The patch titled
Subject: hugetlb: batch freeing of vmemmap pages
has been added to the -mm mm-unstable branch. Its filename is
hugetlb-batch-freeing-of-vmemmap-pages.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-batch-freeing-of-vmemmap-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: batch freeing of vmemmap pages
Date: Fri, 15 Sep 2023 15:15:42 -0700
Now that batching of hugetlb vmemmap optimization processing is possible,
batch the freeing of vmemmap pages. When freeing vmemmap pages for a
hugetlb page, we add them to a list that is freed after the entire batch
has been processed.
This enhances the ability to return contiguous ranges of memory to the low
level allocators.
Link: https://lkml.kernel.org/r/20230915221548.552084-10-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_vmemmap.c | 85 ++++++++++++++++++++++++++++-------------
1 file changed, 59 insertions(+), 26 deletions(-)
--- a/mm/hugetlb_vmemmap.c~hugetlb-batch-freeing-of-vmemmap-pages
+++ a/mm/hugetlb_vmemmap.c
@@ -222,6 +222,9 @@ static void free_vmemmap_page_list(struc
{
struct page *page, *next;
+ if (list_empty(list))
+ return;
+
list_for_each_entry_safe(page, next, list, lru)
free_vmemmap_page(page);
}
@@ -251,7 +254,7 @@ static void vmemmap_remap_pte(pte_t *pte
}
entry = mk_pte(walk->reuse_page, pgprot);
- list_add_tail(&page->lru, walk->vmemmap_pages);
+ list_add(&page->lru, walk->vmemmap_pages);
set_pte_at(&init_mm, addr, pte, entry);
}
@@ -306,18 +309,20 @@ static void vmemmap_restore_pte(pte_t *p
* @end: end address of the vmemmap virtual address range that we want to
* remap.
* @reuse: reuse address.
+ * @vmemmap_pages: list to deposit vmemmap pages to be freed. It is callers
+ * responsibility to free pages.
*
* Return: %0 on success, negative error code otherwise.
*/
static int vmemmap_remap_free(unsigned long start, unsigned long end,
- unsigned long reuse)
+ unsigned long reuse,
+ struct list_head *vmemmap_pages)
{
int ret;
- LIST_HEAD(vmemmap_pages);
struct vmemmap_remap_walk walk = {
.remap_pte = vmemmap_remap_pte,
.reuse_addr = reuse,
- .vmemmap_pages = &vmemmap_pages,
+ .vmemmap_pages = vmemmap_pages,
};
int nid = page_to_nid((struct page *)reuse);
gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
@@ -334,7 +339,7 @@ static int vmemmap_remap_free(unsigned l
if (walk.reuse_page) {
copy_page(page_to_virt(walk.reuse_page),
(void *)walk.reuse_addr);
- list_add(&walk.reuse_page->lru, &vmemmap_pages);
+ list_add(&walk.reuse_page->lru, vmemmap_pages);
}
/*
@@ -365,15 +370,13 @@ static int vmemmap_remap_free(unsigned l
walk = (struct vmemmap_remap_walk) {
.remap_pte = vmemmap_restore_pte,
.reuse_addr = reuse,
- .vmemmap_pages = &vmemmap_pages,
+ .vmemmap_pages = vmemmap_pages,
};
vmemmap_remap_range(reuse, end, &walk);
}
mmap_read_unlock(&init_mm);
- free_vmemmap_page_list(&vmemmap_pages);
-
return ret;
}
@@ -389,7 +392,7 @@ static int alloc_vmemmap_page_list(unsig
page = alloc_pages_node(nid, gfp_mask, 0);
if (!page)
goto out;
- list_add_tail(&page->lru, list);
+ list_add(&page->lru, list);
}
return 0;
@@ -576,24 +579,17 @@ static bool vmemmap_should_optimize(cons
return true;
}
-/**
- * hugetlb_vmemmap_optimize - optimize @head page's vmemmap pages.
- * @h: struct hstate.
- * @head: the head page whose vmemmap pages will be optimized.
- *
- * This function only tries to optimize @head's vmemmap pages and does not
- * guarantee that the optimization will succeed after it returns. The caller
- * can use HPageVmemmapOptimized(@head) to detect if @head's vmemmap pages
- * have been optimized.
- */
-void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
+static int __hugetlb_vmemmap_optimize(const struct hstate *h,
+ struct page *head,
+ struct list_head *vmemmap_pages)
{
+ int ret = 0;
unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
unsigned long vmemmap_reuse;
VM_WARN_ON_ONCE(!PageHuge(head));
if (!vmemmap_should_optimize(h, head))
- return;
+ return ret;
static_branch_inc(&hugetlb_optimize_vmemmap_key);
@@ -603,21 +599,58 @@ void hugetlb_vmemmap_optimize(const stru
/*
* Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end)
- * to the page which @vmemmap_reuse is mapped to, then free the pages
- * which the range [@vmemmap_start, @vmemmap_end] is mapped to.
+ * to the page which @vmemmap_reuse is mapped to. Add pages previously
+ * mapping the range to vmemmap_pages list so that they can be freed by
+ * the caller.
*/
- if (vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse))
+ ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, vmemmap_pages);
+ if (ret)
static_branch_dec(&hugetlb_optimize_vmemmap_key);
else
SetHPageVmemmapOptimized(head);
+
+ return ret;
+}
+
+/**
+ * hugetlb_vmemmap_optimize - optimize @head page's vmemmap pages.
+ * @h: struct hstate.
+ * @head: the head page whose vmemmap pages will be optimized.
+ *
+ * This function only tries to optimize @head's vmemmap pages and does not
+ * guarantee that the optimization will succeed after it returns. The caller
+ * can use HPageVmemmapOptimized(@head) to detect if @head's vmemmap pages
+ * have been optimized.
+ */
+void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
+{
+ LIST_HEAD(vmemmap_pages);
+
+ __hugetlb_vmemmap_optimize(h, head, &vmemmap_pages);
+ free_vmemmap_page_list(&vmemmap_pages);
}
void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
{
struct folio *folio;
+ LIST_HEAD(vmemmap_pages);
- list_for_each_entry(folio, folio_list, lru)
- hugetlb_vmemmap_optimize(h, &folio->page);
+ list_for_each_entry(folio, folio_list, lru) {
+ int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
+ &vmemmap_pages);
+
+ /*
+ * Pages may have been accumulated, thus free what we have
+ * and try again.
+ */
+ if (ret == -ENOMEM) {
+ free_vmemmap_page_list(&vmemmap_pages);
+ INIT_LIST_HEAD(&vmemmap_pages);
+ __hugetlb_vmemmap_optimize(h, &folio->page, &vmemmap_pages);
+ }
+ }
+
+ free_vmemmap_page_list(&vmemmap_pages);
}
static struct ctl_table hugetlb_vmemmap_sysctls[] = {
_
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
