Google Git Google Git
Sign in
android-kvm/linux/4dfdee23989224860d5ca897350863dd222736a3/./kernel/rcu/tasks.h
blob: f4da5fad70f516572d373bcd243e0905f0703ef3 [file]
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Task-based RCU implementations.
*
* Copyright (C) 2020 Paul E. McKenney
*/
#ifdef CONFIG_TASKS_RCU_GENERIC
#include "rcu_segcblist.h"
////////////////////////////////////////////////////////////////////////
//
// Generic data structures.
struct rcu_tasks;
typedef void (*rcu_tasks_gp_func_t)(struct rcu_tasks *rtp);
typedef void (*pregp_func_t)(struct list_head *hop);
typedef void (*pertask_func_t)(struct task_struct *t, struct list_head *hop);
typedef void (*postscan_func_t)(struct list_head *hop);
typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
/**
* struct rcu_tasks_percpu - Per-CPU component of definition for a Tasks-RCU-like mechanism.
* @cblist: Callback list.
* @lock: Lock protecting per-CPU callback list.
* @rtp_jiffies: Jiffies counter value for statistics.
* @lazy_timer: Timer to unlazify callbacks.
* @urgent_gp: Number of additional non-lazy grace periods.
* @rtp_n_lock_retries: Rough lock-contention statistic.
* @rtp_work: Work queue for invoking callbacks.
* @rtp_irq_work: IRQ work queue for deferred wakeups.
* @barrier_q_head: RCU callback for barrier operation.
* @rtp_blkd_tasks: List of tasks blocked as readers.
* @rtp_exit_list: List of tasks in the latter portion of do_exit().
* @cpu: CPU number corresponding to this entry.
* @index: Index of this CPU in rtpcp_array of the rcu_tasks structure.
* @rtpp: Pointer to the rcu_tasks structure.
*/
struct rcu_tasks_percpu {
struct rcu_segcblist cblist;
raw_spinlock_t __private lock;
unsigned long rtp_jiffies;
unsigned long rtp_n_lock_retries;
struct timer_list lazy_timer;
unsigned int urgent_gp;
struct work_struct rtp_work;
struct irq_work rtp_irq_work;
struct rcu_head barrier_q_head;
struct list_head rtp_blkd_tasks;
struct list_head rtp_exit_list;
int cpu;
int index;
struct rcu_tasks *rtpp;
};
/**
* struct rcu_tasks - Definition for a Tasks-RCU-like mechanism.
* @cbs_wait: RCU wait allowing a new callback to get kthread's attention.
* @cbs_gbl_lock: Lock protecting callback list.
* @tasks_gp_mutex: Mutex protecting grace period, needed during mid-boot dead zone.
* @gp_func: This flavor's grace-period-wait function.
* @gp_state: Grace period's most recent state transition (debugging).
* @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
* @init_fract: Initial backoff sleep interval.
* @gp_jiffies: Time of last @gp_state transition.
* @gp_start: Most recent grace-period start in jiffies.
* @tasks_gp_seq: Number of grace periods completed since boot in upper bits.
* @n_ipis: Number of IPIs sent to encourage grace periods to end.
* @n_ipis_fails: Number of IPI-send failures.
* @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
* @lazy_jiffies: Number of jiffies to allow callbacks to be lazy.
* @pregp_func: This flavor's pre-grace-period function (optional).
* @pertask_func: This flavor's per-task scan function (optional).
* @postscan_func: This flavor's post-task scan function (optional).
* @holdouts_func: This flavor's holdout-list scan function (optional).
* @postgp_func: This flavor's post-grace-period function (optional).
* @call_func: This flavor's call_rcu()-equivalent function.
* @wait_state: Task state for synchronous grace-period waits (default TASK_UNINTERRUPTIBLE).
* @rtpcpu: This flavor's rcu_tasks_percpu structure.
* @rtpcp_array: Array of pointers to rcu_tasks_percpu structure of CPUs in cpu_possible_mask.
* @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks.
* @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing.
* @percpu_dequeue_lim: Number of per-CPU callback queues in use for dequeuing.
* @percpu_dequeue_gpseq: RCU grace-period number to propagate enqueue limit to dequeuers.
* @barrier_q_mutex: Serialize barrier operations.
* @barrier_q_count: Number of queues being waited on.
* @barrier_q_completion: Barrier wait/wakeup mechanism.
* @barrier_q_seq: Sequence number for barrier operations.
* @barrier_q_start: Most recent barrier start in jiffies.
* @name: This flavor's textual name.
* @kname: This flavor's kthread name.
*/
struct rcu_tasks {
struct rcuwait cbs_wait;
raw_spinlock_t cbs_gbl_lock;
struct mutex tasks_gp_mutex;
int gp_state;
int gp_sleep;
int init_fract;
unsigned long gp_jiffies;
unsigned long gp_start;
unsigned long tasks_gp_seq;
unsigned long n_ipis;
unsigned long n_ipis_fails;
struct task_struct *kthread_ptr;
unsigned long lazy_jiffies;
rcu_tasks_gp_func_t gp_func;
pregp_func_t pregp_func;
pertask_func_t pertask_func;
postscan_func_t postscan_func;
holdouts_func_t holdouts_func;
postgp_func_t postgp_func;
call_rcu_func_t call_func;
unsigned int wait_state;
struct rcu_tasks_percpu __percpu *rtpcpu;
struct rcu_tasks_percpu **rtpcp_array;
int percpu_enqueue_shift;
int percpu_enqueue_lim;
int percpu_dequeue_lim;
unsigned long percpu_dequeue_gpseq;
struct mutex barrier_q_mutex;
atomic_t barrier_q_count;
struct completion barrier_q_completion;
unsigned long barrier_q_seq;
unsigned long barrier_q_start;
char *name;
char *kname;
};
static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp);
#define DEFINE_RCU_TASKS(rt_name, gp, call, n) \
static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = { \
.lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ## __percpu.cbs_pcpu_lock), \
.rtp_irq_work = IRQ_WORK_INIT_HARD(call_rcu_tasks_iw_wakeup), \
}; \
static struct rcu_tasks rt_name = \
{ \
.cbs_wait = __RCUWAIT_INITIALIZER(rt_name.wait), \
.cbs_gbl_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_gbl_lock), \
.tasks_gp_mutex = __MUTEX_INITIALIZER(rt_name.tasks_gp_mutex), \
.gp_func = gp, \
.call_func = call, \
.wait_state = TASK_UNINTERRUPTIBLE, \
.rtpcpu = &rt_name ## __percpu, \
.lazy_jiffies = DIV_ROUND_UP(HZ, 4), \
.name = n, \
.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS), \
.percpu_enqueue_lim = 1, \
.percpu_dequeue_lim = 1, \
.barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex), \
.barrier_q_seq = (0UL - 50UL) << RCU_SEQ_CTR_SHIFT, \
.kname = #rt_name, \
}
#ifdef CONFIG_TASKS_RCU
/* Report delay of scan exiting tasklist in rcu_tasks_postscan(). */
static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall);
#endif
/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
#define RCU_TASK_BOOT_STALL_TIMEOUT (HZ * 30)
#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
module_param(rcu_task_stall_timeout, int, 0644);
#define RCU_TASK_STALL_INFO (HZ * 10)
static int rcu_task_stall_info __read_mostly = RCU_TASK_STALL_INFO;
module_param(rcu_task_stall_info, int, 0644);
static int rcu_task_stall_info_mult __read_mostly = 3;
module_param(rcu_task_stall_info_mult, int, 0444);
static int rcu_task_enqueue_lim __read_mostly = -1;
module_param(rcu_task_enqueue_lim, int, 0444);
static bool rcu_task_cb_adjust;
static int rcu_task_contend_lim __read_mostly = 100;
module_param(rcu_task_contend_lim, int, 0444);
static int rcu_task_collapse_lim __read_mostly = 10;
module_param(rcu_task_collapse_lim, int, 0444);
static int rcu_task_lazy_lim __read_mostly = 32;
module_param(rcu_task_lazy_lim, int, 0444);
static int rcu_task_cpu_ids;
/* RCU tasks grace-period state for debugging. */
#define RTGS_INIT 0
#define RTGS_WAIT_WAIT_CBS 1
#define RTGS_WAIT_GP 2
#define RTGS_PRE_WAIT_GP 3
#define RTGS_SCAN_TASKLIST 4
#define RTGS_POST_SCAN_TASKLIST 5
#define RTGS_WAIT_SCAN_HOLDOUTS 6
#define RTGS_SCAN_HOLDOUTS 7
#define RTGS_POST_GP 8
#define RTGS_WAIT_READERS 9
#define RTGS_INVOKE_CBS 10
#define RTGS_WAIT_CBS 11
#ifndef CONFIG_TINY_RCU
static const char * const rcu_tasks_gp_state_names[] = {
"RTGS_INIT",
"RTGS_WAIT_WAIT_CBS",
"RTGS_WAIT_GP",
"RTGS_PRE_WAIT_GP",
"RTGS_SCAN_TASKLIST",
"RTGS_POST_SCAN_TASKLIST",
"RTGS_WAIT_SCAN_HOLDOUTS",
"RTGS_SCAN_HOLDOUTS",
"RTGS_POST_GP",
"RTGS_WAIT_READERS",
"RTGS_INVOKE_CBS",
"RTGS_WAIT_CBS",
};
#endif /* #ifndef CONFIG_TINY_RCU */
////////////////////////////////////////////////////////////////////////
//
// Generic code.
static void rcu_tasks_invoke_cbs_wq(struct work_struct *wp);
/* Record grace-period phase and time. */
static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
{
rtp->gp_state = newstate;
rtp->gp_jiffies = jiffies;
}
#ifndef CONFIG_TINY_RCU
/* Return state name. */
static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
{
int i = data_race(rtp->gp_state); // Let KCSAN detect update races
int j = READ_ONCE(i); // Prevent the compiler from reading twice
if (j >= ARRAY_SIZE(rcu_tasks_gp_state_names))
return "???";
return rcu_tasks_gp_state_names[j];
}
#endif /* #ifndef CONFIG_TINY_RCU */
// Initialize per-CPU callback lists for the specified flavor of
// Tasks RCU. Do not enqueue callbacks before this function is invoked.
static void cblist_init_generic(struct rcu_tasks *rtp)
{
int cpu;
int lim;
int shift;
int maxcpu;
int index = 0;
if (rcu_task_enqueue_lim < 0) {
rcu_task_enqueue_lim = 1;
rcu_task_cb_adjust = true;
} else if (rcu_task_enqueue_lim == 0) {
rcu_task_enqueue_lim = 1;
}
lim = rcu_task_enqueue_lim;
rtp->rtpcp_array = kzalloc_objs(struct rcu_tasks_percpu *,
num_possible_cpus());
BUG_ON(!rtp->rtpcp_array);
for_each_possible_cpu(cpu) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
WARN_ON_ONCE(!rtpcp);
if (cpu)
raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
if (rcu_segcblist_empty(&rtpcp->cblist))
rcu_segcblist_init(&rtpcp->cblist);
INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
rtpcp->cpu = cpu;
rtpcp->rtpp = rtp;
rtpcp->index = index;
rtp->rtpcp_array[index] = rtpcp;
index++;
if (!rtpcp->rtp_blkd_tasks.next)
INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
if (!rtpcp->rtp_exit_list.next)
INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
rtpcp->barrier_q_head.next = &rtpcp->barrier_q_head;
maxcpu = cpu;
}
rcu_task_cpu_ids = maxcpu + 1;
if (lim > rcu_task_cpu_ids)
lim = rcu_task_cpu_ids;
shift = ilog2(rcu_task_cpu_ids / lim);
if (((rcu_task_cpu_ids - 1) >> shift) >= lim)
shift++;
rtp->percpu_enqueue_shift = shift;
rtp->percpu_dequeue_lim = lim;
rtp->percpu_enqueue_lim = lim;
pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d rcu_task_cpu_ids=%d.\n",
rtp->name, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim),
rcu_task_cb_adjust, rcu_task_cpu_ids);
}
// Compute wakeup time for lazy callback timer.
static unsigned long rcu_tasks_lazy_time(struct rcu_tasks *rtp)
{
return jiffies + rtp->lazy_jiffies;
}
// Timer handler that unlazifies lazy callbacks.
static void call_rcu_tasks_generic_timer(struct timer_list *tlp)
{
unsigned long flags;
bool needwake = false;
struct rcu_tasks *rtp;
struct rcu_tasks_percpu *rtpcp = timer_container_of(rtpcp, tlp,
lazy_timer);
rtp = rtpcp->rtpp;
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
if (!rcu_segcblist_empty(&rtpcp->cblist) && rtp->lazy_jiffies) {
if (!rtpcp->urgent_gp)
rtpcp->urgent_gp = 1;
needwake = true;
mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
}
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
if (needwake)
rcuwait_wake_up(&rtp->cbs_wait);
}
// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
{
struct rcu_tasks *rtp;
struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct rcu_tasks_percpu, rtp_irq_work);
rtp = rtpcp->rtpp;
rcuwait_wake_up(&rtp->cbs_wait);
}
// Enqueue a callback for the specified flavor of Tasks RCU.
static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
struct rcu_tasks *rtp)
{
int chosen_cpu;
unsigned long flags;
bool havekthread = smp_load_acquire(&rtp->kthread_ptr);
int ideal_cpu;
unsigned long j;
bool needadjust = false;
bool needwake;
struct rcu_tasks_percpu *rtpcp;
rhp->next = NULL;
rhp->func = func;
local_irq_save(flags);
rcu_read_lock();
ideal_cpu = smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift);
chosen_cpu = cpumask_next(ideal_cpu - 1, cpu_possible_mask);
WARN_ON_ONCE(chosen_cpu >= rcu_task_cpu_ids);
rtpcp = per_cpu_ptr(rtp->rtpcpu, chosen_cpu);
if (!raw_spin_trylock_rcu_node(rtpcp)) { // irqs already disabled.
raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
j = jiffies;
if (rtpcp->rtp_jiffies != j) {
rtpcp->rtp_jiffies = j;
rtpcp->rtp_n_lock_retries = 0;
}
if (rcu_task_cb_adjust && ++rtpcp->rtp_n_lock_retries > rcu_task_contend_lim &&
READ_ONCE(rtp->percpu_enqueue_lim) != rcu_task_cpu_ids)
needadjust = true; // Defer adjustment to avoid deadlock.
}
// Queuing callbacks before initialization not yet supported.
if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist)))
rcu_segcblist_init(&rtpcp->cblist);
needwake = (!havekthread && rcu_segcblist_empty(&rtpcp->cblist)) ||
(func == wakeme_after_rcu) ||
(rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim);
if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) {
if (rtp->lazy_jiffies)
mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
else
needwake = rcu_segcblist_empty(&rtpcp->cblist);
}
if (needwake)
rtpcp->urgent_gp = 3;
rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
if (unlikely(needadjust)) {
raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rtp->percpu_enqueue_lim != rcu_task_cpu_ids) {
WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
WRITE_ONCE(rtp->percpu_dequeue_lim, rcu_task_cpu_ids);
smp_store_release(&rtp->percpu_enqueue_lim, rcu_task_cpu_ids);
pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
}
raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
}
rcu_read_unlock();
/* We can't create the thread unless interrupts are enabled. */
if (needwake && READ_ONCE(rtp->kthread_ptr))
irq_work_queue(&rtpcp->rtp_irq_work);
}
// RCU callback function for rcu_barrier_tasks_generic().
static void rcu_barrier_tasks_generic_cb(struct rcu_head *rhp)
{
struct rcu_tasks *rtp;
struct rcu_tasks_percpu *rtpcp;
rhp->next = rhp; // Mark the callback as having been invoked.
rtpcp = container_of(rhp, struct rcu_tasks_percpu, barrier_q_head);
rtp = rtpcp->rtpp;
if (atomic_dec_and_test(&rtp->barrier_q_count))
complete(&rtp->barrier_q_completion);
}
// Wait for all in-flight callbacks for the specified RCU Tasks flavor.
// Operates in a manner similar to rcu_barrier().
static void __maybe_unused rcu_barrier_tasks_generic(struct rcu_tasks *rtp)
{
int cpu;
unsigned long flags;
struct rcu_tasks_percpu *rtpcp;
unsigned long s = rcu_seq_snap(&rtp->barrier_q_seq);
mutex_lock(&rtp->barrier_q_mutex);
if (rcu_seq_done(&rtp->barrier_q_seq, s)) {
smp_mb();
mutex_unlock(&rtp->barrier_q_mutex);
return;
}
rtp->barrier_q_start = jiffies;
rcu_seq_start(&rtp->barrier_q_seq);
init_completion(&rtp->barrier_q_completion);
atomic_set(&rtp->barrier_q_count, 2);
for_each_possible_cpu(cpu) {
if (cpu >= smp_load_acquire(&rtp->percpu_dequeue_lim))
break;
rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
rtpcp->barrier_q_head.func = rcu_barrier_tasks_generic_cb;
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
if (rcu_segcblist_entrain(&rtpcp->cblist, &rtpcp->barrier_q_head))
atomic_inc(&rtp->barrier_q_count);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
if (atomic_sub_and_test(2, &rtp->barrier_q_count))
complete(&rtp->barrier_q_completion);
wait_for_completion(&rtp->barrier_q_completion);
rcu_seq_end(&rtp->barrier_q_seq);
mutex_unlock(&rtp->barrier_q_mutex);
}
// Advance callbacks and indicate whether either a grace period or
// callback invocation is needed.
static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
{
int cpu;
int dequeue_limit;
unsigned long flags;
bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq);
long n;
long ncbs = 0;
long ncbsnz = 0;
int needgpcb = 0;
dequeue_limit = smp_load_acquire(&rtp->percpu_dequeue_lim);
for (cpu = 0; cpu < dequeue_limit; cpu++) {
if (!cpu_possible(cpu))
continue;
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
/* Advance and accelerate any new callbacks. */
if (!rcu_segcblist_n_cbs(&rtpcp->cblist))
continue;
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
// Should we shrink down to a single callback queue?
n = rcu_segcblist_n_cbs(&rtpcp->cblist);
if (n) {
ncbs += n;
if (cpu > 0)
ncbsnz += n;
}
rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
if (rtpcp->urgent_gp > 0 && rcu_segcblist_pend_cbs(&rtpcp->cblist)) {
if (rtp->lazy_jiffies)
rtpcp->urgent_gp--;
needgpcb |= 0x3;
} else if (rcu_segcblist_empty(&rtpcp->cblist)) {
rtpcp->urgent_gp = 0;
}
if (rcu_segcblist_ready_cbs(&rtpcp->cblist))
needgpcb |= 0x1;
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
// Shrink down to a single callback queue if appropriate.
// This is done in two stages: (1) If there are no more than
// rcu_task_collapse_lim callbacks on CPU 0 and none on any other
// CPU, limit enqueueing to CPU 0. (2) After an RCU grace period,
// if there has not been an increase in callbacks, limit dequeuing
// to CPU 0. Note the matching RCU read-side critical section in
// call_rcu_tasks_generic().
if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) {
raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rtp->percpu_enqueue_lim > 1) {
WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(rcu_task_cpu_ids));
smp_store_release(&rtp->percpu_enqueue_lim, 1);
rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu();
gpdone = false;
pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name);
}
raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
}
if (rcu_task_cb_adjust && !ncbsnz && gpdone) {
raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rtp->percpu_enqueue_lim < rtp->percpu_dequeue_lim) {
WRITE_ONCE(rtp->percpu_dequeue_lim, 1);
pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name);
}
if (rtp->percpu_dequeue_lim == 1) {
for (cpu = rtp->percpu_dequeue_lim; cpu < rcu_task_cpu_ids; cpu++) {
if (!cpu_possible(cpu))
continue;
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist));
}
}
raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
}
return needgpcb;
}
// Advance callbacks and invoke any that are ready.
static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu *rtpcp)
{
int cpuwq;
unsigned long flags;
int len;
int index;
struct rcu_head *rhp;
struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
struct rcu_tasks_percpu *rtpcp_next;
index = rtpcp->index * 2 + 1;
if (index < num_possible_cpus()) {
rtpcp_next = rtp->rtpcp_array[index];
if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND;
queue_work_on(cpuwq, system_percpu_wq, &rtpcp_next->rtp_work);
index++;
if (index < num_possible_cpus()) {
rtpcp_next = rtp->rtpcp_array[index];
if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND;
queue_work_on(cpuwq, system_percpu_wq, &rtpcp_next->rtp_work);
}
}
}
}
if (rcu_segcblist_empty(&rtpcp->cblist))
return;
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
rcu_segcblist_extract_done_cbs(&rtpcp->cblist, &rcl);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
len = rcl.len;
for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
cond_resched();
}
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
rcu_segcblist_add_len(&rtpcp->cblist, -len);
(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
// Workqueue flood to advance callbacks and invoke any that are ready.
static void rcu_tasks_invoke_cbs_wq(struct work_struct *wp)
{
struct rcu_tasks *rtp;
struct rcu_tasks_percpu *rtpcp = container_of(wp, struct rcu_tasks_percpu, rtp_work);
rtp = rtpcp->rtpp;
rcu_tasks_invoke_cbs(rtp, rtpcp);
}
// Wait for one grace period.
static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
{
int needgpcb;
mutex_lock(&rtp->tasks_gp_mutex);
// If there were none, wait a bit and start over.
if (unlikely(midboot)) {
needgpcb = 0x2;
} else {
mutex_unlock(&rtp->tasks_gp_mutex);
set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
rcuwait_wait_event(&rtp->cbs_wait,
(needgpcb = rcu_tasks_need_gpcb(rtp)),
TASK_IDLE);
mutex_lock(&rtp->tasks_gp_mutex);
}
if (needgpcb & 0x2) {
// Wait for one grace period.
set_tasks_gp_state(rtp, RTGS_WAIT_GP);
rtp->gp_start = jiffies;
rcu_seq_start(&rtp->tasks_gp_seq);
rtp->gp_func(rtp);
rcu_seq_end(&rtp->tasks_gp_seq);
}
// Invoke callbacks.
set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
rcu_tasks_invoke_cbs(rtp, per_cpu_ptr(rtp->rtpcpu, 0));
mutex_unlock(&rtp->tasks_gp_mutex);
}
// RCU-tasks kthread that detects grace periods and invokes callbacks.
static int __noreturn rcu_tasks_kthread(void *arg)
{
int cpu;
struct rcu_tasks *rtp = arg;
for_each_possible_cpu(cpu) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
timer_setup(&rtpcp->lazy_timer, call_rcu_tasks_generic_timer, 0);
rtpcp->urgent_gp = 1;
}
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_TYPE_RCU);
smp_store_release(&rtp->kthread_ptr, current); // Let GPs start!
/*
* Each pass through the following loop makes one check for
* newly arrived callbacks, and, if there are some, waits for
* one RCU-tasks grace period and then invokes the callbacks.
* This loop is terminated by the system going down. ;-)
*/
for (;;) {
// Wait for one grace period and invoke any callbacks
// that are ready.
rcu_tasks_one_gp(rtp, false);
// Paranoid sleep to keep this from entering a tight loop.
schedule_timeout_idle(rtp->gp_sleep);
}
}
// Wait for a grace period for the specified flavor of Tasks RCU.
static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
{
/* Complain if the scheduler has not started. */
if (WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
"synchronize_%s() called too soon", rtp->name))
return;
// If the grace-period kthread is running, use it.
if (READ_ONCE(rtp->kthread_ptr)) {
wait_rcu_gp_state(rtp->wait_state, rtp->call_func);
return;
}
rcu_tasks_one_gp(rtp, true);
}
/* Spawn RCU-tasks grace-period kthread. */
static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
{
struct task_struct *t;
t = kthread_run(rcu_tasks_kthread, rtp, "%s_kthread", rtp->kname);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start %s grace-period kthread, OOM is now expected behavior\n", __func__, rtp->name))
return;
smp_mb(); /* Ensure others see full kthread. */
}
#ifndef CONFIG_TINY_RCU
/*
* Print any non-default Tasks RCU settings.
*/
static void __init rcu_tasks_bootup_oddness(void)
{
#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
int rtsimc;
if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
rtsimc = clamp(rcu_task_stall_info_mult, 1, 10);
if (rtsimc != rcu_task_stall_info_mult) {
pr_info("\tTasks-RCU CPU stall info multiplier clamped to %d (rcu_task_stall_info_mult).\n", rtsimc);
rcu_task_stall_info_mult = rtsimc;
}
#endif /* #ifdef CONFIG_TASKS_RCU */
#ifdef CONFIG_TASKS_RCU
pr_info("\tTrampoline variant of Tasks RCU enabled.\n");
#endif /* #ifdef CONFIG_TASKS_RCU */
#ifdef CONFIG_TASKS_RUDE_RCU
pr_info("\tRude variant of Tasks RCU enabled.\n");
#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
#ifdef CONFIG_TASKS_TRACE_RCU
pr_info("\tTracing variant of Tasks RCU enabled.\n");
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
}
/* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
{
int cpu;
bool havecbs = false;
bool haveurgent = false;
bool haveurgentcbs = false;
for_each_possible_cpu(cpu) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)))
havecbs = true;
if (data_race(rtpcp->urgent_gp))
haveurgent = true;
if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)) && data_race(rtpcp->urgent_gp))
haveurgentcbs = true;
if (havecbs && haveurgent && haveurgentcbs)
break;
}
pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c%c%c l:%lu %s\n",
rtp->kname,
tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
jiffies - data_race(rtp->gp_jiffies),
data_race(rcu_seq_current(&rtp->tasks_gp_seq)),
data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
".k"[!!data_race(rtp->kthread_ptr)],
".C"[havecbs],
".u"[haveurgent],
".U"[haveurgentcbs],
rtp->lazy_jiffies,
s);
}
/* Dump out more rcutorture-relevant state common to all RCU-tasks flavors. */
static void rcu_tasks_torture_stats_print_generic(struct rcu_tasks *rtp, char *tt,
char *tf, char *tst)
{
cpumask_var_t cm;
int cpu;
bool gotcb = false;
unsigned long j = jiffies;
pr_alert("%s%s Tasks%s RCU g%ld gp_start %lu gp_jiffies %lu gp_state %d (%s).\n",
tt, tf, tst, data_race(rtp->tasks_gp_seq),
j - data_race(rtp->gp_start), j - data_race(rtp->gp_jiffies),
data_race(rtp->gp_state), tasks_gp_state_getname(rtp));
pr_alert("\tEnqueue shift %d limit %d Dequeue limit %d gpseq %lu.\n",
data_race(rtp->percpu_enqueue_shift),
data_race(rtp->percpu_enqueue_lim),
data_race(rtp->percpu_dequeue_lim),
data_race(rtp->percpu_dequeue_gpseq));
(void)zalloc_cpumask_var(&cm, GFP_KERNEL);
pr_alert("\tCallback counts:");
for_each_possible_cpu(cpu) {
long n;
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
if (cpumask_available(cm) && !rcu_barrier_cb_is_done(&rtpcp->barrier_q_head))
cpumask_set_cpu(cpu, cm);
n = rcu_segcblist_n_cbs(&rtpcp->cblist);
if (!n)
continue;
pr_cont(" %d:%ld", cpu, n);
gotcb = true;
}
if (gotcb)
pr_cont(".\n");
else
pr_cont(" (none).\n");
pr_alert("\tBarrier seq %lu start %lu count %d holdout CPUs ",
data_race(rtp->barrier_q_seq), j - data_race(rtp->barrier_q_start),
atomic_read(&rtp->barrier_q_count));
if (cpumask_available(cm) && !cpumask_empty(cm))
pr_cont(" %*pbl.\n", cpumask_pr_args(cm));
else
pr_cont("(none).\n");
free_cpumask_var(cm);
}
#endif // #ifndef CONFIG_TINY_RCU
#if defined(CONFIG_TASKS_RCU)
////////////////////////////////////////////////////////////////////////
//
// Shared code between task-list-scanning variants of Tasks RCU.
/* Wait for one RCU-tasks grace period. */
static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
{
struct task_struct *g;
int fract;
LIST_HEAD(holdouts);
unsigned long j;
unsigned long lastinfo;
unsigned long lastreport;
bool reported = false;
int rtsi;
struct task_struct *t;
set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP);
rtp->pregp_func(&holdouts);
/*
* There were callbacks, so we need to wait for an RCU-tasks
* grace period. Start off by scanning the task list for tasks
* that are not already voluntarily blocked. Mark these tasks
* and make a list of them in holdouts.
*/
set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST);
if (rtp->pertask_func) {
rcu_read_lock();
for_each_process_thread(g, t)
rtp->pertask_func(t, &holdouts);
rcu_read_unlock();
}
set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST);
rtp->postscan_func(&holdouts);
/*
* Each pass through the following loop scans the list of holdout
* tasks, removing any that are no longer holdouts. When the list
* is empty, we are done.
*/
lastreport = jiffies;
lastinfo = lastreport;
rtsi = READ_ONCE(rcu_task_stall_info);
// Start off with initial wait and slowly back off to 1 HZ wait.
fract = rtp->init_fract;
while (!list_empty(&holdouts)) {
ktime_t exp;
bool firstreport;
bool needreport;
int rtst;
// Slowly back off waiting for holdouts
set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
schedule_timeout_idle(fract);
} else {
exp = jiffies_to_nsecs(fract);
__set_current_state(TASK_IDLE);
schedule_hrtimeout_range(&exp, jiffies_to_nsecs(HZ / 2), HRTIMER_MODE_REL_HARD);
}
if (fract < HZ)
fract++;
rtst = READ_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
if (needreport) {
lastreport = jiffies;
reported = true;
}
firstreport = true;
WARN_ON(signal_pending(current));
set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS);
rtp->holdouts_func(&holdouts, needreport, &firstreport);
// Print pre-stall informational messages if needed.
j = jiffies;
if (rtsi > 0 && !reported && time_after(j, lastinfo + rtsi)) {
lastinfo = j;
rtsi = rtsi * rcu_task_stall_info_mult;
pr_info("%s: %s grace period number %lu (since boot) is %lu jiffies old.\n",
__func__, rtp->kname, rtp->tasks_gp_seq, j - rtp->gp_start);
}
}
set_tasks_gp_state(rtp, RTGS_POST_GP);
rtp->postgp_func(rtp);
}
#endif /* #if defined(CONFIG_TASKS_RCU) */
#ifdef CONFIG_TASKS_RCU
////////////////////////////////////////////////////////////////////////
//
// Simple variant of RCU whose quiescent states are voluntary context
// switch, cond_resched_tasks_rcu_qs(), user-space execution, and idle.
// As such, grace periods can take one good long time. There are no
// read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
// because this implementation is intended to get the system into a safe
// state for some of the manipulations involved in tracing and the like.
// Finally, this implementation does not support high call_rcu_tasks()
// rates from multiple CPUs. If this is required, per-CPU callback lists
// will be needed.
//
// The implementation uses rcu_tasks_wait_gp(), which relies on function
// pointers in the rcu_tasks structure. The rcu_spawn_tasks_kthread()
// function sets these function pointers up so that rcu_tasks_wait_gp()
// invokes these functions in this order:
//
// rcu_tasks_pregp_step():
// Invokes synchronize_rcu() in order to wait for all in-flight
// t->on_rq and t->nvcsw transitions to complete. This works because
// all such transitions are carried out with interrupts disabled.
// rcu_tasks_pertask(), invoked on every non-idle task:
// For every runnable non-idle task other than the current one, use
// get_task_struct() to pin down that task, snapshot that task's
// number of voluntary context switches, and add that task to the
// holdout list.
// rcu_tasks_postscan():
// Gather per-CPU lists of tasks in do_exit() to ensure that all
// tasks that were in the process of exiting (and which thus might
// not know to synchronize with this RCU Tasks grace period) have
// completed exiting. The synchronize_rcu() in rcu_tasks_postgp()
// will take care of any tasks stuck in the non-preemptible region
// of do_exit() following its call to exit_tasks_rcu_finish().
// check_all_holdout_tasks(), repeatedly until holdout list is empty:
// Scans the holdout list, attempting to identify a quiescent state
// for each task on the list. If there is a quiescent state, the
// corresponding task is removed from the holdout list.
// rcu_tasks_postgp():
// Invokes synchronize_rcu() in order to ensure that all prior
// t->on_rq and t->nvcsw transitions are seen by all CPUs and tasks
// to have happened before the end of this RCU Tasks grace period.
// Again, this works because all such transitions are carried out
// with interrupts disabled.
//
// For each exiting task, the exit_tasks_rcu_start() and
// exit_tasks_rcu_finish() functions add and remove, respectively, the
// current task to a per-CPU list of tasks that rcu_tasks_postscan() must
// wait on. This is necessary because rcu_tasks_postscan() must wait on
// tasks that have already been removed from the global list of tasks.
//
// Pre-grace-period update-side code is ordered before the grace
// via the raw_spin_lock.*rcu_node(). Pre-grace-period read-side code
// is ordered before the grace period via synchronize_rcu() call in
// rcu_tasks_pregp_step() and by the scheduler's locks and interrupt
// disabling.
/* Pre-grace-period preparation. */
static void rcu_tasks_pregp_step(struct list_head *hop)
{
/*
* Wait for all pre-existing t->on_rq and t->nvcsw transitions
* to complete. Invoking synchronize_rcu() suffices because all
* these transitions occur with interrupts disabled. Without this
* synchronize_rcu(), a read-side critical section that started
* before the grace period might be incorrectly seen as having
* started after the grace period.
*
* This synchronize_rcu() also dispenses with the need for a
* memory barrier on the first store to t->rcu_tasks_holdout,
* as it forces the store to happen after the beginning of the
* grace period.
*/
synchronize_rcu();
}
/* Check for quiescent states since the pregp's synchronize_rcu() */
static bool rcu_tasks_is_holdout(struct task_struct *t)
{
int cpu;
/* Has the task been seen voluntarily sleeping? */
if (!READ_ONCE(t->on_rq))
return false;
/*
* t->on_rq && !t->se.sched_delayed *could* be considered sleeping but
* since it is a spurious state (it will transition into the
* traditional blocked state or get woken up without outside
* dependencies), not considering it such should only affect timing.
*
* Be conservative for now and not include it.
*/
/*
* Idle tasks (or idle injection) within the idle loop are RCU-tasks
* quiescent states. But CPU boot code performed by the idle task
* isn't a quiescent state.
*/
if (is_idle_task(t))
return false;
cpu = task_cpu(t);
/* Idle tasks on offline CPUs are RCU-tasks quiescent states. */
if (t == idle_task(cpu) && !rcu_cpu_online(cpu))
return false;
return true;
}
/* Per-task initial processing. */
static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
{
if (t != current && rcu_tasks_is_holdout(t)) {
get_task_struct(t);
t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
WRITE_ONCE(t->rcu_tasks_holdout, true);
list_add(&t->rcu_tasks_holdout_list, hop);
}
}
void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
/* Processing between scanning taskslist and draining the holdout list. */
static void rcu_tasks_postscan(struct list_head *hop)
{
int cpu;
int rtsi = READ_ONCE(rcu_task_stall_info);
if (!IS_ENABLED(CONFIG_TINY_RCU)) {
tasks_rcu_exit_srcu_stall_timer.expires = jiffies + rtsi;
add_timer(&tasks_rcu_exit_srcu_stall_timer);
}
/*
* Exiting tasks may escape the tasklist scan. Those are vulnerable
* until their final schedule() with TASK_DEAD state. To cope with
* this, divide the fragile exit path part in two intersecting
* read side critical sections:
*
* 1) A task_struct list addition before calling exit_notify(),
* which may remove the task from the tasklist, with the
* removal after the final preempt_disable() call in do_exit().
*
* 2) An _RCU_ read side starting with the final preempt_disable()
* call in do_exit() and ending with the final call to schedule()
* with TASK_DEAD state.
*
* This handles the part 1). And postgp will handle part 2) with a
* call to synchronize_rcu().
*/
for_each_possible_cpu(cpu) {
unsigned long j = jiffies + 1;
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, cpu);
struct task_struct *t;
struct task_struct *t1;
struct list_head tmp;
raw_spin_lock_irq_rcu_node(rtpcp);
list_for_each_entry_safe(t, t1, &rtpcp->rtp_exit_list, rcu_tasks_exit_list) {
if (list_empty(&t->rcu_tasks_holdout_list))
rcu_tasks_pertask(t, hop);
// RT kernels need frequent pauses, otherwise
// pause at least once per pair of jiffies.
if (!IS_ENABLED(CONFIG_PREEMPT_RT) && time_before(jiffies, j))
continue;
// Keep our place in the list while pausing.
// Nothing else traverses this list, so adding a
// bare list_head is OK.
list_add(&tmp, &t->rcu_tasks_exit_list);
raw_spin_unlock_irq_rcu_node(rtpcp);
cond_resched(); // For CONFIG_PREEMPT=n kernels
raw_spin_lock_irq_rcu_node(rtpcp);
t1 = list_entry(tmp.next, struct task_struct, rcu_tasks_exit_list);
list_del(&tmp);
j = jiffies + 1;
}
raw_spin_unlock_irq_rcu_node(rtpcp);
}
if (!IS_ENABLED(CONFIG_TINY_RCU))
timer_delete_sync(&tasks_rcu_exit_srcu_stall_timer);
}
/* See if tasks are still holding out, complain if so. */
static void check_holdout_task(struct task_struct *t,
bool needreport, bool *firstreport)
{
int cpu;
if (!READ_ONCE(t->rcu_tasks_holdout) ||
t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
!rcu_tasks_is_holdout(t) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
!is_idle_task(t) && READ_ONCE(t->rcu_tasks_idle_cpu) >= 0)) {
WRITE_ONCE(t->rcu_tasks_holdout, false);
list_del_init(&t->rcu_tasks_holdout_list);
put_task_struct(t);
return;
}
rcu_request_urgent_qs_task(t);
if (!needreport)
return;
if (*firstreport) {
pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
*firstreport = false;
}
cpu = task_cpu(t);
pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
t, ".I"[is_idle_task(t)],
"N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
data_race(t->rcu_tasks_idle_cpu), cpu);
sched_show_task(t);
}
/* Scan the holdout lists for tasks no longer holding out. */
static void check_all_holdout_tasks(struct list_head *hop,
bool needreport, bool *firstreport)
{
struct task_struct *t, *t1;
list_for_each_entry_safe(t, t1, hop, rcu_tasks_holdout_list) {
check_holdout_task(t, needreport, firstreport);
cond_resched();
}
}
/* Finish off the Tasks-RCU grace period. */
static void rcu_tasks_postgp(struct rcu_tasks *rtp)
{
/*
* Because ->on_rq and ->nvcsw are not guaranteed to have a full
* memory barriers prior to them in the schedule() path, memory
* reordering on other CPUs could cause their RCU-tasks read-side
* critical sections to extend past the end of the grace period.
* However, because these ->nvcsw updates are carried out with
* interrupts disabled, we can use synchronize_rcu() to force the
* needed ordering on all such CPUs.
*
* This synchronize_rcu() also confines all ->rcu_tasks_holdout
* accesses to be within the grace period, avoiding the need for
* memory barriers for ->rcu_tasks_holdout accesses.
*
* In addition, this synchronize_rcu() waits for exiting tasks
* to complete their final preempt_disable() region of execution,
* enforcing the whole region before tasklist removal until
* the final schedule() with TASK_DEAD state to be an RCU TASKS
* read side critical section.
*/
synchronize_rcu();
}
static void tasks_rcu_exit_srcu_stall(struct timer_list *unused)
{
#ifndef CONFIG_TINY_RCU
int rtsi;
rtsi = READ_ONCE(rcu_task_stall_info);
pr_info("%s: %s grace period number %lu (since boot) gp_state: %s is %lu jiffies old.\n",
__func__, rcu_tasks.kname, rcu_tasks.tasks_gp_seq,
tasks_gp_state_getname(&rcu_tasks), jiffies - rcu_tasks.gp_jiffies);
pr_info("Please check any exiting tasks stuck between calls to exit_tasks_rcu_start() and exit_tasks_rcu_finish()\n");
tasks_rcu_exit_srcu_stall_timer.expires = jiffies + rtsi;
add_timer(&tasks_rcu_exit_srcu_stall_timer);
#endif // #ifndef CONFIG_TINY_RCU
}
/**
* call_rcu_tasks() - Queue an RCU for invocation task-based grace period
* @rhp: structure to be used for queueing the RCU updates.
* @func: actual callback function to be invoked after the grace period
*
* The callback function will be invoked some time after a full grace
* period elapses, in other words after all currently executing RCU
* read-side critical sections have completed. call_rcu_tasks() assumes
* that the read-side critical sections end at a voluntary context
* switch (not a preemption!), cond_resched_tasks_rcu_qs(), entry into idle,
* or transition to usermode execution. As such, there are no read-side
* primitives analogous to rcu_read_lock() and rcu_read_unlock() because
* this primitive is intended to determine that all tasks have passed
* through a safe state, not so much for data-structure synchronization.
*
* See the description of call_rcu() for more detailed information on
* memory ordering guarantees.
*/
void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
{
call_rcu_tasks_generic(rhp, func, &rcu_tasks);
}
EXPORT_SYMBOL_GPL(call_rcu_tasks);
/**
* synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
*
* Control will return to the caller some time after a full rcu-tasks
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
* cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
* to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
* tracing and other situations requiring manipulation of function
* preambles and profiling hooks. The synchronize_rcu_tasks() function
* is not (yet) intended for heavy use from multiple CPUs.
*
* See the description of synchronize_rcu() for more detailed information
* on memory ordering guarantees.
*/
void synchronize_rcu_tasks(void)
{
synchronize_rcu_tasks_generic(&rcu_tasks);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
/**
* rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
*
* Although the current implementation is guaranteed to wait, it is not
* obligated to, for example, if there are no pending callbacks.
*/
void rcu_barrier_tasks(void)
{
rcu_barrier_tasks_generic(&rcu_tasks);
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
static int rcu_tasks_lazy_ms = -1;
module_param(rcu_tasks_lazy_ms, int, 0444);
static int __init rcu_spawn_tasks_kthread(void)
{
rcu_tasks.gp_sleep = HZ / 10;
rcu_tasks.init_fract = HZ / 10;
if (rcu_tasks_lazy_ms >= 0)
rcu_tasks.lazy_jiffies = msecs_to_jiffies(rcu_tasks_lazy_ms);
rcu_tasks.pregp_func = rcu_tasks_pregp_step;
rcu_tasks.pertask_func = rcu_tasks_pertask;
rcu_tasks.postscan_func = rcu_tasks_postscan;
rcu_tasks.holdouts_func = check_all_holdout_tasks;
rcu_tasks.postgp_func = rcu_tasks_postgp;
rcu_tasks.wait_state = TASK_IDLE;
rcu_spawn_tasks_kthread_generic(&rcu_tasks);
return 0;
}
#if !defined(CONFIG_TINY_RCU)
void show_rcu_tasks_classic_gp_kthread(void)
{
show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
}
EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread);
void rcu_tasks_torture_stats_print(char *tt, char *tf)
{
rcu_tasks_torture_stats_print_generic(&rcu_tasks, tt, tf, "");
}
EXPORT_SYMBOL_GPL(rcu_tasks_torture_stats_print);
#endif // !defined(CONFIG_TINY_RCU)
struct task_struct *get_rcu_tasks_gp_kthread(void)
{
return rcu_tasks.kthread_ptr;
}
EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
void rcu_tasks_get_gp_data(int *flags, unsigned long *gp_seq)
{
*flags = 0;
*gp_seq = rcu_seq_current(&rcu_tasks.tasks_gp_seq);
}
EXPORT_SYMBOL_GPL(rcu_tasks_get_gp_data);
/*
* Protect against tasklist scan blind spot while the task is exiting and
* may be removed from the tasklist. Do this by adding the task to yet
* another list.
*
* Note that the task will remove itself from this list, so there is no
* need for get_task_struct(), except in the case where rcu_tasks_pertask()
* adds it to the holdout list, in which case rcu_tasks_pertask() supplies
* the needed get_task_struct().
*/
void exit_tasks_rcu_start(void)
{
unsigned long flags;
struct rcu_tasks_percpu *rtpcp;
struct task_struct *t = current;
WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list));
preempt_disable();
rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu);
t->rcu_tasks_exit_cpu = smp_processor_id();
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
WARN_ON_ONCE(!rtpcp->rtp_exit_list.next);
list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
preempt_enable();
}
/*
* Remove the task from the "yet another list" because do_exit() is now
* non-preemptible, allowing synchronize_rcu() to wait beyond this point.
*/
void exit_tasks_rcu_finish(void)
{
unsigned long flags;
struct rcu_tasks_percpu *rtpcp;
struct task_struct *t = current;
WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list));
rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu);
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
list_del_init(&t->rcu_tasks_exit_list);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
#else /* #ifdef CONFIG_TASKS_RCU */
void exit_tasks_rcu_start(void) { }
void exit_tasks_rcu_finish(void) { }
#endif /* #else #ifdef CONFIG_TASKS_RCU */
#ifdef CONFIG_TASKS_RUDE_RCU
////////////////////////////////////////////////////////////////////////
//
// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's
// trick of passing an empty function to schedule_on_each_cpu().
// This approach provides batching of concurrent calls to the synchronous
// synchronize_rcu_tasks_rude() API. This invokes schedule_on_each_cpu()
// in order to send IPIs far and wide and induces otherwise unnecessary
// context switches on all online CPUs, whether idle or not.
//
// Callback handling is provided by the rcu_tasks_kthread() function.
//
// Ordering is provided by the scheduler's context-switch code.
// Empty function to allow workqueues to force a context switch.
static void rcu_tasks_be_rude(struct work_struct *work)
{
}
// Wait for one rude RCU-tasks grace period.
static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp)
{
rtp->n_ipis += cpumask_weight(cpu_online_mask);
schedule_on_each_cpu(rcu_tasks_be_rude);
}
static void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func);
DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
"RCU Tasks Rude");
/*
* call_rcu_tasks_rude() - Queue a callback rude task-based grace period
* @rhp: structure to be used for queueing the RCU updates.
* @func: actual callback function to be invoked after the grace period
*
* The callback function will be invoked some time after a full grace
* period elapses, in other words after all currently executing RCU
* read-side critical sections have completed. call_rcu_tasks_rude()
* assumes that the read-side critical sections end at context switch,
* cond_resched_tasks_rcu_qs(), or transition to usermode execution (as
* usermode execution is schedulable). As such, there are no read-side
* primitives analogous to rcu_read_lock() and rcu_read_unlock() because
* this primitive is intended to determine that all tasks have passed
* through a safe state, not so much for data-structure synchronization.
*
* See the description of call_rcu() for more detailed information on
* memory ordering guarantees.
*
* This is no longer exported, and is instead reserved for use by
* synchronize_rcu_tasks_rude().
*/
static void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func)
{
call_rcu_tasks_generic(rhp, func, &rcu_tasks_rude);
}
/**
* synchronize_rcu_tasks_rude - wait for a rude rcu-tasks grace period
*
* Control will return to the caller some time after a rude rcu-tasks
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
* cond_resched_tasks_rcu_qs(), userspace execution (which is a schedulable
* context), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
* tracing and other situations requiring manipulation of function preambles
* and profiling hooks. The synchronize_rcu_tasks_rude() function is not
* (yet) intended for heavy use from multiple CPUs.
*
* See the description of synchronize_rcu() for more detailed information
* on memory ordering guarantees.
*/
void synchronize_rcu_tasks_rude(void)
{
if (!IS_ENABLED(CONFIG_ARCH_WANTS_NO_INSTR) || IS_ENABLED(CONFIG_FORCE_TASKS_RUDE_RCU))
synchronize_rcu_tasks_generic(&rcu_tasks_rude);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
static int __init rcu_spawn_tasks_rude_kthread(void)
{
rcu_tasks_rude.gp_sleep = HZ / 10;
rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
return 0;
}
#if !defined(CONFIG_TINY_RCU)
void show_rcu_tasks_rude_gp_kthread(void)
{
show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
}
EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
void rcu_tasks_rude_torture_stats_print(char *tt, char *tf)
{
rcu_tasks_torture_stats_print_generic(&rcu_tasks_rude, tt, tf, "");
}
EXPORT_SYMBOL_GPL(rcu_tasks_rude_torture_stats_print);
#endif // !defined(CONFIG_TINY_RCU)
struct task_struct *get_rcu_tasks_rude_gp_kthread(void)
{
return rcu_tasks_rude.kthread_ptr;
}
EXPORT_SYMBOL_GPL(get_rcu_tasks_rude_gp_kthread);
void rcu_tasks_rude_get_gp_data(int *flags, unsigned long *gp_seq)
{
*flags = 0;
*gp_seq = rcu_seq_current(&rcu_tasks_rude.tasks_gp_seq);
}
EXPORT_SYMBOL_GPL(rcu_tasks_rude_get_gp_data);
#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
#ifndef CONFIG_TINY_RCU
void show_rcu_tasks_gp_kthreads(void)
{
show_rcu_tasks_classic_gp_kthread();
show_rcu_tasks_rude_gp_kthread();
}
#endif /* #ifndef CONFIG_TINY_RCU */
#ifdef CONFIG_PROVE_RCU
struct rcu_tasks_test_desc {
struct rcu_head rh;
const char *name;
bool notrun;
unsigned long runstart;
};
static struct rcu_tasks_test_desc tests[] = {
{
.name = "call_rcu_tasks()",
/* If not defined, the test is skipped. */
.notrun = IS_ENABLED(CONFIG_TASKS_RCU),
},
{
.name = "call_rcu_tasks_trace()",
/* If not defined, the test is skipped. */
.notrun = IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
}
};
#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
static void test_rcu_tasks_callback(struct rcu_head *rhp)
{
struct rcu_tasks_test_desc *rttd =
container_of(rhp, struct rcu_tasks_test_desc, rh);
pr_info("Callback from %s invoked.\n", rttd->name);
rttd->notrun = false;
}
#endif // #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
static void rcu_tasks_initiate_self_tests(void)
{
#ifdef CONFIG_TASKS_RCU
pr_info("Running RCU Tasks wait API self tests\n");
tests[0].runstart = jiffies;
synchronize_rcu_tasks();
call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
pr_info("Running RCU Tasks Rude wait API self tests\n");
synchronize_rcu_tasks_rude();
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
pr_info("Running RCU Tasks Trace wait API self tests\n");
tests[1].runstart = jiffies;
synchronize_rcu_tasks_trace();
call_rcu_tasks_trace(&tests[1].rh, test_rcu_tasks_callback);
#endif
}
/*
* Return: 0 - test passed
* 1 - test failed, but have not timed out yet
* -1 - test failed and timed out
*/
static int rcu_tasks_verify_self_tests(void)
{
int ret = 0;
int i;
unsigned long bst = rcu_task_stall_timeout;
if (bst <= 0 || bst > RCU_TASK_BOOT_STALL_TIMEOUT)
bst = RCU_TASK_BOOT_STALL_TIMEOUT;
for (i = 0; i < ARRAY_SIZE(tests); i++) {
while (tests[i].notrun) { // still hanging.
if (time_after(jiffies, tests[i].runstart + bst)) {
pr_err("%s has failed boot-time tests.\n", tests[i].name);
ret = -1;
break;
}
ret = 1;
break;
}
}
WARN_ON(ret < 0);
return ret;
}
/*
* Repeat the rcu_tasks_verify_self_tests() call once every second until the
* test passes or has timed out.
*/
static struct delayed_work rcu_tasks_verify_work;
static void rcu_tasks_verify_work_fn(struct work_struct *work __maybe_unused)
{
int ret = rcu_tasks_verify_self_tests();
if (ret <= 0)
return;
/* Test fails but not timed out yet, reschedule another check */
schedule_delayed_work(&rcu_tasks_verify_work, HZ);
}
static int rcu_tasks_verify_schedule_work(void)
{
INIT_DELAYED_WORK(&rcu_tasks_verify_work, rcu_tasks_verify_work_fn);
rcu_tasks_verify_work_fn(NULL);
return 0;
}
late_initcall(rcu_tasks_verify_schedule_work);
#else /* #ifdef CONFIG_PROVE_RCU */
static void rcu_tasks_initiate_self_tests(void) { }
#endif /* #else #ifdef CONFIG_PROVE_RCU */
void __init tasks_cblist_init_generic(void)
{
lockdep_assert_irqs_disabled();
WARN_ON(num_online_cpus() > 1);
#ifdef CONFIG_TASKS_RCU
cblist_init_generic(&rcu_tasks);
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
cblist_init_generic(&rcu_tasks_rude);
#endif
}
static int __init rcu_init_tasks_generic(void)
{
#ifdef CONFIG_TASKS_RCU
rcu_spawn_tasks_kthread();
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
rcu_spawn_tasks_rude_kthread();
#endif
// Run the self-tests.
rcu_tasks_initiate_self_tests();
return 0;
}
core_initcall(rcu_init_tasks_generic);
#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
static inline void rcu_tasks_bootup_oddness(void) {}
#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
#ifdef CONFIG_TASKS_TRACE_RCU
////////////////////////////////////////////////////////////////////////
//
// Tracing variant of Tasks RCU. This variant is designed to be used
// to protect tracing hooks, including those of BPF. This variant
// is implemented via a straightforward mapping onto SRCU-fast.
DEFINE_SRCU_FAST(rcu_tasks_trace_srcu_struct);
EXPORT_SYMBOL_GPL(rcu_tasks_trace_srcu_struct);
#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */