On Thu, Sep 6, 2012 at 10:33 PM, Christoph Lameter <cl@xxxxxxxxx> wrote: > On Thu, 6 Sep 2012, Luck, Tony wrote: > >> r9 was computed as 32 + return value from a call to allocate_slab() >> >> So I think we are inside the inlined "inc_slabs_node()" call on line 1357 of mm/slub.c > > Ok that would mean its not related to object arrangement within the page > done by the allocator. How can a atomic_long value become misaligned? > Did the items in slab_err() got mixed (see below hunk from my revert-patch)? @@ -3133,7 +3139,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, sizeof(long), GFP_ATOMIC); if (!map) return; - slab_err(s, page, text, s->name); + slab_err(s, page, "%s", text); slab_lock(page); get_map(s, page, map); - Sedat - > > -- > To unsubscribe from this list: send the line "unsubscribe linux-next" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-next" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
