From: Chen Jun <chenjun102@huawei.com> mainline inclusion from mainline-v6.10-rc1 commit 9198ffbd2b494daae3a67cac1d59c3a2754e64cd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAATAS Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- When kmalloc_node() is called without __GFP_THISNODE and the target node lacks sufficient memory, SLUB allocates a folio from a different node other than the requested node, instead of taking a partial slab from it. However, since the allocated folio does not belong to the requested node, on the following allocation it is deactivated and added to the partial slab list of the node it belongs to. This behavior can result in excessive memory usage when the requested node has insufficient memory, as SLUB will repeatedly allocate folios from other nodes without reusing the previously allocated ones. To prevent memory wastage, when a preferred node is indicated (not NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint: 1) try to get a partial slab from target node only by having __GFP_THISNODE in pc.flags for get_partial() 2) if 1) failed, try to allocate a new slab from target node with GFP_NOWAIT | __GFP_THISNODE opportunistically. 3) if 2) failed, retry with original gfpflags which will allow get_partial() try partial lists of other nodes before potentially allocating new page from other nodes Without a preferred node, or with __GFP_THISNODE constraint, the behavior remains unchanged. On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times. cat /proc/slabinfo shows: kmalloc-256 4200530 13519712 256 32 2 : tunables.. after this patch, cat /proc/slabinfo shows: kmalloc-256 4200558 4200768 256 32 2 : tunables.. Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Liu Shixin <liushixin2@huawei.com> --- mm/slub.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index ee3e32cdb7fd..7fcd18261c1e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2392,7 +2392,7 @@ static struct slab *get_partial(struct kmem_cache *s, int node, searchnode = numa_mem_id(); slab = get_partial_node(s, get_node(s, searchnode), pc); - if (slab || node != NUMA_NO_NODE) + if (slab || (node != NUMA_NO_NODE && (pc->flags & __GFP_THISNODE))) return slab; return get_any_partial(s, pc); @@ -3068,6 +3068,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, struct slab *slab; unsigned long flags; struct partial_context pc; + bool try_thisnode = true; stat(s, ALLOC_SLOWPATH); @@ -3194,6 +3195,21 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, new_objects: pc.flags = gfpflags; + /* + * When a preferred node is indicated but no __GFP_THISNODE + * + * 1) try to get a partial slab from target node only by having + * __GFP_THISNODE in pc.flags for get_partial() + * 2) if 1) failed, try to allocate a new slab from target node with + * GPF_NOWAIT | __GFP_THISNODE opportunistically + * 3) if 2) failed, retry with original gfpflags which will allow + * get_partial() try partial lists of other nodes before potentially + * allocating new page from other nodes + */ + if (unlikely(node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) + && try_thisnode)) + pc.flags = GFP_NOWAIT | __GFP_THISNODE; + pc.orig_size = orig_size; slab = get_partial(s, node, &pc); if (slab) { @@ -3215,10 +3231,15 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, } slub_put_cpu_ptr(s->cpu_slab); - slab = new_slab(s, gfpflags, node); + slab = new_slab(s, pc.flags, node); c = slub_get_cpu_ptr(s->cpu_slab); if (unlikely(!slab)) { + if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) + && try_thisnode) { + try_thisnode = false; + goto new_objects; + } slab_out_of_memory(s, gfpflags, node); return NULL; } -- 2.25.1