unsigned long long time;
+ unsigned long long entries;
+ unsigned long long overruns;
+ unsigned long missed = 0;
+ unsigned long hit = 0;
+ unsigned long avg;
+ int cnt = 0;
+
+ /*
+ * Hammer the buffer for 10 secs (this may
+ * make the system stall)
+ */
+ pr_info("Starting ring buffer hammer\n");
+ do_gettimeofday(&start_tv);
+ do {
+ struct ring_buffer_event *event;
+ int *entry;
+
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
+ do_gettimeofday(&end_tv);
+
+ if (consumer && !(++cnt % wakeup_interval))
+ wake_up_process(consumer);
+
+ sched_if_needed(&start_tv, &end_tv);
+
+ } while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
+ pr_info("End ring buffer hammer\n");
+
+ if (consumer) {
+ /* Init both completions here to avoid races */
+ init_completion(&read_start);
+ init_completion(&read_done);
+ /* the completions must be visible before the finish var */
+ smp_wmb();
+ reader_finish = 1;
+ /* finish var visible before waking up the consumer */
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_done);
+ }
+
+ time = end_tv.tv_sec - start_tv.tv_sec;
+ time *= 1000000;
+ time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
+
+ entries = ring_buffer_entries(buffer);
+ overruns = ring_buffer_overruns(buffer);
+
+ if (kill_test)
+ pr_info("ERROR!\n");
+ pr_info("Time: %lld (usecs)\n", time);
+ pr_info("Overruns: %lld\n", overruns);
+ if (disable_reader)
+ pr_info("Read: (reader disabled)\n");
+ else
+ pr_info("Read: %ld (by %s)\n", read,
+ read_events ? "events" : "pages");
+ pr_info("Entries: %lld\n", entries);
+ pr_info("Total: %lld\n", entries + overruns + read);
+ pr_info("Missed: %ld\n", missed);
+ pr_info("Hit: %ld\n", hit);
+
+ do_div(time, 1000);
+ if (time)
+ hit /= (long)time;
+ else
+ pr_info("TIME IS ZERO??\n");
+
+ pr_info("Entries per millisec: %ld\n", hit);
+
+ if (hit) {
+ avg = 1000000 / hit;
+ pr_info("%ld ns per entry\n", avg);
+ }
+}
+
+static void wait_to_die(void)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+ while (!kthread_should_stop() && !kill_test) {
+ complete(&read_start);
+
+ ring_buffer_consumer();
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (kthread_should_stop() || kill_test)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ __set_current_state(TASK_RUNNING);
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+ init_completion(&read_start);
+
+ while (!kthread_should_stop() && !kill_test) {
+ ring_buffer_reset(buffer);
+
+ if (consumer) {
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_start);
+ }
+
+ ring_buffer_producer();
+
+ pr_info("Sleeping for 10 secs\n");
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ * SLEEP_TIME);
+ __set_current_state(TASK_RUNNING);
+ }
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+ int ret;
+
+ /* make a one meg buffer in overwite mode */
+ buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+ if (!buffer)
+ return -ENOMEM;
+
+ if (!disable_reader) {
+ consumer = kthread_create(ring_buffer_consumer_thread,
+ NULL, "rb_consumer");
+ ret = PTR_ERR(consumer);
+ if (IS_ERR(consumer))
+ goto out_fail;
+ }
+
+ producer = kthread_run(ring_buffer_producer_thread,
+ NULL, "rb_producer");
+ ret = PTR_ERR(producer);
+
+ if (IS_ERR(producer))
+ goto out_kill;
+
+ return 0;
+
+ out_kill:
+ if (consumer)
+ kthread_stop(consumer);
+
+ out_fail:
+ ring_buffer_free(buffer);
+ return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+ kthread_stop(producer);
+ if (consumer)
+ kthread_stop(consumer);
+ ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1ce5dc6372b..dd40d232034 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -171,6 +171,13 @@ static struct trace_array global_trace;
static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer_event *event)
+{
+ return filter_check_discard(call, rec, global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(filter_current_check_discard);
+
cycle_t ftrace_now(int cpu)
{
u64 ts;
@@ -255,7 +262,8 @@ 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_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+ TRACE_ITER_GRAPH_TIME;
/**
* trace_wake_up - wake up tasks waiting for trace input
@@ -317,6 +325,7 @@ static const char *trace_options[] = {
"latency-format",
"global-clock",
"sleep-time",
+ "graph-time",
NULL
};
@@ -402,17 +411,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
return cnt;
}
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
- int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
- s->buffer[len] = 0;
- seq_puts(m, s->buffer);
-
- trace_seq_init(s);
-}
-
/**
* update_max_tr - snapshot all trace buffers from global_trace to max_tr
* @tr: tracer
@@ -641,6 +639,16 @@ void tracing_reset_online_cpus(struct trace_array *tr)
tracing_reset(tr, cpu);
}
+void tracing_reset_current(int cpu)
+{
+ tracing_reset(&global_trace, cpu);
+}
+
+void tracing_reset_current_online_cpus(void)
+{
+ tracing_reset_online_cpus(&global_trace);
+}
+
#define SAVED_CMDLINES 128
#define NO_CMDLINE_MAP UINT_MAX
static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -840,7 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
}
struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
- unsigned char type,
+ int type,
unsigned long len,
unsigned long flags, int pc)
{
@@ -883,30 +891,40 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
}
struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+trace_current_buffer_lock_reserve(int type, unsigned long len,
unsigned long flags, int pc)
{
return trace_buffer_lock_reserve(&global_trace,
type, len, flags, pc);
}
+EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc)
{
- return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+ __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
}
+EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc)
{
- return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+ __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+{
+ ring_buffer_discard_commit(global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
void
trace_function(struct trace_array *tr,
unsigned long ip, unsigned long parent_ip, unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_function;
struct ring_buffer_event *event;
struct ftrace_entry *entry;
@@ -921,7 +939,9 @@ trace_function(struct trace_array *tr,
entry = ring_buffer_event_data(event);
entry->ip = ip;
entry->parent_ip = parent_ip;
- ring_buffer_unlock_commit(tr->buffer, event);
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -930,6 +950,7 @@ static int __trace_graph_entry(struct trace_array *tr,
unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_funcgraph_entry;
struct ring_buffer_event *event;
struct ftrace_graph_ent_entry *entry;
@@ -942,7 +963,8 @@ static int __trace_graph_entry(struct trace_array *tr,
return 0;
entry = ring_buffer_event_data(event);
entry->graph_ent = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event);
+ if (!filter_current_check_discard(call, entry, event))
+ ring_buffer_unlock_commit(global_trace.buffer, event);
return 1;
}
@@ -952,6 +974,7 @@ static void __trace_graph_return(struct trace_array *tr,
unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_funcgraph_exit;
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *entry;
@@ -964,7 +987,8 @@ static void __trace_graph_return(struct trace_array *tr,
return;
entry = ring_buffer_event_data(event);
entry->ret = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event);
+ if (!filter_current_check_discard(call, entry, event))
+ ring_buffer_unlock_commit(global_trace.buffer, event);
}
#endif
@@ -982,6 +1006,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
int skip, int pc)
{
#ifdef CONFIG_STACKTRACE
+ struct ftrace_event_call *call = &event_kernel_stack;
struct ring_buffer_event *event;
struct stack_entry *entry;
struct stack_trace trace;
@@ -999,7 +1024,8 @@ static void __ftrace_trace_stack(struct trace_array *tr,
trace.entries = entry->caller;
save_stack_trace(&trace);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
@@ -1024,6 +1050,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
unsigned long flags, int pc)
{
#ifdef CONFIG_STACKTRACE
+ struct ftrace_event_call *call = &event_user_stack;
struct ring_buffer_event *event;
struct userstack_entry *entry;
struct stack_trace trace;
@@ -1045,7 +1072,8 @@ static void ftrace_trace_userstack(struct trace_array *tr,
trace.entries = entry->caller;
save_stack_trace_user(&trace);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
@@ -1089,6 +1117,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
struct task_struct *next,
unsigned long flags, int pc)
{
+ struct ftrace_event_call *call = &event_context_switch;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
@@ -1104,7 +1133,9 @@ tracing_sched_switch_trace(struct trace_array *tr,
entry->next_prio = next->prio;
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
- trace_buffer_unlock_commit(tr, event, flags, pc);
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, flags, pc);
}
void
@@ -1113,6 +1144,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
struct task_struct *curr,
unsigned long flags, int pc)
{
+ struct ftrace_event_call *call = &event_wakeup;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
@@ -1129,7 +1161,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
ftrace_trace_stack(tr, flags, 6, pc);
ftrace_trace_userstack(tr, flags, pc);
}
@@ -1230,11 +1263,13 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
static u32 trace_buf[TRACE_BUF_SIZE];
+ struct ftrace_event_call *call = &event_bprint;
struct ring_buffer_event *event;
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
struct bprint_entry *entry;
unsigned long flags;
+ int disable;
int resched;
int cpu, len = 0, size, pc;
@@ -1249,7 +1284,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- if (unlikely(atomic_read(&data->disabled)))
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
goto out;
/* Lockdep uses trace_printk for lock tracing */
@@ -1269,13 +1305,15 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
entry->fmt = fmt;
memcpy(entry->buf, trace_buf, sizeof(u32) * len);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out_unlock:
__raw_spin_unlock(&trace_buf_lock);
local_irq_restore(flags);
out:
+ atomic_dec_return(&data->disabled);
ftrace_preempt_enable(resched);
unpause_graph_tracing();
@@ -1288,12 +1326,14 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
static char trace_buf[TRACE_BUF_SIZE];
+ struct ftrace_event_call *call = &event_print;
struct ring_buffer_event *event;
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
int cpu, len = 0, size, pc;
struct print_entry *entry;
unsigned long irq_flags;
+ int disable;
if (tracing_disabled || tracing_selftest_running)
return 0;
@@ -1303,7 +1343,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- if (unlikely(atomic_read(&data->disabled)))
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
goto out;
pause_graph_tracing();
@@ -1323,13 +1364,15 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = 0;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out_unlock:
__raw_spin_unlock(&trace_buf_lock);
raw_local_irq_restore(irq_flags);
unpause_graph_tracing();
out:
+ atomic_dec_return(&data->disabled);
preempt_enable_notrace();
return len;
@@ -2397,6 +2440,56 @@ static const struct file_operations tracing_readme_fops = {
};
static ssize_t
+tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *buf_comm;
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int pid;
+ int i;
+
+ file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
+ if (!file_buf)
+ return -ENOMEM;
+
+ buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
+ if (!buf_comm) {
+ kfree(file_buf);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+
+ for (i = 0; i < SAVED_CMDLINES; i++) {
+ int r;
+
+ pid = map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ trace_find_cmdline(pid, buf_comm);
+ r = sprintf(buf, "%d %s\n", pid, buf_comm);
+ buf += r;
+ len += r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, len);
+
+ kfree(file_buf);
+ kfree(buf_comm);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_cmdlines_read,
+};
+
+static ssize_t
tracing_ctrl_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
@@ -3425,7 +3518,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int size, i;
+ int entries, size, i;
size_t ret;
if (*ppos & (PAGE_SIZE - 1)) {
@@ -3440,7 +3533,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
len &= PAGE_MASK;
}
- for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+
+ for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
int r;
@@ -3448,6 +3543,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
if (!ref)
break;
+ ref->ref = 1;
ref->buffer = info->tr->buffer;
ref->page = ring_buffer_alloc_read_page(ref->buffer);
if (!ref->page) {
@@ -3456,7 +3552,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
}
r = ring_buffer_read_page(ref->buffer, &ref->page,
- len, info->cpu, 0);
+ len, info->cpu, 1);
if (r < 0) {
ring_buffer_free_read_page(ref->buffer,
ref->page);
@@ -3480,6 +3576,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
spd.partial[i].private = (unsigned long)ref;
spd.nr_pages++;
*ppos += PAGE_SIZE;
+
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
}
spd.nr_pages = i;
@@ -3507,6 +3605,45 @@ static const struct file_operations tracing_buffers_fops = {
.llseek = no_llseek,
};
+static ssize_t
+tracing_stats_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long cpu = (unsigned long)filp->private_data;
+ struct trace_array *tr = &global_trace;
+ struct trace_seq *s;
+ unsigned long cnt;
+
+ s = kmalloc(sizeof(*s), GFP_ATOMIC);
+ if (!s)
+ return ENOMEM;
+
+ trace_seq_init(s);
+
+ cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "entries: %ld\n", cnt);
+
+ cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "overrun: %ld\n", cnt);
+
+ cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "commit overrun: %ld\n", cnt);
+
+ cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
+
+ count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return count;
+}
+
+static const struct file_operations tracing_stats_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_stats_read,
+};
+
#ifdef CONFIG_DYNAMIC_FTRACE
int __weak ftrace_arch_read_dyn_info(char *buf, int size)
@@ -3596,7 +3733,7 @@ struct dentry *tracing_dentry_percpu(void)
static void tracing_init_debugfs_percpu(long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu();
- struct dentry *entry, *d_cpu;
+ struct dentry *d_cpu;
/* strlen(cpu) + MAX(log10(cpu)) + '\0' */
char cpu_dir[7];
@@ -3611,21 +3748,18 @@ static void tracing_init_debugfs_percpu(long cpu)
}
/* per cpu trace_pipe */
- entry = debugfs_create_file("trace_pipe", 0444, d_cpu,
- (void *) cpu, &tracing_pipe_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_pipe' entry\n");
+ trace_create_file("trace_pipe", 0444, d_cpu,
+ (void *) cpu, &tracing_pipe_fops);
/* per cpu trace */
- entry = debugfs_create_file("trace", 0644, d_cpu,
- (void *) cpu, &tracing_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace' entry\n");
+ trace_create_file("trace", 0644, d_cpu,
+ (void *) cpu, &tracing_fops);
- entry = debugfs_create_file("trace_pipe_raw", 0444, d_cpu,
- (void *) cpu, &tracing_buffers_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_pipe_raw' entry\n");
+ trace_create_file("trace_pipe_raw", 0444, d_cpu,
+ (void *) cpu, &tracing_buffers_fops);
+
+ trace_create_file("stats", 0444, d_cpu,
+ (void *) cpu, &tracing_stats_fops);
}
#ifdef CONFIG_FTRACE_SELFTEST
@@ -3781,6 +3915,22 @@ static const struct file_operations trace_options_core_fops = {
.write = trace_options_core_write,
};
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops)
+{
+ struct dentry *ret;
+
+ ret = debugfs_create_file(name, mode, parent, data, fops);
+ if (!ret)
+ pr_warning("Could not create debugfs '%s' entry\n", name);
+
+ return ret;
+}
+
+
static struct dentry *trace_options_init_dentry(void)
{
struct dentry *d_tracer;
@@ -3808,7 +3958,6 @@ create_trace_option_file(struct trace_option_dentry *topt,
struct tracer_opt *opt)
{
struct dentry *t_options;
- struct dentry *entry;
t_options = trace_options_init_dentry();
if (!t_options)
@@ -3817,11 +3966,9 @@ create_trace_option_file(struct trace_option_dentry *topt,
topt->flags = flags;
topt->opt = opt;
- entry = debugfs_create_file(opt->name, 0644, t_options, topt,
+ topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
&trace_options_fops);
- topt->entry = entry;
-
}
static struct trace_option_dentry *
@@ -3876,123 +4023,84 @@ static struct dentry *
create_trace_option_core_file(const char *option, long index)
{
struct dentry *t_options;
- struct dentry *entry;
t_options = trace_options_init_dentry();
if (!t_options)
return NULL;
- entry = debugfs_create_file(option, 0644, t_options, (void *)index,
+ return trace_create_file(option, 0644, t_options, (void *)index,
&trace_options_core_fops);
-
- return entry;
}
static __init void create_trace_options_dir(void)
{
struct dentry *t_options;
- struct dentry *entry;
int i;
t_options = trace_options_init_dentry();
if (!t_options)
return;
- for (i = 0; trace_options[i]; i++) {
- entry = create_trace_option_core_file(trace_options[i], i);
- if (!entry)
- pr_warning("Could not create debugfs %s entry\n",
- trace_options[i]);
- }
+ for (i = 0; trace_options[i]; i++)
+ create_trace_option_core_file(trace_options[i], i);
}
static __init int tracer_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
int cpu;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("tracing_enabled", 0644, d_tracer,
- &global_trace, &tracing_ctrl_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
+ trace_create_file("tracing_enabled", 0644, d_tracer,
+ &global_trace, &tracing_ctrl_fops);
- entry = debugfs_create_file("trace_options", 0644, d_tracer,
- NULL, &tracing_iter_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_options' entry\n");
+ trace_create_file("trace_options", 0644, d_tracer,
+ NULL, &tracing_iter_fops);
- create_trace_options_dir();
+ trace_create_file("tracing_cpumask", 0644, d_tracer,
+ NULL, &tracing_cpumask_fops);
+
+ trace_create_file("trace", 0644, d_tracer,
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
+
+ trace_create_file("available_tracers", 0444, d_tracer,
+ &global_trace, &show_traces_fops);
- entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
- NULL, &tracing_cpumask_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
-
- entry = debugfs_create_file("trace", 0644, d_tracer,
- (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace' entry\n");
-
- entry = debugfs_create_file("available_tracers", 0444, d_tracer,
- &global_trace, &show_traces_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'available_tracers' entry\n");
-
- entry = debugfs_create_file("current_tracer", 0444, d_tracer,
- &global_trace, &set_tracer_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'current_tracer' entry\n");
-
- entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer,
- &tracing_max_latency,
- &tracing_max_lat_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'tracing_max_latency' entry\n");
-
- entry = debugfs_create_file("tracing_thresh", 0644, d_tracer,
- &tracing_thresh, &tracing_max_lat_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'tracing_thresh' entry\n");
- entry = debugfs_create_file("README", 0644, d_tracer,
- NULL, &tracing_readme_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'README' entry\n");
-
- entry = debugfs_create_file("trace_pipe", 0444, d_tracer,
+ trace_create_file("current_tracer", 0644, d_tracer,
+ &global_trace, &set_tracer_fops);
+
+ trace_create_file("tracing_max_latency", 0644, d_tracer,
+ &tracing_max_latency, &tracing_max_lat_fops);
+
+ trace_create_file("tracing_thresh", 0644, d_tracer,
+ &tracing_thresh, &tracing_max_lat_fops);
+
+ trace_create_file("README", 0444, d_tracer,
+ NULL, &tracing_readme_fops);
+
+ trace_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");
-
- entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
- &global_trace, &tracing_entries_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'buffer_size_kb' entry\n");
-
- entry = debugfs_create_file("trace_marker", 0220, d_tracer,
- NULL, &tracing_mark_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'trace_marker' entry\n");
+
+ trace_create_file("buffer_size_kb", 0644, d_tracer,
+ &global_trace, &tracing_entries_fops);
+
+ trace_create_file("trace_marker", 0220, d_tracer,
+ NULL, &tracing_mark_fops);
+
+ trace_create_file("saved_cmdlines", 0444, d_tracer,
+ NULL, &tracing_saved_cmdlines_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
- entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
- &ftrace_update_tot_cnt,
- &tracing_dyn_info_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'dyn_ftrace_total_info' entry\n");
+ 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();
+
for_each_tracing_cpu(cpu)
tracing_init_debugfs_percpu(cpu);
@@ -4063,7 +4171,8 @@ trace_printk_seq(struct trace_seq *s)
static void __ftrace_dump(bool disable_tracing)
{
- static DEFINE_SPINLOCK(ftrace_dump_lock);
+ static raw_spinlock_t ftrace_dump_lock =
+ (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
unsigned int old_userobj;
@@ -4072,7 +4181,8 @@ static void __ftrace_dump(bool disable_tracing)
int cnt = 0, cpu;
/* only one dump */
- spin_lock_irqsave(&ftrace_dump_lock, flags);
+ local_irq_save(flags);
+ __raw_spin_lock(&ftrace_dump_lock);
if (dump_ran)
goto out;
@@ -4144,7 +4254,8 @@ static void __ftrace_dump(bool disable_tracing)
}
out:
- spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+ __raw_spin_unlock(&ftrace_dump_lock);
+ local_irq_restore(flags);
}
/* By default: disable tracing after the dump */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 7c3f49aad6e..6e735d4771f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,9 +9,12 @@
#include <linux/mmiotrace.h>
#include <linux/ftrace.h>
#include <trace/boot.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include <trace/power.h>
+#include <linux/trace_seq.h>
+#include <linux/ftrace_event.h>
+
enum trace_type {
__TRACE_FIRST_TYPE = 0,
@@ -42,20 +45,6 @@ enum trace_type {
};
/*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- * bash-15816 [01] 235.197585: idle_cpu <- irq_enter
- */
-struct trace_entry {
- unsigned char type;
- unsigned char flags;
- unsigned char preempt_count;
- int pid;
- int tgid;
-};
-
-/*
* Function trace entry - function address and parent function addres:
*/
struct ftrace_entry {
@@ -263,8 +252,6 @@ struct trace_array_cpu {
char comm[TASK_COMM_LEN];
};
-struct trace_iterator;
-
/*
* The trace array - an array of per-CPU trace arrays. This is the
* highest level data structure that individual tracers deal with.
@@ -339,15 +326,6 @@ extern void __ftrace_bad_type(void);
__ftrace_bad_type(); \
} while (0)
-/* Return values for print_line callback */
-enum print_line_t {
- TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */
- TRACE_TYPE_HANDLED = 1,
- TRACE_TYPE_UNHANDLED = 2, /* Relay to other output functions */
- TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */
-};
-
-
/*
* An option specific to a tracer. This is a boolean value.
* The bit is the bit index that sets its value on the
@@ -423,60 +401,30 @@ struct tracer {
struct tracer_stat *stats;
};
-struct trace_seq {
- unsigned char buffer[PAGE_SIZE];
- unsigned int len;
- unsigned int readpos;
-};
-
-static inline void
-trace_seq_init(struct trace_seq *s)
-{
- s->len = 0;
- s->readpos = 0;
-}
-
#define TRACE_PIPE_ALL_CPU -1
-/*
- * Trace iterator - used by printout routines who present trace
- * results to users and which routines might sleep, etc:
- */
-struct trace_iterator {
- struct trace_array *tr;
- struct tracer *trace;
- void *private;
- int cpu_file;
- struct mutex mutex;
- struct ring_buffer_iter *buffer_iter[NR_CPUS];
-
- /* The below is zeroed out in pipe_read */
- struct trace_seq seq;
- struct trace_entry *ent;
- int cpu;
- u64 ts;
-
- unsigned long iter_flags;
- loff_t pos;
- long idx;
-
- cpumask_var_t started;
-};
-
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
void trace_wake_up(void);
void tracing_reset(struct trace_array *tr, int cpu);
void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset_current(int cpu);
+void tracing_reset_current_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops);
+
struct dentry *tracing_init_dentry(void);
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
struct ring_buffer_event;
struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
- unsigned char type,
+ int type,
unsigned long len,
unsigned long flags,
int pc);
@@ -484,14 +432,6 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
struct ring_buffer_event *event,
unsigned long flags, int pc);
-struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
- unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
- unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
- unsigned long flags, int pc);
-
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
struct trace_array_cpu *data);
@@ -514,7 +454,6 @@ void tracing_sched_switch_trace(struct trace_array *tr,
struct task_struct *prev,
struct task_struct *next,
unsigned long flags, int pc);
-void tracing_record_cmdline(struct task_struct *tsk);
void tracing_sched_wakeup_trace(struct trace_array *tr,
struct task_struct *wakee,
@@ -615,6 +554,8 @@ extern unsigned long trace_flags;
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
@@ -646,7 +587,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 1;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
-
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
print_graph_function(struct trace_iterator *iter)
@@ -694,6 +634,7 @@ enum trace_iterator_flags {
TRACE_ITER_LATENCY_FMT = 0x40000,
TRACE_ITER_GLOBAL_CLK = 0x80000,
TRACE_ITER_SLEEP_TIME = 0x100000,
+ TRACE_ITER_GRAPH_TIME = 0x200000,
};
/*
@@ -792,103 +733,113 @@ struct ftrace_event_field {
char *type;
int offset;
int size;
+ int is_signed;
};
-struct ftrace_event_call {
- char *name;
- char *system;
- struct dentry *dir;
- int enabled;
- int (*regfunc)(void);
- void (*unregfunc)(void);
- int id;
- int (*raw_init)(void);
- int (*show_format)(struct trace_seq *s);
- int (*define_fields)(void);
- struct list_head fields;
+struct event_filter {
+ int n_preds;
struct filter_pred **preds;
-
-#ifdef CONFIG_EVENT_PROFILE
- atomic_t profile_count;
- int (*profile_enable)(struct ftrace_event_call *);
- void (*profile_disable)(struct ftrace_event_call *);
-#endif
+ char *filter_string;
};
struct event_subsystem {
struct list_head list;
const char *name;
struct dentry *entry;
- struct filter_pred **preds;
+ void *filter;
};
-#define events_for_each(event) \
- for (event = __start_ftrace_events; \
- (unsigned long)event < (unsigned long)__stop_ftrace_events; \
- event++)
-
-#define MAX_FILTER_PRED 8
-
struct filter_pred;
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
+ int val1, int val2);
struct filter_pred {
filter_pred_fn_t fn;
u64 val;
- char *str_val;
+ char str_val[MAX_FILTER_STR_VAL];
int str_len;
char *field_name;
int offset;
int not;
- int or;
- int compound;
- int clear;
+ int op;
+ int pop_n;
};
-int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size);
-extern void filter_free_pred(struct filter_pred *pred);
-extern void filter_print_preds(struct filter_pred **preds,
+extern void print_event_filter(struct ftrace_event_call *call,
struct trace_seq *s);
-extern int filter_parse(char **pbuf, struct filter_pred *pred);
-extern int filter_add_pred(struct ftrace_event_call *call,
- struct filter_pred *pred);
-extern void filter_free_preds(struct ftrace_event_call *call);
-extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern void filter_free_subsystem_preds(struct event_subsystem *system);
-extern int filter_add_subsystem_pred(struct event_subsystem *system,
- struct filter_pred *pred);
-
-void event_trace_printk(unsigned long ip, const char *fmt, ...);
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
-
-#define for_each_event(event) \
- for (event = __start_ftrace_events; \
- (unsigned long)event < (unsigned long)__stop_ftrace_events; \
- event++)
+extern int apply_event_filter(struct ftrace_event_call *call,
+ char *filter_string);
+extern int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string);
+extern void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s);
+
+static inline int
+filter_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+ ring_buffer_discard_commit(buffer, event);
+ return 1;
+ }
+
+ return 0;
+}
+
+#define DEFINE_COMPARISON_PRED(type) \
+static int filter_pred_##type(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ int match = 0; \
+ \
+ switch (pred->op) { \
+ case OP_LT: \
+ match = (*addr < val); \
+ break; \
+ case OP_LE: \
+ match = (*addr <= val); \
+ break; \
+ case OP_GT: \
+ match = (*addr > val); \
+ break; \
+ case OP_GE: \
+ match = (*addr >= val); \
+ break; \
+ default: \
+ break; \
+ } \
+ \
+ return match; \
+}
+
+#define DEFINE_EQUALITY_PRED(size) \
+static int filter_pred_##size(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ u##size *addr = (u##size *)(event + pred->offset); \
+ u##size val = (u##size)pred->val; \
+ int match; \
+ \
+ match = (val == *addr) ^ pred->not; \
+ \
+ return match; \
+}
+
+extern struct mutex event_mutex;
+extern struct list_head ftrace_events;
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
-/*
- * The double __builtin_constant_p is because gcc will give us an error
- * if we try to allocate the static variable to fmt if it is not a
- * constant. Even with the outer if statement optimizing out.
- */
-#define event_trace_printk(ip, fmt, args...) \
-do { \
- __trace_printk_check_format(fmt, ##args); \
- tracing_record_cmdline(current); \
- if (__builtin_constant_p(fmt)) { \
- static const char *trace_printk_fmt \
- __attribute__((section("__trace_printk_fmt"))) = \
- __builtin_constant_p(fmt) ? fmt : NULL; \
- \
- __trace_bprintk(ip, trace_printk_fmt, ##args); \
- } else \
- __trace_printk(ip, fmt, ##args); \
-} while (0)
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+ extern struct ftrace_event_call event_##call;
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
+#include "trace_event_types.h"
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7a30fc4c364..a29ef23ffb4 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -9,6 +9,7 @@
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/kallsyms.h>
+#include <linux/time.h>
#include "trace.h"
#include "trace_output.h"
@@ -67,7 +68,7 @@ initcall_call_print_line(struct trace_iterator *iter)
trace_assign_type(field, entry);
call = &field->boot_call;
ts = iter->ts;
- nsec_rem = do_div(ts, 1000000000);
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n",
(unsigned long)ts, nsec_rem, call->func, call->caller);
@@ -92,7 +93,7 @@ initcall_ret_print_line(struct trace_iterator *iter)
trace_assign_type(field, entry);
init_ret = &field->boot_ret;
ts = iter->ts;
- nsec_rem = do_div(ts, 1000000000);
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
"returned %d after %llu msecs\n",
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 8333715e406..7a7a9fd249a 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -30,6 +30,7 @@ static struct trace_array *branch_tracer;
static void
probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
+ struct ftrace_event_call *call = &event_branch;
struct trace_array *tr = branch_tracer;
struct ring_buffer_event *event;
struct trace_branch *entry;
@@ -73,7 +74,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
entry->line = f->line;
entry->correct = val == expect;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out:
atomic_dec(&tr->data[cpu]->disabled);
@@ -271,7 +273,7 @@ static int branch_stat_show(struct seq_file *m, void *v)
return 0;
}
-static void *annotated_branch_stat_start(void)
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
{
return __start_annotated_branch_profile;
}
@@ -346,7 +348,7 @@ static int all_branch_stat_headers(struct seq_file *m)
return 0;
}
-static void *all_branch_stat_start(void)
+static void *all_branch_stat_start(struct tracer_stat *trace)
{
return __start_branch_profile;
}
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 22cba997077..5b5895afecf 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -10,22 +10,30 @@
int ftrace_profile_enable(int event_id)
{
struct ftrace_event_call *event;
+ int ret = -EINVAL;
- for_each_event(event) {
- if (event->id == event_id)
- return event->profile_enable(event);
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id) {
+ ret = event->profile_enable(event);
+ break;
+ }
}
+ mutex_unlock(&event_mutex);
- return -EINVAL;
+ return ret;
}
void ftrace_profile_disable(int event_id)
{
struct ftrace_event_call *event;
- for_each_event(event) {
- if (event->id == event_id)
- return event->profile_disable(event);
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id) {
+ event->profile_disable(event);
+ break;
+ }
}
+ mutex_unlock(&event_mutex);
}
-
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index fd78bee71dd..5e32e375134 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -57,7 +57,7 @@ TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore,
TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]")
);
-TRACE_EVENT_FORMAT(special, TRACE_SPECIAL, special_entry, ignore,
+TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned long, arg1, arg1)
TRACE_FIELD(unsigned long, arg2, arg2)
@@ -122,8 +122,10 @@ TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned int, line, line)
- TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, func)
- TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, file)
+ TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
+ TRACE_FUNC_SIZE+1, func)
+ TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
+ TRACE_FUNC_SIZE+1, file)
TRACE_FIELD(char, correct, correct)
),
TP_RAW_FMT("%u:%s:%s (%u)")
@@ -139,8 +141,8 @@ TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore,
TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
TRACE_STRUCT(
- TRACE_FIELD(ktime_t, state_data.stamp, stamp)
- TRACE_FIELD(ktime_t, state_data.end, end)
+ TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
+ TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
TRACE_FIELD(int, state_data.type, type)
TRACE_FIELD(int, state_data.state, state)
),
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 576f4fa2af0..87feb0117ce 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -8,19 +8,25 @@
*
*/
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/delay.h>
#include "trace_output.h"
#define TRACE_SYSTEM "TRACE_SYSTEM"
-static DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_mutex);
+
+LIST_HEAD(ftrace_events);
int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size)
+ char *name, int offset, int size, int is_signed)
{
struct ftrace_event_field *field;
@@ -38,6 +44,7 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
field->offset = offset;
field->size = size;
+ field->is_signed = is_signed;
list_add(&field->link, &call->fields);
return 0;
@@ -51,20 +58,37 @@ err:
return -ENOMEM;
}
+EXPORT_SYMBOL_GPL(trace_define_field);
-static void ftrace_clear_events(void)
+#ifdef CONFIG_MODULES
+
+static void trace_destroy_fields(struct ftrace_event_call *call)
{
- struct ftrace_event_call *call = (void *)__start_ftrace_events;
+ struct ftrace_event_field *field, *next;
+ list_for_each_entry_safe(field, next, &call->fields, link) {
+ list_del(&field->link);
+ kfree(field->type);
+ kfree(field->name);
+ kfree(field);
+ }
+}
+
+#endif /* CONFIG_MODULES */
+
+static void ftrace_clear_events(void)
+{
+ struct ftrace_event_call *call;
- while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
if (call->enabled) {
call->enabled = 0;
call->unregfunc();
}
- call++;
}
+ mutex_unlock(&event_mutex);
}
static void ftrace_event_enable_disable(struct ftrace_event_call *call,
@@ -89,7 +113,7 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
static int ftrace_set_clr_event(char *buf, int set)
{
- struct ftrace_event_call *call = __start_ftrace_events;
+ struct ftrace_event_call *call;
char *event = NULL, *sub = NULL, *match;
int ret = -EINVAL;
@@ -118,7 +142,7 @@ static int ftrace_set_clr_event(char *buf, int set)
}
mutex_lock(&event_mutex);
- for_each_event(call) {
+ list_for_each_entry(call, &ftrace_events, list) {
if (!call->name || !call->regfunc)
continue;
@@ -224,15 +248,17 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = m->private;
- struct ftrace_event_call *next = call;
+ struct list_head *list = m->private;
+ struct ftrace_event_call *call;
(*pos)++;
for (;;) {
- if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+ if (list == &ftrace_events)
return NULL;
+ call = list_entry(list, struct ftrace_event_call, list);
+
/*
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
@@ -240,45 +266,51 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
if (call->regfunc)
break;
- call++;
- next = call;
+ list = list->next;
}
- m->private = ++next;
+ m->private = list->next;
return call;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ mutex_lock(&event_mutex);
+ if (*pos == 0)
+ m->private = ftrace_events.next;
return t_next(m, NULL, pos);
}
static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = m->private;
- struct ftrace_event_call *next;
+ struct list_head *list = m->private;
+ struct ftrace_event_call *call;
(*pos)++;
retry:
- if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+ if (list == &ftrace_events)
return NULL;
+ call = list_entry(list, struct ftrace_event_call, list);
+
if (!call->enabled) {
- call++;
+ list = list->next;
goto retry;
}
- next = call;
- m->private = ++next;
+ m->private = list->next;
return call;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
+ mutex_lock(&event_mutex);
+ if (*pos == 0)
+ m->private = ftrace_events.next;
return s_next(m, NULL, pos);
}
@@ -295,12 +327,12 @@ static int t_show(struct seq_file *m, void *v)
static void t_stop(struct seq_file *m, void *p)
{
+ mutex_unlock(&event_mutex);
}
static int
ftrace_event_seq_open(struct inode *inode, struct file *file)
{
- int ret;
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
@@ -308,13 +340,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
ftrace_clear_events();
seq_ops = inode->i_private;
- ret = seq_open(file, seq_ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
-
- m->private = __start_ftrace_events;
- }
- return ret;
+ return seq_open(file, seq_ops);
}
static ssize_t
@@ -374,8 +400,138 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
return cnt;
}
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char *system = filp->private_data;
+ struct ftrace_event_call *call;
+ char buf[2];
+ int set = -1;
+ int all = 0;
+ int ret;
+
+ if (system[0] == '*')
+ all = 1;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (!all && strcmp(call->system, system) != 0)
+ continue;
+
+ /*
+ * We need to find out if all the events are set
+ * or if all events or cleared, or if we have
+ * a mixture.
+ */
+ if (call->enabled) {
+ switch (set) {
+ case -1:
+ set = 1;
+ break;
+ case 0:
+ set = 2;
+ break;
+ }
+ } else {
+ switch (set) {
+ case -1:
+ set = 0;
+ break;
+ case 1:
+ set = 2;
+ break;
+ }
+ }
+ /*
+ * If we have a mixture, no need to look further.
+ */
+ if (set == 2)
+ break;
+ }
+ mutex_unlock(&event_mutex);
+
+ buf[1] = '\n';
+ switch (set) {
+ case 0:
+ buf[0] = '0';
+ break;
+ case 1:
+ buf[0] = '1';
+ break;
+ case 2:
+ buf[0] = 'X';
+ break;
+ default:
+ buf[0] = '?';
+ }
+
+ ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+
+ return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char *system = filp->private_data;
+ unsigned long val;
+ char *command;
+ char buf[64];
+ ssize_t ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = tracing_update_buffers();
+ if (ret < 0)
+ return ret;
+
+ switch (val) {
+ case 0:
+ case 1:
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ command = kstrdup(system, GFP_KERNEL);
+ if (!command)
+ return -ENOMEM;
+
+ ret = ftrace_set_clr_event(command, val);
+ if (ret)
+ goto out_free;
+
+ ret = cnt;
+
+ out_free:
+ kfree(command);
+
+ *ppos += cnt;
+
+ return ret;
+}
+
+extern char *__bad_type_size(void);
+
#undef FIELD
#define FIELD(type, name) \
+ sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
#type, "common_" #name, offsetof(typeof(field), name), \
sizeof(field.name)
@@ -391,7 +547,7 @@ static int trace_write_header(struct trace_seq *s)
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\n",
- FIELD(unsigned char, type),
+ FIELD(unsigned short, type),
FIELD(unsigned char, flags),
FIELD(unsigned char, preempt_count),
FIELD(int, pid),
@@ -481,7 +637,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
- filter_print_preds(call->preds, s);
+ print_event_filter(call, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
@@ -494,38 +650,26 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
- char buf[64], *pbuf = buf;
- struct filter_pred *pred;
+ char *buf;
int err;
- if (cnt >= sizeof(buf))
+ if (cnt >= PAGE_SIZE)
return -EINVAL;
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
- buf[cnt] = '\0';
-
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
return -ENOMEM;
- err = filter_parse(&pbuf, pred);
- if (err < 0) {
- filter_free_pred(pred);
- return err;
- }
-
- if (pred->clear) {
- filter_free_preds(call);
- filter_free_pred(pred);
- return cnt;
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
}
+ buf[cnt] = '\0';
- err = filter_add_pred(call, pred);
- if (err < 0) {
- filter_free_pred(pred);
+ err = apply_event_filter(call, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
return err;
- }
*ppos += cnt;
@@ -549,7 +693,7 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
- filter_print_preds(system->preds, s);
+ print_subsystem_event_filter(system, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
@@ -562,45 +706,56 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct event_subsystem *system = filp->private_data;
- char buf[64], *pbuf = buf;
- struct filter_pred *pred;
+ char *buf;
int err;
- if (cnt >= sizeof(buf))
+ if (cnt >= PAGE_SIZE)
return -EINVAL;
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
- buf[cnt] = '\0';
-
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
return -ENOMEM;
- err = filter_parse(&pbuf, pred);
- if (err < 0) {
- filter_free_pred(pred);
- return err;
- }
-
- if (pred->clear) {
- filter_free_subsystem_preds(system);
- filter_free_pred(pred);
- return cnt;
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
}
+ buf[cnt] = '\0';
- err = filter_add_subsystem_pred(system, pred);
- if (err < 0) {
- filter_free_subsystem_preds(system);
- filter_free_pred(pred);
+ err = apply_subsystem_event_filter(system, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
return err;
- }
*ppos += cnt;
return cnt;
}
+static ssize_t
+show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ int (*func)(struct trace_seq *s) = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ func(s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
static const struct seq_operations show_event_seq_ops = {
.start = t_start,
.next = t_next,
@@ -658,6 +813,17 @@ static const struct file_operations ftrace_subsystem_filter_fops = {
.write = subsystem_filter_write,
};
+static const struct file_operations ftrace_system_enable_fops = {
+ .open = tracing_open_generic,
+ .read = system_enable_read,
+ .write = system_enable_write,
+};
+
+static const struct file_operations ftrace_show_header_fops = {
+ .open = tracing_open_generic,
+ .read = show_header,
+};
+
static struct dentry *event_trace_events_dir(void)
{
static struct dentry *d_tracer;
@@ -684,6 +850,7 @@ static struct dentry *
event_subsystem_dir(const char *name, struct dentry *d_events)
{
struct event_subsystem *system;
+ struct dentry *entry;
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
@@ -707,16 +874,46 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
return d_events;
}
- system->name = name;
+ system->name = kstrdup(name, GFP_KERNEL);
+ if (!system->name) {
+ debugfs_remove(system->entry);
+ kfree(system);
+ return d_events;
+ }
+
list_add(&system->list, &event_subsystems);
- system->preds = NULL;
+ system->filter = NULL;
+
+ system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+ if (!system->filter) {
+ pr_warning("Could not allocate filter for subsystem "
+ "'%s'\n", name);
+ return system->entry;
+ }
+
+ entry = debugfs_create_file("filter", 0644, system->entry, system,
+ &ftrace_subsystem_filter_fops);
+ if (!entry) {
+ kfree(system->filter);
+ system->filter = NULL;
+ pr_warning("Could not create debugfs "
+ "'%s/filter' entry\n", name);
+ }
+
+ entry = trace_create_file("enable", 0644, system->entry,
+ (void *)system->name,
+ &ftrace_system_enable_fops);
return system->entry;
}
static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+ const struct file_operations *id,
+ const struct file_operations *enable,
+ const struct file_operations *filter,
+ const struct file_operations *format)
{
struct dentry *entry;
int ret;
@@ -725,7 +922,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
- if (strcmp(call->system, "TRACE_SYSTEM") != 0)
+ if (strcmp(call->system, TRACE_SYSTEM) != 0)
d_events = event_subsystem_dir(call->system, d_events);
if (call->raw_init) {
@@ -744,21 +941,13 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
return -1;
}
- if (call->regfunc) {
- entry = debugfs_create_file("enable", 0644, call->dir, call,
- &ftrace_enable_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/enable' entry\n", call->name);
- }
+ if (call->regfunc)
+ entry = trace_create_file("enable", 0644, call->dir, call,
+ enable);
- if (call->id) {
- entry = debugfs_create_file("id", 0444, call->dir, call,
- &ftrace_event_id_fops);
- if (!entry)
- pr_warning("Could not create debugfs '%s/id' entry\n",
- call->name);
- }
+ if (call->id)
+ entry = trace_create_file("id", 0444, call->dir, call,
+ id);
if (call->define_fields) {
ret = call->define_fields();
@@ -767,32 +956,196 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
" events/%s\n", call->name);
return ret;
}
- entry = debugfs_create_file("filter", 0644, call->dir, call,
- &ftrace_event_filter_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/filter' entry\n", call->name);
+ entry = trace_create_file("filter", 0644, call->dir, call,
+ filter);
}
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
- entry = debugfs_create_file("format", 0444, call->dir, call,
- &ftrace_event_format_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/format' entry\n", call->name);
+ entry = trace_create_file("format", 0444, call->dir, call,
+ format);
+
+ return 0;
+}
+
+#define for_each_event(event, start, end) \
+ for (event = start; \
+ (unsigned long)event < (unsigned long)end; \
+ event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+ struct list_head list;
+ struct module *mod;
+ struct file_operations id;
+ struct file_operations enable;
+ struct file_operations format;
+ struct file_operations filter;
+};
+
+static struct ftrace_module_file_ops *
+trace_create_file_ops(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+
+ /*
+ * This is a bit of a PITA. To allow for correct reference
+ * counting, modules must "own" their file_operations.
+ * To do this, we allocate the file operations that will be
+ * used in the event directory.
+ */
+
+ file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
+ if (!file_ops)
+ return NULL;
+
+ file_ops->mod = mod;
+
+ file_ops->id = ftrace_event_id_fops;
+ file_ops->id.owner = mod;
+
+ file_ops->enable = ftrace_enable_fops;
+ file_ops->enable.owner = mod;
+
+ file_ops->filter = ftrace_event_filter_fops;
+ file_ops->filter.owner = mod;
+
+ file_ops->format = ftrace_event_format_fops;
+ file_ops->format.owner = mod;
+
+ list_add(&file_ops->list, &ftrace_module_file_list);
+
+ return file_ops;
+}
+
+static void trace_module_add_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops = NULL;
+ struct ftrace_event_call *call, *start, *end;
+ struct dentry *d_events;
+
+ start = mod->trace_events;
+ end = mod->trace_events + mod->num_trace_events;
+
+ if (start == end)
+ return;
+
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return;
+
+ for_each_event(call, start, end) {
+ /* The linker may leave blanks */
+ if (!call->name)
+ continue;
+
+ /*
+ * This module has events, create file ops for this module
+ * if not already done.
+ */
+ if (!file_ops) {
+ file_ops = trace_create_file_ops(mod);
+ if (!file_ops)
+ return;
+ }
+ call->mod = mod;
+ list_add(&call->list, &ftrace_events);
+ event_create_dir(call, d_events,
+ &file_ops->id, &file_ops->enable,
+ &file_ops->filter, &file_ops->format);
+ }
+}
+
+static void trace_module_remove_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+ struct ftrace_event_call *call, *p;
+ bool found = false;
+
+ list_for_each_entry_safe(call, p, &ftrace_events, list) {
+ if (call->mod == mod) {
+ found = true;
+ if (call->enabled) {
+ call->enabled = 0;
+ call->unregfunc();
+ }
+ if (call->event)
+ unregister_ftrace_event(call->event);
+ debugfs_remove_recursive(call->dir);
+ list_del(&call->list);
+ trace_destroy_fields(call);
+ destroy_preds(call);
+ }
+ }
+
+ /* Now free the file_operations */
+ list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+ if (file_ops->mod == mod)
+ break;
+ }
+ if (&file_ops->list != &ftrace_module_file_list) {
+ list_del(&file_ops->list);
+ kfree(file_ops);
+ }
+
+ /*
+ * It is safest to reset the ring buffer if the module being unloaded
+ * registered any events.
+ */
+ if (found)
+ tracing_reset_current_online_cpus();
+}
+
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+ mutex_lock(&event_mutex);
+ switch (val) {
+ case MODULE_STATE_COMING:
+ trace_module_add_events(mod);
+ break;
+ case MODULE_STATE_GOING:
+ trace_module_remove_events(mod);
+ break;
+ }
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+#else
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
return 0;
}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block trace_module_nb = {
+ .notifier_call = trace_module_notify,
+ .priority = 0,
+};
+
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
static __init int event_trace_init(void)
{
- struct ftrace_event_call *call = __start_ftrace_events;
+ struct ftrace_event_call *call;
struct dentry *d_tracer;
struct dentry *entry;
struct dentry *d_events;
+ int ret;
d_tracer = tracing_init_dentry();
if (!d_tracer)
@@ -816,13 +1169,272 @@ static __init int event_trace_init(void)
if (!d_events)
return 0;
- for_each_event(call) {
+ /* ring buffer internal formats */
+ trace_create_file("header_page", 0444, d_events,
+ ring_buffer_print_page_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("header_event", 0444, d_events,
+ ring_buffer_print_entry_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("enable", 0644, d_events,
+ "*:*", &ftrace_system_enable_fops);
+
+ for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
/* The linker may leave blanks */
if (!call->name)
continue;
- event_create_dir(call, d_events);
+ list_add(&call->list, &ftrace_events);
+ event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops, &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
}
+ ret = register_module_notifier(&trace_module_nb);
+ if (!ret)
+ pr_warning("Failed to register trace events module notifier\n");
+
return 0;
}
fs_initcall(event_trace_init);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_SPINLOCK(test_spinlock_irq);
+static DEFINE_MUTEX(test_mutex);
+
+static __init void test_work(struct work_struct *dummy)
+{
+ spin_lock(&test_spinlock);
+ spin_lock_irq(&test_spinlock_irq);
+ udelay(1);
+ spin_unlock_irq(&test_spinlock_irq);
+ spin_unlock(&test_spinlock);
+
+ mutex_lock(&test_mutex);
+ msleep(1);
+ mutex_unlock(&test_mutex);
+}
+
+static __init int event_test_thread(void *unused)
+{
+ void *test_malloc;
+
+ test_malloc = kmalloc(1234, GFP_KERNEL);
+ if (!test_malloc)
+ pr_info("failed to kmalloc\n");
+
+ schedule_on_each_cpu(test_work);
+
+ kfree(test_malloc);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop())
+ schedule();
+
+ return 0;
+}
+
+/*
+ * Do various things that may trigger events.
+ */
+static __init void event_test_stuff(void)
+{
+ struct task_struct *test_thread;
+
+ test_thread = kthread_run(event_test_thread, NULL, "test-events");
+ msleep(1);
+ kthread_stop(test_thread);
+}
+
+/*
+ * For every trace event defined, we will test each trace point separately,
+ * and then by groups, and finally all trace points.
+ */
+static __init void event_trace_self_tests(void)
+{
+ struct ftrace_event_call *call;
+ struct event_subsystem *system;
+ char *sysname;
+ int ret;
+
+ pr_info("Running tests on trace events:\n");
+
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ /* Only test those that have a regfunc */
+ if (!call->regfunc)
+ continue;
+
+ pr_info("Testing event %s: ", call->name);
+
+ /*
+ * If an event is already enabled, someone is using
+ * it and the self test should not be on.
+ */
+ if (call->enabled) {
+ pr_warning("Enabled event during self test!\n");
+ WARN_ON_ONCE(1);
+ continue;
+ }
+
+ call->enabled = 1;
+ call->regfunc();
+
+ event_test_stuff();
+
+ call->unregfunc();
+ call->enabled = 0;
+
+ pr_cont("OK\n");
+ }
+
+ /* Now test at the sub system level */
+
+ pr_info("Running tests on trace event systems:\n");
+
+ list_for_each_entry(system, &event_subsystems, list) {
+
+ /* the ftrace system is special, skip it */
+ if (strcmp(system->name, "ftrace") == 0)
+ continue;
+
+ pr_info("Testing event system %s: ", system->name);
+
+ /* ftrace_set_clr_event can modify the name passed in. */
+ sysname = kstrdup(system->name, GFP_KERNEL);
+ if (WARN_ON(!sysname)) {
+ pr_warning("Can't allocate memory, giving up!\n");
+ return;
+ }
+ ret = ftrace_set_clr_event(sysname, 1);
+ kfree(sysname);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error enabling system %s\n",
+ system->name);
+ continue;
+ }
+
+ event_test_stuff();
+
+ sysname = kstrdup(system->name, GFP_KERNEL);
+ if (WARN_ON(!sysname)) {
+ pr_warning("Can't allocate memory, giving up!\n");
+ return;
+ }
+ ret = ftrace_set_clr_event(sysname, 0);
+ kfree(sysname);
+
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error disabling system %s\n",
+ system->name);
+
+ pr_cont("OK\n");
+ }
+
+ /* Test with all events enabled */
+
+ pr_info("Running tests on all trace events:\n");
+ pr_info("Testing all events: ");
+
+ sysname = kmalloc(4, GFP_KERNEL);
+ if (WARN_ON(!sysname)) {
+ pr_warning("Can't allocate memory, giving up!\n");
+ return;
+ }
+ memcpy(sysname, "*:*", 4);
+ ret = ftrace_set_clr_event(sysname, 1);
+ if (WARN_ON_ONCE(ret)) {
+ kfree(sysname);
+ pr_warning("error enabling all events\n");
+ return;
+ }
+
+ event_test_stuff();
+
+ /* reset sysname */
+ memcpy(sysname, "*:*", 4);
+ ret = ftrace_set_clr_event(sysname, 0);
+ kfree(sysname);
+
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error disabling all events\n");
+ return;
+ }
+
+ pr_cont("OK\n");
+}
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static DEFINE_PER_CPU(atomic_t, test_event_disable);
+
+static void
+function_test_events_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ring_buffer_event *event;
+ struct ftrace_entry *entry;
+ unsigned long flags;
+ long disabled;
+ int resched;
+ int cpu;
+ int pc;
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+ cpu = raw_smp_processor_id();
+ disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+
+ if (disabled != 1)
+ goto out;
+
+ local_save_flags(flags);
+
+ event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+ flags, pc);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+
+ trace_nowake_buffer_unlock_commit(event, flags, pc);
+
+ out:
+ atomic_dec(&per_cpu(test_event_disable, cpu));
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __initdata =
+{
+ .func = function_test_events_call,
+};
+
+static __init void event_trace_self_test_with_function(void)
+{
+ register_ftrace_function(&trace_ops);
+ pr_info("Running tests again, along with the function tracer\n");
+ event_trace_self_tests();
+ unregister_ftrace_function(&trace_ops);
+}
+#else
+static __init void event_trace_self_test_with_function(void)
+{
+}
+#endif
+
+static __init int event_trace_self_tests_init(void)
+{
+
+ event_trace_self_tests();
+
+ event_trace_self_test_with_function();
+
+ return 0;
+}
+
+late_initcall(event_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e03cbf1e38f..85ad6a8939a 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,119 +22,297 @@
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/mutex.h>
#include "trace.h"
#include "trace_output.h"
-static int filter_pred_64(struct filter_pred *pred, void *event)
+static DEFINE_MUTEX(filter_mutex);
+
+enum filter_op_ids
+{
+ OP_OR,
+ OP_AND,
+ OP_NE,
+ OP_EQ,
+ OP_LT,
+ OP_LE,
+ OP_GT,
+ OP_GE,
+ OP_NONE,
+ OP_OPEN_PAREN,
+};
+
+struct filter_op {
+ int id;
+ char *string;
+ int precedence;
+};
+
+static struct filter_op filter_ops[] = {
+ { OP_OR, "||", 1 },
+ { OP_AND, "&&", 2 },
+ { OP_NE, "!=", 4 },
+ { OP_EQ, "==", 4 },
+ { OP_LT, "<", 5 },
+ { OP_LE, "<=", 5 },
+ { OP_GT, ">", 5 },
+ { OP_GE, ">=", 5 },
+ { OP_NONE, "OP_NONE", 0 },
+ { OP_OPEN_PAREN, "(", 0 },
+};
+
+enum {
+ FILT_ERR_NONE,
+ FILT_ERR_INVALID_OP,
+ FILT_ERR_UNBALANCED_PAREN,
+ FILT_ERR_TOO_MANY_OPERANDS,
+ FILT_ERR_OPERAND_TOO_LONG,
+ FILT_ERR_FIELD_NOT_FOUND,
+ FILT_ERR_ILLEGAL_FIELD_OP,
+ FILT_ERR_ILLEGAL_INTVAL,
+ FILT_ERR_BAD_SUBSYS_FILTER,
+ FILT_ERR_TOO_MANY_PREDS,
+ FILT_ERR_MISSING_FIELD,
+ FILT_ERR_INVALID_FILTER,
+};
+
+static char *err_text[] = {
+ "No error",
+ "Invalid operator",
+ "Unbalanced parens",
+ "Too many operands",
+ "Operand too long",
+ "Field not found",
+ "Illegal operation for field type",
+ "Illegal integer value",
+ "Couldn't find or set field in one of a subsystem's events",
+ "Too many terms in predicate expression",
+ "Missing field name and/or value",
+ "Meaningless filter expression",
+};
+
+struct opstack_op {
+ int op;
+ struct list_head list;
+};
+
+struct postfix_elt {
+ int op;
+ char *operand;
+ struct list_head list;
+};
+
+struct filter_parse_state {
+ struct filter_op *ops;
+ struct list_head opstack;
+ struct list_head postfix;
+ int lasterr;
+ int lasterr_pos;
+
+ struct {
+ char *string;
+ unsigned int cnt;
+ unsigned int tail;
+ } infix;
+
+ struct {
+ char string[MAX_FILTER_STR_VAL];
+ int pos;
+ unsigned int tail;
+ } operand;
+};
+
+DEFINE_COMPARISON_PRED(s64);
+DEFINE_COMPARISON_PRED(u64);
+DEFINE_COMPARISON_PRED(s32);
+DEFINE_COMPARISON_PRED(u32);
+DEFINE_COMPARISON_PRED(s16);
+DEFINE_COMPARISON_PRED(u16);
+DEFINE_COMPARISON_PRED(s8);
+DEFINE_COMPARISON_PRED(u8);
+
+DEFINE_EQUALITY_PRED(64);
+DEFINE_EQUALITY_PRED(32);
+DEFINE_EQUALITY_PRED(16);
+DEFINE_EQUALITY_PRED(8);
+
+static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 && val2;
+}
+
+static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 || val2;
+}
+
+/* Filter predicate for fixed sized arrays of characters */
+static int filter_pred_string(struct filter_pred *pred, void *event,
+ int val1, int val2)
{
- u64 *addr = (u64 *)(event + pred->offset);
- u64 val = (u64)pred->val;
- int match;
+ char *addr = (char *)(event + pred->offset);
+ int cmp, match;
+
+ cmp = strncmp(addr, pred->str_val, pred->str_len);
- match = (val == *addr) ^ pred->not;
+ match = (!cmp) ^ pred->not;
return match;
}
-static int filter_pred_32(struct filter_pred *pred, void *event)
+/*
+ * Filter predicate for dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry.
+ * Also each of these strings have a field in the entry which
+ * contains its offset from the beginning of the entry.
+ * We have then first to get this field, dereference it
+ * and add it to the address of the entry, and at last we have
+ * the address of the string.
+ */
+static int filter_pred_strloc(struct filter_pred *pred, void *event,
+ int val1, int val2)
{
- u32 *addr = (u32 *)(event + pred->offset);
- u32 val = (u32)pred->val;
- int match;
+ int str_loc = *(int *)(event + pred->offset);
+ char *addr = (char *)(event + str_loc);
+ int cmp, match;
+
+ cmp = strncmp(addr, pred->str_val, pred->str_len);
- match = (val == *addr) ^ pred->not;
+ match = (!cmp) ^ pred->not;
return match;
}
-static int filter_pred_16(struct filter_pred *pred, void *event)
+static int filter_pred_none(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ return 0;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
{
- u16 *addr = (u16 *)(event + pred->offset);
- u16 val = (u16)pred->val;
- int match;
+ struct event_filter *filter = call->filter;
+ int match, top = 0, val1 = 0, val2 = 0;
+ int stack[MAX_FILTER_PRED];
+ struct filter_pred *pred;
+ int i;
+
+ for (i = 0; i < filter->n_preds; i++) {
+ pred = filter->preds[i];
+ if (!pred->pop_n) {
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ continue;
+ }
+ if (pred->pop_n > top) {
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+ val1 = stack[--top];
+ val2 = stack[--top];
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ }
- match = (val == *addr) ^ pred->not;
+ return stack[--top];
+}
+EXPORT_SYMBOL_GPL(filter_match_preds);
- return match;
+static void parse_error(struct filter_parse_state *ps, int err, int pos)
+{
+ ps->lasterr = err;
+ ps->lasterr_pos = pos;
}
-static int filter_pred_8(struct filter_pred *pred, void *event)
+static void remove_filter_string(struct event_filter *filter)
{
- u8 *addr = (u8 *)(event + pred->offset);
- u8 val = (u8)pred->val;
- int match;
+ kfree(filter->filter_string);
+ filter->filter_string = NULL;
+}
- match = (val == *addr) ^ pred->not;
+static int replace_filter_string(struct event_filter *filter,
+ char *filter_string)
+{
+ kfree(filter->filter_string);
+ filter->filter_string = kstrdup(filter_string, GFP_KERNEL);
+ if (!filter->filter_string)
+ return -ENOMEM;
- return match;
+ return 0;
}
-static int filter_pred_string(struct filter_pred *pred, void *event)
+static int append_filter_string(struct event_filter *filter,
+ char *string)
{
- char *addr = (char *)(event + pred->offset);
- int cmp, match;
+ int newlen;
+ char *new_filter_string;
- cmp = strncmp(addr, pred->str_val, pred->str_len);
+ BUG_ON(!filter->filter_string);
+ newlen = strlen(filter->filter_string) + strlen(string) + 1;
+ new_filter_string = kmalloc(newlen, GFP_KERNEL);
+ if (!new_filter_string)
+ return -ENOMEM;
- match = (!cmp) ^ pred->not;
+ strcpy(new_filter_string, filter->filter_string);
+ strcat(new_filter_string, string);
+ kfree(filter->filter_string);
+ filter->filter_string = new_filter_string;
- return match;
+ return 0;
}
-/* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+static void append_filter_err(struct filter_parse_state *ps,
+ struct event_filter *filter)
{
- int i, matched, and_failed = 0;
- struct filter_pred *pred;
+ int pos = ps->lasterr_pos;
+ char *buf, *pbuf;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (call->preds[i]) {
- pred = call->preds[i];
- if (and_failed && !pred->or)
- continue;
- matched = pred->fn(pred, rec);
- if (!matched && !pred->or) {
- and_failed = 1;
- continue;
- } else if (matched && pred->or)
- return 1;
- } else
- break;
- }
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return;
- if (and_failed)
- return 0;
+ append_filter_string(filter, "\n");
+ memset(buf, ' ', PAGE_SIZE);
+ if (pos > PAGE_SIZE - 128)
+ pos = 0;
+ buf[pos] = '^';
+ pbuf = &buf[pos] + 1;
- return 1;
+ sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]);
+ append_filter_string(filter, buf);
+ free_page((unsigned long) buf);
}
-void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- char *field_name;
- struct filter_pred *pred;
- int i;
+ struct event_filter *filter = call->filter;
- if (!preds) {
+ mutex_lock(&filter_mutex);
+ if (filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
trace_seq_printf(s, "none\n");
- return;
- }
+ mutex_unlock(&filter_mutex);
+}
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (preds[i]) {
- pred = preds[i];
- field_name = pred->field_name;
- if (i)
- trace_seq_printf(s, pred->or ? "|| " : "&& ");
- trace_seq_printf(s, "%s ", field_name);
- trace_seq_printf(s, pred->not ? "!= " : "== ");
- if (pred->str_val)
- trace_seq_printf(s, "%s\n", pred->str_val);
- else
- trace_seq_printf(s, "%llu\n", pred->val);
- } else
- break;
- }
+void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s)
+{
+ struct event_filter *filter = system->filter;
+
+ mutex_lock(&filter_mutex);
+ if (filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
+ trace_seq_printf(s, "none\n");
+ mutex_unlock(&filter_mutex);
}
static struct ftrace_event_field *
@@ -150,284 +328,826 @@ find_event_field(struct ftrace_event_call *call, char *name)
return NULL;
}
-void filter_free_pred(struct filter_pred *pred)
+static void filter_free_pred(struct filter_pred *pred)
{
if (!pred)
return;
kfree(pred->field_name);
- kfree(pred->str_val);
kfree(pred);
}
-void filter_free_preds(struct ftrace_event_call *call)
+static void filter_clear_pred(struct filter_pred *pred)
{
- int i;
+ kfree(pred->field_name);
+ pred->field_name = NULL;
+ pred->str_len = 0;
+}
- if (call->preds) {
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter_free_pred(call->preds[i]);
- kfree(call->preds);
- call->preds = NULL;
+static int filter_set_pred(struct filter_pred *dest,
+ struct filter_pred *src,
+ filter_pred_fn_t fn)
+{
+ *dest = *src;
+ if (src->field_name) {
+ dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
+ if (!dest->field_name)
+ return -ENOMEM;
}
+ dest->fn = fn;
+
+ return 0;
}
-void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_disable_preds(struct ftrace_event_call *call)
{
- struct ftrace_event_call *call = __start_ftrace_events;
+ struct event_filter *filter = call->filter;
int i;
- if (system->preds) {
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter_free_pred(system->preds[i]);
- kfree(system->preds);
- system->preds = NULL;
- }
+ call->filter_active = 0;
+ filter->n_preds = 0;
- events_for_each(call) {
- if (!call->name || !call->regfunc)
- continue;
+ for (i = 0; i < MAX_FILTER_PRED; i++)
+ filter->preds[i]->fn = filter_pred_none;
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+ struct event_filter *filter = call->filter;
+ int i;
- if (!strcmp(call->system, system->name))
- filter_free_preds(call);
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (filter->preds[i])
+ filter_free_pred(filter->preds[i]);
}
+ kfree(filter->preds);
+ kfree(filter);
+ call->filter = NULL;
}
-static int __filter_add_pred(struct ftrace_event_call *call,
- struct filter_pred *pred)
+int init_preds(struct ftrace_event_call *call)
{
+ struct event_filter *filter;
+ struct filter_pred *pred;
int i;
- if (call->preds && !pred->compound)
- filter_free_preds(call);
+ filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!call->filter)
+ return -ENOMEM;
- if (!call->preds) {
- call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
- GFP_KERNEL);
- if (!call->preds)
- return -ENOMEM;
- }
+ call->filter_active = 0;
+ filter->n_preds = 0;
+
+ filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
+ if (!filter->preds)
+ goto oom;
for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (!call->preds[i]) {
- call->preds[i] = pred;
- return 0;
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ goto oom;
+ pred->fn = filter_pred_none;
+ filter->preds[i] = pred;
+ }
+
+ return 0;
+
+oom:
+ destroy_preds(call);
+
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(init_preds);
+
+static void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+ struct event_filter *filter = system->filter;
+ struct ftrace_event_call *call;
+ int i;
+
+ if (filter->n_preds) {
+ for (i = 0; i < filter->n_preds; i++)
+ filter_free_pred(filter->preds[i]);
+ kfree(filter->preds);
+ filter->preds = NULL;
+ filter->n_preds = 0;
+ }
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->define_fields)
+ continue;
+
+ if (!strcmp(call->system, system->name)) {
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
}
}
+ mutex_unlock(&event_mutex);
+}
+
+static int filter_add_pred_fn(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct filter_pred *pred,
+ filter_pred_fn_t fn)
+{
+ struct event_filter *filter = call->filter;
+ int idx, err;
+
+ if (filter->n_preds == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
+ idx = filter->n_preds;
+ filter_clear_pred(filter->preds[idx]);
+ err = filter_set_pred(filter->preds[idx], pred, fn);
+ if (err)
+ return err;
- return -ENOSPC;
+ filter->n_preds++;
+ call->filter_active = 1;
+
+ return 0;
}
+enum {
+ FILTER_STATIC_STRING = 1,
+ FILTER_DYN_STRING
+};
+
static int is_string_field(const char *type)
{
if (strchr(type, '[') && strstr(type, "char"))
- return 1;
+ return FILTER_STATIC_STRING;
+
+ if (!strcmp(type, "__str_loc"))
+ return FILTER_DYN_STRING;
return 0;
}
-int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+static int is_legal_op(struct ftrace_event_field *field, int op)
+{
+ if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+ return 0;
+
+ return 1;
+}
+
+static filter_pred_fn_t select_comparison_fn(int op, int field_size,
+ int field_is_signed)
+{
+ filter_pred_fn_t fn = NULL;
+
+ switch (field_size) {
+ case 8:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_64;
+ else if (field_is_signed)
+ fn = filter_pred_s64;
+ else
+ fn = filter_pred_u64;
+ break;
+ case 4:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_32;
+ else if (field_is_signed)
+ fn = filter_pred_s32;
+ else
+ fn = filter_pred_u32;
+ break;
+ case 2:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_16;
+ else if (field_is_signed)
+ fn = filter_pred_s16;
+ else
+ fn = filter_pred_u16;
+ break;
+ case 1:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_8;
+ else if (field_is_signed)
+ fn = filter_pred_s8;
+ else
+ fn = filter_pred_u8;
+ break;
+ }
+
+ return fn;
+}
+
+static int filter_add_pred(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct filter_pred *pred)
{
struct ftrace_event_field *field;
+ filter_pred_fn_t fn;
+ unsigned long long val;
+ int string_type;
+
+ pred->fn = filter_pred_none;
+
+ if (pred->op == OP_AND) {
+ pred->pop_n = 2;
+ return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+ } else if (pred->op == OP_OR) {
+ pred->pop_n = 2;
+ return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+ }
field = find_event_field(call, pred->field_name);
- if (!field)
+ if (!field) {
+ parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
return -EINVAL;
+ }
pred->offset = field->offset;
- if (is_string_field(field->type)) {
- if (!pred->str_val)
- return -EINVAL;
- pred->fn = filter_pred_string;
+ if (!is_legal_op(field, pred->op)) {
+ parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0);
+ return -EINVAL;
+ }
+
+ string_type = is_string_field(field->type);
+ if (string_type) {
+ if (string_type == FILTER_STATIC_STRING)
+ fn = filter_pred_string;
+ else
+ fn = filter_pred_strloc;
pred->str_len = field->size;
- return __filter_add_pred(call, pred);
+ if (pred->op == OP_NE)
+ pred->not = 1;
+ return filter_add_pred_fn(ps, call, pred, fn);
} else {
- if (pred->str_val)
+ if (strict_strtoull(pred->str_val, 0, &val)) {
+ parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
return -EINVAL;
+ }
+ pred->val = val;
}
- switch (field->size) {
- case 8:
- pred->fn = filter_pred_64;
- break;
- case 4:
- pred->fn = filter_pred_32;
- break;
- case 2:
- pred->fn = filter_pred_16;
- break;
- case 1:
- pred->fn = filter_pred_8;
- break;
- default:
+ fn = select_comparison_fn(pred->op, field->size, field->is_signed);
+ if (!fn) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
return -EINVAL;
}
- return __filter_add_pred(call, pred);
+ if (pred->op == OP_NE)
+ pred->not = 1;
+
+ return filter_add_pred_fn(ps, call, pred, fn);
}
-static struct filter_pred *copy_pred(struct filter_pred *pred)
+static int filter_add_subsystem_pred(struct filter_parse_state *ps,
+ struct event_subsystem *system,
+ struct filter_pred *pred,
+ char *filter_string)
{
- struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
- if (!new_pred)
- return NULL;
+ struct event_filter *filter = system->filter;
+ struct ftrace_event_call *call;
+ int err = 0;
+
+ if (!filter->preds) {
+ filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+ GFP_KERNEL);
- memcpy(new_pred, pred, sizeof(*pred));
+ if (!filter->preds)
+ return -ENOMEM;
+ }
- if (pred->field_name) {
- new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
- if (!new_pred->field_name) {
- kfree(new_pred);
- return NULL;
- }
+ if (filter->n_preds == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
}
- if (pred->str_val) {
- new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
- if (!new_pred->str_val) {
- filter_free_pred(new_pred);
- return NULL;
+ filter->preds[filter->n_preds] = pred;
+ filter->n_preds++;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ if (!call->define_fields)
+ continue;
+
+ if (strcmp(call->system, system->name))
+ continue;
+
+ err = filter_add_pred(ps, call, pred);
+ if (err) {
+ mutex_unlock(&event_mutex);
+ filter_free_subsystem_preds(system);
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ goto out;
}
+ replace_filter_string(call->filter, filter_string);
}
+ mutex_unlock(&event_mutex);
+out:
+ return err;
+}
+
+static void parse_init(struct filter_parse_state *ps,
+ struct filter_op *ops,
+ char *infix_string)
+{
+ memset(ps, '\0', sizeof(*ps));
- return new_pred;
+ ps->infix.string = infix_string;
+ ps->infix.cnt = strlen(infix_string);
+ ps->ops = ops;
+
+ INIT_LIST_HEAD(&ps->opstack);
+ INIT_LIST_HEAD(&ps->postfix);
}
-int filter_add_subsystem_pred(struct event_subsystem *system,
- struct filter_pred *pred)
+static char infix_next(struct filter_parse_state *ps)
{
- struct ftrace_event_call *call = __start_ftrace_events;
- struct filter_pred *event_pred;
- int i;
+ ps->infix.cnt--;
- if (system->preds && !pred->compound)
- filter_free_subsystem_preds(system);
+ return ps->infix.string[ps->infix.tail++];
+}
- if (!system->preds) {
- system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
- GFP_KERNEL);
- if (!system->preds)
- return -ENOMEM;
+static char infix_peek(struct filter_parse_state *ps)
+{
+ if (ps->infix.tail == strlen(ps->infix.string))
+ return 0;
+
+ return ps->infix.string[ps->infix.tail];
+}
+
+static void infix_advance(struct filter_parse_state *ps)
+{
+ ps->infix.cnt--;
+ ps->infix.tail++;
+}
+
+static inline int is_precedence_lower(struct filter_parse_state *ps,
+ int a, int b)
+{
+ return ps->ops[a].precedence < ps->ops[b].precedence;
+}
+
+static inline int is_op_char(struct filter_parse_state *ps, char c)
+{
+ int i;
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (ps->ops[i].string[0] == c)
+ return 1;
}
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (!system->preds[i]) {
- system->preds[i] = pred;
- break;
+ return 0;
+}
+
+static int infix_get_op(struct filter_parse_state *ps, char firstc)
+{
+ char nextc = infix_peek(ps);
+ char opstr[3];
+ int i;
+
+ opstr[0] = firstc;
+ opstr[1] = nextc;
+ opstr[2] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string)) {
+ infix_advance(ps);
+ return ps->ops[i].id;
}
}
- if (i == MAX_FILTER_PRED)
- return -ENOSPC;
+ opstr[1] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string))
+ return ps->ops[i].id;
+ }
+
+ return OP_NONE;
+}
+
+static inline void clear_operand_string(struct filter_parse_state *ps)
+{
+ memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL);
+ ps->operand.tail = 0;
+}
+
+static inline int append_operand_char(struct filter_parse_state *ps, char c)
+{
+ if (ps->operand.tail == MAX_FILTER_STR_VAL)
+ return -EINVAL;
+
+ ps->operand.string[ps->operand.tail++] = c;
+
+ return 0;
+}
+
+static int filter_opstack_push(struct filter_parse_state *ps, int op)
+{
+ struct opstack_op *opstack_op;
+
+ opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL);
+ if (!opstack_op)
+ return -ENOMEM;
+
+ opstack_op->op = op;
+ list_add(&opstack_op->list, &ps->opstack);
+
+ return 0;
+}
+
+static int filter_opstack_empty(struct filter_parse_state *ps)
+{
+ return list_empty(&ps->opstack);
+}
+
+static int filter_opstack_top(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+
+ return opstack_op->op;
+}
+
+static int filter_opstack_pop(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+ int op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+ op = opstack_op->op;
+ list_del(&opstack_op->list);
+
+ kfree(opstack_op);
+
+ return op;
+}
+
+static void filter_opstack_clear(struct filter_parse_state *ps)
+{
+ while (!filter_opstack_empty(ps))
+ filter_opstack_pop(ps);
+}
+
+static char *curr_operand(struct filter_parse_state *ps)
+{
+ return ps->operand.string;
+}
+
+static int postfix_append_operand(struct filter_parse_state *ps, char *operand)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = OP_NONE;
+ elt->operand = kstrdup(operand, GFP_KERNEL);
+ if (!elt->operand) {
+ kfree(elt);
+ return -ENOMEM;
+ }
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static int postfix_append_op(struct filter_parse_state *ps, int op)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = op;
+ elt->operand = NULL;
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static void postfix_clear(struct filter_parse_state *ps)
+{
+ struct postfix_elt *elt;
+
+ while (!list_empty(&ps->postfix)) {
+ elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
+ kfree(elt->operand);
+ list_del(&elt->list);
+ }
+}
- events_for_each(call) {
- int err;
+static int filter_parse(struct filter_parse_state *ps)
+{
+ int in_string = 0;
+ int op, top_op;
+ char ch;
- if (!call->name || !call->regfunc)
+ while ((ch = infix_next(ps))) {
+ if (ch == '"') {
+ in_string ^= 1;
continue;
+ }
- if (strcmp(call->system, system->name))
+ if (in_string)
+ goto parse_operand;
+
+ if (isspace(ch))
continue;
- if (!find_event_field(call, pred->field_name))
+ if (is_op_char(ps, ch)) {
+ op = infix_get_op(ps, ch);
+ if (op == OP_NONE) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
+ return -EINVAL;
+ }
+
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_top(ps);
+ if (!is_precedence_lower(ps, top_op, op)) {
+ top_op = filter_opstack_pop(ps);
+ postfix_append_op(ps, top_op);
+ continue;
+ }
+ break;
+ }
+
+ filter_opstack_push(ps, op);
continue;
+ }
- event_pred = copy_pred(pred);
- if (!event_pred)
- goto oom;
+ if (ch == '(') {
+ filter_opstack_push(ps, OP_OPEN_PAREN);
+ continue;
+ }
- err = filter_add_pred(call, event_pred);
- if (err)
- filter_free_pred(event_pred);
- if (err == -ENOMEM)
- goto oom;
+ if (ch == ')') {
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ top_op = filter_opstack_pop(ps);
+ while (top_op != OP_NONE) {
+ if (top_op == OP_OPEN_PAREN)
+ break;
+ postfix_append_op(ps, top_op);
+ top_op = filter_opstack_pop(ps);
+ }
+ if (top_op == OP_NONE) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
+ }
+ continue;
+ }
+parse_operand:
+ if (append_operand_char(ps, ch)) {
+ parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0);
+ return -EINVAL;
+ }
+ }
+
+ if (strlen(curr_operand(ps)))
+ postfix_append_operand(ps, curr_operand(ps));
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_pop(ps);
+ if (top_op == OP_NONE)
+ break;
+ if (top_op == OP_OPEN_PAREN) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
+ }
+ postfix_append_op(ps, top_op);
}
return 0;
+}
-oom:
- system->preds[i] = NULL;
- return -ENOMEM;
+static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+{
+ struct filter_pred *pred;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->field_name = kstrdup(operand1, GFP_KERNEL);
+ if (!pred->field_name) {
+ kfree(pred);
+ return NULL;
+ }
+
+ strcpy(pred->str_val, operand2);
+ pred->str_len = strlen(operand2);
+
+ pred->op = op;
+
+ return pred;
}
-int filter_parse(char **pbuf, struct filter_pred *pred)
+static struct filter_pred *create_logical_pred(int op)
{
- char *tmp, *tok, *val_str = NULL;
- int tok_n = 0;
+ struct filter_pred *pred;
- /* field ==/!= number, or/and field ==/!= number, number */
- while ((tok = strsep(pbuf, " \n"))) {
- if (tok_n == 0) {
- if (!strcmp(tok, "0")) {
- pred->clear = 1;
- return 0;
- } else if (!strcmp(tok, "&&")) {
- pred->or = 0;
- pred->compound = 1;
- } else if (!strcmp(tok, "||")) {
- pred->or = 1;
- pred->compound = 1;
- } else
- pred->field_name = tok;
- tok_n = 1;
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->op = op;
+
+ return pred;
+}
+
+static int check_preds(struct filter_parse_state *ps)
+{
+ int n_normal_preds = 0, n_logical_preds = 0;
+ struct postfix_elt *elt;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE)
+ continue;
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ n_logical_preds++;
continue;
}
- if (tok_n == 1) {
- if (!pred->field_name)
- pred->field_name = tok;
- else if (!strcmp(tok, "!="))
- pred->not = 1;
- else if (!strcmp(tok, "=="))
- pred->not = 0;
+ n_normal_preds++;
+ }
+
+ if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+ parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int replace_preds(struct event_subsystem *system,
+ struct ftrace_event_call *call,
+ struct filter_parse_state *ps,
+ char *filter_string)
+{
+ char *operand1 = NULL, *operand2 = NULL;
+ struct filter_pred *pred;
+ struct postfix_elt *elt;
+ int err;
+
+ err = check_preds(ps);
+ if (err)
+ return err;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE) {
+ if (!operand1)
+ operand1 = elt->operand;
+ else if (!operand2)
+ operand2 = elt->operand;
else {
- pred->field_name = NULL;
+ parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
return -EINVAL;
}
- tok_n = 2;
continue;
}
- if (tok_n == 2) {
- if (pred->compound) {
- if (!strcmp(tok, "!="))
- pred->not = 1;
- else if (!strcmp(tok, "=="))
- pred->not = 0;
- else {
- pred->field_name = NULL;
- return -EINVAL;
- }
- } else {
- val_str = tok;
- break; /* done */
- }
- tok_n = 3;
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ pred = create_logical_pred(elt->op);
+ if (call) {
+ err = filter_add_pred(ps, call, pred);
+ filter_free_pred(pred);
+ } else
+ err = filter_add_subsystem_pred(ps, system,
+ pred, filter_string);
+ if (err)
+ return err;
+
+ operand1 = operand2 = NULL;
continue;
}
- if (tok_n == 3) {
- val_str = tok;
- break; /* done */
+
+ if (!operand1 || !operand2) {
+ parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+ return -EINVAL;
}
+
+ pred = create_pred(elt->op, operand1, operand2);
+ if (call) {
+ err = filter_add_pred(ps, call, pred);
+ filter_free_pred(pred);
+ } else
+ err = filter_add_subsystem_pred(ps, system, pred,
+ filter_string);
+ if (err)
+ return err;
+
+ operand1 = operand2 = NULL;
}
- if (!val_str) {
- pred->field_name = NULL;
- return -EINVAL;
+ return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+ int err;
+
+ struct filter_parse_state *ps;
+
+ mutex_lock(&filter_mutex);
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
+ mutex_unlock(&filter_mutex);
+ return 0;
}
- pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
- if (!pred->field_name)
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
return -ENOMEM;
- pred->val = simple_strtoull(val_str, &tmp, 0);
- if (tmp == val_str) {
- pred->str_val = kstrdup(val_str, GFP_KERNEL);
- if (!pred->str_val)
- return -ENOMEM;
- } else if (*tmp != '\0')
- return -EINVAL;
+ filter_disable_preds(call);
+ replace_filter_string(call->filter, filter_string);
- return 0;
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, call->filter);
+ goto out;
+ }
+
+ err = replace_preds(NULL, call, ps, filter_string);
+ if (err)
+ append_filter_err(ps, call->filter);
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+
+ mutex_unlock(&filter_mutex);
+
+ return err;
}
+int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string)
+{
+ int err;
+
+ struct filter_parse_state *ps;
+
+ mutex_lock(&filter_mutex);
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_free_subsystem_preds(system);
+ remove_filter_string(system->filter);
+ mutex_unlock(&filter_mutex);
+ return 0;
+ }
+
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ return -ENOMEM;
+
+ filter_free_subsystem_preds(system);
+ replace_filter_string(system->filter, filter_string);
+
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, system->filter);
+ goto out;
+ }
+
+ err = replace_preds(system, NULL, ps, filter_string);
+ if (err)
+ append_filter_err(ps, system->filter);
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+
+ mutex_unlock(&filter_mutex);
+
+ return err;
+}
diff --git a/kernel/trace/trace_events_stage_1.h b/kernel/trace/trace_events_stage_1.h
deleted file mode 100644
index 38985f9b379..00000000000
--- a/kernel/trace/trace_events_stage_1.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Stage 1 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * struct ftrace_raw_<call> {
- * struct trace_entry ent;
- * <type> <item>;
- * <type2> <item2>[<len>];
- * [...]
- * };
- *
- * The <type> <item> is created by the __field(type, item) macro or
- * the __array(type2, item2, len) macro.
- * We simply do "type item;", and that will create the fields
- * in the structure.
- */
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)
-
-#undef __array
-#define __array(type, item, len) type item[len];
-
-#undef __field
-#define __field(type, item) type item;
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
- struct ftrace_raw_##name { \
- struct trace_entry ent; \
- tstruct \
- }; \
- static struct ftrace_event_call event_##name
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
deleted file mode 100644
index d363c6672c6..00000000000
--- a/kernel/trace/trace_events_stage_2.h
+++ /dev/null
@@ -1,176 +0,0 @@
-/*
- * Stage 2 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * enum print_line_t
- * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
- * {
- * struct trace_seq *s = &iter->seq;
- * struct ftrace_raw_<call> *field; <-- defined in stage 1
- * struct trace_entry *entry;
- * int ret;
- *
- * entry = iter->ent;
- *
- * if (entry->type != event_<call>.id) {
- * WARN_ON_ONCE(1);
- * return TRACE_TYPE_UNHANDLED;
- * }
- *
- * field = (typeof(field))entry;
- *
- * ret = trace_seq_printf(s, <TP_printk> "\n");
- * if (!ret)
- * return TRACE_TYPE_PARTIAL_LINE;
- *
- * return TRACE_TYPE_HANDLED;
- * }
- *
- * This is the method used to print the raw event to the trace
- * output format. Note, this is not needed if the data is read
- * in binary.
- */
-
-#undef __entry
-#define __entry field
-
-#undef TP_printk
-#define TP_printk(fmt, args...) fmt "\n", args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
-enum print_line_t \
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
-{ \
- struct trace_seq *s = &iter->seq; \
- struct ftrace_raw_##call *field; \
- struct trace_entry *entry; \
- int ret; \
- \
- entry = iter->ent; \
- \
- if (entry->type != event_##call.id) { \
- WARN_ON_ONCE(1); \
- return TRACE_TYPE_UNHANDLED; \
- } \
- \
- field = (typeof(field))entry; \
- \
- ret = trace_seq_printf(s, #call ": " print); \
- if (!ret) \
- return TRACE_TYPE_PARTIAL_LINE; \
- \
- return TRACE_TYPE_HANDLED; \
-}
-
-#include <trace/trace_event_types.h>
-
-/*
- * Setup the showing format of trace point.
- *
- * int
- * ftrace_format_##call(struct trace_seq *s)
- * {
- * struct ftrace_raw_##call field;
- * int ret;
- *
- * ret = trace_seq_printf(s, #type " " #item ";"
- * " offset:%u; size:%u;\n",
- * offsetof(struct ftrace_raw_##call, item),
- * sizeof(field.type));
- *
- * }
- */
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef __field
-#define __field(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%u;\tsize:%u;\n", \
- (unsigned int)offsetof(typeof(field), item), \
- (unsigned int)sizeof(field.item)); \
- if (!ret) \
- return 0;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%u;\tsize:%u;\n", \
- (unsigned int)offsetof(typeof(field), item), \
- (unsigned int)sizeof(field.item)); \
- if (!ret) \
- return 0;
-
-#undef __entry
-#define __entry REC
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
-static int \
-ftrace_format_##call(struct trace_seq *s) \
-{ \
- struct ftrace_raw_##call field; \
- int ret; \
- \
- tstruct; \
- \
- trace_seq_printf(s, "\nprint fmt: " print); \
- \
- return ret; \
-}
-
-#include <trace/trace_event_types.h>
-
-#undef __field
-#define __field(type, item) \
- ret = trace_define_field(event_call, #type, #item, \
- offsetof(typeof(field), item), \
- sizeof(field.item)); \
- if (ret) \
- return ret;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_define_field(event_call, #type "[" #len "]", #item, \
- offsetof(typeof(field), item), \
- sizeof(field.item)); \
- if (ret) \
- return ret;
-
-#define __common_field(type, item) \
- ret = trace_define_field(event_call, #type, "common_" #item, \
- offsetof(typeof(field.ent), item), \
- sizeof(field.ent.item)); \
- if (ret) \
- return ret;
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
-int \
-ftrace_define_fields_##call(void) \
-{ \
- struct ftrace_raw_##call field; \
- struct ftrace_event_call *event_call = &event_##call; \
- int ret; \
- \
- __common_field(unsigned char, type); \
- __common_field(unsigned char, flags); \
- __common_field(unsigned char, preempt_count); \
- __common_field(int, pid); \
- __common_field(int, tgid); \
- \
- tstruct; \
- \
- return ret; \
-}
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
deleted file mode 100644
index 9d2fa78cecc..00000000000
--- a/kernel/trace/trace_events_stage_3.h
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Stage 3 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * static void ftrace_event_<call>(proto)
- * {
- * event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(void)
- * {
- * int ret;
- *
- * ret = register_trace_<call>(ftrace_event_<call>);
- * if (!ret)
- * pr_info("event trace: Could not activate trace point "
- * "probe to <call>");
- * return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- * For those macros defined with TRACE_FORMAT:
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- * .name = "<call>",
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
- * }
- *
- *
- * For those macros defined with TRACE_EVENT:
- *
- * static struct ftrace_event_call event_<call>;
- *
- * static void ftrace_raw_event_<call>(proto)
- * {
- * struct ring_buffer_event *event;
- * struct ftrace_raw_<call> *entry; <-- defined in stage 1
- * unsigned long irq_flags;
- * int pc;
- *
- * local_save_flags(irq_flags);
- * pc = preempt_count();
- *
- * event = trace_current_buffer_lock_reserve(event_<call>.id,
- * sizeof(struct ftrace_raw_<call>),
- * irq_flags, pc);
- * if (!event)
- * return;
- * entry = ring_buffer_event_data(event);
- *
- * <assign>; <-- Here we assign the entries by the __field and
- * __array macros.
- *
- * trace_current_buffer_unlock_commit(event, irq_flags, pc);
- * }
- *
- * static int ftrace_raw_reg_event_<call>(void)
- * {
- * int ret;
- *
- * ret = register_trace_<call>(ftrace_raw_event_<call>);
- * if (!ret)
- * pr_info("event trace: Could not activate trace point "
- * "probe to <call>");
- * return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static struct trace_event ftrace_event_type_<call> = {
- * .trace = ftrace_raw_output_<call>, <-- stage 2
- * };
- *
- * static int ftrace_raw_init_event_<call>(void)
- * {
- * int id;
- *
- * id = register_ftrace_event(&ftrace_event_type_<call>);
- * if (!id)
- * return -ENODEV;
- * event_<call>.id = id;
- * return 0;
- * }
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- * .name = "<call>",
- * .system = "<system>",
- * .raw_init = ftrace_raw_init_event_<call>,
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
- * .show_format = ftrace_format_<call>,
- * }
- *
- */
-
-#undef TP_FMT
-#define TP_FMT(fmt, args...) fmt "\n", ##args
-
-#ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args) \
-static void ftrace_profile_##call(proto) \
-{ \
- extern void perf_tpcounter_event(int); \
- perf_tpcounter_event(event_##call.id); \
-} \
- \
-static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \
-{ \
- int ret = 0; \
- \
- if (!atomic_inc_return(&call->profile_count)) \
- ret = register_trace_##call(ftrace_profile_##call); \
- \
- return ret; \
-} \
- \
-static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \
-{ \
- if (atomic_add_negative(-1, &call->profile_count)) \
- unregister_trace_##call(ftrace_profile_##call); \
-}
-
-#define _TRACE_PROFILE_INIT(call) \
- .profile_count = ATOMIC_INIT(-1), \
- .profile_enable = ftrace_profile_enable_##call, \
- .profile_disable = ftrace_profile_disable_##call,
-
-#else
-#define _TRACE_PROFILE(call, proto, args)
-#define _TRACE_PROFILE_INIT(call)
-#endif
-
-#define _TRACE_FORMAT(call, proto, args, fmt) \
-static void ftrace_event_##call(proto) \
-{ \
- event_trace_printk(_RET_IP_, #call ": " fmt); \
-} \
- \
-static int ftrace_reg_event_##call(void) \
-{ \
- int ret; \
- \
- ret = register_trace_##call(ftrace_event_##call); \
- if (ret) \
- pr_info("event trace: Could not activate trace point " \
- "probe to " #call "\n"); \
- return ret; \
-} \
- \
-static void ftrace_unreg_event_##call(void) \
-{ \
- unregister_trace_##call(ftrace_event_##call); \
-} \
- \
-static struct ftrace_event_call event_##call; \
- \
-static int ftrace_init_event_##call(void) \
-{ \
- int id; \
- \
- id = register_ftrace_event(NULL); \
- if (!id) \
- return -ENODEV; \
- event_##call.id = id; \
- return 0; \
-}
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt) \
-_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt)) \
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \
-static struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
- .name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_init_event_##call, \
- .regfunc = ftrace_reg_event_##call, \
- .unregfunc = ftrace_unreg_event_##call, \
- _TRACE_PROFILE_INIT(call) \
-}
-
-#undef __entry
-#define __entry entry
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \
- \
-static struct ftrace_event_call event_##call; \
- \
-static void ftrace_raw_event_##call(proto) \
-{ \
- struct ftrace_event_call *call = &event_##call; \
- struct ring_buffer_event *event; \
- struct ftrace_raw_##call *entry; \
- unsigned long irq_flags; \
- int pc; \
- \
- local_save_flags(irq_flags); \
- pc = preempt_count(); \
- \
- event = trace_current_buffer_lock_reserve(event_##call.id, \
- sizeof(struct ftrace_raw_##call), \
- irq_flags, pc); \
- if (!event) \
- return; \
- entry = ring_buffer_event_data(event); \
- \
- assign; \
- \
- if (call->preds && !filter_match_preds(call, entry)) \
- ring_buffer_event_discard(event); \
- \
- trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
- \
-} \
- \
-static int ftrace_raw_reg_event_##call(void) \
-{ \
- int ret; \
- \
- ret = register_trace_##call(ftrace_raw_event_##call); \
- if (ret) \
- pr_info("event trace: Could not activate trace point " \
- "probe to " #call "\n"); \
- return ret; \
-} \
- \
-static void ftrace_raw_unreg_event_##call(void) \
-{ \
- unregister_trace_##call(ftrace_raw_event_##call); \
-} \
- \
-static struct trace_event ftrace_event_type_##call = { \
- .trace = ftrace_raw_output_##call, \
-}; \
- \
-static int ftrace_raw_init_event_##call(void) \
-{ \
- int id; \
- \
- id = register_ftrace_event(&ftrace_event_type_##call); \
- if (!id) \
- return -ENODEV; \
- event_##call.id = id; \
- INIT_LIST_HEAD(&event_##call.fields); \
- return 0; \
-} \
- \
-static struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
- .name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_raw_init_event_##call, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
- .show_format = ftrace_format_##call, \
- .define_fields = ftrace_define_fields_##call, \
- _TRACE_PROFILE_INIT(call) \
-}
-
-#include <trace/trace_event_types.h>
-
-#undef _TRACE_PROFILE
-#undef _TRACE_PROFILE_INIT
-
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 07a22c33ebf..d06cf898dc8 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -19,8 +19,12 @@
#undef TRACE_STRUCT
#define TRACE_STRUCT(args...) args
+extern void __bad_type_size(void);
+
#undef TRACE_FIELD
#define TRACE_FIELD(type, item, assign) \
+ if (sizeof(type) != sizeof(field.item)) \
+ __bad_type_size(); \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
"offset:%u;\tsize:%u;\n", \
(unsigned int)offsetof(typeof(field), item), \
@@ -30,7 +34,7 @@
#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t" \
"offset:%u;\tsize:%u;\n", \
(unsigned int)offsetof(typeof(field), item), \
@@ -46,6 +50,9 @@
if (!ret) \
return 0;
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ TRACE_FIELD(type, item, assign)
#undef TP_RAW_FMT
#define TP_RAW_FMT(args...) args
@@ -65,6 +72,22 @@ ftrace_format_##call(struct trace_seq *s) \
return ret; \
}
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt) \
+static int \
+ftrace_format_##call(struct trace_seq *s) \
+{ \
+ struct args field; \
+ int ret; \
+ \
+ tstruct; \
+ \
+ trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \
+ \
+ return ret; \
+}
+
#include "trace_event_types.h"
#undef TRACE_ZERO_CHAR
@@ -78,6 +101,10 @@ ftrace_format_##call(struct trace_seq *s) \
#define TRACE_FIELD(type, item, assign)\
entry->item = assign;
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ TRACE_FIELD(type, item, assign)
+
#undef TP_CMD
#define TP_CMD(cmd...) cmd
@@ -85,18 +112,95 @@ ftrace_format_##call(struct trace_seq *s) \
#define TRACE_ENTRY entry
#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
cmd;
#undef TRACE_EVENT_FORMAT
#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+int ftrace_define_fields_##call(void); \
+static int ftrace_raw_init_event_##call(void); \
+ \
+struct ftrace_event_call __used \
+__attribute__((__aligned__(4))) \
+__attribute__((section("_ftrace_events"))) event_##call = { \
+ .name = #call, \
+ .id = proto, \
+ .system = __stringify(TRACE_SYSTEM), \
+ .raw_init = ftrace_raw_init_event_##call, \
+ .show_format = ftrace_format_##call, \
+ .define_fields = ftrace_define_fields_##call, \
+}; \
+static int ftrace_raw_init_event_##call(void) \
+{ \
+ INIT_LIST_HEAD(&event_##call.fields); \
+ init_preds(&event_##call); \
+ return 0; \
+} \
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt) \
\
-static struct ftrace_event_call __used \
+struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = proto, \
.system = __stringify(TRACE_SYSTEM), \
.show_format = ftrace_format_##call, \
+};
+
+#include "trace_event_types.h"
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_SPECIAL
+#define TRACE_FIELD_SPECIAL(type, item, len, cmd) \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), 0); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_ZERO_CHAR
+#define TRACE_FIELD_ZERO_CHAR(item)
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+int \
+ftrace_define_fields_##call(void) \
+{ \
+ struct ftrace_event_call *event_call = &event_##call; \
+ struct args field; \
+ int ret; \
+ \
+ __common_field(unsigned char, type, 0); \
+ __common_field(unsigned char, flags, 0); \
+ __common_field(unsigned char, preempt_count, 0); \
+ __common_field(int, pid, 1); \
+ __common_field(int, tgid, 1); \
+ \
+ tstruct; \
+ \
+ return ret; \
}
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt)
+
#include "trace_event_types.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d28687e7b3a..10f6ad7d85f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -78,13 +78,14 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
+ current->ret_stack[index].subtime = 0;
*depth = index;
return 0;
}
/* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
{
int index;
@@ -104,9 +105,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(&current->trace_overrun);
trace->depth = index;
- barrier();
- current->curr_ret_stack--;
-
}
/*
@@ -121,6 +119,8 @@ unsigned long ftrace_return_to_handler(void)
ftrace_pop_return_trace(&trace, &ret);
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
+ barrier();
+ current->curr_ret_stack--;
if (unlikely(!ret)) {
ftrace_graph_stop();
@@ -426,8 +426,8 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
{
unsigned long nsecs_rem = do_div(duration, 1000);
/* log10(ULONG_MAX) + '\0' */
@@ -464,12 +464,23 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_print_graph_duration(duration, s);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
ret = trace_seq_printf(s, "| ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
- return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_HANDLED;
}
/* Case of a leaf function on its call entry */
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 50565d8cd2e..ca7d7c4d0c2 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -162,6 +162,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
void trace_hw_branch(u64 from, u64 to)
{
+ struct ftrace_event_call *call = &event_hw_branch;
struct trace_array *tr = hw_branch_trace;
struct ring_buffer_event *event;
struct hw_branch_entry *entry;
@@ -188,7 +189,8 @@ void trace_hw_branch(u64 from, u64 to)
entry->ent.type = TRACE_HW_BRANCHES;
entry->from = from;
entry->to = to;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
atomic_dec(&tr->data[cpu]->disabled);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 8e37fcddd8b..d53b45ed080 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,8 @@
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
+#include <linux/time.h>
+
#include <asm/atomic.h>
#include "trace.h"
@@ -174,7 +176,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
struct mmiotrace_rw *rw;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
- unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret = 1;
@@ -221,7 +223,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter)
struct mmiotrace_map *m;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
- unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 64b54a59c55..8bd9a2c1a46 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -19,6 +19,16 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
+void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+ int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+
+ s->buffer[len] = 0;
+ seq_puts(m, s->buffer);
+
+ trace_seq_init(s);
+}
+
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
@@ -84,6 +94,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
return len;
}
+EXPORT_SYMBOL_GPL(trace_seq_printf);
int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
{
@@ -472,6 +483,36 @@ struct trace_event *ftrace_find_event(int type)
return NULL;
}
+static LIST_HEAD(ftrace_event_list);
+
+static int trace_search_list(struct list_head **list)
+{
+ struct trace_event *e;
+ int last = __TRACE_LAST_TYPE;
+
+ if (list_empty(&ftrace_event_list)) {
+ *list = &ftrace_event_list;
+ return last + 1;
+ }
+
+ /*
+ * We used up all possible max events,
+ * lets see if somebody freed one.
+ */
+ list_for_each_entry(e, &ftrace_event_list, list) {
+ if (e->type != last + 1)
+ break;
+ last++;
+ }
+
+ /* Did we used up all 65 thousand events??? */
+ if ((last + 1) > FTRACE_MAX_EVENT)
+ return 0;
+
+ *list = &e->list;
+ return last + 1;
+}
+
/**
* register_ftrace_event - register output for an event type
* @event: the event type to register
@@ -494,20 +535,40 @@ int register_ftrace_event(struct trace_event *event)
mutex_lock(&trace_event_mutex);
- if (!event) {
- ret = next_event_type++;
+ if (WARN_ON(!event))
goto out;
- }
- if (!event->type)
- event->type = next_event_type++;
- else if (event->type > __TRACE_LAST_TYPE) {
+ INIT_LIST_HEAD(&event->list);
+
+ if (!event->type) {
+ struct list_head *list = NULL;
+
+ if (next_event_type > FTRACE_MAX_EVENT) {
+
+ event->type = trace_search_list(&list);
+ if (!event->type)
+ goto out;
+
+ } else {
+
+ event->type = next_event_type++;
+ list = &ftrace_event_list;
+ }
+
+ if (WARN_ON(ftrace_find_event(event->type)))
+ goto out;
+
+ list_add_tail(&event->list, list);
+
+ } else if (event->type > __TRACE_LAST_TYPE) {
printk(KERN_WARNING "Need to add type to trace.h\n");
WARN_ON(1);
- }
-
- if (ftrace_find_event(event->type))
goto out;
+ } else {
+ /* Is this event already used */
+ if (ftrace_find_event(event->type))
+ goto out;
+ }
if (event->trace == NULL)
event->trace = trace_nop_print;
@@ -528,6 +589,7 @@ int register_ftrace_event(struct trace_event *event)
return ret;
}
+EXPORT_SYMBOL_GPL(register_ftrace_event);
/**
* unregister_ftrace_event - remove a no longer used event
@@ -537,10 +599,12 @@ int unregister_ftrace_event(struct trace_event *event)
{
mutex_lock(&trace_event_mutex);
hlist_del(&event->node);
+ list_del(&event->list);
mutex_unlock(&trace_event_mutex);
return 0;
}
+EXPORT_SYMBOL_GPL(unregister_ftrace_event);
/*
* Standard events
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index e0bde39c2dd..6e220a8e570 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -1,41 +1,17 @@
#ifndef __TRACE_EVENTS_H
#define __TRACE_EVENTS_H
+#include <linux/trace_seq.h>
#include "trace.h"
-typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
- int flags);
-
-struct trace_event {
- struct hlist_node node;
- int type;
- trace_print_func trace;
- trace_print_func raw;
- trace_print_func hex;
- trace_print_func binary;
-};
-
extern enum print_line_t
trace_print_bprintk_msg_only(struct trace_iterator *iter);
extern enum print_line_t
trace_print_printk_msg_only(struct trace_iterator *iter);
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
- __attribute__ ((format (printf, 2, 3)));
-extern int
-trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
extern int
seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
unsigned long sym_flags);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
- size_t cnt);
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
-extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
- size_t len);
-extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
-extern int trace_seq_path(struct trace_seq *s, struct path *path);
extern int seq_print_userip_objs(const struct userstack_entry *entry,
struct trace_seq *s, unsigned long sym_flags);
extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
@@ -45,8 +21,6 @@ extern int trace_print_context(struct trace_iterator *iter);
extern int trace_print_lat_context(struct trace_iterator *iter);
extern struct trace_event *ftrace_find_event(int type);
-extern int register_ftrace_event(struct trace_event *event);
-extern int unregister_ftrace_event(struct trace_event *event);
extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
int flags);
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 118439709fb..8a30d9874cd 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -36,6 +36,7 @@ static void probe_power_start(struct power_trace *it, unsigned int type,
static void probe_power_end(struct power_trace *it)
{
+ struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
@@ -54,7 +55,8 @@ static void probe_power_end(struct power_trace *it)
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
@@ -62,6 +64,7 @@ static void probe_power_end(struct power_trace *it)
static void probe_power_mark(struct power_trace *it, unsigned int type,
unsigned int level)
{
+ struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
@@ -84,7 +87,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index eb81556107f..9bece9687b6 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -245,17 +245,13 @@ static const struct file_operations ftrace_formats_fops = {
static __init int init_trace_printk_function_export(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
if (!d_tracer)
return 0;
- entry = debugfs_create_file("printk_formats", 0444, d_tracer,
+ trace_create_file("printk_formats", 0444, d_tracer,
NULL, &ftrace_formats_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'printk_formats' entry\n");
return 0;
}
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 9117cea6f1a..a98106dd979 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -10,7 +10,7 @@
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include "trace.h"
@@ -29,13 +29,13 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
int cpu;
int pc;
- if (!sched_ref || sched_stopped)
+ if (unlikely(!sched_ref))
return;
tracing_record_cmdline(prev);
tracing_record_cmdline(next);
- if (!tracer_enabled)
+ if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
@@ -56,15 +56,15 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
unsigned long flags;
int cpu, pc;
- if (!likely(tracer_enabled))
+ if (unlikely(!sched_ref))
return;
- pc = preempt_count();
tracing_record_cmdline(current);
- if (sched_stopped)
+ if (!tracer_enabled || sched_stopped)
return;
+ pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5bc00e8f153..eacb2722517 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -15,7 +15,7 @@
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include "trace.h"
@@ -138,9 +138,6 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
pc = preempt_count();
- /* The task we are waiting for is waking up */
- data = wakeup_trace->data[wakeup_cpu];
-
/* disable local data, not wakeup_cpu data */
cpu = raw_smp_processor_id();
disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
@@ -154,6 +151,9 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
if (unlikely(!tracer_enabled || next != wakeup_task))
goto out_unlock;
+ /* The task we are waiting for is waking up */
+ data = wakeup_trace->data[wakeup_cpu];
+
trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c750f65f966..1796f00524e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -352,19 +352,14 @@ __setup("stacktrace", enable_stacktrace);
static __init int stack_trace_init(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
- &max_stack_size, &stack_max_size_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+ trace_create_file("stack_max_size", 0644, d_tracer,
+ &max_stack_size, &stack_max_size_fops);
- entry = debugfs_create_file("stack_trace", 0444, d_tracer,
- NULL, &stack_trace_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'stack_trace' entry\n");
+ trace_create_file("stack_trace", 0444, d_tracer,
+ NULL, &stack_trace_fops);
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index acdebd771a9..fdde3a4a94c 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -85,7 +85,7 @@ static int stat_seq_init(struct tracer_stat_session *session)
if (!ts->stat_cmp)
ts->stat_cmp = dummy_cmp;
- stat = ts->stat_start();
+ stat = ts->stat_start(ts);
if (!stat)
goto exit;
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 202274cf7f3..f3546a2cd82 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -12,7 +12,7 @@ struct tracer_stat {
/* The name of your stat file */
const char *name;
/* Iteration over statistic entries */
- void *(*stat_start)(void);
+ void *(*stat_start)(struct tracer_stat *trace);
void *(*stat_next)(void *prev, int idx);
/* Compare two entries for stats sorting */
int (*stat_cmp)(void *p1, void *p2);
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 91fd19c2149..e04b76cc238 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -321,11 +321,7 @@ static const struct file_operations sysprof_sample_fops = {
void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
{
- struct dentry *entry;
- entry = debugfs_create_file("sysprof_sample_period", 0644,
+ trace_create_file("sysprof_sample_period", 0644,
d_tracer, NULL, &sysprof_sample_fops);
- if (entry)
- return;
- pr_warning("Could not create debugfs 'sysprof_sample_period' entry\n");
}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 797201e4a13..984b9175c13 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -152,7 +152,7 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
return ret;
}
-static void *workqueue_stat_start(void)
+static void *workqueue_stat_start(struct tracer_stat *trace)
{
int cpu;
void *ret = NULL;