The patch titled
Subject: hugetlb: add hugetlb demote page support
has been added to the -mm tree. Its filename is
hugetlb-add-hugetlb-demote-page-support.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/hugetlb-add-hugetlb-demote-page-support.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/hugetlb-add-hugetlb-demote-page-support.patch
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 and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: add hugetlb demote page support
Demote page functionality will split a huge page into a number of huge
pages of a smaller size. For example, on x86 a 1GB huge page can be
demoted into 512 2M huge pages. Demotion is done 'in place' by simply
splitting the huge page.
Added '*_for_demote' wrappers for remove_hugetlb_page,
destroy_compound_gigantic_page and prep_compound_gigantic_page for use by
demote code.
Link: https://lkml.kernel.org/r/20210816224953.157796-5-mike.kravetz@xxxxxxxxxx
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 73 insertions(+), 3 deletions(-)
--- a/mm/hugetlb.c~hugetlb-add-hugetlb-demote-page-support
+++ a/mm/hugetlb.c
@@ -1279,6 +1279,12 @@ static void destroy_compound_gigantic_pa
__destroy_compound_gigantic_page(page, order, false);
}
+static void destroy_compound_gigantic_page_for_demote(struct page *page,
+ unsigned int order)
+{
+ __destroy_compound_gigantic_page(page, order, true);
+}
+
static void free_gigantic_page(struct page *page, unsigned int order)
{
#ifdef CONFIG_CMA
@@ -1418,6 +1424,12 @@ static void remove_hugetlb_page(struct h
__remove_hugetlb_page(h, page, adjust_surplus, false);
}
+static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page,
+ bool adjust_surplus)
+{
+ __remove_hugetlb_page(h, page, adjust_surplus, true);
+}
+
static void add_hugetlb_page(struct hstate *h, struct page *page,
bool adjust_surplus)
{
@@ -1767,6 +1779,12 @@ static bool prep_compound_gigantic_page(
return __prep_compound_gigantic_page(page, order, false);
}
+static bool prep_compound_gigantic_page_for_demote(struct page *page,
+ unsigned int order)
+{
+ return __prep_compound_gigantic_page(page, order, true);
+}
+
/*
* PageHuge() only returns true for hugetlbfs pages, but not for normal or
* transparent huge pages. See the PageTransHuge() documentation for more
@@ -3274,9 +3292,55 @@ out:
return 0;
}
+static int demote_free_huge_page(struct hstate *h, struct page *page)
+{
+ int i, nid = page_to_nid(page);
+ struct hstate *target_hstate;
+ bool cma_page = HPageCma(page);
+
+ target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
+
+ remove_hugetlb_page_for_demote(h, page, false);
+ spin_unlock_irq(&hugetlb_lock);
+
+ if (alloc_huge_page_vmemmap(h, page)) {
+ /* Allocation of vmemmmap failed, we can not demote page */
+ spin_lock_irq(&hugetlb_lock);
+ set_page_refcounted(page);
+ add_hugetlb_page(h, page, false);
+ return 1;
+ }
+
+ /*
+ * Use destroy_compound_gigantic_page_for_demote for all huge page
+ * sizes as it will not ref count pages.
+ */
+ destroy_compound_gigantic_page_for_demote(page, huge_page_order(h));
+
+ for (i = 0; i < pages_per_huge_page(h);
+ i += pages_per_huge_page(target_hstate)) {
+ if (hstate_is_gigantic(target_hstate))
+ prep_compound_gigantic_page_for_demote(page + i,
+ target_hstate->order);
+ else
+ prep_compound_page(page + i, target_hstate->order);
+ set_page_private(page + i, 0);
+ set_page_refcounted(page + i);
+ prep_new_huge_page(target_hstate, page + i, nid);
+ if (cma_page)
+ SetHPageCma(page + i);
+ put_page(page + i);
+ }
+
+ spin_lock_irq(&hugetlb_lock);
+ return 0;
+}
+
static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
__must_hold(&hugetlb_lock)
{
+ int nr_nodes, node;
+ struct page *page;
int rc = 0;
lockdep_assert_held(&hugetlb_lock);
@@ -3292,9 +3356,15 @@ static int demote_pool_huge_page(struct
return 1;
}
- /*
- * TODO - demote fucntionality will be added in subsequent patch
- */
+ for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+ if (!list_empty(&h->hugepage_freelists[node])) {
+ page = list_entry(h->hugepage_freelists[node].next,
+ struct page, lru);
+ rc = !demote_free_huge_page(h, page);
+ break;
+ }
+ }
+
return rc;
}
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-simplify-prep_compound_gigantic_page-ref-count-racing-code.patch
hugetlb-drop-ref-count-earlier-after-page-allocation.patch
hugetlb-before-freeing-hugetlb-page-set-dtor-to-appropriate-value.patch
hugetlb-add-demote-hugetlb-page-sysfs-interfaces.patch
hugetlb-add-hpagecma-flag-and-code-to-free-non-gigantic-pages-in-cma.patch
hugetlb-add-demote-bool-to-gigantic-page-routines.patch
hugetlb-add-hugetlb-demote-page-support.patch
hugetlb-document-the-demote-sysfs-interfaces.patch
hugetlb-vmemmap-optimizations-when-demoting-hugetlb-pages.patch
hugetlb-prepare-destroy-and-prep-routines-for-vmemmap-optimized-pages.patch
hugetlb-optimized-demote-vmemmap-optimizatized-pages.patch
