p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

rcu/nocb: Forbid NOCB toggling on offline CPUs 

It makes no sense to de-offload an offline CPU because that CPU will never
invoke any remaining callbacks.  It also makes little sense to offload an
offline CPU because any pending RCU callbacks were migrated when that CPU
went offline.  Yes, it is in theory possible to use a number of tricks
to permit offloading and deoffloading offline CPUs in certain cases, but
in practice it is far better to have the simple and deterministic rule
"Toggling the offload state of an offline CPU is forbidden".

For but one example, consider that an offloaded offline CPU might have
millions of callbacks queued.  Best to just say "no".

This commit therefore forbids toggling of the offloaded state of
offline CPUs.

Reported-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Neeraj Upadhyay <neeraju@codeaurora.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit is contained in:
Frederic Weisbecker 2021-01-28 18:12:09 +01:00 committed by Paul E. McKenney
parent 5de2e5bb80
commit 64305db285
2 changed files with 22 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
kernel/rcu/tree.c
View File

@ -4086,8 +4086,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
/*
* Lock in case the CB/GP kthreads are still around handling
* old callbacks (longer term we should flush all callbacks
* before completing CPU offline)
* old callbacks.
*/
rcu_nocb_lock(rdp);
if (rcu_segcblist_empty(&rdp->cblist)) /* No early-boot CBs? */

57
kernel/rcu/tree_plugin.h
View File

@ -2399,23 +2399,18 @@ static int rdp_offload_toggle(struct rcu_data *rdp,
return 0;
}
static int __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
static long rcu_nocb_rdp_deoffload(void *arg)
{
struct rcu_data *rdp = arg;
struct rcu_segcblist *cblist = &rdp->cblist;
unsigned long flags;
int ret;
WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
pr_info("De-offloading %d\n", rdp->cpu);
rcu_nocb_lock_irqsave(rdp, flags);
/*
* If there are still pending work offloaded, the offline
* CPU won't help much handling them.
*/
if (cpu_is_offline(rdp->cpu) && !rcu_segcblist_empty(&rdp->cblist)) {
rcu_nocb_unlock_irqrestore(rdp, flags);
return -EBUSY;
}
ret = rdp_offload_toggle(rdp, false, flags);
swait_event_exclusive(rdp->nocb_state_wq,
@ -2446,14 +2441,6 @@ static int __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
return ret;
}
static long rcu_nocb_rdp_deoffload(void *arg)
{
struct rcu_data *rdp = arg;
WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
return __rcu_nocb_rdp_deoffload(rdp);
}
int rcu_nocb_cpu_deoffload(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@ -2466,12 +2453,14 @@ int rcu_nocb_cpu_deoffload(int cpu)
mutex_lock(&rcu_state.barrier_mutex);
cpus_read_lock();
if (rcu_rdp_is_offloaded(rdp)) {
if (cpu_online(cpu))
if (cpu_online(cpu)) {
ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
else
ret = __rcu_nocb_rdp_deoffload(rdp);
if (!ret)
cpumask_clear_cpu(cpu, rcu_nocb_mask);
if (!ret)
cpumask_clear_cpu(cpu, rcu_nocb_mask);
} else {
pr_info("NOCB: Can't CB-deoffload an offline CPU\n");
ret = -EINVAL;
}
}
cpus_read_unlock();
mutex_unlock(&rcu_state.barrier_mutex);
@ -2480,12 +2469,14 @@ int rcu_nocb_cpu_deoffload(int cpu)
}
EXPORT_SYMBOL_GPL(rcu_nocb_cpu_deoffload);
static int __rcu_nocb_rdp_offload(struct rcu_data *rdp)
static long rcu_nocb_rdp_offload(void *arg)
{
struct rcu_data *rdp = arg;
struct rcu_segcblist *cblist = &rdp->cblist;
unsigned long flags;
int ret;
WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
/*
* For now we only support re-offload, ie: the rdp must have been
* offloaded on boot first.
@ -2525,14 +2516,6 @@ static int __rcu_nocb_rdp_offload(struct rcu_data *rdp)
return ret;
}
static long rcu_nocb_rdp_offload(void *arg)
{
struct rcu_data *rdp = arg;
WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
return __rcu_nocb_rdp_offload(rdp);
}
int rcu_nocb_cpu_offload(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@ -2541,12 +2524,14 @@ int rcu_nocb_cpu_offload(int cpu)
mutex_lock(&rcu_state.barrier_mutex);
cpus_read_lock();
if (!rcu_rdp_is_offloaded(rdp)) {
if (cpu_online(cpu))
if (cpu_online(cpu)) {
ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
else
ret = __rcu_nocb_rdp_offload(rdp);
if (!ret)
cpumask_set_cpu(cpu, rcu_nocb_mask);
if (!ret)
cpumask_set_cpu(cpu, rcu_nocb_mask);
} else {
pr_info("NOCB: Can't CB-offload an offline CPU\n");
ret = -EINVAL;
}
}
cpus_read_unlock();
mutex_unlock(&rcu_state.barrier_mutex);