From: Marco Elver <elver@xxxxxxxxxx> commit e64f81946adf68cd75e2207dd9a51668348a4af8 upstream. On NUMA systems, __GFP_THISNODE indicates that an allocation _must_ be on a particular node, and failure to allocate on the desired node will result in a failed allocation. Skip __GFP_THISNODE allocations if we are running on a NUMA system, since KFENCE can't guarantee which node its pool pages are allocated on. Link: https://lkml.kernel.org/r/20250124120145.410066-1-elver@xxxxxxxxxx Fixes: 236e9f153852 ("kfence: skip all GFP_ZONEMASK allocations") Signed-off-by: Marco Elver <elver@xxxxxxxxxx> Reported-by: Vlastimil Babka <vbabka@xxxxxxx> Acked-by: Vlastimil Babka <vbabka@xxxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxx> Cc: Alexander Potapenko <glider@xxxxxxxxxx> Cc: Chistoph Lameter <cl@xxxxxxxxx> Cc: Dmitriy Vyukov <dvyukov@xxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- mm/kfence/core.c | 2 ++ 1 file changed, 2 insertions(+) --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -21,6 +21,7 @@ #include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> +#include <linux/nodemask.h> #include <linux/notifier.h> #include <linux/panic_notifier.h> #include <linux/random.h> @@ -997,6 +998,7 @@ void *__kfence_alloc(struct kmem_cache * * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || + ((flags & __GFP_THISNODE) && num_online_nodes() > 1) || (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; Patches currently in stable-queue which might be from elver@xxxxxxxxxx are queue-6.1/kfence-skip-__gfp_thisnode-allocations-on-numa-systems.patch
