Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
	mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
	dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, viro@zeniv.linux.org.uk,
	akpm@linux-foundation.org, paulmck@kernel.org,
	mchehab+huawei@kernel.org, pawan.kumar.gupta@linux.intel.com,
	rdunlap@infradead.org, oneukum@suse.com,
	anshuman.khandual@arm.com, jroedel@suse.de,
	almasrymina@google.com, rientjes@google.com, willy@infradead.org
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linux-fsdevel@vger.kernel.org,
	Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v2 08/19] mm/hugetlb: Defer freeing of hugetlb pages
Date: Mon, 26 Oct 2020 22:51:03 +0800
Message-ID: <20201026145114.59424-9-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201026145114.59424-1-songmuchun@bytedance.com>

In the subsequent patch, we will allocate the vmemmap pages when free
huge pages. But update_and_free_page() is be called from a non-task
context(and hold hugetlb_lock), we can defer the actual freeing in
a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 85 insertions(+), 9 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aa012d603e06..a5500c79e2df 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1292,6 +1292,8 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
+static void __free_hugepage(struct hstate *h, struct page *page);
+
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 #include <linux/bootmem_info.h>
 
@@ -1601,6 +1603,64 @@ static void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	free_vmemmap_page_list(&free_pages);
 }
+
+/*
+ * As update_and_free_page() is be called from a non-task context(and hold
+ * hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
+ * use GFP_ATOMIC to allocate a lot of vmemmap pages.
+ *
+ * update_hpage_vmemmap_workfn() locklessly retrieves the linked list of
+ * pages to be freed and frees them one-by-one. As the page->mapping pointer
+ * is going to be cleared in update_hpage_vmemmap_workfn() anyway, it is
+ * reused as the llist_node structure of a lockless linked list of huge
+ * pages to be freed.
+ */
+static LLIST_HEAD(hpage_update_freelist);
+
+static void update_hpage_vmemmap_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_update_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		page->mapping = NULL;
+		__free_hugepage(page_hstate(page), page);
+
+		cond_resched();
+	}
+}
+static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
+
+static inline void __update_and_free_page(struct hstate *h, struct page *page)
+{
+	/* No need to allocate vmemmap pages */
+	if (!nr_free_vmemmap(h)) {
+		__free_hugepage(h, page);
+		return;
+	}
+
+	/*
+	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap
+	 * pages.
+	 *
+	 * Only call schedule_work() if hpage_update_freelist is previously
+	 * empty. Otherwise, schedule_work() had been called but the workfn
+	 * hasn't retrieved the list yet.
+	 */
+	if (llist_add((struct llist_node *)&page->mapping,
+		      &hpage_update_freelist))
+		schedule_work(&hpage_update_work);
+}
+
+static inline void free_gigantic_page_comm(struct hstate *h, struct page *page)
+{
+	free_gigantic_page(page, huge_page_order(h));
+}
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
@@ -1618,17 +1678,39 @@ static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
+
+static inline void __update_and_free_page(struct hstate *h, struct page *page)
+{
+	__free_hugepage(h, page);
+}
+
+static inline void free_gigantic_page_comm(struct hstate *h, struct page *page)
+{
+	/*
+	 * Temporarily drop the hugetlb_lock, because
+	 * we might block in free_gigantic_page().
+	 */
+	spin_unlock(&hugetlb_lock);
+	free_gigantic_page(page, huge_page_order(h));
+	spin_lock(&hugetlb_lock);
+}
 #endif
 
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
-	int i;
-
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
+
+	__update_and_free_page(h, page);
+}
+
+static void __free_hugepage(struct hstate *h, struct page *page)
+{
+	int i;
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
@@ -1640,14 +1722,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
-		/*
-		 * Temporarily drop the hugetlb_lock, because
-		 * we might block in free_gigantic_page().
-		 */
-		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
-		free_gigantic_page(page, huge_page_order(h));
-		spin_lock(&hugetlb_lock);
+		free_gigantic_page_comm(h, page);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
-- 
2.20.1


  parent reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-26 14:50 [PATCH v2 00/19] Free some vmemmap pages of hugetlb page Muchun Song
2020-10-26 14:50 ` [PATCH v2 01/19] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-10-26 14:50 ` [PATCH v2 02/19] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-10-26 14:50 ` [PATCH v2 03/19] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-10-29 10:29   ` Oscar Salvador
2020-10-29 13:34     ` [External] " Muchun Song
2020-10-26 14:50 ` [PATCH v2 04/19] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-10-27 22:03   ` Mike Kravetz
2020-10-29 13:26   ` Oscar Salvador
2020-10-29 13:41     ` [External] " Muchun Song
2020-10-26 14:51 ` [PATCH v2 05/19] mm/hugetlb: Introduce pgtable allocation/freeing helpers Muchun Song
2020-10-28  0:32   ` Mike Kravetz
2020-10-28  7:26     ` [External] " Muchun Song
2020-10-28 23:42       ` Mike Kravetz
2020-11-05 13:23   ` Oscar Salvador
2020-11-05 16:08     ` [External] " Muchun Song
2020-11-06  9:46       ` Oscar Salvador
2020-11-06 16:43         ` Muchun Song
2020-10-26 14:51 ` [PATCH v2 06/19] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-10-26 14:51 ` [PATCH v2 07/19] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-10-26 16:01   ` Matthew Wilcox
2020-10-27  2:58     ` [External] " Muchun Song
2020-10-28 23:42   ` Mike Kravetz
2020-10-29  6:13     ` [External] " Muchun Song
2020-10-29 21:59       ` Mike Kravetz
2020-10-30  2:58         ` Muchun Song
2020-10-26 14:51 ` Muchun Song [this message]
2020-10-26 14:51 ` [PATCH v2 09/19] mm/hugetlb: Allocate " Muchun Song
2020-10-26 14:51 ` [PATCH v2 10/19] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-10-26 14:51 ` [PATCH v2 11/19] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-10-26 14:51 ` [PATCH v2 12/19] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-10-26 14:51 ` [PATCH v2 13/19] mm/hugetlb: Add a BUILD_BUG_ON to check if struct page size is a power of two Muchun Song
2020-10-26 14:51 ` [PATCH v2 14/19] mm/hugetlb: Clear PageHWPoison on the non-error memory page Muchun Song
2020-10-26 14:51 ` [PATCH v2 15/19] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-10-26 14:51 ` [PATCH v2 16/19] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-10-26 14:51 ` [PATCH v2 17/19] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-10-26 14:51 ` [PATCH v2 18/19] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-10-26 14:51 ` [PATCH v2 19/19] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-10-26 15:53 ` [PATCH v2 00/19] Free some vmemmap pages of hugetlb page Matthew Wilcox
2020-10-27  2:54   ` [External] " Muchun Song
2020-10-30  9:14 ` Michal Hocko
2020-10-30 10:24   ` [External] " Muchun Song
2020-10-30 15:19     ` Michal Hocko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201026145114.59424-9-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=almasrymina@google.com \
    --cc=anshuman.khandual@arm.com \
    --cc=bp@alien8.de \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=duanxiongchun@bytedance.com \
    --cc=hpa@zytor.com \
    --cc=jroedel@suse.de \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mchehab+huawei@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mingo@redhat.com \
    --cc=oneukum@suse.com \
    --cc=paulmck@kernel.org \
    --cc=pawan.kumar.gupta@linux.intel.com \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=rientjes@google.com \
    --cc=tglx@linutronix.de \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git