OpenCloudOS-Kernel/kernel/irq/cpuhotplug.c

234 lines
6.6 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* 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 <linux/sched/isolation.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);
unsigned int cpu = smp_processor_id();
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
/*
* The cpumask_empty() check is a workaround for interrupt chips,
* which do not implement effective affinity, but the architecture has
* enabled the config switch. Use the general affinity mask instead.
*/
if (cpumask_empty(m))
m = irq_data_get_affinity_mask(d);
/*
* Sanity check. If the mask is not empty when excluding the outgoing
* CPU then it must contain at least one online CPU. The outgoing CPU
* has been removed from the online mask already.
*/
if (cpumask_any_but(m, cpu) < nr_cpu_ids &&
cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) {
/*
* If this happens then there was a missed IRQ fixup at some
* point. Warn about it and enforce fixup.
*/
pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n",
cpumask_pr_args(m), d->irq, cpu);
return true;
}
#endif
return cpumask_test_cpu(cpu, 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) {
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
/*
* 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_and_deactivate(desc);
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
return false;
}
affinity = cpu_online_mask;
brokeaff = true;
}
genirq/cpuhotplug: Revert "Set force affinity flag on hotplug migration" 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: 77f85e66aa8b ("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>
2017-07-27 18:21:11 +08:00
/*
* 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());
}
}
}
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
{
const struct cpumask *hk_mask;
if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
return false;
hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
return false;
return cpumask_test_cpu(cpu, hk_mask);
}
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
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)) {
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
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 unless the
* isolation mechanism requests to move it to an upcoming
* housekeeping CPU.
*/
if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
genirq/cpuhotplug: Handle managed IRQs on CPU hotplug If a CPU goes offline, interrupts affine to the CPU are moved away. If the outgoing CPU is the last CPU in the affinity mask the migration code breaks the affinity and sets it it all online cpus. This is a problem for affinity managed interrupts as CPU hotplug is often used for power management purposes. If the affinity is broken, the interrupt is not longer affine to the CPUs to which it was allocated. The affinity spreading allows to lay out multi queue devices in a way that they are assigned to a single CPU or a group of CPUs. If the last CPU goes offline, then the queue is not longer used, so the interrupt can be shutdown gracefully and parked until one of the assigned CPUs comes online again. Add a graceful shutdown mechanism into the irq affinity breaking code path, mark the irq as MANAGED_SHUTDOWN and leave the affinity mask unmodified. In the online path, scan the active interrupts for managed interrupts and if the interrupt is functional and the newly online CPU is part of the affinity mask, restart the interrupt if it is marked MANAGED_SHUTDOWN or if the interrupts is started up, try to add the CPU back to the effective affinity mask. Originally-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170619235447.273417334@linutronix.de
2017-06-20 07:37:51 +08:00
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;
}