| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20231019023113.345257-6-mike.kravetz@oracle.com>
Date: Wed, 18 Oct 2023 19:31:07 -0700
From: Mike Kravetz <mike.kravetz@...cle.com>
To: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: Muchun Song <songmuchun@...edance.com>,
Joao Martins <joao.m.martins@...cle.com>,
Konrad Dybcio <konradybcio@...nel.org>,
Oscar Salvador <osalvador@...e.de>,
David Hildenbrand <david@...hat.com>,
Miaohe Lin <linmiaohe@...wei.com>,
David Rientjes <rientjes@...gle.com>,
Anshuman Khandual <anshuman.khandual@....com>,
Naoya Horiguchi <naoya.horiguchi@...ux.dev>,
Barry Song <21cnbao@...il.com>, Michal Hocko <mhocko@...e.com>,
Matthew Wilcox <willy@...radead.org>,
Xiongchun Duan <duanxiongchun@...edance.com>,
Sergey Senozhatsky <senozhatsky@...omium.org>,
Usama Arif <usama.arif@...edance.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH v8 5/8] hugetlb: batch freeing of vmemmap pages
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.
Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
Reviewed-by: Muchun Song <songmuchun@...edance.com>
---
mm/hugetlb_vmemmap.c | 82 ++++++++++++++++++++++++++++++--------------
1 file changed, 56 insertions(+), 26 deletions(-)
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 77f44b81ff01..4ac521e596db 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -251,7 +251,7 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
}
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 +306,20 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
* @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 +336,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
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 +367,13 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
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 +389,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
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;
@@ -577,24 +577,17 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h
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);
@@ -604,21 +597,58 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
/*
* 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) {
+ int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
+ &vmemmap_pages);
+
+ /*
+ * Pages to be freed may have been accumulated. If we
+ * encounter an ENOMEM, free what we have and try again.
+ */
+ if (ret == -ENOMEM && !list_empty(&vmemmap_pages)) {
+ free_vmemmap_page_list(&vmemmap_pages);
+ INIT_LIST_HEAD(&vmemmap_pages);
+ __hugetlb_vmemmap_optimize(h, &folio->page, &vmemmap_pages);
+ }
+ }
- list_for_each_entry(folio, folio_list, lru)
- hugetlb_vmemmap_optimize(h, &folio->page);
+ free_vmemmap_page_list(&vmemmap_pages);
}
static struct ctl_table hugetlb_vmemmap_sysctls[] = {
--
2.41.0
Powered by blists - more mailing lists