[PATCH] CPU hotplug compatible alloc_percpu()
This patch splits alloc_percpu() up into two phases. Likewise for free_percpu(). This allows clients to limit initial allocations to online cpu's, and to populate or depopulate per-cpu data at run time as needed: struct my_struct *obj; /* initial allocation for online cpu's */ obj = percpu_alloc(sizeof(struct my_struct), GFP_KERNEL); ... /* populate per-cpu data for cpu coming online */ ptr = percpu_populate(obj, sizeof(struct my_struct), GFP_KERNEL, cpu); ... /* access per-cpu object */ ptr = percpu_ptr(obj, smp_processor_id()); ... /* depopulate per-cpu data for cpu going offline */ percpu_depopulate(obj, cpu); ... /* final removal */ percpu_free(obj); Signed-off-by: Martin Peschke <mp3@de.ibm.com> Cc: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Martin Peschke
committed by
Linus Torvalds
Linus Torvalds
parent
8bc719d3ca
commit
7ff6f08295
174
mm/slab.c
174
mm/slab.c
@@ -3371,52 +3371,127 @@ EXPORT_SYMBOL(__kmalloc_track_caller);
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/**
|
||||
* __alloc_percpu - allocate one copy of the object for every present
|
||||
* cpu in the system, zeroing them.
|
||||
* Objects should be dereferenced using the per_cpu_ptr macro only.
|
||||
* percpu_depopulate - depopulate per-cpu data for given cpu
|
||||
* @__pdata: per-cpu data to depopulate
|
||||
* @cpu: depopulate per-cpu data for this cpu
|
||||
*
|
||||
* @size: how many bytes of memory are required.
|
||||
* Depopulating per-cpu data for a cpu going offline would be a typical
|
||||
* use case. You need to register a cpu hotplug handler for that purpose.
|
||||
*/
|
||||
void *__alloc_percpu(size_t size)
|
||||
void percpu_depopulate(void *__pdata, int cpu)
|
||||
{
|
||||
int i;
|
||||
struct percpu_data *pdata = kmalloc(sizeof(*pdata), GFP_KERNEL);
|
||||
struct percpu_data *pdata = __percpu_disguise(__pdata);
|
||||
if (pdata->ptrs[cpu]) {
|
||||
kfree(pdata->ptrs[cpu]);
|
||||
pdata->ptrs[cpu] = NULL;
|
||||
}
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(percpu_depopulate);
|
||||
|
||||
if (!pdata)
|
||||
/**
|
||||
* percpu_depopulate_mask - depopulate per-cpu data for some cpu's
|
||||
* @__pdata: per-cpu data to depopulate
|
||||
* @mask: depopulate per-cpu data for cpu's selected through mask bits
|
||||
*/
|
||||
void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
|
||||
{
|
||||
int cpu;
|
||||
for_each_cpu_mask(cpu, *mask)
|
||||
percpu_depopulate(__pdata, cpu);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(__percpu_depopulate_mask);
|
||||
|
||||
/**
|
||||
* percpu_populate - populate per-cpu data for given cpu
|
||||
* @__pdata: per-cpu data to populate further
|
||||
* @size: size of per-cpu object
|
||||
* @gfp: may sleep or not etc.
|
||||
* @cpu: populate per-data for this cpu
|
||||
*
|
||||
* Populating per-cpu data for a cpu coming online would be a typical
|
||||
* use case. You need to register a cpu hotplug handler for that purpose.
|
||||
* Per-cpu object is populated with zeroed buffer.
|
||||
*/
|
||||
void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
|
||||
{
|
||||
struct percpu_data *pdata = __percpu_disguise(__pdata);
|
||||
int node = cpu_to_node(cpu);
|
||||
|
||||
BUG_ON(pdata->ptrs[cpu]);
|
||||
if (node_online(node)) {
|
||||
/* FIXME: kzalloc_node(size, gfp, node) */
|
||||
pdata->ptrs[cpu] = kmalloc_node(size, gfp, node);
|
||||
if (pdata->ptrs[cpu])
|
||||
memset(pdata->ptrs[cpu], 0, size);
|
||||
} else
|
||||
pdata->ptrs[cpu] = kzalloc(size, gfp);
|
||||
return pdata->ptrs[cpu];
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(percpu_populate);
|
||||
|
||||
/**
|
||||
* percpu_populate_mask - populate per-cpu data for more cpu's
|
||||
* @__pdata: per-cpu data to populate further
|
||||
* @size: size of per-cpu object
|
||||
* @gfp: may sleep or not etc.
|
||||
* @mask: populate per-cpu data for cpu's selected through mask bits
|
||||
*
|
||||
* Per-cpu objects are populated with zeroed buffers.
|
||||
*/
|
||||
int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
|
||||
cpumask_t *mask)
|
||||
{
|
||||
cpumask_t populated = CPU_MASK_NONE;
|
||||
int cpu;
|
||||
|
||||
for_each_cpu_mask(cpu, *mask)
|
||||
if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
|
||||
__percpu_depopulate_mask(__pdata, &populated);
|
||||
return -ENOMEM;
|
||||
} else
|
||||
cpu_set(cpu, populated);
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(__percpu_populate_mask);
|
||||
|
||||
/**
|
||||
* percpu_alloc_mask - initial setup of per-cpu data
|
||||
* @size: size of per-cpu object
|
||||
* @gfp: may sleep or not etc.
|
||||
* @mask: populate per-data for cpu's selected through mask bits
|
||||
*
|
||||
* Populating per-cpu data for all online cpu's would be a typical use case,
|
||||
* which is simplified by the percpu_alloc() wrapper.
|
||||
* Per-cpu objects are populated with zeroed buffers.
|
||||
*/
|
||||
void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
|
||||
{
|
||||
void *pdata = kzalloc(sizeof(struct percpu_data), gfp);
|
||||
void *__pdata = __percpu_disguise(pdata);
|
||||
|
||||
if (unlikely(!pdata))
|
||||
return NULL;
|
||||
|
||||
/*
|
||||
* Cannot use for_each_online_cpu since a cpu may come online
|
||||
* and we have no way of figuring out how to fix the array
|
||||
* that we have allocated then....
|
||||
*/
|
||||
for_each_possible_cpu(i) {
|
||||
int node = cpu_to_node(i);
|
||||
|
||||
if (node_online(node))
|
||||
pdata->ptrs[i] = kmalloc_node(size, GFP_KERNEL, node);
|
||||
else
|
||||
pdata->ptrs[i] = kmalloc(size, GFP_KERNEL);
|
||||
|
||||
if (!pdata->ptrs[i])
|
||||
goto unwind_oom;
|
||||
memset(pdata->ptrs[i], 0, size);
|
||||
}
|
||||
|
||||
/* Catch derefs w/o wrappers */
|
||||
return (void *)(~(unsigned long)pdata);
|
||||
|
||||
unwind_oom:
|
||||
while (--i >= 0) {
|
||||
if (!cpu_possible(i))
|
||||
continue;
|
||||
kfree(pdata->ptrs[i]);
|
||||
}
|
||||
if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask)))
|
||||
return __pdata;
|
||||
kfree(pdata);
|
||||
return NULL;
|
||||
}
|
||||
EXPORT_SYMBOL(__alloc_percpu);
|
||||
#endif
|
||||
EXPORT_SYMBOL_GPL(__percpu_alloc_mask);
|
||||
|
||||
/**
|
||||
* percpu_free - final cleanup of per-cpu data
|
||||
* @__pdata: object to clean up
|
||||
*
|
||||
* We simply clean up any per-cpu object left. No need for the client to
|
||||
* track and specify through a bis mask which per-cpu objects are to free.
|
||||
*/
|
||||
void percpu_free(void *__pdata)
|
||||
{
|
||||
__percpu_depopulate_mask(__pdata, &cpu_possible_map);
|
||||
kfree(__percpu_disguise(__pdata));
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(percpu_free);
|
||||
#endif /* CONFIG_SMP */
|
||||
|
||||
/**
|
||||
* kmem_cache_free - Deallocate an object
|
||||
@@ -3463,29 +3538,6 @@ void kfree(const void *objp)
|
||||
}
|
||||
EXPORT_SYMBOL(kfree);
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/**
|
||||
* free_percpu - free previously allocated percpu memory
|
||||
* @objp: pointer returned by alloc_percpu.
|
||||
*
|
||||
* Don't free memory not originally allocated by alloc_percpu()
|
||||
* The complemented objp is to check for that.
|
||||
*/
|
||||
void free_percpu(const void *objp)
|
||||
{
|
||||
int i;
|
||||
struct percpu_data *p = (struct percpu_data *)(~(unsigned long)objp);
|
||||
|
||||
/*
|
||||
* We allocate for all cpus so we cannot use for online cpu here.
|
||||
*/
|
||||
for_each_possible_cpu(i)
|
||||
kfree(p->ptrs[i]);
|
||||
kfree(p);
|
||||
}
|
||||
EXPORT_SYMBOL(free_percpu);
|
||||
#endif
|
||||
|
||||
unsigned int kmem_cache_size(struct kmem_cache *cachep)
|
||||
{
|
||||
return obj_size(cachep);
|
||||
|
||||
Reference in New Issue
Block a user