From: yangge <yangge1116@xxxxxxx>
My machine has 4 NUMA nodes, each equipped with 32GB of memory. I
have configured each NUMA node with 16GB of CMA and 16GB of in-use
hugetlb pages. The allocation of contiguous memory via the
cma_alloc() function can fail probabilistically.
The cma_alloc() function may fail if it sees an in-use hugetlb page
within the allocation range, even if that page has already been
migrated. When in-use hugetlb pages are migrated, they may simply
be released back into the free hugepage pool instead of being
returned to the buddy system. This can cause the
test_pages_isolated() function check to fail, ultimately leading
to the failure of the cma_alloc() function:
cma_alloc()
__alloc_contig_migrate_range() // migrate in-use hugepage
test_pages_isolated()
__test_page_isolated_in_pageblock()
PageBuddy(page) // check if the page is in buddy
To address this issue, we will add a function named
replace_free_hugepage_folios(). This function will replace the
hugepage in the free hugepage pool with a new one and release the
old one to the buddy system. After the migration of in-use hugetlb
pages is completed, we will invoke the replace_free_hugepage_folios()
function to ensure that these hugepages are properly released to
the buddy system. Following this step, when the test_pages_isolated()
function is executed for inspection, it will successfully pass.
Signed-off-by: yangge <yangge1116@xxxxxxx>
---
include/linux/hugetlb.h | 6 ++++++
mm/hugetlb.c | 37 +++++++++++++++++++++++++++++++++++++
mm/page_alloc.c | 13 ++++++++++++-
3 files changed, 55 insertions(+), 1 deletion(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ae4fe86..7d36ac8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -681,6 +681,7 @@ struct huge_bootmem_page {
};
int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve);
struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
@@ -1059,6 +1060,11 @@ static inline int isolate_or_dissolve_huge_page(struct page *page,
return -ENOMEM;
}
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
+{
+ return 0;
+}
+
static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr,
int avoid_reserve)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8e1db80..a099c54 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2975,6 +2975,43 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
return ret;
}
+/*
+ * replace_free_hugepage_folios - Replace free hugepage folios in a given pfn
+ * range with new folios.
+ * @stat_pfn: start pfn of the given pfn range
+ * @end_pfn: end pfn of the given pfn range
+ * Returns 0 on success, otherwise negated error.
+ */
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
+{
+ struct hstate *h;
+ struct folio *folio;
+ int ret = 0;
+
+ LIST_HEAD(isolate_list);
+
+ while (start_pfn < end_pfn) {
+ folio = pfn_folio(start_pfn);
+ if (folio_test_hugetlb(folio)) {
+ h = folio_hstate(folio);
+ } else {
+ start_pfn++;
+ continue;
+ }
+
+ if (!folio_ref_count(folio)) {
+ ret = alloc_and_dissolve_hugetlb_folio(h, folio, &isolate_list);
+ if (ret)
+ break;
+
+ putback_movable_pages(&isolate_list);
+ }
+ start_pfn++;
+ }
+
+ return ret;
+}
+
struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve)
{
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dde19db..1dcea28 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6504,7 +6504,18 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
ret = __alloc_contig_migrate_range(&cc, start, end, migratetype);
if (ret && ret != -EBUSY)
goto done;
- ret = 0;
+
+ /*
+ * When in-use hugetlb pages are migrated, they may simply be
+ * released back into the free hugepage pool instead of being
+ * returned to the buddy system. After the migration of in-use
+ * huge pages is completed, we will invoke the
+ * replace_free_hugepage_folios() function to ensure that
+ * these hugepages are properly released to the buddy system.
+ */
+ ret = replace_free_hugepage_folios(start, end);
+ if (ret)
+ goto done;
/*
* Pages from [start, end) are within a pageblock_nr_pages
--
2.7.4
