Re: [PATCH v2] lib: cpu_rmap: avoid flushing all workqueues

From: David Decotigny
Date: Fri Dec 28 2012 - 16:44:15 EST


Thanks,

Ok for the cpu_rmap_put helper. Will do this in v3 of this patch.

Your comments suggest more refactoring, which might be better in the
form of 1 or 2 additional patches that:
- rename alloc_cpu_rmap & co according to new conventions (cpu_rmap_*)
- remove the cpu_rmap sub-API altogether, keeping only irq_cpu_rmap
(controversial?)

I'd rather current patch is integrated in its own as it fixes an actual bug.
I will send the other patch(es) separately later.

v3 for this patch coming soon.

On Fri, Dec 28, 2012 at 1:14 PM, Eric Dumazet <eric.dumazet@xxxxxxxxx> wrote:
> On Fri, 2012-12-28 at 11:03 -0800, David Decotigny wrote:
>> In some cases, free_irq_cpu_rmap() is called while holding a lock
>> (eg. rtnl). This can lead to deadlocks, because it invokes
>> flush_scheduled_work() which ends up waiting for whole system
>> workqueue to flush, but some pending works might try to acquire the
>> lock we are already holding.
>>
>> This commit uses reference-counting to replace
>> irq_run_affinity_notifiers(). It also removes
>> irq_run_affinity_notifiers() altogether.
>>
>> Signed-off-by: David Decotigny <decot@xxxxxxxxxxxx>
>> ---
>> include/linux/cpu_rmap.h | 13 ++++---------
>> include/linux/interrupt.h | 5 -----
>> lib/cpu_rmap.c | 47 +++++++++++++++++++++++++++++++++++++++------
>> 3 files changed, 45 insertions(+), 20 deletions(-)
>>
>> diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
>> index ac3bbb5..3be2813 100644
>> --- a/include/linux/cpu_rmap.h
>> +++ b/include/linux/cpu_rmap.h
>> @@ -13,9 +13,11 @@
>> #include <linux/cpumask.h>
>> #include <linux/gfp.h>
>> #include <linux/slab.h>
>> +#include <linux/kref.h>
>>
>> /**
>> * struct cpu_rmap - CPU affinity reverse-map
>> + * @refcount: kref for object
>> * @size: Number of objects to be reverse-mapped
>> * @used: Number of objects added
>> * @obj: Pointer to array of object pointers
>> @@ -23,6 +25,7 @@
>> * based on affinity masks
>> */
>> struct cpu_rmap {
>> + struct kref refcount;
>> u16 size, used;
>> void **obj;
>> struct {
>> @@ -33,15 +36,7 @@ struct cpu_rmap {
>> #define CPU_RMAP_DIST_INF 0xffff
>>
>> extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
>> -
>> -/**
>> - * free_cpu_rmap - free CPU affinity reverse-map
>> - * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL
>> - */
>> -static inline void free_cpu_rmap(struct cpu_rmap *rmap)
>> -{
>> - kfree(rmap);
>> -}
>> +extern void free_cpu_rmap(struct cpu_rmap *rmap);
>>
>> extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
>> extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
>> diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
>> index 5e4e617..5fa5afe 100644
>> --- a/include/linux/interrupt.h
>> +++ b/include/linux/interrupt.h
>> @@ -268,11 +268,6 @@ struct irq_affinity_notify {
>> extern int
>> irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
>>
>> -static inline void irq_run_affinity_notifiers(void)
>> -{
>> - flush_scheduled_work();
>> -}
>> -
>> #else /* CONFIG_SMP */
>>
>> static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
>> diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
>> index 145dec5..bb5d0af 100644
>> --- a/lib/cpu_rmap.c
>> +++ b/lib/cpu_rmap.c
>> @@ -45,6 +45,7 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
>> if (!rmap)
>> return NULL;
>>
>> + kref_init(&rmap->refcount);
>> rmap->obj = (void **)((char *)rmap + obj_offset);
>>
>> /* Initially assign CPUs to objects on a rota, since we have
>> @@ -63,6 +64,26 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
>> }
>> EXPORT_SYMBOL(alloc_cpu_rmap);
>>
>> +/**
>> + * reclaim_cpu_rmap - internal reclaiming helper called from kref_put
>> + * @ref: kref to struct cpu_rmap
>> + */
>> +static void reclaim_cpu_rmap(struct kref *ref)
>
> Could be named cpu_rmap_free()
>
> (and alloc_cpu_rmap() should be renamed as cpu_rmap_alloc()
>
>> +{
>> + struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
>> + kfree(rmap);
>> +}
>> +
>> +/**
>> + * free_cpu_rmap - free CPU affinity reverse-map
>> + * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL
>> + */
>> +void free_cpu_rmap(struct cpu_rmap *rmap)
>
> This could be named : cpu_rmap_put()
>
>> +{
>> + kref_put(&rmap->refcount, reclaim_cpu_rmap);
>> +}
>> +EXPORT_SYMBOL(free_cpu_rmap);
>
> It seems this function could be static, and not exported.
>
>> +
>> /* Reevaluate nearest object for given CPU, comparing with the given
>> * neighbours at the given distance.
>> */
>> @@ -197,8 +218,7 @@ struct irq_glue {
>> * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
>> * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
>> *
>> - * Must be called in process context, before freeing the IRQs, and
>> - * without holding any locks required by global workqueue items.
>> + * Must be called in process context, before freeing the IRQs.
>> */
>> void free_irq_cpu_rmap(struct cpu_rmap *rmap)
>> {
>> @@ -212,12 +232,18 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap)
>> glue = rmap->obj[index];
>> irq_set_affinity_notifier(glue->notify.irq, NULL);
>> }
>> - irq_run_affinity_notifiers();
>>
>> - kfree(rmap);
>> + free_cpu_rmap(rmap);
>> }
>> EXPORT_SYMBOL(free_irq_cpu_rmap);
>>
>> +/**
>> + * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
>> + * @notify: struct irq_affinity_notify passed by irq/manage.c
>> + * @mask: cpu mask for new SMP affinity
>> + *
>> + * This is executed in workqueue context.
>> + */
>> static void
>> irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
>> {
>> @@ -230,16 +256,22 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
>> pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
>> }
>>
>> +/**
>> + * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
>> + * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
>> + */
>> static void irq_cpu_rmap_release(struct kref *ref)
>> {
>> struct irq_glue *glue =
>> container_of(ref, struct irq_glue, notify.kref);
>> +
>> + kref_put(&glue->rmap->refcount, reclaim_cpu_rmap);
>
> cpu_rmap_put(glue->rmap);
>
>> kfree(glue);
>> }
>>
>> /**
>> * irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
>> - * @rmap: The reverse-map
>> + * @rmap: The per-IRQ reverse-map
>> * @irq: The IRQ number
>> *
>> * This adds an IRQ affinity notifier that will update the reverse-map
>> @@ -259,9 +291,12 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
>> glue->notify.release = irq_cpu_rmap_release;
>> glue->rmap = rmap;
>> glue->index = cpu_rmap_add(rmap, glue);
>> + kref_get(&rmap->refcount);
>> rc = irq_set_affinity_notifier(irq, &glue->notify);
>> - if (rc)
>> + if (rc) {
>> + kref_put(&rmap->refcount, reclaim_cpu_rmap);
>
> cpu_rmap_put(rmap);
>
>> kfree(glue);
>> + }
>> return rc;
>> }
>> EXPORT_SYMBOL(irq_cpu_rmap_add);
>
> I personally don't like kref abstraction, especially when used without
> wrapper :
>
> kref_put(&rmap->refcount, reclaim_cpu_rmap);
>
> Its cleaner to have instead :
>
> cpu_rmap_put(rmap);
>
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/