Commit 5a04848d authored by Paul E. McKenney's avatar Paul E. McKenney
Browse files

rcu: Consolidate initialization and CPU-hotplug code



This commit consolidates the initialization and CPU-hotplug code at
the end of kernel/rcu/tree.c.  This is strictly a code-motion commit.
No functionality has changed.

Signed-off-by: default avatarPaul E. McKenney <paulmck@kernel.org>
parent c004d231
Loading
Loading
Loading
Loading
+158 −156
Original line number Diff line number Diff line
@@ -144,14 +144,16 @@ static int rcu_scheduler_fully_active __read_mostly;

static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
			      unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
static bool rcu_rdp_is_offloaded(struct rcu_data *rdp);
static bool rcu_rdp_cpu_online(struct rcu_data *rdp);
static bool rcu_init_invoked(void);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);

/*
 * rcuc/rcub/rcuop kthread realtime priority. The "rcuop"
@@ -214,27 +216,6 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
 */
#define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays for debugging. */

/*
 * Compute the mask of online CPUs for the specified rcu_node structure.
 * This will not be stable unless the rcu_node structure's ->lock is
 * held, but the bit corresponding to the current CPU will be stable
 * in most contexts.
 */
static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
	return READ_ONCE(rnp->qsmaskinitnext);
}

/*
 * Is the CPU corresponding to the specified rcu_data structure online
 * from RCU's perspective?  This perspective is given by that structure's
 * ->qsmaskinitnext field rather than by the global cpu_online_mask.
 */
static bool rcu_rdp_cpu_online(struct rcu_data *rdp)
{
	return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode));
}

/*
 * Return true if an RCU grace period is in progress.  The READ_ONCE()s
 * permit this function to be invoked without holding the root rcu_node
@@ -734,46 +715,6 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
	smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true);
}

#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)

/*
 * Is the current CPU online as far as RCU is concerned?
 *
 * Disable preemption to avoid false positives that could otherwise
 * happen due to the current CPU number being sampled, this task being
 * preempted, its old CPU being taken offline, resuming on some other CPU,
 * then determining that its old CPU is now offline.
 *
 * Disable checking if in an NMI handler because we cannot safely
 * report errors from NMI handlers anyway.  In addition, it is OK to use
 * RCU on an offline processor during initial boot, hence the check for
 * rcu_scheduler_fully_active.
 */
bool rcu_lockdep_current_cpu_online(void)
{
	struct rcu_data *rdp;
	bool ret = false;

	if (in_nmi() || !rcu_scheduler_fully_active)
		return true;
	preempt_disable_notrace();
	rdp = this_cpu_ptr(&rcu_data);
	/*
	 * Strictly, we care here about the case where the current CPU is
	 * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
	 * not being up to date. So arch_spin_is_locked() might have a
	 * false positive if it's held by some *other* CPU, but that's
	 * OK because that just means a false *negative* on the warning.
	 */
	if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock))
		ret = true;
	preempt_enable_notrace();
	return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);

#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */

/*
 * When trying to report a quiescent state on behalf of some other CPU,
 * it is our responsibility to check for and handle potential overflow
@@ -1350,13 +1291,6 @@ static void rcu_strict_gp_boundary(void *unused)
	invoke_rcu_core();
}

// Has rcu_init() been invoked?  This is used (for example) to determine
// whether spinlocks may be acquired safely.
static bool rcu_init_invoked(void)
{
	return !!rcu_state.n_online_cpus;
}

// Make the polled API aware of the beginning of a grace period.
static void rcu_poll_gp_seq_start(unsigned long *snap)
{
@@ -2091,92 +2025,6 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
	rcu_report_qs_rdp(rdp);
}

/*
 * Near the end of the offline process.  Trace the fact that this CPU
 * is going offline.
 */
int rcutree_dying_cpu(unsigned int cpu)
{
	bool blkd;
	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
	struct rcu_node *rnp = rdp->mynode;

	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
		return 0;

	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
	return 0;
}

/*
 * All CPUs for the specified rcu_node structure have gone offline,
 * and all tasks that were preempted within an RCU read-side critical
 * section while running on one of those CPUs have since exited their RCU
 * read-side critical section.  Some other CPU is reporting this fact with
 * the specified rcu_node structure's ->lock held and interrupts disabled.
 * This function therefore goes up the tree of rcu_node structures,
 * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
 * the leaf rcu_node structure's ->qsmaskinit field has already been
 * updated.
 *
 * This function does check that the specified rcu_node structure has
 * all CPUs offline and no blocked tasks, so it is OK to invoke it
 * prematurely.  That said, invoking it after the fact will cost you
 * a needless lock acquisition.  So once it has done its work, don't
 * invoke it again.
 */
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
	long mask;
	struct rcu_node *rnp = rnp_leaf;

	raw_lockdep_assert_held_rcu_node(rnp_leaf);
	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
	    WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
	    WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
		return;
	for (;;) {
		mask = rnp->grpmask;
		rnp = rnp->parent;
		if (!rnp)
			break;
		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
		rnp->qsmaskinit &= ~mask;
		/* Between grace periods, so better already be zero! */
		WARN_ON_ONCE(rnp->qsmask);
		if (rnp->qsmaskinit) {
			raw_spin_unlock_rcu_node(rnp);
			/* irqs remain disabled. */
			return;
		}
		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
	}
}

/*
 * The CPU has been completely removed, and some other CPU is reporting
 * this fact from process context.  Do the remainder of the cleanup.
 * There can only be one CPU hotplug operation at a time, so no need for
 * explicit locking.
 */
int rcutree_dead_cpu(unsigned int cpu)
{
	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */

	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
		return 0;

	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
	/* Adjust any no-longer-needed kthreads. */
	rcu_boost_kthread_setaffinity(rnp, -1);
	// Stop-machine done, so allow nohz_full to disable tick.
	tick_dep_clear(TICK_DEP_BIT_RCU);
	return 0;
}

/*
 * Invoke any RCU callbacks that have made it to the end of their grace
 * period.  Throttle as specified by rdp->blimit.
@@ -4079,6 +3927,160 @@ void rcu_barrier(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier);

/*
 * Compute the mask of online CPUs for the specified rcu_node structure.
 * This will not be stable unless the rcu_node structure's ->lock is
 * held, but the bit corresponding to the current CPU will be stable
 * in most contexts.
 */
static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
	return READ_ONCE(rnp->qsmaskinitnext);
}

/*
 * Is the CPU corresponding to the specified rcu_data structure online
 * from RCU's perspective?  This perspective is given by that structure's
 * ->qsmaskinitnext field rather than by the global cpu_online_mask.
 */
static bool rcu_rdp_cpu_online(struct rcu_data *rdp)
{
	return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode));
}

#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)

/*
 * Is the current CPU online as far as RCU is concerned?
 *
 * Disable preemption to avoid false positives that could otherwise
 * happen due to the current CPU number being sampled, this task being
 * preempted, its old CPU being taken offline, resuming on some other CPU,
 * then determining that its old CPU is now offline.
 *
 * Disable checking if in an NMI handler because we cannot safely
 * report errors from NMI handlers anyway.  In addition, it is OK to use
 * RCU on an offline processor during initial boot, hence the check for
 * rcu_scheduler_fully_active.
 */
bool rcu_lockdep_current_cpu_online(void)
{
	struct rcu_data *rdp;
	bool ret = false;

	if (in_nmi() || !rcu_scheduler_fully_active)
		return true;
	preempt_disable_notrace();
	rdp = this_cpu_ptr(&rcu_data);
	/*
	 * Strictly, we care here about the case where the current CPU is
	 * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
	 * not being up to date. So arch_spin_is_locked() might have a
	 * false positive if it's held by some *other* CPU, but that's
	 * OK because that just means a false *negative* on the warning.
	 */
	if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock))
		ret = true;
	preempt_enable_notrace();
	return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);

#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */

// Has rcu_init() been invoked?  This is used (for example) to determine
// whether spinlocks may be acquired safely.
static bool rcu_init_invoked(void)
{
	return !!rcu_state.n_online_cpus;
}

/*
 * Near the end of the offline process.  Trace the fact that this CPU
 * is going offline.
 */
int rcutree_dying_cpu(unsigned int cpu)
{
	bool blkd;
	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
	struct rcu_node *rnp = rdp->mynode;

	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
		return 0;

	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
	return 0;
}

/*
 * All CPUs for the specified rcu_node structure have gone offline,
 * and all tasks that were preempted within an RCU read-side critical
 * section while running on one of those CPUs have since exited their RCU
 * read-side critical section.  Some other CPU is reporting this fact with
 * the specified rcu_node structure's ->lock held and interrupts disabled.
 * This function therefore goes up the tree of rcu_node structures,
 * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
 * the leaf rcu_node structure's ->qsmaskinit field has already been
 * updated.
 *
 * This function does check that the specified rcu_node structure has
 * all CPUs offline and no blocked tasks, so it is OK to invoke it
 * prematurely.  That said, invoking it after the fact will cost you
 * a needless lock acquisition.  So once it has done its work, don't
 * invoke it again.
 */
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
	long mask;
	struct rcu_node *rnp = rnp_leaf;

	raw_lockdep_assert_held_rcu_node(rnp_leaf);
	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
	    WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
	    WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
		return;
	for (;;) {
		mask = rnp->grpmask;
		rnp = rnp->parent;
		if (!rnp)
			break;
		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
		rnp->qsmaskinit &= ~mask;
		/* Between grace periods, so better already be zero! */
		WARN_ON_ONCE(rnp->qsmask);
		if (rnp->qsmaskinit) {
			raw_spin_unlock_rcu_node(rnp);
			/* irqs remain disabled. */
			return;
		}
		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
	}
}

/*
 * The CPU has been completely removed, and some other CPU is reporting
 * this fact from process context.  Do the remainder of the cleanup.
 * There can only be one CPU hotplug operation at a time, so no need for
 * explicit locking.
 */
int rcutree_dead_cpu(unsigned int cpu)
{
	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */

	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
		return 0;

	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
	/* Adjust any no-longer-needed kthreads. */
	rcu_boost_kthread_setaffinity(rnp, -1);
	// Stop-machine done, so allow nohz_full to disable tick.
	tick_dep_clear(TICK_DEP_BIT_RCU);
	return 0;
}

/*
 * Propagate ->qsinitmask bits up the rcu_node tree to account for the
 * first CPU in a given leaf rcu_node structure coming online.  The caller