.level = { &sname##_state.node[0] }, \
.call = cr, \
.fqs_state = RCU_GP_IDLE, \
- .gpnum = -300, \
- .completed = -300, \
+ .gpnum = 0UL - 300UL, \
+ .completed = 0UL - 300UL, \
.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
.orphan_nxttail = &sname##_state.orphan_nxtlist, \
.orphan_donetail = &sname##_state.orphan_donelist, \
DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
.dynticks = ATOMIC_INIT(1),
-#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE)
- .ignore_user_qs = true,
-#endif
};
-static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */
-static int qhimark = 10000; /* If this many pending, ignore blimit. */
-static int qlowmark = 100; /* Once only this many pending, use blimit. */
+static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */
+static long qhimark = 10000; /* If this many pending, ignore blimit. */
+static long qlowmark = 100; /* Once only this many pending, use blimit. */
-module_param(blimit, int, 0444);
-module_param(qhimark, int, 0444);
-module_param(qlowmark, int, 0444);
+module_param(blimit, long, 0444);
+module_param(qhimark, long, 0444);
+module_param(qlowmark, long, 0444);
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
static int
cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
{
- return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL];
+ return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
+ rdp->nxttail[RCU_DONE_TAIL] != NULL;
}
/*
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- return *rdp->nxttail[RCU_DONE_TAIL +
- ACCESS_ONCE(rsp->completed) != rdp->completed] &&
+ struct rcu_head **ntp;
+
+ ntp = rdp->nxttail[RCU_DONE_TAIL +
+ (ACCESS_ONCE(rsp->completed) != rdp->completed)];
+ return rdp->nxttail[RCU_DONE_TAIL] && ntp && *ntp &&
!rcu_gp_in_progress(rsp);
}
*/
void rcu_user_enter(void)
{
- unsigned long flags;
- struct rcu_dynticks *rdtp;
-
- /*
- * Some contexts may involve an exception occuring in an irq,
- * leading to that nesting:
- * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
- * This would mess up the dyntick_nesting count though. And rcu_irq_*()
- * helpers are enough to protect RCU uses inside the exception. So
- * just return immediately if we detect we are in an IRQ.
- */
- if (in_interrupt())
- return;
-
- WARN_ON_ONCE(!current->mm);
-
- local_irq_save(flags);
- rdtp = &__get_cpu_var(rcu_dynticks);
- if (!rdtp->ignore_user_qs && !rdtp->in_user) {
- rdtp->in_user = true;
- rcu_eqs_enter(true);
- }
- local_irq_restore(flags);
+ rcu_eqs_enter(1);
}
/**
*/
void rcu_user_exit(void)
{
- unsigned long flags;
- struct rcu_dynticks *rdtp;
-
- /*
- * Some contexts may involve an exception occuring in an irq,
- * leading to that nesting:
- * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
- * This would mess up the dyntick_nesting count though. And rcu_irq_*()
- * helpers are enough to protect RCU uses inside the exception. So
- * just return immediately if we detect we are in an IRQ.
- */
- if (in_interrupt())
- return;
-
- local_irq_save(flags);
- rdtp = &__get_cpu_var(rcu_dynticks);
- if (rdtp->in_user) {
- rdtp->in_user = false;
- rcu_eqs_exit(true);
- }
- local_irq_restore(flags);
+ rcu_eqs_exit(1);
}
/**
}
EXPORT_SYMBOL(rcu_is_cpu_idle);
-#ifdef CONFIG_RCU_USER_QS
-void rcu_user_hooks_switch(struct task_struct *prev,
- struct task_struct *next)
-{
- struct rcu_dynticks *rdtp;
-
- /* Interrupts are disabled in context switch */
- rdtp = &__get_cpu_var(rcu_dynticks);
- if (!rdtp->ignore_user_qs) {
- clear_tsk_thread_flag(prev, TIF_NOHZ);
- set_tsk_thread_flag(next, TIF_NOHZ);
- }
-}
-#endif /* #ifdef CONFIG_RCU_USER_QS */
-
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
rsp->jiffies_stall = jiffies + jiffies_till_stall_check();
}
+/*
+ * Dump stacks of all tasks running on stalled CPUs. This is a fallback
+ * for architectures that do not implement trigger_all_cpu_backtrace().
+ * The NMI-triggered stack traces are more accurate because they are
+ * printed by the target CPU.
+ */
+static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
+{
+ int cpu;
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ rcu_for_each_leaf_node(rsp, rnp) {
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ if (rnp->qsmask != 0) {
+ for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+ if (rnp->qsmask & (1UL << cpu))
+ dump_cpu_task(rnp->grplo + cpu);
+ }
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ }
+}
+
static void print_other_cpu_stall(struct rcu_state *rsp)
{
int cpu;
unsigned long flags;
int ndetected = 0;
struct rcu_node *rnp = rcu_get_root(rsp);
+ long totqlen = 0;
/* Only let one CPU complain about others per time interval. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
print_cpu_stall_info_end();
- printk(KERN_CONT "(detected by %d, t=%ld jiffies)\n",
- smp_processor_id(), (long)(jiffies - rsp->gp_start));
+ for_each_possible_cpu(cpu)
+ totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ pr_cont("(detected by %d, t=%ld jiffies, g=%lu, c=%lu, q=%lu)\n",
+ smp_processor_id(), (long)(jiffies - rsp->gp_start),
+ rsp->gpnum, rsp->completed, totqlen);
if (ndetected == 0)
printk(KERN_ERR "INFO: Stall ended before state dump start\n");
else if (!trigger_all_cpu_backtrace())
- dump_stack();
+ rcu_dump_cpu_stacks(rsp);
/* Complain about tasks blocking the grace period. */
static void print_cpu_stall(struct rcu_state *rsp)
{
+ int cpu;
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
+ long totqlen = 0;
/*
* OK, time to rat on ourselves...
print_cpu_stall_info_begin();
print_cpu_stall_info(rsp, smp_processor_id());
print_cpu_stall_info_end();
- printk(KERN_CONT " (t=%lu jiffies)\n", jiffies - rsp->gp_start);
+ for_each_possible_cpu(cpu)
+ totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ pr_cont(" (t=%lu jiffies g=%lu c=%lu q=%lu)\n",
+ jiffies - rsp->gp_start, rsp->gpnum, rsp->completed, totqlen);
if (!trigger_all_cpu_backtrace())
dump_stack();
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
+ init_nocb_callback_list(rdp);
}
/*
!cpu_needs_another_gp(rsp, rdp)) {
/*
* Either we have not yet spawned the grace-period
- * task or this CPU does not need another grace period.
+ * task, this CPU does not need another grace period,
+ * or a grace period is already in progress.
* Either way, don't start a new grace period.
*/
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
+ /*
+ * Because there is no grace period in progress right now,
+ * any callbacks we have up to this point will be satisfied
+ * by the next grace period. So promote all callbacks to be
+ * handled after the end of the next grace period. If the
+ * CPU is not yet aware of the end of the previous grace period,
+ * we need to allow for the callback advancement that will
+ * occur when it does become aware. Deadlock prevents us from
+ * making it aware at this point: We cannot acquire a leaf
+ * rcu_node ->lock while holding the root rcu_node ->lock.
+ */
+ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ if (rdp->completed == rsp->completed)
+ rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
rsp->gp_flags = RCU_GP_FLAG_INIT;
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
+
+ /* Ensure that CPU is aware of completion of last grace period. */
+ rcu_process_gp_end(rsp, rdp);
+ local_irq_restore(flags);
+
+ /* Wake up rcu_gp_kthread() to start the grace period. */
wake_up(&rsp->gp_wq);
}
rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
struct rcu_node *rnp, struct rcu_data *rdp)
{
+ /* No-CBs CPUs do not have orphanable callbacks. */
+ if (is_nocb_cpu(rdp->cpu))
+ return;
+
/*
* Orphan the callbacks. First adjust the counts. This is safe
* because _rcu_barrier() excludes CPU-hotplug operations, so it
int i;
struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
+ /* No-CBs CPUs are handled specially. */
+ if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+ return;
+
/* Do the accounting first. */
rdp->qlen_lazy += rsp->qlen_lazy;
rdp->qlen += rsp->qlen;
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
- int bl, count, count_lazy, i;
+ long bl, count, count_lazy;
+ int i;
/* If no callbacks are ready, just return.*/
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
}
}
+/*
+ * Helper function for call_rcu() and friends. The cpu argument will
+ * normally be -1, indicating "currently running CPU". It may specify
+ * a CPU only if that CPU is a no-CBs CPU. Currently, only _rcu_barrier()
+ * is expected to specify a CPU.
+ */
static void
__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
- struct rcu_state *rsp, bool lazy)
+ struct rcu_state *rsp, int cpu, bool lazy)
{
unsigned long flags;
struct rcu_data *rdp;
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
- if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL)) {
+ if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
+ int offline;
+
+ if (cpu != -1)
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ offline = !__call_rcu_nocb(rdp, head, lazy);
+ WARN_ON_ONCE(offline);
/* _call_rcu() is illegal on offline CPU; leak the callback. */
- WARN_ON_ONCE(1);
local_irq_restore(flags);
return;
}
*/
void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_sched_state, 0);
+ __call_rcu(head, func, &rcu_sched_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);
*/
void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_bh_state, 0);
+ __call_rcu(head, func, &rcu_bh_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
* rcu_read_lock_sched().
*
* This means that all preempt_disable code sequences, including NMI and
- * hardware-interrupt handlers, in progress on entry will have completed
- * before this primitive returns. However, this does not guarantee that
- * softirq handlers will have completed, since in some kernels, these
- * handlers can run in process context, and can block.
+ * non-threaded hardware-interrupt handlers, in progress on entry will
+ * have completed before this primitive returns. However, this does not
+ * guarantee that softirq handlers will have completed, since in some
+ * kernels, these handlers can run in process context, and can block.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_sched() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since the
+ * end of its last RCU-sched read-side critical section whose beginning
+ * preceded the call to synchronize_sched(). In addition, each CPU having
+ * an RCU read-side critical section that extends beyond the return from
+ * synchronize_sched() is guaranteed to have executed a full memory barrier
+ * after the beginning of synchronize_sched() and before the beginning of
+ * that RCU read-side critical section. Note that these guarantees include
+ * CPUs that are offline, idle, or executing in user mode, as well as CPUs
+ * that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_sched(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
*
* This primitive provides the guarantees made by the (now removed)
* synchronize_kernel() API. In contrast, synchronize_rcu() only
"Illegal synchronize_sched() in RCU-sched read-side critical section");
if (rcu_blocking_is_gp())
return;
- wait_rcu_gp(call_rcu_sched);
+ if (rcu_expedited)
+ synchronize_sched_expedited();
+ else
+ wait_rcu_gp(call_rcu_sched);
}
EXPORT_SYMBOL_GPL(synchronize_sched);
* read-side critical sections have completed. RCU read-side critical
* sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
* and may be nested.
+ *
+ * See the description of synchronize_sched() for more detailed information
+ * on memory ordering guarantees.
*/
void synchronize_rcu_bh(void)
{
"Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
if (rcu_blocking_is_gp())
return;
- wait_rcu_gp(call_rcu_bh);
+ if (rcu_expedited)
+ synchronize_rcu_bh_expedited();
+ else
+ wait_rcu_gp(call_rcu_bh);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
if (trycount++ < 10) {
udelay(trycount * num_online_cpus());
} else {
- synchronize_sched();
+ wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
return;
}
* When that callback is invoked, we will know that all of the
* corresponding CPU's preceding callbacks have been invoked.
*/
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
+ if (!cpu_online(cpu) && !is_nocb_cpu(cpu))
+ continue;
rdp = per_cpu_ptr(rsp->rda, cpu);
- if (ACCESS_ONCE(rdp->qlen)) {
+ if (is_nocb_cpu(cpu)) {
+ _rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+ rsp->n_barrier_done);
+ atomic_inc(&rsp->barrier_cpu_count);
+ __call_rcu(&rdp->barrier_head, rcu_barrier_callback,
+ rsp, cpu, 0);
+ } else if (ACCESS_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
#endif
rdp->cpu = cpu;
rdp->rsp = rsp;
+ rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
struct rcu_node *rnp = rdp->mynode;
struct rcu_state *rsp;
+ int ret = NOTIFY_OK;
trace_rcu_utilization("Start CPU hotplug");
switch (action) {
rcu_boost_kthread_setaffinity(rnp, -1);
break;
case CPU_DOWN_PREPARE:
- rcu_boost_kthread_setaffinity(rnp, cpu);
+ if (nocb_cpu_expendable(cpu))
+ rcu_boost_kthread_setaffinity(rnp, cpu);
+ else
+ ret = NOTIFY_BAD;
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
break;
}
trace_rcu_utilization("End CPU hotplug");
- return NOTIFY_OK;
+ return ret;
}
/*
raw_spin_lock_irqsave(&rnp->lock, flags);
rsp->gp_kthread = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ rcu_spawn_nocb_kthreads(rsp);
}
return 0;
}
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
__rcu_init_preempt();
+ rcu_init_nocb();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
/*