forked from luck/tmp_suning_uos_patched
a33a5d2d16
The generic pending interrupt mechanism moves interrupts from the interrupt
handler on the original target CPU to the new destination CPU. This is
required for x86 and ia64 due to the way the interrupt delivery and
acknowledge works if the interrupts are not remapped.
However that update can fail for various reasons. Some of them are valid
reasons to discard the pending update, but the case, when the previous move
has not been fully cleaned up is not a legit reason to fail.
Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
tried again when the next interrupt arrives.
Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Song Liu <songliubraving@fb.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <liu.song.a23@gmail.com>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: stable@vger.kernel.org
Cc: Mike Travis <mike.travis@hpe.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Tariq Toukan <tariqt@mellanox.com>
Link: https://lkml.kernel.org/r/20180604162224.386544292@linutronix.de
123 lines
3.1 KiB
C
123 lines
3.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/irq.h>
|
|
#include <linux/interrupt.h>
|
|
|
|
#include "internals.h"
|
|
|
|
/**
|
|
* irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
|
|
* @desc: Interrupt descpriptor to clean up
|
|
* @force_clear: If set clear the move pending bit unconditionally.
|
|
* If not set, clear it only when the dying CPU is the
|
|
* last one in the pending mask.
|
|
*
|
|
* Returns true if the pending bit was set and the pending mask contains an
|
|
* online CPU other than the dying CPU.
|
|
*/
|
|
bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
|
|
{
|
|
struct irq_data *data = irq_desc_get_irq_data(desc);
|
|
|
|
if (!irqd_is_setaffinity_pending(data))
|
|
return false;
|
|
|
|
/*
|
|
* The outgoing CPU might be the last online target in a pending
|
|
* interrupt move. If that's the case clear the pending move bit.
|
|
*/
|
|
if (cpumask_any_and(desc->pending_mask, cpu_online_mask) >= nr_cpu_ids) {
|
|
irqd_clr_move_pending(data);
|
|
return false;
|
|
}
|
|
if (force_clear)
|
|
irqd_clr_move_pending(data);
|
|
return true;
|
|
}
|
|
|
|
void irq_move_masked_irq(struct irq_data *idata)
|
|
{
|
|
struct irq_desc *desc = irq_data_to_desc(idata);
|
|
struct irq_data *data = &desc->irq_data;
|
|
struct irq_chip *chip = data->chip;
|
|
|
|
if (likely(!irqd_is_setaffinity_pending(data)))
|
|
return;
|
|
|
|
irqd_clr_move_pending(data);
|
|
|
|
/*
|
|
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
|
|
*/
|
|
if (irqd_is_per_cpu(data)) {
|
|
WARN_ON(1);
|
|
return;
|
|
}
|
|
|
|
if (unlikely(cpumask_empty(desc->pending_mask)))
|
|
return;
|
|
|
|
if (!chip->irq_set_affinity)
|
|
return;
|
|
|
|
assert_raw_spin_locked(&desc->lock);
|
|
|
|
/*
|
|
* If there was a valid mask to work with, please
|
|
* do the disable, re-program, enable sequence.
|
|
* This is *not* particularly important for level triggered
|
|
* but in a edge trigger case, we might be setting rte
|
|
* when an active trigger is coming in. This could
|
|
* cause some ioapics to mal-function.
|
|
* Being paranoid i guess!
|
|
*
|
|
* For correct operation this depends on the caller
|
|
* masking the irqs.
|
|
*/
|
|
if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
|
|
int ret;
|
|
|
|
ret = irq_do_set_affinity(data, desc->pending_mask, false);
|
|
/*
|
|
* If the there is a cleanup pending in the underlying
|
|
* vector management, reschedule the move for the next
|
|
* interrupt. Leave desc->pending_mask intact.
|
|
*/
|
|
if (ret == -EBUSY) {
|
|
irqd_set_move_pending(data);
|
|
return;
|
|
}
|
|
}
|
|
cpumask_clear(desc->pending_mask);
|
|
}
|
|
|
|
void irq_move_irq(struct irq_data *idata)
|
|
{
|
|
bool masked;
|
|
|
|
/*
|
|
* Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
|
|
* and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
|
|
* disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
|
|
*/
|
|
idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
|
|
|
|
if (likely(!irqd_is_setaffinity_pending(idata)))
|
|
return;
|
|
|
|
if (unlikely(irqd_irq_disabled(idata)))
|
|
return;
|
|
|
|
/*
|
|
* Be careful vs. already masked interrupts. If this is a
|
|
* threaded interrupt with ONESHOT set, we can end up with an
|
|
* interrupt storm.
|
|
*/
|
|
masked = irqd_irq_masked(idata);
|
|
if (!masked)
|
|
idata->chip->irq_mask(idata);
|
|
irq_move_masked_irq(idata);
|
|
if (!masked)
|
|
idata->chip->irq_unmask(idata);
|
|
}
|