mm/hugetlb: perform vmemmap optimization batchly for specific node allocation

When HVO is enabled and huge page memory allocs are made, the freed memory
can be aggregated into higher order memory in the following paths, which
facilitates further allocs for higher order memory.

echo 200000 > /proc/sys/vm/nr_hugepages
echo 200000 > /sys/devices/system/node/node*/hugepages/hugepages-2048kB/nr_hugepages
grub default_hugepagesz=2M hugepagesz=2M hugepages=200000

Currently not support for releasing aggregations to higher order in the
following way, which will releasing to lower order.

grub: default_hugepagesz=2M hugepagesz=2M hugepages=0:100000,1:100000

This patch supports the release of huge page optimizations aggregates to
higher order memory.

eg:
cat /proc/cmdline
BOOT_IMAGE=/boot/vmlinuz-xxx ... default_hugepagesz=2M hugepagesz=2M hugepages=0:100000,1:100000

Before:
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
...
Node    0, zone   Normal, type    Unmovable  55282  97039  99307      0      1      1      0      1      1      1      0
Node    0, zone   Normal, type      Movable     25     11    345     87     48     21      2     20      9      3  75061
Node    0, zone   Normal, type  Reclaimable      4      2      2      4      3      0      2      1      1      1      0
Node    0, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0
...
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
Node    1, zone   Normal, type    Unmovable  98888  99650  99679      2      3      1      2      2      2      0      0
Node    1, zone   Normal, type      Movable      1      1      0      1      1      0      1      0      1      1  75937
Node    1, zone   Normal, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
Node    1, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0

After:
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
...
Node    0, zone   Normal, type    Unmovable    152    158     37      2      2      0      3      4      2      6    717
Node    0, zone   Normal, type      Movable      1     37     53      3     55     49     16      6      2      1  75000
Node    0, zone   Normal, type  Reclaimable      1      4      3      1      2      1      1      1      1      1      0
Node    0, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0
...
Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
Node    1, zone   Normal, type    Unmovable      5      3      2      1      3      4      2      2      2      0    779
Node    1, zone   Normal, type      Movable      1      0      1      1      1      0      1      0      1      1  75849
Node    1, zone   Normal, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
Node    1, zone   Normal, type   HighAtomic      0      0      0      0      0      0      0      0      0      0      0

Link: https://lkml.kernel.org/r/20241012070802.1876-1-suhua1@kingsoft.com
Signed-off-by: suhua <suhua1@kingsoft.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 190fa05635f4a9d4af14bfa6bda116298f2dce71..906294ac85dc85ca8535cce4b57a53d274d169b7 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3301,6 +3301,7 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 {
        unsigned long i;
        char buf[32];
+       LIST_HEAD(folio_list);
 
        for (i = 0; i < h->max_huge_pages_node[nid]; ++i) {
                if (hstate_is_gigantic(h)) {
@@ -3310,14 +3311,18 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
                        struct folio *folio;
                        gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 
-                       folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid,
-                                       &node_states[N_MEMORY]);
+                       folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid,
+                                       &node_states[N_MEMORY], NULL);
                        if (!folio)
                                break;
-                       free_huge_folio(folio); /* free it into the hugepage allocator */
+                       list_add(&folio->lru, &folio_list);
                }
                cond_resched();
        }
+
+       if (!list_empty(&folio_list))
+               prep_and_add_allocated_folios(h, &folio_list);
+
        if (i == h->max_huge_pages_node[nid])
                return;