8397913303
That commit was part of the changes moving x86 to the generic CPU hotplug
interrupt migration code. The force flag was required on x86 before the
hierarchical irqdomain rework, but invoking set_affinity() with force=true
stayed and had no side effects.
At some point in the past, the force flag got repurposed to support the
exynos timer interrupt affinity setting to a not yet online CPU, so the
interrupt controller callback does not verify the supplied affinity mask
against cpu_online_mask.
Setting the flag in the CPU hotplug code causes the cpu online masking to
be blocked on these irq controllers and results in potentially affining an
interrupt to the CPU which is unplugged, i.e. instead of moving it away,
it's just reassigned to it.
As the force flags is not longer needed on x86, it's safe to revert that
patch so the ARM irqchips which use the force flag work again.
Add comments to that effect, so this won't happen again.
Note: The online mask handling should be done in the generic code and the
force flag and the masking in the irq chips removed all together, but
that's not a change possible for 4.13.
Fixes: 77f85e66aa
("genirq/cpuhotplug: Set force affinity flag on hotplug migration")
Reported-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: LAK <linux-arm-kernel@lists.infradead.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1707271217590.3109@nanos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
189 lines
5.2 KiB
C
189 lines
5.2 KiB
C
/*
|
|
* Generic cpu hotunplug interrupt migration code copied from the
|
|
* arch/arm implementation
|
|
*
|
|
* Copyright (C) Russell King
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/interrupt.h>
|
|
#include <linux/ratelimit.h>
|
|
#include <linux/irq.h>
|
|
|
|
#include "internals.h"
|
|
|
|
/* For !GENERIC_IRQ_EFFECTIVE_AFF_MASK this looks at general affinity mask */
|
|
static inline bool irq_needs_fixup(struct irq_data *d)
|
|
{
|
|
const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
|
|
|
|
return cpumask_test_cpu(smp_processor_id(), m);
|
|
}
|
|
|
|
static bool migrate_one_irq(struct irq_desc *desc)
|
|
{
|
|
struct irq_data *d = irq_desc_get_irq_data(desc);
|
|
struct irq_chip *chip = irq_data_get_irq_chip(d);
|
|
bool maskchip = !irq_can_move_pcntxt(d) && !irqd_irq_masked(d);
|
|
const struct cpumask *affinity;
|
|
bool brokeaff = false;
|
|
int err;
|
|
|
|
/*
|
|
* IRQ chip might be already torn down, but the irq descriptor is
|
|
* still in the radix tree. Also if the chip has no affinity setter,
|
|
* nothing can be done here.
|
|
*/
|
|
if (!chip || !chip->irq_set_affinity) {
|
|
pr_debug("IRQ %u: Unable to migrate away\n", d->irq);
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* No move required, if:
|
|
* - Interrupt is per cpu
|
|
* - Interrupt is not started
|
|
* - Affinity mask does not include this CPU.
|
|
*
|
|
* Note: Do not check desc->action as this might be a chained
|
|
* interrupt.
|
|
*/
|
|
if (irqd_is_per_cpu(d) || !irqd_is_started(d) || !irq_needs_fixup(d)) {
|
|
/*
|
|
* If an irq move is pending, abort it if the dying CPU is
|
|
* the sole target.
|
|
*/
|
|
irq_fixup_move_pending(desc, false);
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Complete an eventually pending irq move cleanup. If this
|
|
* interrupt was moved in hard irq context, then the vectors need
|
|
* to be cleaned up. It can't wait until this interrupt actually
|
|
* happens and this CPU was involved.
|
|
*/
|
|
irq_force_complete_move(desc);
|
|
|
|
/*
|
|
* If there is a setaffinity pending, then try to reuse the pending
|
|
* mask, so the last change of the affinity does not get lost. If
|
|
* there is no move pending or the pending mask does not contain
|
|
* any online CPU, use the current affinity mask.
|
|
*/
|
|
if (irq_fixup_move_pending(desc, true))
|
|
affinity = irq_desc_get_pending_mask(desc);
|
|
else
|
|
affinity = irq_data_get_affinity_mask(d);
|
|
|
|
/* Mask the chip for interrupts which cannot move in process context */
|
|
if (maskchip && chip->irq_mask)
|
|
chip->irq_mask(d);
|
|
|
|
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
|
|
/*
|
|
* If the interrupt is managed, then shut it down and leave
|
|
* the affinity untouched.
|
|
*/
|
|
if (irqd_affinity_is_managed(d)) {
|
|
irqd_set_managed_shutdown(d);
|
|
irq_shutdown(desc);
|
|
return false;
|
|
}
|
|
affinity = cpu_online_mask;
|
|
brokeaff = true;
|
|
}
|
|
/*
|
|
* Do not set the force argument of irq_do_set_affinity() as this
|
|
* disables the masking of offline CPUs from the supplied affinity
|
|
* mask and therefore might keep/reassign the irq to the outgoing
|
|
* CPU.
|
|
*/
|
|
err = irq_do_set_affinity(d, affinity, false);
|
|
if (err) {
|
|
pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
|
|
d->irq, err);
|
|
brokeaff = false;
|
|
}
|
|
|
|
if (maskchip && chip->irq_unmask)
|
|
chip->irq_unmask(d);
|
|
|
|
return brokeaff;
|
|
}
|
|
|
|
/**
|
|
* irq_migrate_all_off_this_cpu - Migrate irqs away from offline cpu
|
|
*
|
|
* The current CPU has been marked offline. Migrate IRQs off this CPU.
|
|
* If the affinity settings do not allow other CPUs, force them onto any
|
|
* available CPU.
|
|
*
|
|
* Note: we must iterate over all IRQs, whether they have an attached
|
|
* action structure or not, as we need to get chained interrupts too.
|
|
*/
|
|
void irq_migrate_all_off_this_cpu(void)
|
|
{
|
|
struct irq_desc *desc;
|
|
unsigned int irq;
|
|
|
|
for_each_active_irq(irq) {
|
|
bool affinity_broken;
|
|
|
|
desc = irq_to_desc(irq);
|
|
raw_spin_lock(&desc->lock);
|
|
affinity_broken = migrate_one_irq(desc);
|
|
raw_spin_unlock(&desc->lock);
|
|
|
|
if (affinity_broken) {
|
|
pr_warn_ratelimited("IRQ %u: no longer affine to CPU%u\n",
|
|
irq, smp_processor_id());
|
|
}
|
|
}
|
|
}
|
|
|
|
static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
|
|
{
|
|
struct irq_data *data = irq_desc_get_irq_data(desc);
|
|
const struct cpumask *affinity = irq_data_get_affinity_mask(data);
|
|
|
|
if (!irqd_affinity_is_managed(data) || !desc->action ||
|
|
!irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
|
|
return;
|
|
|
|
if (irqd_is_managed_and_shutdown(data)) {
|
|
irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* If the interrupt can only be directed to a single target
|
|
* CPU then it is already assigned to a CPU in the affinity
|
|
* mask. No point in trying to move it around.
|
|
*/
|
|
if (!irqd_is_single_target(data))
|
|
irq_set_affinity_locked(data, affinity, false);
|
|
}
|
|
|
|
/**
|
|
* irq_affinity_online_cpu - Restore affinity for managed interrupts
|
|
* @cpu: Upcoming CPU for which interrupts should be restored
|
|
*/
|
|
int irq_affinity_online_cpu(unsigned int cpu)
|
|
{
|
|
struct irq_desc *desc;
|
|
unsigned int irq;
|
|
|
|
irq_lock_sparse();
|
|
for_each_active_irq(irq) {
|
|
desc = irq_to_desc(irq);
|
|
raw_spin_lock_irq(&desc->lock);
|
|
irq_restore_affinity_of_irq(desc, cpu);
|
|
raw_spin_unlock_irq(&desc->lock);
|
|
}
|
|
irq_unlock_sparse();
|
|
|
|
return 0;
|
|
}
|