From 2ad654bc5e2b211e92f66da1d819e47d79a866f0 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:41:02 +0800 Subject: cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags When we change cpuset.memory_spread_{page,slab}, cpuset will flip PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset. This should be done using atomic bitops, but currently we don't, which is broken. Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happened when one thread tried to clear PF_USED_MATH while at the same time another thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on the same task. Here's the full report: https://lkml.org/lkml/2014/9/19/230 To fix this, we make PF_SPREAD_PAGE and PF_SPREAD_SLAB atomic flags. v4: - updated mm/slab.c. (Fengguang Wu) - updated Documentation. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Cc: Kees Cook Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time") Cc: # 2.6.31+ Reported-by: Tetsuo Handa Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- mm/slab.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/slab.c') diff --git a/mm/slab.c b/mm/slab.c index a467b308c682..881951e67f12 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2994,7 +2994,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. + * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3226,7 +3226,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { + if (current->mempolicy || cpuset_do_slab_mem_spread()) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; -- cgit v1.2.2 From d4a5fca592b9ab52b90bb261a90af3c8f53be011 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 25 Sep 2014 16:05:20 -0700 Subject: mm, slab: initialize object alignment on cache creation Since commit 4590685546a3 ("mm/sl[aou]b: Common alignment code"), the "ralign" automatic variable in __kmem_cache_create() may be used as uninitialized. The proper alignment defaults to BYTES_PER_WORD and can be overridden by SLAB_RED_ZONE or the alignment specified by the caller. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=85031 Signed-off-by: David Rientjes Reported-by: Andrei Elovikov Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'mm/slab.c') diff --git a/mm/slab.c b/mm/slab.c index a467b308c682..b8b619bc84ad 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2124,7 +2124,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, freelist_size, ralign; + size_t left_over, freelist_size; + size_t ralign = BYTES_PER_WORD; gfp_t gfp; int err; size_t size = cachep->size; @@ -2157,14 +2158,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size &= ~(BYTES_PER_WORD - 1); } - /* - * Redzoning and user store require word alignment or possibly larger. - * Note this will be overridden by architecture or caller mandated - * alignment if either is greater than BYTES_PER_WORD. - */ - if (flags & SLAB_STORE_USER) - ralign = BYTES_PER_WORD; - if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably -- cgit v1.2.2