From: Chen Jun <chenjun102@huawei.com> mainline inclusion from mainline-v6.10-rc1 commit 9198ffbd2b494daae3a67cac1d59c3a2754e64cd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBH72Q 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> Conflicts: mm/slub.c [The conflict is large. Because OLK-5.10 does not merge mainline patch 53a0de06e50acb372c75d87fcc72ddfdf4a060ee ("mm, slub: dissolve new_slab_objects() into ___slab_alloc()")] Signed-off-by: Kaixiong Yu <yukaixiong@huawei.com> --- mm/slub.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 9dd4cc478ec3..d4e7e88df7ff 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2105,7 +2105,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, searchnode = numa_mem_id(); object = get_partial_node(s, get_node(s, searchnode), c, flags); - if (object || node != NUMA_NO_NODE) + if (object || (node != NUMA_NO_NODE && (flags & __GFP_THISNODE))) return object; return get_any_partial(s, flags, c); @@ -2687,6 +2687,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, { void *freelist; struct page *page; + bool try_thisnode = true; + gfp_t pc_gfpflags; stat(s, ALLOC_SLOWPATH); @@ -2764,9 +2766,33 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto redo; } - freelist = new_slab_objects(s, gfpflags, node, &c); +new_objects: + + pc_gfpflags = 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_gfpflags for new_slab_objects() + * 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 + * new_slab_objects() 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_gfpflags = GFP_NOWAIT | __GFP_THISNODE; + + freelist = new_slab_objects(s, pc_gfpflags, node, &c); if (unlikely(!freelist)) { + 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; } -- 2.34.1