aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorChristoph Lameter <clameter@sgi.com>2007-05-31 03:40:51 -0400
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-05-31 10:58:14 -0400
commit8ffa68755a0eddf3baeecd0e7612a5106cf2db23 (patch)
tree8c0fa3d0adda180687e7e35d49f978eae3284ddd
parentfbe9c9612930e0604dc99ef2da7e063fa3278817 (diff)
SLUB: Fix NUMA / SYSFS bootstrap issue
We need this patch in ASAP. Patch fixes the mysterious hang that remained on some particular configurations with lockdep on after the first fix that moved the #idef CONFIG_SLUB_DEBUG to the right location. See http://marc.info/?t=117963072300001&r=1&w=2 The kmem_cache_node cache is very special because it is needed for NUMA bootstrap. Under certain conditions (like for example if lockdep is enabled and significantly increases the size of spinlock_t) the structure may become exactly the size as one of the larger caches in the kmalloc array. That early during bootstrap we cannot perform merging properly. The unique id for the kmem_cache_node cache will match one of the kmalloc array. Sysfs will complain about a duplicate directory entry. All of this occurs while the console is not yet fully operational. Thus boot may appear to be silently failing. The kmem_cache_node cache is very special. During early boostrap the main allocation function is not operational yet and so we have to run our own small special alloc function during early boot. It is also special in that it is never freed. We really do not want any merging on that cache. Set the refcount -1 and forbid merging of slabs that have a negative refcount. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/slub.c7
1 files changed, 7 insertions, 0 deletions
diff --git a/mm/slub.c b/mm/slub.c
index 3e5aefcb4075..238c5a6ee896 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2435,6 +2435,7 @@ void __init kmem_cache_init(void)
2435 */ 2435 */
2436 create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node", 2436 create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
2437 sizeof(struct kmem_cache_node), GFP_KERNEL); 2437 sizeof(struct kmem_cache_node), GFP_KERNEL);
2438 kmalloc_caches[0].refcount = -1;
2438#endif 2439#endif
2439 2440
2440 /* Able to allocate the per node structures */ 2441 /* Able to allocate the per node structures */
@@ -2482,6 +2483,12 @@ static int slab_unmergeable(struct kmem_cache *s)
2482 if (s->ctor) 2483 if (s->ctor)
2483 return 1; 2484 return 1;
2484 2485
2486 /*
2487 * We may have set a slab to be unmergeable during bootstrap.
2488 */
2489 if (s->refcount < 0)
2490 return 1;
2491
2485 return 0; 2492 return 0;
2486} 2493}
2487 2494