* Copyright (c) 2018 Facebook, Inc.
* Author: Johannes Weiner <hannes@cmpxchg.org>
*
+ * Polling support by Suren Baghdasaryan <surenb@google.com>
+ * Copyright (c) 2018 Google, Inc.
+ *
* When CPU, memory and IO are contended, tasks experience delays that
* reduce throughput and introduce latencies into the workload. Memory
* and IO contention, in addition, can cause a full loss of forward
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/seqlock.h>
+#include <linux/uaccess.h>
#include <linux/cgroup.h>
#include <linux/module.h>
#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/file.h>
+#include <linux/poll.h>
#include <linux/psi.h>
#include "sched.h"
DEFINE_STATIC_KEY_FALSE(psi_disabled);
#ifdef CONFIG_PSI_DEFAULT_DISABLED
-bool psi_enable;
+static bool psi_enable;
#else
-bool psi_enable = true;
+static bool psi_enable = true;
#endif
static int __init setup_psi(char *str)
{
#define EXP_60s 1981 /* 1/exp(2s/60s) */
#define EXP_300s 2034 /* 1/exp(2s/300s) */
+/* PSI trigger definitions */
+#define WINDOW_MIN_US 500000 /* Min window size is 500ms */
+#define WINDOW_MAX_US 10000000 /* Max window size is 10s */
+#define UPDATES_PER_WINDOW 10 /* 10 updates per window */
+
/* Sampling frequency in nanoseconds */
static u64 psi_period __read_mostly;
/* System-level pressure and stall tracking */
static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu);
-static struct psi_group psi_system = {
+struct psi_group psi_system = {
.pcpu = &system_group_pcpu,
};
-static void psi_update_work(struct work_struct *work);
+static void psi_avgs_work(struct work_struct *work);
static void group_init(struct psi_group *group)
{
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
- group->next_update = sched_clock() + psi_period;
- INIT_DELAYED_WORK(&group->clock_work, psi_update_work);
- mutex_init(&group->stat_lock);
+ group->avg_next_update = sched_clock() + psi_period;
+ INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
+ mutex_init(&group->avgs_lock);
+ /* Init trigger-related members */
+ atomic_set(&group->poll_scheduled, 0);
+ mutex_init(&group->trigger_lock);
+ INIT_LIST_HEAD(&group->triggers);
+ memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
+ group->poll_states = 0;
+ group->poll_min_period = U32_MAX;
+ memset(group->polling_total, 0, sizeof(group->polling_total));
+ group->polling_next_update = ULLONG_MAX;
+ group->polling_until = 0;
+ rcu_assign_pointer(group->poll_kworker, NULL);
}
void __init psi_init(void)
}
}
-static void get_recent_times(struct psi_group *group, int cpu, u32 *times)
+static void get_recent_times(struct psi_group *group, int cpu,
+ enum psi_aggregators aggregator, u32 *times,
+ u32 *pchanged_states)
{
struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
- unsigned int tasks[NR_PSI_TASK_COUNTS];
u64 now, state_start;
+ enum psi_states s;
unsigned int seq;
- int s;
+ u32 state_mask;
+
+ *pchanged_states = 0;
/* Snapshot a coherent view of the CPU state */
do {
seq = read_seqcount_begin(&groupc->seq);
now = cpu_clock(cpu);
memcpy(times, groupc->times, sizeof(groupc->times));
- memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
+ state_mask = groupc->state_mask;
state_start = groupc->state_start;
} while (read_seqcount_retry(&groupc->seq, seq));
* (u32) and our reported pressure close to what's
* actually happening.
*/
- if (test_state(tasks, s))
+ if (state_mask & (1 << s))
times[s] += now - state_start;
- delta = times[s] - groupc->times_prev[s];
- groupc->times_prev[s] = times[s];
+ delta = times[s] - groupc->times_prev[aggregator][s];
+ groupc->times_prev[aggregator][s] = times[s];
times[s] = delta;
+ if (delta)
+ *pchanged_states |= (1 << s);
}
}
avg[2] = calc_load(avg[2], EXP_300s, pct);
}
-static bool update_stats(struct psi_group *group)
+static void collect_percpu_times(struct psi_group *group,
+ enum psi_aggregators aggregator,
+ u32 *pchanged_states)
{
u64 deltas[NR_PSI_STATES - 1] = { 0, };
- unsigned long missed_periods = 0;
unsigned long nonidle_total = 0;
- u64 now, expires, period;
+ u32 changed_states = 0;
int cpu;
int s;
- mutex_lock(&group->stat_lock);
-
/*
* Collect the per-cpu time buckets and average them into a
* single time sample that is normalized to wallclock time.
for_each_possible_cpu(cpu) {
u32 times[NR_PSI_STATES];
u32 nonidle;
+ u32 cpu_changed_states;
- get_recent_times(group, cpu, times);
+ get_recent_times(group, cpu, aggregator, times,
+ &cpu_changed_states);
+ changed_states |= cpu_changed_states;
nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]);
nonidle_total += nonidle;
/* total= */
for (s = 0; s < NR_PSI_STATES - 1; s++)
- group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));
+ group->total[aggregator][s] +=
+ div_u64(deltas[s], max(nonidle_total, 1UL));
+
+ if (pchanged_states)
+ *pchanged_states = changed_states;
+}
+
+static u64 update_averages(struct psi_group *group, u64 now)
+{
+ unsigned long missed_periods = 0;
+ u64 expires, period;
+ u64 avg_next_update;
+ int s;
/* avgX= */
- now = sched_clock();
- expires = group->next_update;
- if (now < expires)
- goto out;
+ expires = group->avg_next_update;
if (now - expires >= psi_period)
missed_periods = div_u64(now - expires, psi_period);
* But the deltas we sample out of the per-cpu buckets above
* are based on the actual time elapsing between clock ticks.
*/
- group->next_update = expires + ((1 + missed_periods) * psi_period);
- period = now - (group->last_update + (missed_periods * psi_period));
- group->last_update = now;
+ avg_next_update = expires + ((1 + missed_periods) * psi_period);
+ period = now - (group->avg_last_update + (missed_periods * psi_period));
+ group->avg_last_update = now;
for (s = 0; s < NR_PSI_STATES - 1; s++) {
u32 sample;
- sample = group->total[s] - group->total_prev[s];
+ sample = group->total[PSI_AVGS][s] - group->avg_total[s];
/*
* Due to the lockless sampling of the time buckets,
* recorded time deltas can slip into the next period,
*/
if (sample > period)
sample = period;
- group->total_prev[s] += sample;
+ group->avg_total[s] += sample;
calc_avgs(group->avg[s], missed_periods, sample, period);
}
-out:
- mutex_unlock(&group->stat_lock);
- return nonidle_total;
+
+ return avg_next_update;
}
-static void psi_update_work(struct work_struct *work)
+static void psi_avgs_work(struct work_struct *work)
{
struct delayed_work *dwork;
struct psi_group *group;
+ u32 changed_states;
bool nonidle;
+ u64 now;
dwork = to_delayed_work(work);
- group = container_of(dwork, struct psi_group, clock_work);
+ group = container_of(dwork, struct psi_group, avgs_work);
+
+ mutex_lock(&group->avgs_lock);
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_AVGS, &changed_states);
+ nonidle = changed_states & (1 << PSI_NONIDLE);
/*
* If there is task activity, periodically fold the per-cpu
* times and feed samples into the running averages. If things
* Once restarted, we'll catch up the running averages in one
* go - see calc_avgs() and missed_periods.
*/
-
- nonidle = update_stats(group);
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
if (nonidle) {
- unsigned long delay = 0;
- u64 now;
+ schedule_delayed_work(dwork, nsecs_to_jiffies(
+ group->avg_next_update - now) + 1);
+ }
+
+ mutex_unlock(&group->avgs_lock);
+}
+
+/* Trigger tracking window manupulations */
+static void window_reset(struct psi_window *win, u64 now, u64 value,
+ u64 prev_growth)
+{
+ win->start_time = now;
+ win->start_value = value;
+ win->prev_growth = prev_growth;
+}
+
+/*
+ * PSI growth tracking window update and growth calculation routine.
+ *
+ * This approximates a sliding tracking window by interpolating
+ * partially elapsed windows using historical growth data from the
+ * previous intervals. This minimizes memory requirements (by not storing
+ * all the intermediate values in the previous window) and simplifies
+ * the calculations. It works well because PSI signal changes only in
+ * positive direction and over relatively small window sizes the growth
+ * is close to linear.
+ */
+static u64 window_update(struct psi_window *win, u64 now, u64 value)
+{
+ u64 elapsed;
+ u64 growth;
+
+ elapsed = now - win->start_time;
+ growth = value - win->start_value;
+ /*
+ * After each tracking window passes win->start_value and
+ * win->start_time get reset and win->prev_growth stores
+ * the average per-window growth of the previous window.
+ * win->prev_growth is then used to interpolate additional
+ * growth from the previous window assuming it was linear.
+ */
+ if (elapsed > win->size)
+ window_reset(win, now, value, growth);
+ else {
+ u32 remaining;
+
+ remaining = win->size - elapsed;
+ growth += div_u64(win->prev_growth * remaining, win->size);
+ }
+
+ return growth;
+}
+
+static void init_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+
+ list_for_each_entry(t, &group->triggers, node)
+ window_reset(&t->win, now,
+ group->total[PSI_POLL][t->state], 0);
+ memcpy(group->polling_total, group->total[PSI_POLL],
+ sizeof(group->polling_total));
+ group->polling_next_update = now + group->poll_min_period;
+}
+
+static u64 update_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+ bool new_stall = false;
+ u64 *total = group->total[PSI_POLL];
+
+ /*
+ * On subsequent updates, calculate growth deltas and let
+ * watchers know when their specified thresholds are exceeded.
+ */
+ list_for_each_entry(t, &group->triggers, node) {
+ u64 growth;
+
+ /* Check for stall activity */
+ if (group->polling_total[t->state] == total[t->state])
+ continue;
+
+ /*
+ * Multiple triggers might be looking at the same state,
+ * remember to update group->polling_total[] once we've
+ * been through all of them. Also remember to extend the
+ * polling time if we see new stall activity.
+ */
+ new_stall = true;
- now = sched_clock();
- if (group->next_update > now)
- delay = nsecs_to_jiffies(group->next_update - now) + 1;
- schedule_delayed_work(dwork, delay);
+ /* Calculate growth since last update */
+ growth = window_update(&t->win, now, total[t->state]);
+ if (growth < t->threshold)
+ continue;
+
+ /* Limit event signaling to once per window */
+ if (now < t->last_event_time + t->win.size)
+ continue;
+
+ /* Generate an event */
+ if (cmpxchg(&t->event, 0, 1) == 0)
+ wake_up_interruptible(&t->event_wait);
+ t->last_event_time = now;
}
+
+ if (new_stall)
+ memcpy(group->polling_total, total,
+ sizeof(group->polling_total));
+
+ return now + group->poll_min_period;
+}
+
+/*
+ * Schedule polling if it's not already scheduled. It's safe to call even from
+ * hotpath because even though kthread_queue_delayed_work takes worker->lock
+ * spinlock that spinlock is never contended due to poll_scheduled atomic
+ * preventing such competition.
+ */
+static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
+{
+ struct kthread_worker *kworker;
+
+ /* Do not reschedule if already scheduled */
+ if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+ return;
+
+ rcu_read_lock();
+
+ kworker = rcu_dereference(group->poll_kworker);
+ /*
+ * kworker might be NULL in case psi_trigger_destroy races with
+ * psi_task_change (hotpath) which can't use locks
+ */
+ if (likely(kworker))
+ kthread_queue_delayed_work(kworker, &group->poll_work, delay);
+ else
+ atomic_set(&group->poll_scheduled, 0);
+
+ rcu_read_unlock();
+}
+
+static void psi_poll_work(struct kthread_work *work)
+{
+ struct kthread_delayed_work *dwork;
+ struct psi_group *group;
+ u32 changed_states;
+ u64 now;
+
+ dwork = container_of(work, struct kthread_delayed_work, work);
+ group = container_of(dwork, struct psi_group, poll_work);
+
+ atomic_set(&group->poll_scheduled, 0);
+
+ mutex_lock(&group->trigger_lock);
+
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_POLL, &changed_states);
+
+ if (changed_states & group->poll_states) {
+ /* Initialize trigger windows when entering polling mode */
+ if (now > group->polling_until)
+ init_triggers(group, now);
+
+ /*
+ * Keep the monitor active for at least the duration of the
+ * minimum tracking window as long as monitor states are
+ * changing.
+ */
+ group->polling_until = now +
+ group->poll_min_period * UPDATES_PER_WINDOW;
+ }
+
+ if (now > group->polling_until) {
+ group->polling_next_update = ULLONG_MAX;
+ goto out;
+ }
+
+ if (now >= group->polling_next_update)
+ group->polling_next_update = update_triggers(group, now);
+
+ psi_schedule_poll_work(group,
+ nsecs_to_jiffies(group->polling_next_update - now) + 1);
+
+out:
+ mutex_unlock(&group->trigger_lock);
}
static void record_times(struct psi_group_cpu *groupc, int cpu,
delta = now - groupc->state_start;
groupc->state_start = now;
- if (test_state(groupc->tasks, PSI_IO_SOME)) {
+ if (groupc->state_mask & (1 << PSI_IO_SOME)) {
groupc->times[PSI_IO_SOME] += delta;
- if (test_state(groupc->tasks, PSI_IO_FULL))
+ if (groupc->state_mask & (1 << PSI_IO_FULL))
groupc->times[PSI_IO_FULL] += delta;
}
- if (test_state(groupc->tasks, PSI_MEM_SOME)) {
+ if (groupc->state_mask & (1 << PSI_MEM_SOME)) {
groupc->times[PSI_MEM_SOME] += delta;
- if (test_state(groupc->tasks, PSI_MEM_FULL))
+ if (groupc->state_mask & (1 << PSI_MEM_FULL))
groupc->times[PSI_MEM_FULL] += delta;
else if (memstall_tick) {
u32 sample;
}
}
- if (test_state(groupc->tasks, PSI_CPU_SOME))
+ if (groupc->state_mask & (1 << PSI_CPU_SOME))
groupc->times[PSI_CPU_SOME] += delta;
- if (test_state(groupc->tasks, PSI_NONIDLE))
+ if (groupc->state_mask & (1 << PSI_NONIDLE))
groupc->times[PSI_NONIDLE] += delta;
}
-static void psi_group_change(struct psi_group *group, int cpu,
- unsigned int clear, unsigned int set)
+static u32 psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set)
{
struct psi_group_cpu *groupc;
unsigned int t, m;
+ enum psi_states s;
+ u32 state_mask = 0;
groupc = per_cpu_ptr(group->pcpu, cpu);
if (set & (1 << t))
groupc->tasks[t]++;
+ /* Calculate state mask representing active states */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ if (test_state(groupc->tasks, s))
+ state_mask |= (1 << s);
+ }
+ groupc->state_mask = state_mask;
+
write_seqcount_end(&groupc->seq);
+
+ return state_mask;
}
static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
*/
if (unlikely((clear & TSK_RUNNING) &&
(task->flags & PF_WQ_WORKER) &&
- wq_worker_last_func(task) == psi_update_work))
+ wq_worker_last_func(task) == psi_avgs_work))
wake_clock = false;
while ((group = iterate_groups(task, &iter))) {
- psi_group_change(group, cpu, clear, set);
- if (wake_clock && !delayed_work_pending(&group->clock_work))
- schedule_delayed_work(&group->clock_work, PSI_FREQ);
+ u32 state_mask = psi_group_change(group, cpu, clear, set);
+
+ if (state_mask & group->poll_states)
+ psi_schedule_poll_work(group, 1);
+
+ if (wake_clock && !delayed_work_pending(&group->avgs_work))
+ schedule_delayed_work(&group->avgs_work, PSI_FREQ);
}
}
if (static_branch_likely(&psi_disabled))
return;
- cancel_delayed_work_sync(&cgroup->psi.clock_work);
+ cancel_delayed_work_sync(&cgroup->psi.avgs_work);
free_percpu(cgroup->psi.pcpu);
+ /* All triggers must be removed by now */
+ WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n");
}
/**
int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
{
int full;
+ u64 now;
if (static_branch_likely(&psi_disabled))
return -EOPNOTSUPP;
- update_stats(group);
+ /* Update averages before reporting them */
+ mutex_lock(&group->avgs_lock);
+ now = sched_clock();
+ collect_percpu_times(group, PSI_AVGS, NULL);
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
+ mutex_unlock(&group->avgs_lock);
for (full = 0; full < 2 - (res == PSI_CPU); full++) {
unsigned long avg[3];
for (w = 0; w < 3; w++)
avg[w] = group->avg[res * 2 + full][w];
- total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC);
+ total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+ NSEC_PER_USEC);
seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
full ? "full" : "some",
return single_open(file, psi_cpu_show, NULL);
}
+struct psi_trigger *psi_trigger_create(struct psi_group *group,
+ char *buf, size_t nbytes, enum psi_res res)
+{
+ struct psi_trigger *t;
+ enum psi_states state;
+ u32 threshold_us;
+ u32 window_us;
+
+ if (static_branch_likely(&psi_disabled))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_SOME + res * 2;
+ else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_FULL + res * 2;
+ else
+ return ERR_PTR(-EINVAL);
+
+ if (state >= PSI_NONIDLE)
+ return ERR_PTR(-EINVAL);
+
+ if (window_us < WINDOW_MIN_US ||
+ window_us > WINDOW_MAX_US)
+ return ERR_PTR(-EINVAL);
+
+ /* Check threshold */
+ if (threshold_us == 0 || threshold_us > window_us)
+ return ERR_PTR(-EINVAL);
+
+ t = kmalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return ERR_PTR(-ENOMEM);
+
+ t->group = group;
+ t->state = state;
+ t->threshold = threshold_us * NSEC_PER_USEC;
+ t->win.size = window_us * NSEC_PER_USEC;
+ window_reset(&t->win, 0, 0, 0);
+
+ t->event = 0;
+ t->last_event_time = 0;
+ init_waitqueue_head(&t->event_wait);
+ kref_init(&t->refcount);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!rcu_access_pointer(group->poll_kworker)) {
+ struct sched_param param = {
+ .sched_priority = 1,
+ };
+ struct kthread_worker *kworker;
+
+ kworker = kthread_create_worker(0, "psimon");
+ if (IS_ERR(kworker)) {
+ kfree(t);
+ mutex_unlock(&group->trigger_lock);
+ return ERR_CAST(kworker);
+ }
+ sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m);
+ kthread_init_delayed_work(&group->poll_work,
+ psi_poll_work);
+ rcu_assign_pointer(group->poll_kworker, kworker);
+ }
+
+ list_add(&t->node, &group->triggers);
+ group->poll_min_period = min(group->poll_min_period,
+ div_u64(t->win.size, UPDATES_PER_WINDOW));
+ group->nr_triggers[t->state]++;
+ group->poll_states |= (1 << t->state);
+
+ mutex_unlock(&group->trigger_lock);
+
+ return t;
+}
+
+static void psi_trigger_destroy(struct kref *ref)
+{
+ struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
+ struct psi_group *group = t->group;
+ struct kthread_worker *kworker_to_destroy = NULL;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ /*
+ * Wakeup waiters to stop polling. Can happen if cgroup is deleted
+ * from under a polling process.
+ */
+ wake_up_interruptible(&t->event_wait);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!list_empty(&t->node)) {
+ struct psi_trigger *tmp;
+ u64 period = ULLONG_MAX;
+
+ list_del(&t->node);
+ group->nr_triggers[t->state]--;
+ if (!group->nr_triggers[t->state])
+ group->poll_states &= ~(1 << t->state);
+ /* reset min update period for the remaining triggers */
+ list_for_each_entry(tmp, &group->triggers, node)
+ period = min(period, div_u64(tmp->win.size,
+ UPDATES_PER_WINDOW));
+ group->poll_min_period = period;
+ /* Destroy poll_kworker when the last trigger is destroyed */
+ if (group->poll_states == 0) {
+ group->polling_until = 0;
+ kworker_to_destroy = rcu_dereference_protected(
+ group->poll_kworker,
+ lockdep_is_held(&group->trigger_lock));
+ rcu_assign_pointer(group->poll_kworker, NULL);
+ }
+ }
+
+ mutex_unlock(&group->trigger_lock);
+
+ /*
+ * Wait for both *trigger_ptr from psi_trigger_replace and
+ * poll_kworker RCUs to complete their read-side critical sections
+ * before destroying the trigger and optionally the poll_kworker
+ */
+ synchronize_rcu();
+ /*
+ * Destroy the kworker after releasing trigger_lock to prevent a
+ * deadlock while waiting for psi_poll_work to acquire trigger_lock
+ */
+ if (kworker_to_destroy) {
+ /*
+ * After the RCU grace period has expired, the worker
+ * can no longer be found through group->poll_kworker.
+ * But it might have been already scheduled before
+ * that - deschedule it cleanly before destroying it.
+ */
+ kthread_cancel_delayed_work_sync(&group->poll_work);
+ atomic_set(&group->poll_scheduled, 0);
+
+ kthread_destroy_worker(kworker_to_destroy);
+ }
+ kfree(t);
+}
+
+void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new)
+{
+ struct psi_trigger *old = *trigger_ptr;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ rcu_assign_pointer(*trigger_ptr, new);
+ if (old)
+ kref_put(&old->refcount, psi_trigger_destroy);
+}
+
+__poll_t psi_trigger_poll(void **trigger_ptr,
+ struct file *file, poll_table *wait)
+{
+ __poll_t ret = DEFAULT_POLLMASK;
+ struct psi_trigger *t;
+
+ if (static_branch_likely(&psi_disabled))
+ return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
+
+ rcu_read_lock();
+
+ t = rcu_dereference(*(void __rcu __force **)trigger_ptr);
+ if (!t) {
+ rcu_read_unlock();
+ return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
+ }
+ kref_get(&t->refcount);
+
+ rcu_read_unlock();
+
+ poll_wait(file, &t->event_wait, wait);
+
+ if (cmpxchg(&t->event, 1, 0) == 1)
+ ret |= EPOLLPRI;
+
+ kref_put(&t->refcount, psi_trigger_destroy);
+
+ return ret;
+}
+
+static ssize_t psi_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, enum psi_res res)
+{
+ char buf[32];
+ size_t buf_size;
+ struct seq_file *seq;
+ struct psi_trigger *new;
+
+ if (static_branch_likely(&psi_disabled))
+ return -EOPNOTSUPP;
+
+ buf_size = min(nbytes, (sizeof(buf) - 1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size - 1] = '\0';
+
+ new = psi_trigger_create(&psi_system, buf, nbytes, res);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ seq = file->private_data;
+ /* Take seq->lock to protect seq->private from concurrent writes */
+ mutex_lock(&seq->lock);
+ psi_trigger_replace(&seq->private, new);
+ mutex_unlock(&seq->lock);
+
+ return nbytes;
+}
+
+static ssize_t psi_io_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_IO);
+}
+
+static ssize_t psi_memory_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_MEM);
+}
+
+static ssize_t psi_cpu_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_CPU);
+}
+
+static __poll_t psi_fop_poll(struct file *file, poll_table *wait)
+{
+ struct seq_file *seq = file->private_data;
+
+ return psi_trigger_poll(&seq->private, file, wait);
+}
+
+static int psi_fop_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+
+ psi_trigger_replace(&seq->private, NULL);
+ return single_release(inode, file);
+}
+
static const struct file_operations psi_io_fops = {
.open = psi_io_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_io_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static const struct file_operations psi_memory_fops = {
.open = psi_memory_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_memory_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static const struct file_operations psi_cpu_fops = {
.open = psi_cpu_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_cpu_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static int __init psi_proc_init(void)
git.samba.org / sfrench / cifs-2.6.git / blobdiff