/*
* Cross CPU call to read the hardware event
*/
static void __perf_event_read(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
/*
* If this is a task context, we need to check whether it is
* the current task context of this cpu. If not it has been
* scheduled out before the smp call arrived. In that case
* event->count would have been updated to a recent sample
* when the event was scheduled out.
*/
if (ctx->task && cpuctx->task_ctx != ctx)
return;
raw_spin_lock(&ctx->lock);
if (ctx->is_active) {
update_context_time(ctx);
update_cgrp_time_from_event(event);
}
update_event_times(event);
if (event->state == PERF_EVENT_STATE_ACTIVE)
event->pmu->read(event);
raw_spin_unlock(&ctx->lock);
}
static inline u64 perf_event_count(struct perf_event *event)
{
if (event->pmu->count)
return event->pmu->count(event);
return __perf_event_count(event);
}
static u64 perf_event_read(struct perf_event *event)
{
/*
* If event is enabled and currently active on a CPU, update the
* value in the event structure:
*/
if (event->state == PERF_EVENT_STATE_ACTIVE) {
smp_call_function_single(event->oncpu,
__perf_event_read, event, 1);
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
raw_spin_lock_irqsave(&ctx->lock, flags);
/*
* may read while context is not active
* (e.g., thread is blocked), in that case
* we cannot update context time
*/
if (ctx->is_active) {
update_context_time(ctx);
update_cgrp_time_from_event(event);
}
update_event_times(event);
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
return perf_event_count(event);
}
/*
* Initialize the perf_event context in a task_struct:
*/
static void __perf_event_init_context(struct perf_event_context *ctx)
{
raw_spin_lock_init(&ctx->lock);
mutex_init(&ctx->mutex);
INIT_LIST_HEAD(&ctx->active_ctx_list);
INIT_LIST_HEAD(&ctx->pinned_groups);
INIT_LIST_HEAD(&ctx->flexible_groups);
INIT_LIST_HEAD(&ctx->event_list);
atomic_set(&ctx->refcount, 1);
INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
}
static struct perf_event_context *
alloc_perf_context(struct pmu *pmu, struct task_struct *task)
{
struct perf_event_context *ctx;
ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
if (!ctx)
return NULL;
__perf_event_init_context(ctx);
if (task) {
ctx->task = task;
get_task_struct(task);
}
ctx->pmu = pmu;
return ctx;
}
static struct task_struct *
find_lively_task_by_vpid(pid_t vpid)
{
struct task_struct *task;
int err;
rcu_read_lock();
if (!vpid)
task = current;
else
task = find_task_by_vpid(vpid);
if (task)
get_task_struct(task);
rcu_read_unlock();
if (!task)
return ERR_PTR(-ESRCH);
/* Reuse ptrace permission checks for now. */
err = -EACCES;
if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto errout;
return task;
errout:
put_task_struct(task);
return ERR_PTR(err);
}
/*
* Returns a matching context with refcount and pincount.
*/
static struct perf_event_context *
find_get_context(struct pmu *pmu, struct task_struct *task,
struct perf_event *event)
{
struct perf_event_context *ctx, *clone_ctx = NULL;
struct perf_cpu_context *cpuctx;
void *task_ctx_data = NULL;
unsigned long flags;
int ctxn, err;
int cpu = event->cpu;
if (!task) {
/* Must be root to operate on a CPU event: */
if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
return ERR_PTR(-EACCES);
/*
* We could be clever and allow to attach a event to an
* offline CPU and activate it when the CPU comes up, but
* that's for later.
*/
if (!cpu_online(cpu))
return ERR_PTR(-ENODEV);
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
ctx = &cpuctx->ctx;
get_ctx(ctx);
++ctx->pin_count;
return ctx;
}
err = -EINVAL;
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto errout;
if (event->attach_state & PERF_ATTACH_TASK_DATA) {
task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
if (!task_ctx_data) {
err = -ENOMEM;
goto errout;
}
}
retry:
ctx = perf_lock_task_context(task, ctxn, &flags);
if (ctx) {
clone_ctx = unclone_ctx(ctx);
++ctx->pin_count;
if (task_ctx_data && !ctx->task_ctx_data) {
ctx->task_ctx_data = task_ctx_data;
task_ctx_data = NULL;
}
raw_spin_unlock_irqrestore(&ctx->lock, flags);
if (clone_ctx)
put_ctx(clone_ctx);
} else {
ctx = alloc_perf_context(pmu, task);
err = -ENOMEM;
if (!ctx)
goto errout;
if (task_ctx_data) {
ctx->task_ctx_data = task_ctx_data;
task_ctx_data = NULL;
}
err = 0;
mutex_lock(&task->perf_event_mutex);
/*
* If it has already passed perf_event_exit_task().
* we must see PF_EXITING, it takes this mutex too.
*/
if (task->flags & PF_EXITING)
err = -ESRCH;
else if (task->perf_event_ctxp[ctxn])
err = -EAGAIN;
else {
get_ctx(ctx);
++ctx->pin_count;
rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
}
mutex_unlock(&task->perf_event_mutex);
if (unlikely(err)) {
put_ctx(ctx);
if (err == -EAGAIN)
goto retry;
goto errout;
}
}
kfree(task_ctx_data);
return ctx;
errout:
kfree(task_ctx_data);
return ERR_PTR(err);
}
static void perf_event_free_filter(struct perf_event *event);
static void perf_event_free_bpf_prog(struct perf_event *event);
static void free_event_rcu(struct rcu_head *head)
{
struct perf_event *event;
event = container_of(head, struct perf_event, rcu_head);
if (event->ns)
put_pid_ns(event->ns);
perf_event_free_filter(event);
kfree(event);
}
static void ring_buffer_attach(struct perf_event *event,
struct ring_buffer *rb);
static void unaccount_event_cpu(struct perf_event *event, int cpu)
{
if (event->parent)
return;
if (is_cgroup_event(event))
atomic_dec(&per_cpu(perf_cgroup_events, cpu));
}
static void unaccount_event(struct perf_event *event)
{
if (event->parent)
return;
if (event->attach_state & PERF_ATTACH_TASK)
static_key_slow_dec_deferred(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
atomic_dec(&nr_comm_events);
if (event->attr.task)
atomic_dec(&nr_task_events);
if (event->attr.freq)
atomic_dec(&nr_freq_events);
if (is_cgroup_event(event))
static_key_slow_dec_deferred(&perf_sched_events);
if (has_branch_stack(event))
static_key_slow_dec_deferred(&perf_sched_events);
unaccount_event_cpu(event, event->cpu);
}
/*
* The following implement mutual exclusion of events on "exclusive" pmus
* (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
* at a time, so we disallow creating events that might conflict, namely:
*
* 1) cpu-wide events in the presence of per-task events,
* 2) per-task events in the presence of cpu-wide events,
* 3) two matching events on the same context.
*
* The former two cases are handled in the allocation path (perf_event_alloc(),
* __free_event()), the latter -- before the first perf_install_in_context().
*/
static int exclusive_event_init(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return 0;
/*
* Prevent co-existence of per-task and cpu-wide events on the
* same exclusive pmu.
*
* Negative pmu::exclusive_cnt means there are cpu-wide
* events on this "exclusive" pmu, positive means there are
* per-task events.
*
* Since this is called in perf_event_alloc() path, event::ctx
* doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK
* to mean "per-task event", because unlike other attach states it
* never gets cleared.
*/
if (event->attach_state & PERF_ATTACH_TASK) {
if (!atomic_inc_unless_negative(&pmu->exclusive_cnt))
return -EBUSY;
} else {
if (!atomic_dec_unless_positive(&pmu->exclusive_cnt))
return -EBUSY;
}
return 0;
}
static void exclusive_event_destroy(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return;
/* see comment in exclusive_event_init() */
if (event->attach_state & PERF_ATTACH_TASK)
atomic_dec(&pmu->exclusive_cnt);
else
atomic_inc(&pmu->exclusive_cnt);
}
static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
{
if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
(e1->cpu == e2->cpu ||
e1->cpu == -1 ||
e2->cpu == -1))
return true;
return false;
}
/* Called under the same ctx::mutex as perf_install_in_context() */
static bool exclusive_event_installable(struct perf_event *event,
struct perf_event_context *ctx)
{
struct perf_event *iter_event;
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return true;
list_for_each_entry(iter_event, &ctx->event_list, event_entry) {
if (exclusive_event_match(iter_event, event))
return false;
}
return true;
}
static void __free_event(struct perf_event *event)
{
if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
put_callchain_buffers();
}
perf_event_free_bpf_prog(event);
if (event->destroy)
event->destroy(event);
if (event->ctx)
put_ctx(event->ctx);
if (event->pmu) {
exclusive_event_destroy(event);
module_put(event->pmu->module);
}
call_rcu(&event->rcu_head, free_event_rcu);
}
static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
unaccount_event(event);
if (event->rb) {
/*
* Can happen when we close an event with re-directed output.
*
* Since we have a 0 refcount, perf_mmap_close() will skip
* over us; possibly making our ring_buffer_put() the last.
*/
mutex_lock(&event->mmap_mutex);
ring_buffer_attach(event, NULL);
mutex_unlock(&event->mmap_mutex);
}
if (is_cgroup_event(event))
perf_detach_cgroup(event);
__free_event(event);
}
/*
* Used to free events which have a known refcount of 1, such as in error paths
* where the event isn't exposed yet and inherited events.
*/
static void free_event(struct perf_event *event)
{
if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
"unexpected event refcount: %ld; ptr=%p\n",
atomic_long_read(&event->refcount), event)) {
/* leak to avoid use-after-free */
return;
}
_free_event(event);
}
/*
* Remove user event from the owner task.
*/
static void perf_remove_from_owner(struct perf_event *event)
{
struct task_struct *owner;
rcu_read_lock();
owner = ACCESS_ONCE(event->owner);
/*
* Matches the smp_wmb() in perf_event_exit_task(). If we observe
* !owner it means the list deletion is complete and we can indeed
* free this event, otherwise we need to serialize on
* owner->perf_event_mutex.
*/
smp_read_barrier_depends();
if (owner) {
/*
* Since delayed_put_task_struct() also drops the last
* task reference we can safely take a new reference
* while holding the rcu_read_lock().
*/
get_task_struct(owner);
}
rcu_read_unlock();
if (owner) {
/*
* If we're here through perf_event_exit_task() we're already
* holding ctx->mutex which would be an inversion wrt. the
* normal lock order.
*
* However we can safely take this lock because its the child
* ctx->mutex.
*/
mutex_lock_nested(&owner->perf_event_mutex, SINGLE_DEPTH_NESTING);
/*
* We have to re-check the event->owner field, if it is cleared
* we raced with perf_event_exit_task(), acquiring the mutex
* ensured they're done, and we can proceed with freeing the
* event.
*/
if (event->owner)
list_del_init(&event->owner_entry);
mutex_unlock(&owner->perf_event_mutex);
put_task_struct(owner);
}
}
static void put_event(struct perf_event *event)
{
struct perf_event_context *ctx;
if (!atomic_long_dec_and_test(&event->refcount))
return;
if (!is_kernel_event(event))
perf_remove_from_owner(event);
/*
* There are two ways this annotation is useful:
*
* 1) there is a lock recursion from perf_event_exit_task
* see the comment there.
*
* 2) there is a lock-inversion with mmap_sem through
* perf_event_read_group(), which takes faults while
* holding ctx->mutex, however this is called after
* the last filedesc died, so there is no possibility
* to trigger the AB-BA case.
*/
ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
WARN_ON_ONCE(ctx->parent_ctx);
perf_remove_from_context(event, true);
perf_event_ctx_unlock(event, ctx);
_free_event(event);
}
int perf_event_release_kernel(struct perf_event *event)
{
put_event(event);
return 0;
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);
/*
* Called when the last reference to the file is gone.
*/
static int perf_release(struct inode *inode, struct file *file)
{
put_event(file->private_data);
return 0;
}
/*
* Remove all orphanes events from the context.
*/
static void orphans_remove_work(struct work_struct *work)
{
struct perf_event_context *ctx;
struct perf_event *event, *tmp;
ctx = container_of(work, struct perf_event_context,
orphans_remove.work);
mutex_lock(&ctx->mutex);
list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
struct perf_event *parent_event = event->parent;
if (!is_orphaned_child(event))
continue;
perf_remove_from_context(event, true);
mutex_lock(&parent_event->child_mutex);
list_del_init(&event->child_list);
mutex_unlock(&parent_event->child_mutex);
free_event(event);
put_event(parent_event);
}
raw_spin_lock_irq(&ctx->lock);
ctx->orphans_remove_sched = false;
raw_spin_unlock_irq(&ctx->lock);
mutex_unlock(&ctx->mutex);
put_ctx(ctx);
}
u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
{
struct perf_event *child;
u64 total = 0;
*enabled = 0;
*running = 0;
mutex_lock(&event->child_mutex);
total += perf_event_read(event);
*enabled += event->total_time_enabled +
atomic64_read(&event->child_total_time_enabled);
*running += event->total_time_running +
atomic64_read(&event->child_total_time_running);
list_for_each_entry(child, &event->child_list, child_list) {
total += perf_event_read(child);
*enabled += child->total_time_enabled;
*running += child->total_time_running;
}
mutex_unlock(&event->child_mutex);
return total;
}
EXPORT_SYMBOL_GPL(perf_event_read_value);
static int perf_event_read_group(struct perf_event *event,
u64 read_format, char __user *buf)
{
struct perf_event *leader = event->group_leader, *sub;
struct perf_event_context *ctx = leader->ctx;
int n = 0, size = 0, ret;
u64 count, enabled, running;
u64 values[5];
lockdep_assert_held(&ctx->mutex);
count = perf_event_read_value(leader, &enabled, &running);
values[n++] = 1 + leader->nr_siblings;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
values[n++] = running;
values[n++] = count;
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
size = n * sizeof(u64);
if (copy_to_user(buf, values, size))
return -EFAULT;
ret = size;
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
n = 0;
values[n++] = perf_event_read_value(sub, &enabled, &running);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
size = n * sizeof(u64);
if (copy_to_user(buf + ret, values, size)) {
return -EFAULT;
}
ret += size;
}
return ret;
}
static int perf_event_read_one(struct perf_event *event,
u64 read_format, char __user *buf)
{
u64 enabled, running;
u64 values[4];
int n = 0;
values[n++] = perf_event_read_value(event, &enabled, &running);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
values[n++] = running;
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(event);
if (copy_to_user(buf, values, n * sizeof(u64)))
return -EFAULT;
return n * sizeof(u64);
}
static bool is_event_hup(struct perf_event *event)
{
bool no_children;
if (event->state != PERF_EVENT_STATE_EXIT)
return false;
mutex_lock(&event->child_mutex);
no_children = list_empty(&event->child_list);
mutex_unlock(&event->child_mutex);
return no_children;
}
/*
* Read the performance event - simple non blocking version for now
*/
static ssize_t
perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
{
u64 read_format = event->attr.read_format;
int ret;
/*
* Return end-of-file for a read on a event that is in
* error state (i.e. because it was pinned but it couldn't be
* scheduled on to the CPU at some point).
*/
if (event->state == PERF_EVENT_STATE_ERROR)
return 0;
if (count < event->read_size)
return -ENOSPC;
WARN_ON_ONCE(event->ctx->parent_ctx);
if (read_format & PERF_FORMAT_GROUP)
ret = perf_event_read_group(event, read_format, buf);
else
ret = perf_event_read_one(event, read_format, buf);
return ret;
}
static ssize_t
perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
struct perf_event *event = file->private_data;
struct perf_event_context *ctx;
int ret;
ctx = perf_event_ctx_lock(event);
ret = perf_read_hw(event, buf, count);
perf_event_ctx_unlock(event, ctx);
return ret;
}
static unsigned int perf_poll(struct file *file, poll_table *wait)
{
struct perf_event *event = file->private_data;
struct ring_buffer *rb;
unsigned int events = POLLHUP;
poll_wait(file, &event->waitq, wait);
if (is_event_hup(event))
return events;
/*
* Pin the event->rb by taking event->mmap_mutex; otherwise
* perf_event_set_output() can swizzle our rb and make us miss wakeups.
*/
mutex_lock(&event->mmap_mutex);
rb = event->rb;
if (rb)
events = atomic_xchg(&rb->poll, 0);
mutex_unlock(&event->mmap_mutex);
return events;
}
static void _perf_event_reset(struct perf_event *event)
{
(void)perf_event_read(event);
local64_set(&event->count, 0);
perf_event_update_userpage(event);
}
/*
* Holding the top-level event's child_mutex means that any
* descendant process that has inherited this event will block
* in sync_child_event if it goes to exit, thus satisfying the
* task existence requirements of perf_event_enable/disable.
*/
static void perf_event_for_each_child(struct perf_event *event,
void (*func)(struct perf_event *))
{
struct perf_event *child;
WARN_ON_ONCE(event->ctx->parent_ctx);
mutex_lock(&event->child_mutex);
func(event);
list_for_each_entry(child, &event->child_list, child_list)
func(child);
mutex_unlock(&event->child_mutex);
}
static void perf_event_for_each(struct perf_event *event,
void (*func)(struct perf_event *))
{
struct perf_event_context *ctx = event->ctx;
struct perf_event *sibling;
lockdep_assert_held(&ctx->mutex);
event = event->group_leader;
perf_event_for_each_child(event, func);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
perf_event_for_each_child(sibling, func);
}
struct period_event {
struct perf_event *event;
u64 value;
};
static int __perf_event_period(void *info)
{
struct period_event *pe = info;
struct perf_event *event = pe->event;
struct perf_event_context *ctx = event->ctx;
u64 value = pe->value;
bool active;
raw_spin_lock(&ctx->lock);
if (event->attr.freq) {
event->attr.sample_freq = value;
} else {
event->attr.sample_period = value;
event->hw.sample_period = value;
}
active = (event->state == PERF_EVENT_STATE_ACTIVE);
if (active) {
perf_pmu_disable(ctx->pmu);
event->pmu->stop(event, PERF_EF_UPDATE);
}
local64_set(&event->hw.period_left, 0);
if (active) {
event->pmu->start(event, PERF_EF_RELOAD);
perf_pmu_enable(ctx->pmu);
}
raw_spin_unlock(&ctx->lock);
return 0;
}
static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
struct period_event pe = { .event = event, };
struct perf_event_context *ctx = event->ctx;
struct task_struct *task;
u64 value;
if (!is_sampling_event(event))
return -EINVAL;
if (copy_from_user(&value, arg, sizeof(value)))
return -EFAULT;
if (!value)
return -EINVAL;
if (event->attr.freq && value > sysctl_perf_event_sample_rate)
return -EINVAL;
task = ctx->task;
pe.value = value;
if (!task) {
cpu_function_call(event->cpu, __perf_event_period, &pe);
return 0;
}
retry:
if (!task_function_call(task, __perf_event_period, &pe))
return 0;
raw_spin_lock_irq(&ctx->lock);
if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
task = ctx->task;
goto retry;
}
__perf_event_period(&pe);
raw_spin_unlock_irq(&ctx->lock);
return 0;
}
static const struct file_operations perf_fops;
static inline int perf_fget_light(int fd, struct fd *p)
{
struct fd f = fdget(fd);
if (!f.file)
return -EBADF;
if (f.file->f_op != &perf_fops) {
fdput(f);
return -EBADF;
}
*p = f;
return 0;
}
static int perf_event_set_output(struct perf_event *event,
struct perf_event *output_event);
static int perf_event_set_filter(struct perf_event *event, void __user *arg);
static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd);
static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
{
void (*func)(struct perf_event *);
u32 flags = arg;
switch (cmd) {
case PERF_EVENT_IOC_ENABLE:
func = _perf_event_enable;
break;
case PERF_EVENT_IOC_DISABLE:
func = _perf_event_disable;
break;
case PERF_EVENT_IOC_RESET:
func = _perf_event_reset;
break;
case PERF_EVENT_IOC_REFRESH:
return _perf_event_refresh(event, arg);
case PERF_EVENT_IOC_PERIOD:
return perf_event_period(event, (u64 __user *)arg);
case PERF_EVENT_IOC_ID:
{
u64 id = primary_event_id(event);
if (copy_to_user((void __user *)arg, &id, sizeof(id)))
return -EFAULT;
return 0;
}
case PERF_EVENT_IOC_SET_OUTPUT:
{
int ret;
if (arg != -1) {
struct perf_event *output_event;
struct fd output;
ret = perf_fget_light(arg, &output);
if (ret)
return ret;
output_event = output.file->private_data;
ret = perf_event_set_output(event, output_event);
fdput(output);
} else {
ret = perf_event_set_output(event, NULL);
}
return ret;
}
case PERF_EVENT_IOC_SET_FILTER:
return perf_event_set_filter(event, (void __user *)arg);
case PERF_EVENT_IOC_SET_BPF:
return perf_event_set_bpf_prog(event, arg);
default:
return -ENOTTY;
}
if (flags & PERF_IOC_FLAG_GROUP)
perf_event_for_each(event, func);
else
perf_event_for_each_child(event, func);
return 0;
}
static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct perf_event *event = file->private_data;
struct perf_event_context *ctx;
long ret;
ctx = perf_event_ctx_lock(event);
ret = _perf_ioctl(event, cmd, arg);
perf_event_ctx_unlock(event, ctx);
return ret;
}
#ifdef CONFIG_COMPAT
static long perf_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
switch (_IOC_NR(cmd)) {
case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
case _IOC_NR(PERF_EVENT_IOC_ID):
/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
cmd &= ~IOCSIZE_MASK;
cmd |= sizeof(void *) << IOCSIZE_SHIFT;
}
break;
}
return perf_ioctl(file, cmd, arg);
}
#else
# define perf_compat_ioctl NULL
#endif
int perf_event_task_enable(void)
{
struct perf_event_context *ctx;
struct perf_event *event;
mutex_lock(¤t->perf_event_mutex);
list_for_each_entry(event, ¤t->perf_event_list, owner_entry) {
ctx = perf_event_ctx_lock(event);
perf_event_for_each_child(event, _perf_event_enable);
perf_event_ctx_unlock(event, ctx);
}
mutex_unlock(¤t->perf_event_mutex);
return 0;
}
int perf_event_task_disable(void)
{
struct perf_event_context *ctx;
struct perf_event *event;
mutex_lock(¤t->perf_event_mutex);
list_for_each_entry(event, ¤t->perf_event_list, owner_entry) {
ctx = perf_event_ctx_lock(event);
perf_event_for_each_child(event, _perf_event_disable);
perf_event_ctx_unlock(event, ctx);
}
mutex_unlock(¤t->perf_event_mutex);
return 0;
}
static int perf_event_index(struct perf_event *event)
{
if (event->hw.state & PERF_HES_STOPPED)
return 0;
if (event->state != PERF_EVENT_STATE_ACTIVE)
return 0;
return event->pmu->event_idx(event);
}
static void calc_timer_values(struct perf_event *event,
u64 *now,
u64 *enabled,
u64 *running)
{
u64 ctx_time;
*now = perf_clock();
ctx_time = event->shadow_ctx_time + *now;
*enabled = ctx_time - event->tstamp_enabled;
*running = ctx_time - event->tstamp_running;
}
static void perf_event_init_userpage(struct perf_event *event)
{
struct perf_event_mmap_page *userpg;
struct ring_buffer *rb;
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (!rb)
goto unlock;
userpg = rb->user_page;
/* Allow new userspace to detect that bit 0 is deprecated */
userpg->cap_bit0_is_deprecated = 1;
userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
userpg->data_offset = PAGE_SIZE;
userpg->data_size = perf_data_size(rb);
unlock:
rcu_read_unlock();
}
void __weak arch_perf_update_userpage(
struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now)
{
}
/*
* Callers need to ensure there can be no nesting of this function, otherwise
* the seqlock logic goes bad. We can not serialize this because the arch
* code calls this from NMI context.
*/
void perf_event_update_userpage(struct perf_event *event)
{
struct perf_event_mmap_page *userpg;
struct ring_buffer *rb;
u64 enabled, running, now;
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (!rb)
goto unlock;
/*
* compute total_time_enabled, total_time_running
* based on snapshot values taken when the event
* was last scheduled in.
*
* we cannot simply called update_context_time()
* because of locking issue as we can be called in
* NMI context
*/
calc_timer_values(event, &now, &enabled, &running);
userpg = rb->user_page;
/*
* Disable preemption so as to not let the corresponding user-space
* spin too long if we get preempted.
*/
preempt_disable();
++userpg->lock;
barrier();
userpg->index = perf_event_index(event);
userpg->offset = perf_event_count(event);
if (userpg->index)
userpg->offset -= local64_read(&event->hw.prev_count);
userpg->time_enabled = enabled +
atomic64_read(&event->child_total_time_enabled);
userpg->time_running = running +
atomic64_read(&event->child_total_time_running);
arch_perf_update_userpage(event, userpg, now);
barrier();
++userpg->lock;
preempt_enable();
unlock:
rcu_read_unlock();
}
static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct perf_event *event = vma->vm_file->private_data;
struct ring_buffer *rb;
int ret = VM_FAULT_SIGBUS;
if (vmf->flags & FAULT_FLAG_MKWRITE) {
if (vmf->pgoff == 0)
ret = 0;
return ret;
}
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (!rb)
goto unlock;
if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
goto unlock;
vmf->page = perf_mmap_to_page(rb, vmf->pgoff);
if (!vmf->page)
goto unlock;
get_page(vmf->page);
vmf->page->mapping = vma->vm_file->f_mapping;
vmf->page->index = vmf->pgoff;
ret = 0;
unlock:
rcu_read_unlock();
return ret;
}
static void ring_buffer_attach(struct perf_event *event,
struct ring_buffer *rb)
{
struct ring_buffer *old_rb = NULL;
unsigned long flags;
if (event->rb) {
/*
* Should be impossible, we set this when removing
* event->rb_entry and wait/clear when adding event->rb_entry.
*/
WARN_ON_ONCE(event->rcu_pending);
old_rb = event->rb;
spin_lock_irqsave(&old_rb->event_lock, flags);
list_del_rcu(&event->rb_entry);
spin_unlock_irqrestore(&old_rb->event_lock, flags);
event->rcu_batches = get_state_synchronize_rcu();
event->rcu_pending = 1;
}
if (rb) {
if (event->rcu_pending) {
cond_synchronize_rcu(event->rcu_batches);
event->rcu_pending = 0;
}
spin_lock_irqsave(&rb->event_lock, flags);
list_add_rcu(&event->rb_entry, &rb->event_list);
spin_unlock_irqrestore(&rb->event_lock, flags);
}
rcu_assign_pointer(event->rb, rb);
if (old_rb) {
ring_buffer_put(old_rb);
/*
* Since we detached before setting the new rb, so that we
* could attach the new rb, we could have missed a wakeup.
* Provide it now.
*/
wake_up_all(&event->waitq);
}
}
static void ring_buffer_wakeup(struct perf_event *event)
{
struct ring_buffer *rb;
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (rb) {
list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
wake_up_all(&event->waitq);
}
rcu_read_unlock();
}
struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
struct ring_buffer *rb;
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (rb) {
if (!atomic_inc_not_zero(&rb->refcount))
rb = NULL;
}
rcu_read_unlock();
return rb;
}
void ring_buffer_put(struct ring_buffer *rb)
{
if (!atomic_dec_and_test(&rb->refcount))
return;
WARN_ON_ONCE(!list_empty(&rb->event_list));
call_rcu(&rb->rcu_head, rb_free_rcu);
}
static void perf_mmap_open(struct vm_area_struct *vma)
{
struct perf_event *event = vma->vm_file->private_data;
atomic_inc(&event->mmap_count);
atomic_inc(&event->rb->mmap_count);
if (vma->vm_pgoff)
atomic_inc(&event->rb->aux_mmap_count);
if (event->pmu->event_mapped)
event->pmu->event_mapped(event);
}
/*
* A buffer can be mmap()ed multiple times; either directly through the same
* event, or through other events by use of perf_event_set_output().
*
* In order to undo the VM accounting done by perf_mmap() we need to destroy
* the buffer here, where we still have a VM context. This means we need
* to detach all events redirecting to us.
*/
static void perf_mmap_close(struct vm_area_struct *vma)
{
struct perf_event *event = vma->vm_file->private_data;
struct ring_buffer *rb = ring_buffer_get(event);
struct user_struct *mmap_user = rb->mmap_user;
int mmap_locked = rb->mmap_locked;
unsigned long size = perf_data_size(rb);
if (event->pmu->event_unmapped)
event->pmu->event_unmapped(event);
/*
* rb->aux_mmap_count will always drop before rb->mmap_count and
* event->mmap_count, so it is ok to use event->mmap_mutex to
* serialize with perf_mmap here.
*/
if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff &&
atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) {
atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
vma->vm_mm->pinned_vm -= rb->aux_mmap_locked;
rb_free_aux(rb);
mutex_unlock(&event->mmap_mutex);
}
atomic_dec(&rb->mmap_count);
if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
goto out_put;
ring_buffer_attach(event, NULL);
mutex_unlock(&event->mmap_mutex);
/* If there's still other mmap()s of this buffer, we're done. */
if (atomic_read(&rb->mmap_count))
goto out_put;
/*
* No other mmap()s, detach from all other events that might redirect
* into the now unreachable buffer. Somewhat complicated by the
* fact that rb::event_lock otherwise nests inside mmap_mutex.
*/
again:
rcu_read_lock();
list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
if (!atomic_long_inc_not_zero(&event->refcount)) {
/*
* This event is en-route to free_event() which will
* detach it and remove it from the list.
*/
continue;
}
rcu_read_unlock();
mutex_lock(&event->mmap_mutex);
/*
* Check we didn't race with perf_event_set_output() which can
* swizzle the rb from under us while we were waiting to
* acquire mmap_mutex.
*
* If we find a different rb; ignore this event, a next
* iteration will no longer find it on the list. We have to
* still restart the iteration to make sure we're not now
* iterating the wrong list.
*/
if (event->rb == rb)
ring_buffer_attach(event, NULL);
mutex_unlock(&event->mmap_mutex);
put_event(event);
/*
* Restart the iteration; either we're on the wrong list or
* destroyed its integrity by doing a deletion.
*/
goto again;
}
rcu_read_unlock();
/*
* It could be there's still a few 0-ref events on the list; they'll
* get cleaned up by free_event() -- they'll also still have their
* ref on the rb and will free it whenever they are done with it.
*
* Aside from that, this buffer is 'fully' detached and unmapped,
* undo the VM accounting.
*/
atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
vma->vm_mm->pinned_vm -= mmap_locked;
free_uid(mmap_user);
out_put:
ring_buffer_put(rb); /* could be last */
}
static const struct vm_operations_struct perf_mmap_vmops = {
.open = perf_mmap_open,
.close = perf_mmap_close, /* non mergable */
.fault = perf_mmap_fault,
.page_mkwrite = perf_mmap_fault,
};
static int perf_mmap(struct file *file, struct vm_area_struct *vma)
{
struct perf_event *event = file->private_data;
unsigned long user_locked, user_lock_limit;
struct user_struct *user = current_user();
unsigned long locked, lock_limit;
struct ring_buffer *rb = NULL;
unsigned long vma_size;
unsigned long nr_pages;
long user_extra = 0, extra = 0;
int ret = 0, flags = 0;
/*
* Don't allow mmap() of inherited per-task counters. This would
* create a performance issue due to all children writing to the
* same rb.
*/
if (event->cpu == -1 && event->attr.inherit)
return -EINVAL;
if (!(vma->vm_flags & VM_SHARED))
return -EINVAL;
vma_size = vma->vm_end - vma->vm_start;
if (vma->vm_pgoff == 0) {
nr_pages = (vma_size / PAGE_SIZE) - 1;
} else {
/*
* AUX area mapping: if rb->aux_nr_pages != 0, it's already
* mapped, all subsequent mappings should have the same size
* and offset. Must be above the normal perf buffer.
*/
u64 aux_offset, aux_size;
if (!event->rb)
return -EINVAL;
nr_pages = vma_size / PAGE_SIZE;
mutex_lock(&event->mmap_mutex);
ret = -EINVAL;
rb = event->rb;
if (!rb)
goto aux_unlock;
aux_offset = ACCESS_ONCE(rb->user_page->aux_offset);
aux_size = ACCESS_ONCE(rb->user_page->aux_size);
if (aux_offset < perf_data_size(rb) + PAGE_SIZE)
goto aux_unlock;
if (aux_offset != vma->vm_pgoff << PAGE_SHIFT)
goto aux_unlock;
/* already mapped with a different offset */
if (rb_has_aux(rb) && rb->aux_pgoff != vma->vm_pgoff)
goto aux_unlock;
if (aux_size != vma_size || aux_size != nr_pages * PAGE_SIZE)
goto aux_unlock;
/* already mapped with a different size */
if (rb_has_aux(rb) && rb->aux_nr_pages != nr_pages)
goto aux_unlock;
if (!is_power_of_2(nr_pages))
goto aux_unlock;
if (!atomic_inc_not_zero(&rb->mmap_count))
goto aux_unlock;
if (rb_has_aux(rb)) {
atomic_inc(&rb->aux_mmap_count);
ret = 0;
goto unlock;
}
atomic_set(&rb->aux_mmap_count, 1);
user_extra = nr_pages;
goto accounting;
}
/*
* If we have rb pages ensure they're a power-of-two number, so we
* can do bitmasks instead of modulo.
*/
if (nr_pages != 0 && !is_power_of_2(nr_pages))
return -EINVAL;
if (vma_size != PAGE_SIZE * (1 + nr_pages))
return -EINVAL;
WARN_ON_ONCE(event->ctx->parent_ctx);
again:
mutex_lock(&event->mmap_mutex);
if (event->rb) {
if (event->rb->nr_pages != nr_pages) {
ret = -EINVAL;
goto unlock;
}
if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
/*
* Raced against perf_mmap_close() through
* perf_event_set_output(). Try again, hope for better
* luck.
*/
mutex_unlock(&event->mmap_mutex);
goto again;
}
goto unlock;
}
user_extra = nr_pages + 1;
accounting:
user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
/*
* Increase the limit linearly with more CPUs:
*/
user_lock_limit *= num_online_cpus();
user_locked = atomic_long_read(&user->locked_vm) + user_extra;
if (user_locked > user_lock_limit)
extra = user_locked - user_lock_limit;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = vma->vm_mm->pinned_vm + extra;
if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
!capable(CAP_IPC_LOCK)) {
ret = -EPERM;
goto unlock;
}
WARN_ON(!rb && event->rb);
if (vma->vm_flags & VM_WRITE)
flags |= RING_BUFFER_WRITABLE;
if (!rb) {
rb = rb_alloc(nr_pages,
event->attr.watermark ? event->attr.wakeup_watermark : 0,
event->cpu, flags);
if (!rb) {
ret = -ENOMEM;
goto unlock;
}
atomic_set(&rb->mmap_count, 1);
rb->mmap_user = get_current_user();
rb->mmap_locked = extra;
ring_buffer_attach(event, rb);
perf_event_init_userpage(event);
perf_event_update_userpage(event);
} else {
ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages,
event->attr.aux_watermark, flags);
if (!ret)
rb->aux_mmap_locked = extra;
}
unlock:
if (!ret) {
atomic_long_add(user_extra, &user->locked_vm);
vma->vm_mm->pinned_vm += extra;
atomic_inc(&event->mmap_count);
} else if (rb) {
atomic_dec(&rb->mmap_count);
}
aux_unlock:
mutex_unlock(&event->mmap_mutex);
/*
* Since pinned accounting is per vm we cannot allow fork() to copy our
* vma.
*/
vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
vma->vm_ops = &perf_mmap_vmops;
if (event->pmu->event_mapped)
event->pmu->event_mapped(event);
return ret;
}
static int perf_fasync(int fd, struct file *filp, int on)
{
struct inode *inode = file_inode(filp);
struct perf_event *event = filp->private_data;
int retval;
mutex_lock(&inode->i_mutex);
retval = fasync_helper(fd, filp, on, &event->fasync);
mutex_unlock(&inode->i_mutex);
if (retval < 0)
return retval;
return 0;
}
static const struct file_operations perf_fops = {
.llseek = no_llseek,
.release = perf_release,
.read = perf_read,
.poll = perf_poll,
.unlocked_ioctl = perf_ioctl,
.compat_ioctl = perf_compat_ioctl,
.mmap = perf_mmap,
.fasync = perf_fasync,
};
/*
* Perf event wakeup
*
* If there's data, ensure we set the poll() state and publish everything
* to user-space before waking everybody up.
*/
static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
{
/* only the parent has fasync state */
if (event->parent)
event = event->parent;
return &event->fasync;
}
void perf_event_wakeup(struct perf_event *event)
{
ring_buffer_wakeup(event);
if (event->pending_kill) {
kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
event->pending_kill = 0;
}
}
static void perf_pending_event(struct irq_work *entry)
{
struct perf_event *event = container_of(entry,
struct perf_event, pending);
int rctx;
rctx = perf_swevent_get_recursion_context();
/*
* If we 'fail' here, that's OK, it means recursion is already disabled
* and we won't recurse 'further'.
*/
if (event->pending_disable) {
event->pending_disable = 0;
__perf_event_disable(event);
}
if (event->pending_wakeup) {
event->pending_wakeup = 0;
perf_event_wakeup(event);
}
if (rctx >= 0)
perf_swevent_put_recursion_context(rctx);
}
/*
* We assume there is only KVM supporting the callbacks.
* Later on, we might change it to a list if there is
* another virtualization implementation supporting the callbacks.
*/
struct perf_guest_info_callbacks *perf_guest_cbs;
int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
perf_guest_cbs = cbs;
return 0;
}
EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
perf_guest_cbs = NULL;
return 0;
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
static void
perf_output_sample_regs(struct perf_output_handle *handle,
struct pt_regs *regs, u64 mask)
{
int bit;
for_each_set_bit(bit, (const unsigned long *) &mask,
sizeof(mask) * BITS_PER_BYTE) {
u64 val;
val = perf_reg_value(regs, bit);
perf_output_put(handle, val);
}
}
static void perf_sample_regs_user(struct perf_regs *regs_user,
struct pt_regs *regs,
struct pt_regs *regs_user_copy)
{
if (user_mode(regs)) {
regs_user->abi = perf_reg_abi(current);
regs_user->regs = regs;
} else if (current->mm) {
perf_get_regs_user(regs_user, regs, regs_user_copy);
} else {
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
regs_user->regs = NULL;
}
}
static void perf_sample_regs_intr(struct perf_regs *regs_intr,
struct pt_regs *regs)
{
regs_intr->regs = regs;
regs_intr->abi = perf_reg_abi(current);
}
/*
* Get remaining task size from user stack pointer.
*
* It'd be better to take stack vma map and limit this more
* precisly, but there's no way to get it safely under interrupt,
* so using TASK_SIZE as limit.
*/
static u64 perf_ustack_task_size(struct pt_regs *regs)
{
unsigned long addr = perf_user_stack_pointer(regs);
if (!addr || addr >= TASK_SIZE)
return 0;
return TASK_SIZE - addr;
}
static u16
perf_sample_ustack_size(u16 stack_size, u16 header_size,
struct pt_regs *regs)
{
u64 task_size;
/* No regs, no stack pointer, no dump. */
if (!regs)
return 0;
/*
* Check if we fit in with the requested stack size into the:
* - TASK_SIZE
* If we don't, we limit the size to the TASK_SIZE.
*
* - remaining sample size
* If we don't, we customize the stack size to
* fit in to the remaining sample size.
*/
task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
stack_size = min(stack_size, (u16) task_size);
/* Current header size plus static size and dynamic size. */
header_size += 2 * sizeof(u64);
/* Do we fit in with the current stack dump size? */
if ((u16) (header_size + stack_size) < header_size) {
/*
* If we overflow the maximum size for the sample,
* we customize the stack dump size to fit in.
*/
stack_size = USHRT_MAX - header_size - sizeof(u64);
stack_size = round_up(stack_size, sizeof(u64));
}
return stack_size;
}
static void
perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
struct pt_regs *regs)
{
/* Case of a kernel thread, nothing to dump */
if (!regs) {
u64 size = 0;
perf_output_put(handle, size);
} else {
unsigned long sp;
unsigned int rem;
u64 dyn_size;
/*
* We dump:
* static size
* - the size requested by user or the best one we can fit
* in to the sample max size
* data
* - user stack dump data
* dynamic size
* - the actual dumped size
*/
/* Static size. */
perf_output_put(handle, dump_size);
/* Data. */
sp = perf_user_stack_pointer(regs);
rem = __output_copy_user(handle, (void *) sp, dump_size);
dyn_size = dump_size - rem;
perf_output_skip(handle, rem);
/* Dynamic size. */
perf_output_put(handle, dyn_size);
}
}
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
{
u64 sample_type = event->attr.sample_type;
data->type = sample_type;
header->size += event->id_header_size;
if (sample_type & PERF_SAMPLE_TID) {
/* namespace issues */
data->tid_entry.pid = perf_event_pid(event, current);
data->tid_entry.tid = perf_event_tid(event, current);
}
if (sample_type & PERF_SAMPLE_TIME)
data->time = perf_event_clock(event);
if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
data->id = primary_event_id(event);
if (sample_type & PERF_SAMPLE_STREAM_ID)
data->stream_id = event->id;
if (sample_type & PERF_SAMPLE_CPU) {
data->cpu_entry.cpu = raw_smp_processor_id();
data->cpu_entry.reserved = 0;
}
}
void perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
{
if (event->attr.sample_id_all)
__perf_event_header__init_id(header, data, event);
}
static void __perf_event__output_id_sample(struct perf_output_handle *handle,
struct perf_sample_data *data)
{
u64 sample_type = data->type;
if (sample_type & PERF_SAMPLE_TID)
perf_output_put(handle, data->tid_entry);
if (sample_type & PERF_SAMPLE_TIME)
perf_output_put(handle, data->time);
if (sample_type & PERF_SAMPLE_ID)
perf_output_put(handle, data->id);
if (sample_type & PERF_SAMPLE_STREAM_ID)
perf_output_put(handle, data->stream_id);
if (sample_type & PERF_SAMPLE_CPU)
perf_output_put(handle, data->cpu_entry);
if (sample_type & PERF_SAMPLE_IDENTIFIER)
perf_output_put(handle, data->id);
}
void perf_event__output_id_sample(struct perf_event *event,
struct perf_output_handle *handle,
struct perf_sample_data *sample)
{
if (event->attr.sample_id_all)
__perf_event__output_id_sample(handle, sample);
}
static void perf_output_read_one(struct perf_output_handle *handle,
struct perf_event *event,
u64 enabled, u64 running)
{
u64 read_format = event->attr.read_format;
u64 values[4];
int n = 0;
values[n++] = perf_event_count(event);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
values[n++] = enabled +
atomic64_read(&event->child_total_time_enabled);
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
values[n++] = running +
atomic64_read(&event->child_total_time_running);
}
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(event);
__output_copy(handle, values, n * sizeof(u64));
}
/*
* XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
*/
static void perf_output_read_group(struct perf_output_handle *handle,
struct perf_event *event,
u64 enabled, u64 running)
{
struct perf_event *leader = event->group_leader, *sub;
u64 read_format = event->attr.read_format;
u64 values[5];
int n = 0;
values[n++] = 1 + leader->nr_siblings;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
values[n++] = running;
if (leader != event)
leader->pmu->read(leader);
values[n++] = perf_event_count(leader);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
__output_copy(handle, values, n * sizeof(u64));
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
n = 0;
if ((sub != event) &&
(sub->state == PERF_EVENT_STATE_ACTIVE))
sub->pmu->read(sub);
values[n++] = perf_event_count(sub);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
__output_copy(handle, values, n * sizeof(u64));
}
}
#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
PERF_FORMAT_TOTAL_TIME_RUNNING)
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
u64 enabled = 0, running = 0, now;
u64 read_format = event->attr.read_format;
/*
* compute total_time_enabled, total_time_running
* based on snapshot values taken when the event
* was last scheduled in.
*
* we cannot simply called update_context_time()
* because of locking issue as we are called in
* NMI context
*/
if (read_format & PERF_FORMAT_TOTAL_TIMES)
calc_timer_values(event, &now, &enabled, &running);
if (event->attr.read_format & PERF_FORMAT_GROUP)
perf_output_read_group(handle, event, enabled, running);
else
perf_output_read_one(handle, event, enabled, running);
}
void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
{
u64 sample_type = data->type;
perf_output_put(handle, *header);
if (sample_type & PERF_SAMPLE_IDENTIFIER)
perf_output_put(handle, data->id);
if (sample_type & PERF_SAMPLE_IP)
perf_output_put(handle, data->ip);
if (sample_type & PERF_SAMPLE_TID)
perf_output_put(handle, data->tid_entry);
if (sample_type & PERF_SAMPLE_TIME)
perf_output_put(handle, data->time);
if (sample_type & PERF_SAMPLE_ADDR)
perf_output_put(handle, data->addr);
if (sample_type & PERF_SAMPLE_ID)
perf_output_put(handle, data->id);
if (sample_type & PERF_SAMPLE_STREAM_ID)
perf_output_put(handle, data->stream_id);
if (sample_type & PERF_SAMPLE_CPU)
perf_output_put(handle, data->cpu_entry);
if (sample_type & PERF_SAMPLE_PERIOD)
perf_output_put(handle, data->period);
if (sample_type & PERF_SAMPLE_READ)
perf_output_read(handle, event);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
if (data->callchain) {
int size = 1;
if (data->callchain)
size += data->callchain->nr;
size *= sizeof(u64);
__output_copy(handle, data->callchain, size);
} else {
u64 nr = 0;
perf_output_put(handle, nr);
}
}
if (sample_type & PERF_SAMPLE_RAW) {
if (data->raw) {
perf_output_put(handle, data->raw->size);
__output_copy(handle, data->raw->data,
data->raw->size);
} else {
struct {
u32 size;
u32 data;
} raw = {
.size = sizeof(u32),
.data = 0,
};
perf_output_put(handle, raw);
}
}
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
if (data->br_stack) {
size_t size;
size = data->br_stack->nr
* sizeof(struct perf_branch_entry);
perf_output_put(handle, data->br_stack->nr);
perf_output_copy(handle, data->br_stack->entries, size);
} else {
/*
* we always store at least the value of nr
*/
u64 nr = 0;
perf_output_put(handle, nr);
}
}
if (sample_type & PERF_SAMPLE_REGS_USER) {
u64 abi = data->regs_user.abi;
/*
* If there are no regs to dump, notice it through
* first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
*/
perf_output_put(handle, abi);
if (abi) {
u64 mask = event->attr.sample_regs_user;
perf_output_sample_regs(handle,
data->regs_user.regs,
mask);
}
}
if (sample_type & PERF_SAMPLE_STACK_USER) {
perf_output_sample_ustack(handle,
data->stack_user_size,
data->regs_user.regs);
}
if (sample_type & PERF_SAMPLE_WEIGHT)
perf_output_put(handle, data->weight);
if (sample_type & PERF_SAMPLE_DATA_SRC)
perf_output_put(handle, data->data_src.val);
if (sample_type & PERF_SAMPLE_TRANSACTION)
perf_output_put(handle, data->txn);
if (sample_type & PERF_SAMPLE_REGS_INTR) {
u64 abi = data->regs_intr.abi;
/*
* If there are no regs to dump, notice it through
* first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
*/
perf_output_put(handle, abi);
if (abi) {
u64 mask = event->attr.sample_regs_intr;
perf_output_sample_regs(handle,
data->regs_intr.regs,
mask);
}
}
if (!event->attr.watermark) {
int wakeup_events = event->attr.wakeup_events;
if (wakeup_events) {
struct ring_buffer *rb = handle->rb;
int events = local_inc_return(&rb->events);
if (events >= wakeup_events) {
local_sub(wakeup_events, &rb->events);
local_inc(&rb->wakeup);
}
}
}
}
void perf_prepare_sample(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs)
{
u64 sample_type = event->attr.sample_type;
header->type = PERF_RECORD_SAMPLE;
header->size = sizeof(*header) + event->header_size;
header->misc = 0;
header->misc |= perf_misc_flags(regs);
__perf_event_header__init_id(header, data, event);
if (sample_type & PERF_SAMPLE_IP)
data->ip = perf_instruction_pointer(regs);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
data->callchain = perf_callchain(event, regs);
if (data->callchain)
size += data->callchain->nr;
header->size += size * sizeof(u64);
}
if (sample_type & PERF_SAMPLE_RAW) {
int size = sizeof(u32);
if (data->raw)
size += data->raw->size;
else
size += sizeof(u32);
WARN_ON_ONCE(size & (sizeof(u64)-1));
header->size += size;
}
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
int size = sizeof(u64); /* nr */
if (data->br_stack) {
size += data->br_stack->nr
* sizeof(struct perf_branch_entry);
}
header->size += size;
}
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
perf_sample_regs_user(&data->regs_user, regs,
&data->regs_user_copy);
if (sample_type & PERF_SAMPLE_REGS_USER) {
/* regs dump ABI info */
int size = sizeof(u64);
if (data->regs_user.regs) {
u64 mask = event->attr.sample_regs_user;
size += hweight64(mask) * sizeof(u64);
}
header->size += size;
}
if (sample_type & PERF_SAMPLE_STACK_USER) {
/*
* Either we need PERF_SAMPLE_STACK_USER bit to be allways
* processed as the last one or have additional check added
* in case new sample type is added, because we could eat
* up the rest of the sample size.
*/
u16 stack_size = event->attr.sample_stack_user;
u16 size = sizeof(u64);
stack_size = perf_sample_ustack_size(stack_size, header->size,
data->regs_user.regs);
/*
* If there is something to dump, add space for the dump
* itself and for the field that tells the dynamic size,
* which is how many have been actually dumped.
*/
if (stack_size)
size += sizeof(u64) + stack_size;
data->stack_user_size = stack_size;
header->size += size;
}
if (sample_type & PERF_SAMPLE_REGS_INTR) {
/* regs dump ABI info */
int size = sizeof(u64);
perf_sample_regs_intr(&data->regs_intr, regs);
if (data->regs_intr.regs) {
u64 mask = event->attr.sample_regs_intr;
size += hweight64(mask) * sizeof(u64);
}
header->size += size;
}
}
void perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
{
struct perf_output_handle handle;
struct perf_event_header header;
/* protect the callchain buffers */
rcu_read_lock();
perf_prepare_sample(&header, data, event, regs);
if (perf_output_begin(&handle, event, header.size))
goto exit;
perf_output_sample(&handle, &header, data, event);
perf_output_end(&handle);
exit:
rcu_read_unlock();
}
/*
* read event_id
*/
struct perf_read_event {
struct perf_event_header header;
u32 pid;
u32 tid;
};
static void
perf_event_read_event(struct perf_event *event,
struct task_struct *task)
{
struct perf_output_handle handle;
struct perf_sample_data sample;
struct perf_read_event read_event = {
.header = {
.type = PERF_RECORD_READ,
.misc = 0,
.size = sizeof(read_event) + event->read_size,
},
.pid = perf_event_pid(event, task),
.tid = perf_event_tid(event, task),
};
int ret;
perf_event_header__init_id(&read_event.header, &sample, event);
ret = perf_output_begin(&handle, event, read_event.header.size);
if (ret)
return;
perf_output_put(&handle, read_event);
perf_output_read(&handle, event);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);
static void
perf_event_aux_ctx(struct perf_event_context *ctx,
perf_event_aux_output_cb output,
void *data)
{
struct perf_event *event;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state < PERF_EVENT_STATE_INACTIVE)
continue;
if (!event_filter_match(event))
continue;
output(event, data);
}
}
static void
perf_event_aux(perf_event_aux_output_cb output, void *data,
struct perf_event_context *task_ctx)
{
struct perf_cpu_context *cpuctx;
struct perf_event_context *ctx;
struct pmu *pmu;
int ctxn;
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
goto next;
perf_event_aux_ctx(&cpuctx->ctx, output, data);
if (task_ctx)
goto next;
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto next;
ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
if (ctx)
perf_event_aux_ctx(ctx, output, data);
next:
put_cpu_ptr(pmu->pmu_cpu_context);
}
if (task_ctx) {
preempt_disable();
perf_event_aux_ctx(task_ctx, output, data);
preempt_enable();
}
rcu_read_unlock();
}
/*
* task tracking -- fork/exit
*
* enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task
*/
struct perf_task_event {
struct task_struct *task;
struct perf_event_context *task_ctx;
struct {
struct perf_event_header header;
u32 pid;
u32 ppid;
u32 tid;
u32 ptid;
u64 time;
} event_id;
};
static int perf_event_task_match(struct perf_event *event)
{
return event->attr.comm || event->attr.mmap ||
event->attr.mmap2 || event->attr.mmap_data ||
event->attr.task;
}
static void perf_event_task_output(struct perf_event *event,
void *data)
{
struct perf_task_event *task_event = data;
struct perf_output_handle handle;
struct perf_sample_data sample;
struct task_struct *task = task_event->task;
int ret, size = task_event->event_id.header.size;
if (!perf_event_task_match(event))
return;
perf_event_header__init_id(&task_event->event_id.header, &sample, event);
ret = perf_output_begin(&handle, event,
task_event->event_id.header.size);
if (ret)
goto out;
task_event->event_id.pid = perf_event_pid(event, task);
task_event->event_id.ppid = perf_event_pid(event, current);
task_event->event_id.tid = perf_event_tid(event, task);
task_event->event_id.ptid = perf_event_tid(event, current);
task_event->event_id.time = perf_event_clock(event);
perf_output_put(&handle, task_event->event_id);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
out:
task_event->event_id.header.size = size;
}
static void perf_event_task(struct task_struct *task,
struct perf_event_context *task_ctx,
int new)
{
struct perf_task_event task_event;
if (!atomic_read(&nr_comm_events) &&
!atomic_read(&nr_mmap_events) &&
!atomic_read(&nr_task_events))
return;
task_event = (struct perf_task_event){
.task = task,
.task_ctx = task_ctx,
.event_id = {
.header = {
.type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT,
.misc = 0,
.size = sizeof(task_event.event_id),
},
/* .pid */
/* .ppid */
/* .tid */
/* .ptid */
/* .time */
},
};
perf_event_aux(perf_event_task_output,
&task_event,
task_ctx);
}
void perf_event_fork(struct task_struct *task)
{
perf_event_task(task, NULL, 1);
}
/*
* comm tracking
*/
struct perf_comm_event {
struct task_struct *task;
char *comm;
int comm_size;
struct {
struct perf_event_header header;
u32 pid;
u32 tid;
} event_id;
};
static int perf_event_comm_match(struct perf_event *event)
{
return event->attr.comm;
}
static void perf_event_comm_output(struct perf_event *event,
void *data)
{
struct perf_comm_event *comm_event = data;
struct perf_output_handle handle;
struct perf_sample_data sample;
int size = comm_event->event_id.header.size;
int ret;
if (!perf_event_comm_match(event))
return;
perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
ret = perf_output_begin(&handle, event,
comm_event->event_id.header.size);
if (ret)
goto out;
comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
perf_output_put(&handle, comm_event->event_id);
__output_copy(&handle, comm_event->comm,
comm_event->comm_size);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
out:
comm_event->event_id.header.size = size;
}
static void perf_event_comm_event(struct perf_comm_event *comm_event)
{
char comm[TASK_COMM_LEN];
unsigned int size;
memset(comm, 0, sizeof(comm));
strlcpy(comm, comm_event->task->comm, sizeof(comm));
size = ALIGN(strlen(comm)+1, sizeof(u64));
comm_event->comm = comm;
comm_event->comm_size = size;
comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
perf_event_aux(perf_event_comm_output,
comm_event,
NULL);
}
void perf_event_comm(struct task_struct *task, bool exec)
{
struct perf_comm_event comm_event;
if (!atomic_read(&nr_comm_events))
return;
comm_event = (struct perf_comm_event){
.task = task,
/* .comm */
/* .comm_size */
.event_id = {
.header = {
.type = PERF_RECORD_COMM,
.misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0,
/* .size */
},
/* .pid */
/* .tid */
},
};
perf_event_comm_event(&comm_event);
}
/*
* mmap tracking
*/
struct perf_mmap_event {
struct vm_area_struct *vma;
const char *file_name;
int file_size;
int maj, min;
u64 ino;
u64 ino_generation;
u32 prot, flags;
struct {
struct perf_event_header header;
u32 pid;
u32 tid;
u64 start;
u64 len;
u64 pgoff;
} event_id;
};
static int perf_event_mmap_match(struct perf_event *event,
void *data)
{
struct perf_mmap_event *mmap_event = data;
struct vm_area_struct *vma = mmap_event->vma;
int executable = vma->vm_flags & VM_EXEC;
return (!executable && event->attr.mmap_data) ||
(executable && (event->attr.mmap || event->attr.mmap2));
}
static void perf_event_mmap_output(struct perf_event *event,
void *data)
{
struct perf_mmap_event *mmap_event = data;
struct perf_output_handle handle;
struct perf_sample_data sample;
int size = mmap_event->event_id.header.size;
int ret;
if (!perf_event_mmap_match(event, data))
return;
if (event->attr.mmap2) {
mmap_event->event_id.header.type = PERF_RECORD_MMAP2;
mmap_event->event_id.header.size += sizeof(mmap_event->maj);
mmap_event->event_id.header.size += sizeof(mmap_event->min);
mmap_event->event_id.header.size += sizeof(mmap_event->ino);
mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
mmap_event->event_id.header.size += sizeof(mmap_event->prot);
mmap_event->event_id.header.size += sizeof(mmap_event->flags);
}
perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
ret = perf_output_begin(&handle, event,
mmap_event->event_id.header.size);
if (ret)
goto out;
mmap_event->event_id.pid = perf_event_pid(event, current);
mmap_event->event_id.tid = perf_event_tid(event, current);
perf_output_put(&handle, mmap_event->event_id);
if (event->attr.mmap2) {
perf_output_put(&handle, mmap_event->maj);
perf_output_put(&handle, mmap_event->min);
perf_output_put(&handle, mmap_event->ino);
perf_output_put(&handle, mmap_event->ino_generation);
perf_output_put(&handle, mmap_event->prot);
perf_output_put(&handle, mmap_event->flags);
}
__output_copy(&handle, mmap_event->file_name,
mmap_event->file_size);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
out:
mmap_event->event_id.header.size = size;
}
static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
{
struct vm_area_struct *vma = mmap_event->vma;
struct file *file = vma->vm_file;
int maj = 0, min = 0;
u64 ino = 0, gen = 0;
u32 prot = 0, flags = 0;
unsigned int size;
char tmp[16];
char *buf = NULL;
char *name;
if (file) {
struct inode *inode;
dev_t dev;
buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf) {
name = "//enomem";
goto cpy_name;
}
/*
* d_path() works from the end of the rb backwards, so we
* need to add enough zero bytes after the string to handle
* the 64bit alignment we do later.
*/
name = file_path(file, buf, PATH_MAX - sizeof(u64));
if (IS_ERR(name)) {
name = "//toolong";
goto cpy_name;
}
inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
gen = inode->i_generation;
maj = MAJOR(dev);
min = MINOR(dev);
if (vma->vm_flags & VM_READ)
prot |= PROT_READ;
if (vma->vm_flags & VM_WRITE)
prot |= PROT_WRITE;
if (vma->vm_flags & VM_EXEC)
prot |= PROT_EXEC;
if (vma->vm_flags & VM_MAYSHARE)
flags = MAP_SHARED;
else
flags = MAP_PRIVATE;
if (vma->vm_flags & VM_DENYWRITE)
flags |= MAP_DENYWRITE;
if (vma->vm_flags & VM_MAYEXEC)
flags |= MAP_EXECUTABLE;
if (vma->vm_flags & VM_LOCKED)
flags |= MAP_LOCKED;
if (vma->vm_flags & VM_HUGETLB)
flags |= MAP_HUGETLB;
goto got_name;
} else {
if (vma->vm_ops && vma->vm_ops->name) {
name = (char *) vma->vm_ops->name(vma);
if (name)
goto cpy_name;
}
name = (char *)arch_vma_name(vma);
if (name)
goto cpy_name;
if (vma->vm_start <= vma->vm_mm->start_brk &&
vma->vm_end >= vma->vm_mm->brk) {
name = "[heap]";
goto cpy_name;
}
if (vma->vm_start <= vma->vm_mm->start_stack &&
vma->vm_end >= vma->vm_mm->start_stack) {
name = "[stack]";
goto cpy_name;
}
name = "//anon";
goto cpy_name;
}
cpy_name:
strlcpy(tmp, name, sizeof(tmp));
name = tmp;
got_name:
/*
* Since our buffer works in 8 byte units we need to align our string
* size to a multiple of 8. However, we must guarantee the tail end is
* zero'd out to avoid leaking random bits to userspace.
*/
size = strlen(name)+1;
while (!IS_ALIGNED(size, sizeof(u64)))
name[size++] = '\0';
mmap_event->file_name = name;
mmap_event->file_size = size;
mmap_event->maj = maj;
mmap_event->min = min;
mmap_event->ino = ino;
mmap_event->ino_generation = gen;
mmap_event->prot = prot;
mmap_event->flags = flags;
if (!(vma->vm_flags & VM_EXEC))
mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
perf_event_aux(perf_event_mmap_output,
mmap_event,
NULL);
kfree(buf);
}
void perf_event_mmap(struct vm_area_struct *vma)
{
struct perf_mmap_event mmap_event;
if (!atomic_read(&nr_mmap_events))
return;
mmap_event = (struct perf_mmap_event){
.vma = vma,
/* .file_name */
/* .file_size */
.event_id = {
.header = {
.type = PERF_RECORD_MMAP,
.misc = PERF_RECORD_MISC_USER,
/* .size */
},
/* .pid */
/* .tid */
.start = vma->vm_start,
.len = vma->vm_end - vma->vm_start,
.pgoff = (u64)vma->vm_pgoff << PAGE_SHIFT,
},
/* .maj (attr_mmap2 only) */
/* .min (attr_mmap2 only) */
/* .ino (attr_mmap2 only) */
/* .ino_generation (attr_mmap2 only) */
/* .prot (attr_mmap2 only) */
/* .flags (attr_mmap2 only) */
};
perf_event_mmap_event(&mmap_event);
}
void perf_event_aux_event(struct perf_event *event, unsigned long head,
unsigned long size, u64 flags)
{
struct perf_output_handle handle;
struct perf_sample_data sample;
struct perf_aux_event {
struct perf_event_header header;
u64 offset;
u64 size;
u64 flags;
} rec = {
.header = {
.type = PERF_RECORD_AUX,
.misc = 0,
.size = sizeof(rec),
},
.offset = head,
.size = size,
.flags = flags,
};
int ret;
perf_event_header__init_id(&rec.header, &sample, event);
ret = perf_output_begin(&handle, event, rec.header.size);
if (ret)
return;
perf_output_put(&handle, rec);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
/*
* Lost/dropped samples logging
*/
void perf_log_lost_samples(struct perf_event *event, u64 lost)
{
struct perf_output_handle handle;
struct perf_sample_data sample;
int ret;
struct {
struct perf_event_header header;
u64 lost;
} lost_samples_event = {
.header = {
.type = PERF_RECORD_LOST_SAMPLES,
.misc = 0,
.size = sizeof(lost_samples_event),
},
.lost = lost,
};
perf_event_header__init_id(&lost_samples_event.header, &sample, event);
ret = perf_output_begin(&handle, event,
lost_samples_event.header.size);
if (ret)
return;
perf_output_put(&handle, lost_samples_event);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
/*
* IRQ throttle logging
*/
static void perf_log_throttle(struct perf_event *event, int enable)
{
struct perf_output_handle handle;
struct perf_sample_data sample;
int ret;
struct {
struct perf_event_header header;
u64 time;
u64 id;
u64 stream_id;
} throttle_event = {
.header = {
.type = PERF_RECORD_THROTTLE,
.misc = 0,
.size = sizeof(throttle_event),
},
.time = perf_event_clock(event),
.id = primary_event_id(event),
.stream_id = event->id,
};
if (enable)
throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
perf_event_header__init_id(&throttle_event.header, &sample, event);
ret = perf_output_begin(&handle, event,
throttle_event.header.size);
if (ret)
return;
perf_output_put(&handle, throttle_event);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
static void perf_log_itrace_start(struct perf_event *event)
{
struct perf_output_handle handle;
struct perf_sample_data sample;
struct perf_aux_event {
struct perf_event_header header;
u32 pid;
u32 tid;
} rec;
int ret;
if (event->parent)
event = event->parent;
if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) ||
event->hw.itrace_started)
return;
event->hw.itrace_started = 1;
rec.header.type = PERF_RECORD_ITRACE_START;
rec.header.misc = 0;
rec.header.size = sizeof(rec);
rec.pid = perf_event_pid(event, current);
rec.tid = perf_event_tid(event, current);
perf_event_header__init_id(&rec.header, &sample, event);
ret = perf_output_begin(&handle, event, rec.header.size);
if (ret)
return;
perf_output_put(&handle, rec);
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
/*
* Generic event overflow handling, sampling.
*/
static int __perf_event_overflow(struct perf_event *event,
int throttle, struct perf_sample_data *data,
struct pt_regs *regs)
{
int events = atomic_read(&event->event_limit);
struct hw_perf_event *hwc = &event->hw;
u64 seq;
int ret = 0;
/*
* Non-sampling counters might still use the PMI to fold short
* hardware counters, ignore those.
*/
if (unlikely(!is_sampling_event(event)))
return 0;
seq = __this_cpu_read(perf_throttled_seq);
if (seq != hwc->interrupts_seq) {
hwc->interrupts_seq = seq;
hwc->interrupts = 1;
} else {
hwc->interrupts++;
if (unlikely(throttle
&& hwc->interrupts >= max_samples_per_tick)) {
__this_cpu_inc(perf_throttled_count);
hwc->interrupts = MAX_INTERRUPTS;
perf_log_throttle(event, 0);
tick_nohz_full_kick();
ret = 1;
}
}
if (event->attr.freq) {
u64 now = perf_clock();
s64 delta = now - hwc->freq_time_stamp;
hwc->freq_time_stamp = now;
if (delta > 0 && delta < 2*TICK_NSEC)
perf_adjust_period(event, delta, hwc->last_period, true);
}
/*
* XXX event_limit might not quite work as expected on inherited
* events
*/
event->pending_kill = POLL_IN;
if (events && atomic_dec_and_test(&event->event_limit)) {
ret = 1;
event->pending_kill = POLL_HUP;
event->pending_disable = 1;
irq_work_queue(&event->pending);
}
if (event->overflow_handler)
event->overflow_handler(event, data, regs);
else
perf_event_output(event, data, regs);
if (*perf_event_fasync(event) && event->pending_kill) {
event->pending_wakeup = 1;
irq_work_queue(&event->pending);
}
return ret;
}
int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
{
return __perf_event_overflow(event, 1, data, regs);
}
/*
* Generic software event infrastructure
*/
struct swevent_htable {
struct swevent_hlist *swevent_hlist;
struct mutex hlist_mutex;
int hlist_refcount;
/* Recursion avoidance in each contexts */
int recursion[PERF_NR_CONTEXTS];
/* Keeps track of cpu being initialized/exited */
bool online;
};
static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
/*
* We directly increment event->count and keep a second value in
* event->hw.period_left to count intervals. This period event
* is kept in the range [-sample_period, 0] so that we can use the
* sign as trigger.
*/
u64 perf_swevent_set_period(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
u64 period = hwc->last_period;
u64 nr, offset;
s64 old, val;
hwc->last_period = hwc->sample_period;
again:
old = val = local64_read(&hwc->period_left);
if (val < 0)
return 0;
nr = div64_u64(period + val, period);
offset = nr * period;
val -= offset;
if (local64_cmpxchg(&hwc->period_left, old, val) != old)
goto again;
return nr;
}
static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
struct perf_sample_data *data,
struct pt_regs *regs)
{
struct hw_perf_event *hwc = &event->hw;
int throttle = 0;
if (!overflow)
overflow = perf_swevent_set_period(event);
if (hwc->interrupts == MAX_INTERRUPTS)
return;
for (; overflow; overflow--) {
if (__perf_event_overflow(event, throttle,
data, regs)) {
/*
* We inhibit the overflow from happening when
* hwc->interrupts == MAX_INTERRUPTS.
*/
break;
}
throttle = 1;
}
}
static void perf_swevent_event(struct perf_event *event, u64 nr,
struct perf_sample_data *data,
struct pt_regs *regs)
{
struct hw_perf_event *hwc = &event->hw;
local64_add(nr, &event->count);
if (!regs)
return;
if (!is_sampling_event(event))
return;
if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
data->period = nr;
return perf_swevent_overflow(event, 1, data, regs);
} else
data->period = event->hw.last_period;
if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
return perf_swevent_overflow(event, 1, data, regs);
if (local64_add_negative(nr, &hwc->period_left))
return;
perf_swevent_overflow(event, 0, data, regs);
}
static int perf_exclude_event(struct perf_event *event,
struct pt_regs *regs)
{
if (event->hw.state & PERF_HES_STOPPED)
return 1;
if (regs) {
if (event->attr.exclude_user && user_mode(regs))
return 1;
if (event->attr.exclude_kernel && !user_mode(regs))
return 1;
}
return 0;
}
static int perf_swevent_match(struct perf_event *event,
enum perf_type_id type,
u32 event_id,
struct perf_sample_data *data,
struct pt_regs *regs)
{
if (event->attr.type != type)
return 0;
if (event->attr.config != event_id)
return 0;
if (perf_exclude_event(event, regs))
return 0;
return 1;
}
static inline u64 swevent_hash(u64 type, u32 event_id)
{
u64 val = event_id | (type << 32);
return hash_64(val, SWEVENT_HLIST_BITS);
}
static inline struct hlist_head *
__find_swevent_head(struct swevent_hlist *hlist, u64 type, u32 event_id)
{
u64 hash = swevent_hash(type, event_id);
return &hlist->heads[hash];
}
/* For the read side: events when they trigger */
static inline struct hlist_head *
find_swevent_head_rcu(struct swevent_htable *swhash, u64 type, u32 event_id)
{
struct swevent_hlist *hlist;
hlist = rcu_dereference(swhash->swevent_hlist);
if (!hlist)
return NULL;
return __find_swevent_head(hlist, type, event_id);
}
/* For the event head insertion and removal in the hlist */
static inline struct hlist_head *
find_swevent_head(struct swevent_htable *swhash, struct perf_event *event)
{
struct swevent_hlist *hlist;
u32 event_id = event->attr.config;
u64 type = event->attr.type;
/*
* Event scheduling is always serialized against hlist allocation
* and release. Which makes the protected version suitable here.
* The context lock guarantees that.
*/
hlist = rcu_dereference_protected(swhash->swevent_hlist,
lockdep_is_held(&event->ctx->lock));
if (!hlist)
return NULL;
return __find_swevent_head(hlist, type, event_id);
}
static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
u64 nr,
struct perf_sample_data *data,
struct pt_regs *regs)
{
struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
struct perf_event *event;
struct hlist_head *head;
rcu_read_lock();
head = find_swevent_head_rcu(swhash, type, event_id);
if (!head)
goto end;
hlist_for_each_entry_rcu(event, head, hlist_entry) {
if (perf_swevent_match(event, type, event_id, data, regs))
perf_swevent_event(event, nr, data, regs);
}
end:
rcu_read_unlock();
}
DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]);
int perf_swevent_get_recursion_context(void)
{
struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
return get_recursion_context(swhash->recursion);
}
EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
inline void perf_swevent_put_recursion_context(int rctx)
{
struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
put_recursion_context(swhash->recursion, rctx);
}
void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
struct perf_sample_data data;
if (WARN_ON_ONCE(!regs))
return;
perf_sample_data_init(&data, addr, 0);
do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
}
void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
int rctx;
preempt_disable_notrace();
rctx = perf_swevent_get_recursion_context();
if (unlikely(rctx < 0))
goto fail;
___perf_sw_event(event_id, nr, regs, addr);
perf_swevent_put_recursion_context(rctx);
fail:
preempt_enable_notrace();
}
static void perf_swevent_read(struct perf_event *event)
{
}
static int perf_swevent_add(struct perf_event *event, int flags)
{
struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
struct hw_perf_event *hwc = &event->hw;
struct hlist_head *head;
if (is_sampling_event(event)) {
hwc->last_period = hwc->sample_period;
perf_swevent_set_period(event);
}
hwc->state = !(flags & PERF_EF_START);
head = find_swevent_head(swhash, event);
if (!head) {
/*
* We can race with cpu hotplug code. Do not
* WARN if the cpu just got unplugged.
*/
WARN_ON_ONCE(swhash->online);
return -EINVAL;
}
hlist_add_head_rcu(&event->hlist_entry, head);
perf_event_update_userpage(event);
return 0;
}
static void perf_swevent_del(struct perf_event *event, int flags)
{
hlist_del_rcu(&event->hlist_entry);
}
static void perf_swevent_start(struct perf_event *event, int flags)
{
event->hw.state = 0;
}
static void perf_swevent_stop(struct perf_event *event, int flags)
{
event->hw.state = PERF_HES_STOPPED;
}
/* Deref the hlist from the update side */
static inline struct swevent_hlist *
swevent_hlist_deref(struct swevent_htable *swhash)
{
return rcu_dereference_protected(swhash->swevent_hlist,
lockdep_is_held(&swhash->hlist_mutex));
}
static void swevent_hlist_release(struct swevent_htable *swhash)
{
struct swevent_hlist *hlist = swevent_hlist_deref(swhash);
if (!hlist)
return;
RCU_INIT_POINTER(swhash->swevent_hlist, NULL);
kfree_rcu(hlist, rcu_head);
}
static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
mutex_lock(&swhash->hlist_mutex);
if (!--swhash->hlist_refcount)
swevent_hlist_release(swhash);
mutex_unlock(&swhash->hlist_mutex);
}
static void swevent_hlist_put(struct perf_event *event)
{
int cpu;
for_each_possible_cpu(cpu)
swevent_hlist_put_cpu(event, cpu);
}
static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
int err = 0;
mutex_lock(&swhash->hlist_mutex);
if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
struct swevent_hlist *hlist;
hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
if (!hlist) {
err = -ENOMEM;
goto exit;
}
rcu_assign_pointer(swhash->swevent_hlist, hlist);
}
swhash->hlist_refcount++;
exit:
mutex_unlock(&swhash->hlist_mutex);
return err;
}
static int swevent_hlist_get(struct perf_event *event)
{
int err;
int cpu, failed_cpu;
get_online_cpus();
for_each_possible_cpu(cpu) {
err = swevent_hlist_get_cpu(event, cpu);
if (err) {
failed_cpu = cpu;
goto fail;
}
}
put_online_cpus();
return 0;
fail:
for_each_possible_cpu(cpu) {
if (cpu == failed_cpu)
break;
swevent_hlist_put_cpu(event, cpu);
}
put_online_cpus();
return err;
}
struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
static void sw_perf_event_destroy(struct perf_event *event)
{
u64 event_id = event->attr.config;
WARN_ON(event->parent);
static_key_slow_dec(&perf_swevent_enabled[event_id]);
swevent_hlist_put(event);
}
static int perf_swevent_init(struct perf_event *event)
{
u64 event_id = event->attr.config;
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event_id) {
case PERF_COUNT_SW_CPU_CLOCK:
case PERF_COUNT_SW_TASK_CLOCK:
return -ENOENT;
default:
break;
}
if (event_id >= PERF_COUNT_SW_MAX)
return -ENOENT;
if (!event->parent) {
int err;
err = swevent_hlist_get(event);
if (err)
return err;
static_key_slow_inc(&perf_swevent_enabled[event_id]);
event->destroy = sw_perf_event_destroy;
}
return 0;
}
static struct pmu perf_swevent = {
.task_ctx_nr = perf_sw_context,
.capabilities = PERF_PMU_CAP_NO_NMI,
.event_init = perf_swevent_init,
.add = perf_swevent_add,
.del = perf_swevent_del,
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
};
#ifdef CONFIG_EVENT_TRACING
static int perf_tp_filter_match(struct perf_event *event,
struct perf_sample_data *data)
{
void *record = data->raw->data;
if (likely(!event->filter) || filter_match_preds(event->filter, record))
return 1;
return 0;
}
static int perf_tp_event_match(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
{
if (event->hw.state & PERF_HES_STOPPED)
return 0;
/*
* All tracepoints are from kernel-space.
*/
if (event->attr.exclude_kernel)
return 0;
if (!perf_tp_filter_match(event, data))
return 0;
return 1;
}
void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
struct pt_regs *regs, struct hlist_head *head, int rctx,
struct task_struct *task)
{
struct perf_sample_data data;
struct perf_event *event;
struct perf_raw_record raw = {
.size = entry_size,
.data = record,
};
perf_sample_data_init(&data, addr, 0);
data.raw = &raw;
hlist_for_each_entry_rcu(event, head, hlist_entry) {
if (perf_tp_event_match(event, &data, regs))
perf_swevent_event(event, count, &data, regs);
}
/*
* If we got specified a target task, also iterate its context and
* deliver this event there too.
*/
if (task && task != current) {
struct perf_event_context *ctx;
struct trace_entry *entry = record;
rcu_read_lock();
ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]);
if (!ctx)
goto unlock;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->attr.type != PERF_TYPE_TRACEPOINT)
continue;
if (event->attr.config != entry->type)
continue;
if (perf_tp_event_match(event, &data, regs))
perf_swevent_event(event, count, &data, regs);
}
unlock:
rcu_read_unlock();
}
perf_swevent_put_recursion_context(rctx);
}
EXPORT_SYMBOL_GPL(perf_tp_event);
static void tp_perf_event_destroy(struct perf_event *event)
{
perf_trace_destroy(event);
}
static int perf_tp_event_init(struct perf_event *event)
{
int err;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -ENOENT;
/*
* no branch sampling for tracepoint events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
err = perf_trace_init(event);
if (err)
return err;
event->destroy = tp_perf_event_destroy;
return 0;
}
static struct pmu perf_tracepoint = {
.task_ctx_nr = perf_sw_context,
.event_init = perf_tp_event_init,
.add = perf_trace_add,
.del = perf_trace_del,
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
};
static inline void perf_tp_register(void)
{
perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}
static int perf_event_set_filter(struct perf_event *event, void __user *arg)
{
char *filter_str;
int ret;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -EINVAL;
filter_str = strndup_user(arg, PAGE_SIZE);
if (IS_ERR(filter_str))
return PTR_ERR(filter_str);
ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
kfree(filter_str);
return ret;
}
static void perf_event_free_filter(struct perf_event *event)
{
ftrace_profile_free_filter(event);
}
static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
{
struct bpf_prog *prog;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -EINVAL;
if (event->tp_event->prog)
return -EEXIST;
if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE))
/* bpf programs can only be attached to kprobes */
return -EINVAL;
prog = bpf_prog_get(prog_fd);
if (IS_ERR(prog))
return PTR_ERR(prog);
if (prog->type != BPF_PROG_TYPE_KPROBE) {
/* valid fd, but invalid bpf program type */
bpf_prog_put(prog);
return -EINVAL;
}
event->tp_event->prog = prog;
return 0;
}
static void perf_event_free_bpf_prog(struct perf_event *event)
{
struct bpf_prog *prog;
if (!event->tp_event)
return;
prog = event->tp_event->prog;
if (prog) {
event->tp_event->prog = NULL;
bpf_prog_put(prog);
}
}
#else
static inline void perf_tp_register(void)
{
}
static int perf_event_set_filter(struct perf_event *event, void __user *arg)
{
return -ENOENT;
}
static void perf_event_free_filter(struct perf_event *event)
{
}
static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
{
return -ENOENT;
}
static void perf_event_free_bpf_prog(struct perf_event *event)
{
}
#endif /* CONFIG_EVENT_TRACING */
#ifdef CONFIG_HAVE_HW_BREAKPOINT
void perf_bp_event(struct perf_event *bp, void *data)
{
struct perf_sample_data sample;
struct pt_regs *regs = data;
perf_sample_data_init(&sample, bp->attr.bp_addr, 0);
if (!bp->hw.state && !perf_exclude_event(bp, regs))
perf_swevent_event(bp, 1, &sample, regs);
}
#endif
/*
* hrtimer based swevent callback
*/
static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
{
enum hrtimer_restart ret = HRTIMER_RESTART;
struct perf_sample_data data;
struct pt_regs *regs;
struct perf_event *event;
u64 period;
event = container_of(hrtimer, struct perf_event, hw.hrtimer);
if (event->state != PERF_EVENT_STATE_ACTIVE)
return HRTIMER_NORESTART;
event->pmu->read(event);
perf_sample_data_init(&data, 0, event->hw.last_period);
regs = get_irq_regs();
if (regs && !perf_exclude_event(event, regs)) {
if (!(event->attr.exclude_idle && is_idle_task(current)))
if (__perf_event_overflow(event, 1, &data, regs))
ret = HRTIMER_NORESTART;
}
period = max_t(u64, 10000, event->hw.sample_period);
hrtimer_forward_now(hrtimer, ns_to_ktime(period));
return ret;
}
static void perf_swevent_start_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
s64 period;
if (!is_sampling_event(event))
return;
period = local64_read(&hwc->period_left);
if (period) {
if (period < 0)
period = 10000;
local64_set(&hwc->period_left, 0);
} else {
period = max_t(u64, 10000, hwc->sample_period);
}
hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
HRTIMER_MODE_REL_PINNED);
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
if (is_sampling_event(event)) {
ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
local64_set(&hwc->period_left, ktime_to_ns(remaining));
hrtimer_cancel(&hwc->hrtimer);
}
}
static void perf_swevent_init_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
if (!is_sampling_event(event))
return;
hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hwc->hrtimer.function = perf_swevent_hrtimer;
/*
* Since hrtimers have a fixed rate, we can do a static freq->period
* mapping and avoid the whole period adjust feedback stuff.
*/
if (event->attr.freq) {
long freq = event->attr.sample_freq;
event->attr.sample_period = NSEC_PER_SEC / freq;
hwc->sample_period = event->attr.sample_period;
local64_set(&hwc->period_left, hwc->sample_period);
hwc->last_period = hwc->sample_period;
event->attr.freq = 0;
}
}
/*
* Software event: cpu wall time clock
*/
static void cpu_clock_event_update(struct perf_event *event)
{
s64 prev;
u64 now;
now = local_clock();
prev = local64_xchg(&event->hw.prev_count, now);
local64_add(now - prev, &event->count);
}
static void cpu_clock_event_start(struct perf_event *event, int flags)
{
local64_set(&event->hw.prev_count, local_clock());
perf_swevent_start_hrtimer(event);
}
static void cpu_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
cpu_clock_event_update(event);
}
static int cpu_clock_event_add(struct perf_event *event, int flags)
{
if (flags & PERF_EF_START)
cpu_clock_event_start(event, flags);
perf_event_update_userpage(event);
return 0;
}
static void cpu_clock_event_del(struct perf_event *event, int flags)
{
cpu_clock_event_stop(event, flags);
}
static void cpu_clock_event_read(struct perf_event *event)
{
cpu_clock_event_update(event);
}
static int cpu_clock_event_init(struct perf_event *event)
{
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
perf_swevent_init_hrtimer(event);
return 0;
}
static struct pmu perf_cpu_clock = {
.task_ctx_nr = perf_sw_context,
.capabilities = PERF_PMU_CAP_NO_NMI,
.event_init = cpu_clock_event_init,
.add = cpu_clock_event_add,
.del = cpu_clock_event_del,
.start = cpu_clock_event_start,
.stop = cpu_clock_event_stop,
.read = cpu_clock_event_read,
};
/*
* Software event: task time clock
*/
static void task_clock_event_update(struct perf_event *event, u64 now)
{
u64 prev;
s64 delta;
prev = local64_xchg(&event->hw.prev_count, now);
delta = now - prev;
local64_add(delta, &event->count);
}
static void task_clock_event_start(struct perf_event *event, int flags)
{
local64_set(&event->hw.prev_count, event->ctx->time);
perf_swevent_start_hrtimer(event);
}
static void task_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
task_clock_event_update(event, event->ctx->time);
}
static int task_clock_event_add(struct perf_event *event, int flags)
{
if (flags & PERF_EF_START)
task_clock_event_start(event, flags);
perf_event_update_userpage(event);
return 0;
}
static void task_clock_event_del(struct perf_event *event, int flags)
{
task_clock_event_stop(event, PERF_EF_UPDATE);
}
static void task_clock_event_read(struct perf_event *event)
{
u64 now = perf_clock();
u64 delta = now - event->ctx->timestamp;
u64 time = event->ctx->time + delta;
task_clock_event_update(event, time);
}
static int task_clock_event_init(struct perf_event *event)
{
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
perf_swevent_init_hrtimer(event);
return 0;
}
static struct pmu perf_task_clock = {
.task_ctx_nr = perf_sw_context,
.capabilities = PERF_PMU_CAP_NO_NMI,
.event_init = task_clock_event_init,
.add = task_clock_event_add,
.del = task_clock_event_del,
.start = task_clock_event_start,
.stop = task_clock_event_stop,
.read = task_clock_event_read,
};
static void perf_pmu_nop_void(struct pmu *pmu)
{
}
static int perf_pmu_nop_int(struct pmu *pmu)
{
return 0;
}
static void perf_pmu_start_txn(struct pmu *pmu)
{
perf_pmu_disable(pmu);
}
static int perf_pmu_commit_txn(struct pmu *pmu)
{
perf_pmu_enable(pmu);
return 0;
}
static void perf_pmu_cancel_txn(struct pmu *pmu)
{
perf_pmu_enable(pmu);
}
static int perf_event_idx_default(struct perf_event *event)
{
return 0;
}
/*
* Ensures all contexts with the same task_ctx_nr have the same
* pmu_cpu_context too.
*/
static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
{
struct pmu *pmu;
if (ctxn < 0)
return NULL;
list_for_each_entry(pmu, &pmus, entry) {
if (pmu->task_ctx_nr == ctxn)
return pmu->pmu_cpu_context;
}
return NULL;
}
static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
{
int cpu;
for_each_possible_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
if (cpuctx->unique_pmu == old_pmu)
cpuctx->unique_pmu = pmu;
}
}
static void free_pmu_context(struct pmu *pmu)
{
struct pmu *i;
mutex_lock(&pmus_lock);
/*
* Like a real lame refcount.
*/
list_for_each_entry(i, &pmus, entry) {
if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
update_pmu_context(i, pmu);
goto out;
}
}
free_percpu(pmu->pmu_cpu_context);
out:
mutex_unlock(&pmus_lock);
}
static struct idr pmu_idr;
static ssize_t
type_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct pmu *pmu = dev_get_drvdata(dev);
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
}
static DEVICE_ATTR_RO(type);
static ssize_t
perf_event_mux_interval_ms_show(struct device *dev,
struct device_attribute *attr,
char *page)
{
struct pmu *pmu = dev_get_drvdata(dev);
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
}
static DEFINE_MUTEX(mux_interval_mutex);
static ssize_t
perf_event_mux_interval_ms_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct pmu *pmu = dev_get_drvdata(dev);
int timer, cpu, ret;
ret = kstrtoint(buf, 0, &timer);
if (ret)
return ret;
if (timer < 1)
return -EINVAL;
/* same value, noting to do */
if (timer == pmu->hrtimer_interval_ms)
return count;
mutex_lock(&mux_interval_mutex);
pmu->hrtimer_interval_ms = timer;
/* update all cpuctx for this PMU */
get_online_cpus();
for_each_online_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
cpu_function_call(cpu,
(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
}
put_online_cpus();
mutex_unlock(&mux_interval_mutex);
return count;
}
static DEVICE_ATTR_RW(perf_event_mux_interval_ms);
static struct attribute *pmu_dev_attrs[] = {
&dev_attr_type.attr,
&dev_attr_perf_event_mux_interval_ms.attr,
NULL,
};
ATTRIBUTE_GROUPS(pmu_dev);
static int pmu_bus_running;
static struct bus_type pmu_bus = {
.name = "event_source",
.dev_groups = pmu_dev_groups,
};
static void pmu_dev_release(struct device *dev)
{
kfree(dev);
}
static int pmu_dev_alloc(struct pmu *pmu)
{
int ret = -ENOMEM;
pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
if (!pmu->dev)
goto out;
pmu->dev->groups = pmu->attr_groups;
device_initialize(pmu->dev);
ret = dev_set_name(pmu->dev, "%s", pmu->name);
if (ret)
goto free_dev;
dev_set_drvdata(pmu->dev, pmu);
pmu->dev->bus = &pmu_bus;
pmu->dev->release = pmu_dev_release;
ret = device_add(pmu->dev);
if (ret)
goto free_dev;
out:
return ret;
free_dev:
put_device(pmu->dev);
goto out;
}
static struct lock_class_key cpuctx_mutex;
static struct lock_class_key cpuctx_lock;
int perf_pmu_register(struct pmu *pmu, const char *name, int type)
{
int cpu, ret;
mutex_lock(&pmus_lock);
ret = -ENOMEM;
pmu->pmu_disable_count = alloc_percpu(int);
if (!pmu->pmu_disable_count)
goto unlock;
pmu->type = -1;
if (!name)
goto skip_type;
pmu->name = name;
if (type < 0) {
type = idr_alloc(&pmu_idr, pmu, PERF_TYPE_MAX, 0, GFP_KERNEL);
if (type < 0) {
ret = type;
goto free_pdc;
}
}
pmu->type = type;
if (pmu_bus_running) {
ret = pmu_dev_alloc(pmu);
if (ret)
goto free_idr;
}
skip_type:
pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
if (pmu->pmu_cpu_context)
goto got_cpu_context;
ret = -ENOMEM;
pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
if (!pmu->pmu_cpu_context)
goto free_dev;
for_each_possible_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
__perf_event_init_context(&cpuctx->ctx);
lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
cpuctx->ctx.pmu = pmu;
__perf_mux_hrtimer_init(cpuctx, cpu);
cpuctx->unique_pmu = pmu;
}
got_cpu_context:
if (!pmu->start_txn) {
if (pmu->pmu_enable) {
/*
* If we have pmu_enable/pmu_disable calls, install
* transaction stubs that use that to try and batch
* hardware accesses.
*/
pmu->start_txn = perf_pmu_start_txn;
pmu->commit_txn = perf_pmu_commit_txn;
pmu->cancel_txn = perf_pmu_cancel_txn;
} else {
pmu->start_txn = perf_pmu_nop_void;
pmu->commit_txn = perf_pmu_nop_int;
pmu->cancel_txn = perf_pmu_nop_void;
}
}
if (!pmu->pmu_enable) {
pmu->pmu_enable = perf_pmu_nop_void;
pmu->pmu_disable = perf_pmu_nop_void;
}
if (!pmu->event_idx)
pmu->event_idx = perf_event_idx_default;
list_add_rcu(&pmu->entry, &pmus);
atomic_set(&pmu->exclusive_cnt, 0);
ret = 0;
unlock:
mutex_unlock(&pmus_lock);
return ret;
free_dev:
device_del(pmu->dev);
put_device(pmu->dev);
free_idr:
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
free_pdc:
free_percpu(pmu->pmu_disable_count);
goto unlock;
}
EXPORT_SYMBOL_GPL(perf_pmu_register);
void perf_pmu_unregister(struct pmu *pmu)
{
mutex_lock(&pmus_lock);
list_del_rcu(&pmu->entry);
mutex_unlock(&pmus_lock);
/*
* We dereference the pmu list under both SRCU and regular RCU, so
* synchronize against both of those.
*/
synchronize_srcu(&pmus_srcu);
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
device_del(pmu->dev);
put_device(pmu->dev);
free_pmu_context(pmu);
}
EXPORT_SYMBOL_GPL(perf_pmu_unregister);
static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
{
struct perf_event_context *ctx = NULL;
int ret;
if (!try_module_get(pmu->module))
return -ENODEV;
if (event->group_leader != event) {
/*
* This ctx->mutex can nest when we're called through
* inheritance. See the perf_event_ctx_lock_nested() comment.
*/
ctx = perf_event_ctx_lock_nested(event->group_leader,
SINGLE_DEPTH_NESTING);
BUG_ON(!ctx);
}
event->pmu = pmu;
ret = pmu->event_init(event);
if (ctx)
perf_event_ctx_unlock(event->group_leader, ctx);
if (ret)
module_put(pmu->module);
return ret;
}
struct pmu *perf_init_event(struct perf_event *event)
{
struct pmu *pmu = NULL;
int idx;
int ret;
idx = srcu_read_lock(&pmus_srcu);
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
if (pmu) {
ret = perf_try_init_event(pmu, event);
if (ret)
pmu = ERR_PTR(ret);
goto unlock;
}
list_for_each_entry_rcu(pmu, &pmus, entry) {
ret = perf_try_init_event(pmu, event);
if (!ret)
goto unlock;
if (ret != -ENOENT) {
pmu = ERR_PTR(ret);
goto unlock;
}
}
pmu = ERR_PTR(-ENOENT);
unlock:
srcu_read_unlock(&pmus_srcu, idx);
return pmu;
}
static void account_event_cpu(struct perf_event *event, int cpu)
{
if (event->parent)
return;
if (is_cgroup_event(event))
atomic_inc(&per_cpu(perf_cgroup_events, cpu));
}
static void account_event(struct perf_event *event)
{
if (event->parent)
return;
if (event->attach_state & PERF_ATTACH_TASK)
static_key_slow_inc(&perf_sched_events.key);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
atomic_inc(&nr_comm_events);
if (event->attr.task)
atomic_inc(&nr_task_events);
if (event->attr.freq) {
if (atomic_inc_return(&nr_freq_events) == 1)
tick_nohz_full_kick_all();
}
if (has_branch_stack(event))
static_key_slow_inc(&perf_sched_events.key);
if (is_cgroup_event(event))
static_key_slow_inc(&perf_sched_events.key);
account_event_cpu(event, event->cpu);
}
/*
* Allocate and initialize a event structure
*/
static struct perf_event *
perf_event_alloc(struct perf_event_attr *attr, int cpu,
struct task_struct *task,
struct perf_event *group_leader,
struct perf_event *parent_event,
perf_overflow_handler_t overflow_handler,
void *context, int cgroup_fd)
{
struct pmu *pmu;
struct perf_event *event;
struct hw_perf_event *hwc;
long err = -EINVAL;
if ((unsigned)cpu >= nr_cpu_ids) {
if (!task || cpu != -1)
return ERR_PTR(-EINVAL);
}
event = kzalloc(sizeof(*event), GFP_KERNEL);
if (!event)
return ERR_PTR(-ENOMEM);
/*
* Single events are their own group leaders, with an
* empty sibling list:
*/
if (!group_leader)
group_leader = event;
mutex_init(&event->child_mutex);
INIT_LIST_HEAD(&event->child_list);
INIT_LIST_HEAD(&event->group_entry);
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
INIT_LIST_HEAD(&event->active_entry);
INIT_HLIST_NODE(&event->hlist_entry);
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
mutex_init(&event->mmap_mutex);
atomic_long_set(&event->refcount, 1);
event->cpu = cpu;
event->attr = *attr;
event->group_leader = group_leader;
event->pmu = NULL;
event->oncpu = -1;
event->parent = parent_event;
event->ns = get_pid_ns(task_active_pid_ns(current));
event->id = atomic64_inc_return(&perf_event_id);
event->state = PERF_EVENT_STATE_INACTIVE;
if (task) {
event->attach_state = PERF_ATTACH_TASK;
/*
* XXX pmu::event_init needs to know what task to account to
* and we cannot use the ctx information because we need the
* pmu before we get a ctx.
*/
event->hw.target = task;
}
event->clock = &local_clock;
if (parent_event)
event->clock = parent_event->clock;
if (!overflow_handler && parent_event) {
overflow_handler = parent_event->overflow_handler;
context = parent_event->overflow_handler_context;
}
event->overflow_handler = overflow_handler;
event->overflow_handler_context = context;
perf_event__state_init(event);
pmu = NULL;
hwc = &event->hw;
hwc->sample_period = attr->sample_period;
if (attr->freq && attr->sample_freq)
hwc->sample_period = 1;
hwc->last_period = hwc->sample_period;
local64_set(&hwc->period_left, hwc->sample_period);
/*
* we currently do not support PERF_FORMAT_GROUP on inherited events
*/
if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
goto err_ns;
if (!has_branch_stack(event))
event->attr.branch_sample_type = 0;
if (cgroup_fd != -1) {
err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
if (err)
goto err_ns;
}
pmu = perf_init_event(event);
if (!pmu)
goto err_ns;
else if (IS_ERR(pmu)) {
err = PTR_ERR(pmu);
goto err_ns;
}
err = exclusive_event_init(event);
if (err)
goto err_pmu;
if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
err = get_callchain_buffers();
if (err)
goto err_per_task;
}
}
return event;
err_per_task:
exclusive_event_destroy(event);
err_pmu:
if (event->destroy)
event->destroy(event);
module_put(pmu->module);
err_ns:
if (is_cgroup_event(event))
perf_detach_cgroup(event);
if (event->ns)
put_pid_ns(event->ns);
kfree(event);
return ERR_PTR(err);
}
static int perf_copy_attr(struct perf_event_attr __user *uattr,
struct perf_event_attr *attr)
{
u32 size;
int ret;
if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
return -EFAULT;
/*
* zero the full structure, so that a short copy will be nice.
*/
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
if (size > PAGE_SIZE) /* silly large */
goto err_size;
if (!size) /* abi compat */
size = PERF_ATTR_SIZE_VER0;
if (size < PERF_ATTR_SIZE_VER0)
goto err_size;
/*
* If we're handed a bigger struct than we know of,
* ensure all the unknown bits are 0 - i.e. new
* user-space does not rely on any kernel feature
* extensions we dont know about yet.
*/
if (size > sizeof(*attr)) {
unsigned char __user *addr;
unsigned char __user *end;
unsigned char val;
addr = (void __user *)uattr + sizeof(*attr);
end = (void __user *)uattr + size;
for (; addr < end; addr++) {
ret = get_user(val, addr);
if (ret)
return ret;
if (val)
goto err_size;
}
size = sizeof(*attr);
}
ret = copy_from_user(attr, uattr, size);
if (ret)
return -EFAULT;
if (attr->__reserved_1)
return -EINVAL;
if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
return -EINVAL;
if (attr->read_format & ~(PERF_FORMAT_MAX-1))
return -EINVAL;
if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
u64 mask = attr->branch_sample_type;
/* only using defined bits */
if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
return -EINVAL;
/* at least one branch bit must be set */
if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
return -EINVAL;
/* propagate priv level, when not set for branch */
if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
/* exclude_kernel checked on syscall entry */
if (!attr->exclude_kernel)
mask |= PERF_SAMPLE_BRANCH_KERNEL;
if (!attr->exclude_user)
mask |= PERF_SAMPLE_BRANCH_USER;
if (!attr->exclude_hv)
mask |= PERF_SAMPLE_BRANCH_HV;
/*
* adjust user setting (for HW filter setup)
*/
attr->branch_sample_type = mask;
}
/* privileged levels capture (kernel, hv): check permissions */
if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
&& perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
return -EACCES;
}
if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
ret = perf_reg_validate(attr->sample_regs_user);
if (ret)
return ret;
}
if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
if (!arch_perf_have_user_stack_dump())
return -ENOSYS;
/*
* We have __u32 type for the size, but so far
* we can only use __u16 as maximum due to the
* __u16 sample size limit.
*/
if (attr->sample_stack_user >= USHRT_MAX)
ret = -EINVAL;
else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
ret = -EINVAL;
}
if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
ret = perf_reg_validate(attr->sample_regs_intr);
out:
return ret;
err_size:
put_user(sizeof(*attr), &uattr->size);
ret = -E2BIG;
goto out;
}
static int
perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
{
struct ring_buffer *rb = NULL;
int ret = -EINVAL;
if (!output_event)
goto set;
/* don't allow circular references */
if (event == output_event)
goto out;
/*
* Don't allow cross-cpu buffers
*/
if (output_event->cpu != event->cpu)
goto out;
/*
* If its not a per-cpu rb, it must be the same task.
*/
if (output_event->cpu == -1 && output_event->ctx != event->ctx)
goto out;
/*
* Mixing clocks in the same buffer is trouble you don't need.
*/
if (output_event->clock != event->clock)
goto out;
/*
* If both events generate aux data, they must be on the same PMU
*/
if (has_aux(event) && has_aux(output_event) &&
event->pmu != output_event->pmu)
goto out;
set:
mutex_lock(&event->mmap_mutex);
/* Can't redirect output if we've got an active mmap() */
if (atomic_read(&event->mmap_count))
goto unlock;
if (output_event) {
/* get the rb we want to redirect to */
rb = ring_buffer_get(output_event);
if (!rb)
goto unlock;
}
ring_buffer_attach(event, rb);
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);
out:
return ret;
}
static void mutex_lock_double(struct mutex *a, struct mutex *b)
{
if (b < a)
swap(a, b);
mutex_lock(a);
mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
}
static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
{
bool nmi_safe = false;
switch (clk_id) {
case CLOCK_MONOTONIC:
event->clock = &ktime_get_mono_fast_ns;
nmi_safe = true;
break;
case CLOCK_MONOTONIC_RAW:
event->clock = &ktime_get_raw_fast_ns;
nmi_safe = true;
break;
case CLOCK_REALTIME:
event->clock = &ktime_get_real_ns;
break;
case CLOCK_BOOTTIME:
event->clock = &ktime_get_boot_ns;
break;
case CLOCK_TAI:
event->clock = &ktime_get_tai_ns;
break;
default:
return -EINVAL;
}
if (!nmi_safe && !(event->pmu->capabilities & PERF_PMU_CAP_NO_NMI))
return -EINVAL;
return 0;
}
/**
* sys_perf_event_open - open a performance event, associate it to a task/cpu
*
* @attr_uptr: event_id type attributes for monitoring/sampling
* @pid: target pid
* @cpu: target cpu
* @group_fd: group leader event fd
*/
SYSCALL_DEFINE5(perf_event_open,
struct perf_event_attr __user *, attr_uptr,
pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
{
struct perf_event *group_leader = NULL, *output_event = NULL;
struct perf_event *event, *sibling;
struct perf_event_attr attr;
struct perf_event_context *ctx, *uninitialized_var(gctx);
struct file *event_file = NULL;
struct fd group = {NULL, 0};
struct task_struct *task = NULL;
struct pmu *pmu;
int event_fd;
int move_group = 0;
int err;
int f_flags = O_RDWR;
int cgroup_fd = -1;
/* for future expandability... */
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
if (!attr.exclude_kernel) {
if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
return -EACCES;
}
if (attr.freq) {
if (attr.sample_freq > sysctl_perf_event_sample_rate)
return -EINVAL;
} else {
if (attr.sample_period & (1ULL << 63))
return -EINVAL;
}
/*
* In cgroup mode, the pid argument is used to pass the fd
* opened to the cgroup directory in cgroupfs. The cpu argument
* designates the cpu on which to monitor threads from that
* cgroup.
*/
if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
return -EINVAL;
if (flags & PERF_FLAG_FD_CLOEXEC)
f_flags |= O_CLOEXEC;
event_fd = get_unused_fd_flags(f_flags);
if (event_fd < 0)
return event_fd;
if (group_fd != -1) {
err = perf_fget_light(group_fd, &group);
if (err)
goto err_fd;
group_leader = group.file->private_data;
if (flags & PERF_FLAG_FD_OUTPUT)
output_event = group_leader;
if (flags & PERF_FLAG_FD_NO_GROUP)
group_leader = NULL;
}
if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
task = find_lively_task_by_vpid(pid);
if (IS_ERR(task)) {
err = PTR_ERR(task);
goto err_group_fd;
}
}
if (task && group_leader &&
group_leader->attr.inherit != attr.inherit) {
err = -EINVAL;
goto err_task;
}
get_online_cpus();
if (flags & PERF_FLAG_PID_CGROUP)
cgroup_fd = pid;
event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
NULL, NULL, cgroup_fd);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err_cpus;
}
if (is_sampling_event(event)) {
if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
err = -ENOTSUPP;
goto err_alloc;
}
}
account_event(event);
/*
* Special case software events and allow them to be part of
* any hardware group.
*/
pmu = event->pmu;
if (attr.use_clockid) {
err = perf_event_set_clock(event, attr.clockid);
if (err)
goto err_alloc;
}
if (group_leader &&
(is_software_event(event) != is_software_event(group_leader))) {
if (is_software_event(event)) {
/*
* If event and group_leader are not both a software
* event, and event is, then group leader is not.
*
* Allow the addition of software events to !software
* groups, this is safe because software events never
* fail to schedule.
*/
pmu = group_leader->pmu;
} else if (is_software_event(group_leader) &&
(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
/*
* In case the group is a pure software group, and we
* try to add a hardware event, move the whole group to
* the hardware context.
*/
move_group = 1;
}
}
/*
* Get the target context (task or percpu):
*/
ctx = find_get_context(pmu, task, event);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
goto err_alloc;
}
if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) {
err = -EBUSY;
goto err_context;
}
if (task) {
put_task_struct(task);
task = NULL;
}
/*
* Look up the group leader (we will attach this event to it):
*/
if (group_leader) {
err = -EINVAL;
/*
* Do not allow a recursive hierarchy (this new sibling
* becoming part of another group-sibling):
*/
if (group_leader->group_leader != group_leader)
goto err_context;
/* All events in a group should have the same clock */
if (group_leader->clock != event->clock)
goto err_context;
/*
* Do not allow to attach to a group in a different
* task or CPU context:
*/
if (move_group) {
/*
* Make sure we're both on the same task, or both
* per-cpu events.
*/
if (group_leader->ctx->task != ctx->task)
goto err_context;
/*
* Make sure we're both events for the same CPU;
* grouping events for different CPUs is broken; since
* you can never concurrently schedule them anyhow.
*/
if (group_leader->cpu != event->cpu)
goto err_context;
} else {
if (group_leader->ctx != ctx)
goto err_context;
}
/*
* Only a group leader can be exclusive or pinned
*/
if (attr.exclusive || attr.pinned)
goto err_context;
}
if (output_event) {
err = perf_event_set_output(event, output_event);
if (err)
goto err_context;
}
event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
f_flags);
if (IS_ERR(event_file)) {
err = PTR_ERR(event_file);
goto err_context;
}
if (move_group) {
gctx = group_leader->ctx;
/*
* See perf_event_ctx_lock() for comments on the details
* of swizzling perf_event::ctx.
*/
mutex_lock_double(&gctx->mutex, &ctx->mutex);
perf_remove_from_context(group_leader, false);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
perf_remove_from_context(sibling, false);
put_ctx(gctx);
}
} else {
mutex_lock(&ctx->mutex);
}
WARN_ON_ONCE(ctx->parent_ctx);
if (move_group) {
/*
* Wait for everybody to stop referencing the events through
* the old lists, before installing it on new lists.
*/
synchronize_rcu();
/*
* Install the group siblings before the group leader.
*
* Because a group leader will try and install the entire group
* (through the sibling list, which is still in-tact), we can
* end up with siblings installed in the wrong context.
*
* By installing siblings first we NO-OP because they're not
* reachable through the group lists.
*/
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
perf_event__state_init(sibling);
perf_install_in_context(ctx, sibling, sibling->cpu);
get_ctx(ctx);
}
/*
* Removing from the context ends up with disabled
* event. What we want here is event in the initial
* startup state, ready to be add into new context.
*/
perf_event__state_init(group_leader);
perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx);
}
if (!exclusive_event_installable(event, ctx)) {
err = -EBUSY;
mutex_unlock(&ctx->mutex);
fput(event_file);
goto err_context;
}
perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
if (move_group) {
mutex_unlock(&gctx->mutex);
put_ctx(gctx);
}
mutex_unlock(&ctx->mutex);
put_online_cpus();
event->owner = current;
mutex_lock(¤t->perf_event_mutex);
list_add_tail(&event->owner_entry, ¤t->perf_event_list);
mutex_unlock(¤t->perf_event_mutex);
/*
* Precalculate sample_data sizes
*/
perf_event__header_size(event);
perf_event__id_header_size(event);
/*
* Drop the reference on the group_event after placing the
* new event on the sibling_list. This ensures destruction
* of the group leader will find the pointer to itself in
* perf_group_detach().
*/
fdput(group);
fd_install(event_fd, event_file);
return event_fd;
err_context:
perf_unpin_context(ctx);
put_ctx(ctx);
err_alloc:
free_event(event);
err_cpus:
put_online_cpus();
err_task:
if (task)
put_task_struct(task);
err_group_fd:
fdput(group);
err_fd:
put_unused_fd(event_fd);
return err;
}
/**
* perf_event_create_kernel_counter
*
* @attr: attributes of the counter to create
* @cpu: cpu in which the counter is bound
* @task: task to profile (NULL for percpu)
*/
struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
struct task_struct *task,
perf_overflow_handler_t overflow_handler,
void *context)
{
struct perf_event_context *ctx;
struct perf_event *event;
int err;
/*
* Get the target context (task or percpu):
*/
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
overflow_handler, context, -1);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err;
}
/* Mark owner so we could distinguish it from user events. */
event->owner = EVENT_OWNER_KERNEL;
account_event(event);
ctx = find_get_context(event->pmu, task, event);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
goto err_free;
}
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
if (!exclusive_event_installable(event, ctx)) {
mutex_unlock(&ctx->mutex);
perf_unpin_context(ctx);
put_ctx(ctx);
err = -EBUSY;
goto err_free;
}
perf_install_in_context(ctx, event, cpu);
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
return event;
err_free:
free_event(event);
err:
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
{
struct perf_event_context *src_ctx;
struct perf_event_context *dst_ctx;
struct perf_event *event, *tmp;
LIST_HEAD(events);
src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;
/*
* See perf_event_ctx_lock() for comments on the details
* of swizzling perf_event::ctx.
*/
mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
event_entry) {
perf_remove_from_context(event, false);
unaccount_event_cpu(event, src_cpu);
put_ctx(src_ctx);
list_add(&event->migrate_entry, &events);
}
/*
* Wait for the events to quiesce before re-instating them.
*/
synchronize_rcu();
/*
* Re-instate events in 2 passes.
*
* Skip over group leaders and only install siblings on this first
* pass, siblings will not get enabled without a leader, however a
* leader will enable its siblings, even if those are still on the old
* context.
*/
list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
if (event->group_leader == event)
continue;
list_del(&event->migrate_entry);
if (event->state >= PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_INACTIVE;
account_event_cpu(event, dst_cpu);
perf_install_in_context(dst_ctx, event, dst_cpu);
get_ctx(dst_ctx);
}
/*
* Once all the siblings are setup properly, install the group leaders
* to make it go.
*/
list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
list_del(&event->migrate_entry);
if (event->state >= PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_INACTIVE;
account_event_cpu(event, dst_cpu);
perf_install_in_context(dst_ctx, event, dst_cpu);
get_ctx(dst_ctx);
}
mutex_unlock(&dst_ctx->mutex);
mutex_unlock(&src_ctx->mutex);
}
EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
kkkkk09
最新推荐文章于 2024-10-17 19:11:48 发布