Currently while allocating a slab for a offline node, we use its
associated node_numa_mem to search for a partial slab. If we don't find
a partial slab, we try allocating a slab from the offline node using
__alloc_pages_node. However this is bound to fail.
NIP [c00000000039a300] __alloc_pages_nodemask+0x130/0x3b0
LR [c00000000039a3c4] __alloc_pages_nodemask+0x1f4/0x3b0
Call Trace:
[c0000008b36837f0] [c00000000039a3b4] __alloc_pages_nodemask+0x1e4/0x3b0 (unreliable)
[c0000008b3683870] [c0000000003d1ff8] new_slab+0x128/0xcf0
[c0000008b3683950] [c0000000003d6060] ___slab_alloc+0x410/0x820
[c0000008b3683a40] [c0000000003d64a4] __slab_alloc+0x34/0x60
[c0000008b3683a70] [c0000000003d78b0] __kmalloc_node+0x110/0x490
[c0000008b3683af0] [c000000000343a08] kvmalloc_node+0x58/0x110
[c0000008b3683b30] [c0000000003ffd44] mem_cgroup_css_online+0x104/0x270
[c0000008b3683b90] [c000000000234e08] online_css+0x48/0xd0
[c0000008b3683bc0] [c00000000023dedc] cgroup_apply_control_enable+0x2ec/0x4d0
[c0000008b3683ca0] [c0000000002416f8] cgroup_mkdir+0x228/0x5f0
[c0000008b3683d10] [c000000000520360] kernfs_iop_mkdir+0x90/0xf0
[c0000008b3683d50] [c00000000043e400] vfs_mkdir+0x110/0x230
[c0000008b3683da0] [c000000000441ee0] do_mkdirat+0xb0/0x1a0
[c0000008b3683e20] [c00000000000b278] system_call+0x5c/0x68
Mitigate this by allocating the new slab from the node_numa_mem.
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Sachin Sant <sachinp@xxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Christopher Lameter <cl@xxxxxxxxx>
Cc: linuxppc-dev@xxxxxxxxxxxxxxxx
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
Cc: Bharata B Rao <bharata@xxxxxxxxxxxxx>
Reported-by: Sachin Sant <sachinp@xxxxxxxxxxxxxxxxxx>
Tested-by: Sachin Sant <sachinp@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
---
mm/slub.c | 19 ++++++++-----------
1 file changed, 8 insertions(+), 11 deletions(-)
diff --git a/mm/slub.c b/mm/slub.c
index 1c55bf7892bf..fdf7f38f96e6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1970,14 +1970,8 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
struct kmem_cache_cpu *c)
{
void *object;
- int searchnode = node;
- if (node == NUMA_NO_NODE)
- searchnode = numa_mem_id();
- else if (!node_present_pages(node))
- searchnode = node_to_mem_node(node);
-
- object = get_partial_node(s, get_node(s, searchnode), c, flags);
+ object = get_partial_node(s, get_node(s, node), c, flags);
if (object || node != NUMA_NO_NODE)
return object;
@@ -2470,6 +2464,11 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO));
+ if (node == NUMA_NO_NODE)
+ node = numa_mem_id();
+ else if (!node_present_pages(node))
+ node = node_to_mem_node(node);
+
freelist = get_partial(s, flags, node, c);
if (freelist)
@@ -2569,12 +2568,10 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
redo:
if (unlikely(!node_match(page, node))) {
- int searchnode = node;
-
if (node != NUMA_NO_NODE && !node_present_pages(node))
- searchnode = node_to_mem_node(node);
+ node = node_to_mem_node(node);
- if (unlikely(!node_match(page, searchnode))) {
+ if (unlikely(!node_match(page, node))) {
stat(s, ALLOC_NODE_MISMATCH);
deactivate_slab(s, page, c->freelist, c);
goto new_slab;
--
2.18.1
