Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Wed, 16 Jan 2013, Joonsoo Kim wrote: > These slabs are not on the partial list, but on the cpu_slab of boot cpu. > Reason for this is described in changelog. > Because these slabs are not on partial list, we need to > check kmem_cache_cpu's cpu slab. This patch implement it. Ah. Ok. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Tue, Jan 15, 2013 at 03:36:10PM +, Christoph Lameter wrote: > On Tue, 15 Jan 2013, Joonsoo Kim wrote: > > > These didn't make any error previously, because we normally don't free > > objects which comes from kmem_cache's first slab and kmem_cache_node's. > > And these slabs are on the partial list because the objects are typically > relatively small compared to page size. Do you have a system with a very > large kmem_cache size? These slabs are not on the partial list, but on the cpu_slab of boot cpu. Reason for this is described in changelog. Because these slabs are not on partial list, we need to check kmem_cache_cpu's cpu slab. This patch implement it. > > Problem will be solved if we consider a cpu slab in bootstrap(). > > This patch implement it. > > At boot time only one processor is up so you do not need the loop over all > processors. Okay! I will fix and submit v2, soon. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Tue, Jan 15, 2013 at 03:36:10PM +, Christoph Lameter wrote: On Tue, 15 Jan 2013, Joonsoo Kim wrote: These didn't make any error previously, because we normally don't free objects which comes from kmem_cache's first slab and kmem_cache_node's. And these slabs are on the partial list because the objects are typically relatively small compared to page size. Do you have a system with a very large kmem_cache size? These slabs are not on the partial list, but on the cpu_slab of boot cpu. Reason for this is described in changelog. Because these slabs are not on partial list, we need to check kmem_cache_cpu's cpu slab. This patch implement it. Problem will be solved if we consider a cpu slab in bootstrap(). This patch implement it. At boot time only one processor is up so you do not need the loop over all processors. Okay! I will fix and submit v2, soon. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Wed, 16 Jan 2013, Joonsoo Kim wrote: These slabs are not on the partial list, but on the cpu_slab of boot cpu. Reason for this is described in changelog. Because these slabs are not on partial list, we need to check kmem_cache_cpu's cpu slab. This patch implement it. Ah. Ok. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Tue, 15 Jan 2013, Joonsoo Kim wrote: > These didn't make any error previously, because we normally don't free > objects which comes from kmem_cache's first slab and kmem_cache_node's. And these slabs are on the partial list because the objects are typically relatively small compared to page size. Do you have a system with a very large kmem_cache size? > Problem will be solved if we consider a cpu slab in bootstrap(). > This patch implement it. At boot time only one processor is up so you do not need the loop over all processors. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
On Tue, 15 Jan 2013, Joonsoo Kim wrote: These didn't make any error previously, because we normally don't free objects which comes from kmem_cache's first slab and kmem_cache_node's. And these slabs are on the partial list because the objects are typically relatively small compared to page size. Do you have a system with a very large kmem_cache size? Problem will be solved if we consider a cpu slab in bootstrap(). This patch implement it. At boot time only one processor is up so you do not need the loop over all processors. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
Current implementation of bootstrap() is not sufficient for kmem_cache and kmem_cache_node. First, for kmem_cache. bootstrap() call kmem_cache_zalloc() at first. When kmem_cache_zalloc() is called, kmem_cache's slab is moved to cpu slab for satisfying kmem_cache allocation request. In current implementation, we only consider n->partial slabs, so, we miss this cpu slab for kmem_cache. Second, for kmem_cache_node. When slab_state = PARTIAL, create_boot_cache() is called. And then, kmem_cache_node's slab is moved to cpu slab for satisfying kmem_cache_node allocation request. So, we also miss this slab. These didn't make any error previously, because we normally don't free objects which comes from kmem_cache's first slab and kmem_cache_node's. Problem will be solved if we consider a cpu slab in bootstrap(). This patch implement it. Signed-off-by: Joonsoo Kim diff --git a/mm/slub.c b/mm/slub.c index abef30e..830348b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3613,11 +3613,22 @@ static int slab_memory_callback(struct notifier_block *self, static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) { + int cpu; int node; struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); memcpy(s, static_cache, kmem_cache->object_size); + for_each_possible_cpu(cpu) { + struct kmem_cache_cpu *c; + struct page *p; + + c = per_cpu_ptr(s->cpu_slab, cpu); + p = c->page; + if (p) + p->slab_cache = s; + } + for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = get_node(s, node); struct page *p; -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH 2/3] slub: correct bootstrap() for kmem_cache, kmem_cache_node
Current implementation of bootstrap() is not sufficient for kmem_cache and kmem_cache_node. First, for kmem_cache. bootstrap() call kmem_cache_zalloc() at first. When kmem_cache_zalloc() is called, kmem_cache's slab is moved to cpu slab for satisfying kmem_cache allocation request. In current implementation, we only consider n-partial slabs, so, we miss this cpu slab for kmem_cache. Second, for kmem_cache_node. When slab_state = PARTIAL, create_boot_cache() is called. And then, kmem_cache_node's slab is moved to cpu slab for satisfying kmem_cache_node allocation request. So, we also miss this slab. These didn't make any error previously, because we normally don't free objects which comes from kmem_cache's first slab and kmem_cache_node's. Problem will be solved if we consider a cpu slab in bootstrap(). This patch implement it. Signed-off-by: Joonsoo Kim iamjoonsoo@lge.com diff --git a/mm/slub.c b/mm/slub.c index abef30e..830348b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3613,11 +3613,22 @@ static int slab_memory_callback(struct notifier_block *self, static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) { + int cpu; int node; struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); memcpy(s, static_cache, kmem_cache-object_size); + for_each_possible_cpu(cpu) { + struct kmem_cache_cpu *c; + struct page *p; + + c = per_cpu_ptr(s-cpu_slab, cpu); + p = c-page; + if (p) + p-slab_cache = s; + } + for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = get_node(s, node); struct page *p; -- 1.7.9.5 -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/