diff options
| author | Alexander Potapenko <[email protected]> | 2021-07-23 15:50:14 -0700 |
|---|---|---|
| committer | Linus Torvalds <[email protected]> | 2021-07-23 17:43:28 -0700 |
| commit | 236e9f1538523d3d380dda1cc99571d587058f37 (patch) | |
| tree | 73abd0f5a03436f381a8bd7ec43338efa7b872a9 | |
| parent | 235a85cb32bb123854ad31de46fdbf04c1d57cda (diff) | |
kfence: skip all GFP_ZONEMASK allocations
Allocation requests outside ZONE_NORMAL (MOVABLE, HIGHMEM or DMA) cannot
be fulfilled by KFENCE, because KFENCE memory pool is located in a zone
different from the requested one.
Because callers of kmem_cache_alloc() may actually rely on the
allocation to reside in the requested zone (e.g. memory allocations
done with __GFP_DMA must be DMAable), skip all allocations done with
GFP_ZONEMASK and/or respective SLAB flags (SLAB_CACHE_DMA and
SLAB_CACHE_DMA32).
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Alexander Potapenko <[email protected]>
Reviewed-by: Marco Elver <[email protected]>
Acked-by: Souptick Joarder <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Souptick Joarder <[email protected]>
Cc: <[email protected]> [5.12+]
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
| -rw-r--r-- | mm/kfence/core.c | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 2623ff401a10..575c685aa642 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -741,6 +741,15 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) return NULL; /* + * Skip allocations from non-default zones, including DMA. We cannot + * guarantee that pages in the KFENCE pool will have the requested + * properties (e.g. reside in DMAable memory). + */ + if ((flags & GFP_ZONEMASK) || + (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) + return NULL; + + /* * allocation_gate only needs to become non-zero, so it doesn't make * sense to continue writing to it and pay the associated contention * cost, in case we have a large number of concurrent allocations. |