The patch titled
Subject: hugetlb: perform vmemmap restoration on a list of pages
has been added to the -mm mm-unstable branch. Its filename is
hugetlb-perform-vmemmap-restoration-on-a-list-of-pages.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-perform-vmemmap-restoration-on-a-list-of-pages.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: perform vmemmap restoration on a list of pages
Date: Fri, 15 Sep 2023 15:15:41 -0700
The routine update_and_free_pages_bulk already performs vmemmap
restoration on the list of hugetlb pages in a separate step. In
preparation for more functionality to be added in this step, create a new
routine hugetlb_vmemmap_restore_folios() that will restore vmemmap for a
list of folios.
This new routine must provide sufficient feedback about errors and actual
restoration performed so that update_and_free_pages_bulk can perform
optimally.
Link: https://lkml.kernel.org/r/20230915221548.552084-9-mike.kravetz@xxxxxxxxxx
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: James Houghton <jthoughton@xxxxxxxxxx>
Cc: Joao Martins <joao.m.martins@xxxxxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Sidhartha Kumar <sidhartha.kumar@xxxxxxxxxx>
Cc: Xiongchun Duan <duanxiongchun@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 36 ++++++++++++++++++------------------
mm/hugetlb_vmemmap.c | 37 +++++++++++++++++++++++++++++++++++++
mm/hugetlb_vmemmap.h | 11 +++++++++++
3 files changed, 66 insertions(+), 18 deletions(-)
--- a/mm/hugetlb.c~hugetlb-perform-vmemmap-restoration-on-a-list-of-pages
+++ a/mm/hugetlb.c
@@ -1829,36 +1829,36 @@ static void update_and_free_hugetlb_foli
static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
{
+ int ret;
+ unsigned long restored;
struct folio *folio, *t_folio;
- bool clear_dtor = false;
/*
- * First allocate required vmemmmap (if necessary) for all folios on
- * list. If vmemmap can not be allocated, we can not free folio to
- * lower level allocator, so add back as hugetlb surplus page.
- * add_hugetlb_folio() removes the page from THIS list.
- * Use clear_dtor to note if vmemmap was successfully allocated for
- * ANY page on the list.
+ * First allocate required vmemmmap (if necessary) for all folios.
*/
- list_for_each_entry_safe(folio, t_folio, list, lru) {
- if (folio_test_hugetlb_vmemmap_optimized(folio)) {
- if (hugetlb_vmemmap_restore(h, &folio->page)) {
- spin_lock_irq(&hugetlb_lock);
+ ret = hugetlb_vmemmap_restore_folios(h, list, &restored);
+
+ /*
+ * If there was an error restoring vmemmap for ANY folios on the list,
+ * add them back as surplus hugetlb pages. add_hugetlb_folio() removes
+ * the folio from THIS list.
+ */
+ if (ret < 0) {
+ spin_lock_irq(&hugetlb_lock);
+ list_for_each_entry_safe(folio, t_folio, list, lru)
+ if (folio_test_hugetlb_vmemmap_optimized(folio))
add_hugetlb_folio(h, folio, true);
- spin_unlock_irq(&hugetlb_lock);
- } else
- clear_dtor = true;
- }
+ spin_unlock_irq(&hugetlb_lock);
}
/*
- * If vmemmmap allocation was performed on any folio above, take lock
- * to clear destructor of all folios on list. This avoids the need to
+ * If vmemmmap allocation was performed on ANY folio , take lock to
+ * clear destructor of all folios on list. This avoids the need to
* lock/unlock for each individual folio.
* The assumption is vmemmap allocation was performed on all or none
* of the folios on the list. This is true expect in VERY rare cases.
*/
- if (clear_dtor) {
+ if (restored) {
spin_lock_irq(&hugetlb_lock);
list_for_each_entry(folio, list, lru)
__clear_hugetlb_destructor(h, folio);
--- a/mm/hugetlb_vmemmap.c~hugetlb-perform-vmemmap-restoration-on-a-list-of-pages
+++ a/mm/hugetlb_vmemmap.c
@@ -480,6 +480,43 @@ int hugetlb_vmemmap_restore(const struct
return ret;
}
+/**
+ * hugetlb_vmemmap_restore_folios - restore vmemmap for every folio on the list.
+ * @h: struct hstate.
+ * @folio_list: list of folios.
+ * @restored: Set to number of folios for which vmemmap was restored
+ * successfully if caller passes a non-NULL pointer.
+ *
+ * Return: %0 if vmemmap exists for all folios on the list. If an error is
+ * encountered restoring vmemmap for ANY folio, an error code
+ * will be returned to the caller. It is then the responsibility
+ * of the caller to check the hugetlb vmemmap optimized flag of
+ * each folio to determine if vmemmap was actually restored.
+ */
+int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+ struct list_head *folio_list,
+ unsigned long *restored)
+{
+ unsigned long num_restored;
+ struct folio *folio;
+ int ret = 0, t_ret;
+
+ num_restored = 0;
+ list_for_each_entry(folio, folio_list, lru) {
+ if (folio_test_hugetlb_vmemmap_optimized(folio)) {
+ t_ret = hugetlb_vmemmap_restore(h, &folio->page);
+ if (t_ret)
+ ret = t_ret;
+ else
+ num_restored++;
+ }
+ }
+
+ if (*restored)
+ *restored = num_restored;
+ return ret;
+}
+
/* Return true iff a HugeTLB whose vmemmap should and can be optimized. */
static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head)
{
--- a/mm/hugetlb_vmemmap.h~hugetlb-perform-vmemmap-restoration-on-a-list-of-pages
+++ a/mm/hugetlb_vmemmap.h
@@ -19,6 +19,8 @@
#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head);
+int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+ struct list_head *folio_list, unsigned long *restored);
void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head);
void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list);
@@ -45,6 +47,15 @@ static inline int hugetlb_vmemmap_restor
return 0;
}
+static inline int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+ struct list_head *folio_list,
+ unsigned long *restored)
+{
+ if (restored)
+ *restored = 0;
+ return 0;
+}
+
static inline void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
{
}
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-set-hugetlb-page-flag-before-optimizing-vmemmap.patch
hugetlb-optimize-update_and_free_pages_bulk-to-avoid-lock-cycles.patch
hugetlb-restructure-pool-allocations.patch
hugetlb-perform-vmemmap-optimization-on-a-list-of-pages.patch
hugetlb-perform-vmemmap-restoration-on-a-list-of-pages.patch
hugetlb-batch-freeing-of-vmemmap-pages.patch
hugetlb-batch-tlb-flushes-when-restoring-vmemmap.patch
