.orphan_nxttail = &sname##_state.orphan_nxtlist, \
.orphan_donetail = &sname##_state.orphan_donelist, \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
+ .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
.name = #sname, \
}
#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;
raw_spin_unlock_irq(&rnp->lock);
/* Exclude any concurrent CPU-hotplug operations. */
- get_online_cpus();
+ mutex_lock(&rsp->onoff_mutex);
/*
* Set the quiescent-state-needed bits in all the rcu_node
cond_resched();
}
- put_online_cpus();
+ mutex_unlock(&rsp->onoff_mutex);
return 1;
}
!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);
}
/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
/* Exclude any attempts to start a new grace period. */
+ mutex_lock(&rsp->onoff_mutex);
raw_spin_lock_irqsave(&rsp->onofflock, flags);
/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
init_callback_list(rdp);
/* Disallow further callbacks on this CPU. */
rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+ mutex_unlock(&rsp->onoff_mutex);
}
#else /* #ifdef CONFIG_HOTPLUG_CPU */
{
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)) {
* 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
* 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)
{
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
+ /* Exclude new grace periods. */
+ mutex_lock(&rsp->onoff_mutex);
+
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
rdp->beenonline = 1; /* We have now been online. */
rcu_prepare_for_idle_init(cpu);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
- /*
- * A new grace period might start here. If so, we won't be part
- * of it, but that is OK, as we are currently in a quiescent state.
- */
-
- /* Exclude any attempts to start a new GP on large systems. */
- raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */
-
/* Add CPU to rcu_node bitmasks. */
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
rnp = rnp->parent;
} while (rnp != NULL && !(rnp->qsmaskinit & mask));
+ local_irq_restore(flags);
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+ mutex_unlock(&rsp->onoff_mutex);
}
static void __cpuinit rcu_prepare_cpu(int cpu)