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,
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,
osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com,
david@redhat.com, naoya.horiguchi@nec.com,
joao.m.martins@oracle.com
Cc: duanxiongchun@bytedance.com, fam.zheng@bytedance.com,
zhengqi.arch@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 v23 5/9] mm: hugetlb: defer freeing of HugeTLB pages
Date: Mon, 10 May 2021 11:00:23 +0800 [thread overview]
Message-ID: <20210510030027.56044-6-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210510030027.56044-1-songmuchun@bytedance.com>
In the subsequent patch, we should allocate the vmemmap pages when
freeing a HugeTLB page. But update_and_free_page() can be called
under any context, so we cannot use GFP_KERNEL to allocate vmemmap
pages. However, we can defer the actual freeing in a kworker to
prevent from using GFP_ATOMIC to allocate the vmemmap pages.
The __update_and_free_page() is where the call to allocate vmemmmap
pages will be inserted.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
---
mm/hugetlb.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++-----
mm/hugetlb_vmemmap.c | 12 --------
mm/hugetlb_vmemmap.h | 17 +++++++++++
3 files changed, 93 insertions(+), 19 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fd39fc94b23f..a3629c664f6a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1376,7 +1376,7 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page,
h->nr_huge_pages_node[nid]--;
}
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void __update_and_free_page(struct hstate *h, struct page *page)
{
int i;
struct page *subpage = page;
@@ -1399,12 +1399,79 @@ static void update_and_free_page(struct hstate *h, struct page *page)
}
}
+/*
+ * As update_and_free_page() can be called under any context, so we cannot
+ * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the
+ * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate
+ * the vmemmap pages.
+ *
+ * free_hpage_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 free_hpage_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_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+ struct llist_node *node;
+
+ node = llist_del_all(&hpage_freelist);
+
+ while (node) {
+ struct page *page;
+ struct hstate *h;
+
+ page = container_of((struct address_space **)node,
+ struct page, mapping);
+ node = node->next;
+ page->mapping = NULL;
+ /*
+ * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate()
+ * is going to trigger because a previous call to
+ * remove_hugetlb_page() will set_compound_page_dtor(page,
+ * NULL_COMPOUND_DTOR), so do not use page_hstate() directly.
+ */
+ h = size_to_hstate(page_size(page));
+
+ __update_and_free_page(h, page);
+
+ cond_resched();
+ }
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+static inline void flush_free_hpage_work(struct hstate *h)
+{
+ if (free_vmemmap_pages_per_hpage(h))
+ flush_work(&free_hpage_work);
+}
+
+static void update_and_free_page(struct hstate *h, struct page *page,
+ bool atomic)
+{
+ if (!free_vmemmap_pages_per_hpage(h) || !atomic) {
+ __update_and_free_page(h, page);
+ return;
+ }
+
+ /*
+ * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages.
+ *
+ * Only call schedule_work() if hpage_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_freelist))
+ schedule_work(&free_hpage_work);
+}
+
static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
{
struct page *page, *t_page;
list_for_each_entry_safe(page, t_page, list, lru) {
- update_and_free_page(h, page);
+ update_and_free_page(h, page, false);
cond_resched();
}
}
@@ -1471,12 +1538,12 @@ void free_huge_page(struct page *page)
if (HPageTemporary(page)) {
remove_hugetlb_page(h, page, false);
spin_unlock_irqrestore(&hugetlb_lock, flags);
- update_and_free_page(h, page);
+ update_and_free_page(h, page, true);
} else if (h->surplus_huge_pages_node[nid]) {
/* remove the page from active list */
remove_hugetlb_page(h, page, true);
spin_unlock_irqrestore(&hugetlb_lock, flags);
- update_and_free_page(h, page);
+ update_and_free_page(h, page, true);
} else {
arch_clear_hugepage_flags(page);
enqueue_huge_page(h, page);
@@ -1798,7 +1865,7 @@ int dissolve_free_huge_page(struct page *page)
remove_hugetlb_page(h, page, false);
h->max_huge_pages--;
spin_unlock_irq(&hugetlb_lock);
- update_and_free_page(h, head);
+ update_and_free_page(h, head, false);
return 0;
}
out:
@@ -2343,14 +2410,14 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
* Pages have been replaced, we can safely free the old one.
*/
spin_unlock_irq(&hugetlb_lock);
- update_and_free_page(h, old_page);
+ update_and_free_page(h, old_page, false);
}
return ret;
free_new:
spin_unlock_irq(&hugetlb_lock);
- update_and_free_page(h, new_page);
+ update_and_free_page(h, new_page, false);
return ret;
}
@@ -2764,6 +2831,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
* pages in hstate via the proc/sysfs interfaces.
*/
mutex_lock(&h->resize_lock);
+ flush_free_hpage_work(h);
spin_lock_irq(&hugetlb_lock);
/*
@@ -2873,6 +2941,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
/* free the pages after dropping lock */
spin_unlock_irq(&hugetlb_lock);
update_and_free_pages_bulk(h, &page_list);
+ flush_free_hpage_work(h);
spin_lock_irq(&hugetlb_lock);
while (count < persistent_huge_pages(h)) {
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index e45a138a7f85..cb28c5b6c9ff 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -180,18 +180,6 @@
#define RESERVE_VMEMMAP_NR 2U
#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
-/*
- * How many vmemmap pages associated with a HugeTLB page that can be freed
- * to the buddy allocator.
- *
- * Todo: Returns zero for now, which means the feature is disabled. We will
- * enable it once all the infrastructure is there.
- */
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-{
- return 0;
-}
-
static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
{
return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 6923f03534d5..01f8637adbe0 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,9 +12,26 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+
+/*
+ * How many vmemmap pages associated with a HugeTLB page that can be freed
+ * to the buddy allocator.
+ *
+ * Todo: Returns zero for now, which means the feature is disabled. We will
+ * enable it once all the infrastructure is there.
+ */
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+ return 0;
+}
#else
static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+ return 0;
+}
#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
#endif /* _LINUX_HUGETLB_VMEMMAP_H */
--
2.11.0
next prev parent reply other threads:[~2021-05-10 3:04 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-10 3:00 [PATCH v23 0/9] Free some vmemmap pages of HugeTLB page Muchun Song
2021-05-10 3:00 ` [PATCH v23 1/9] mm: memory_hotplug: factor out bootmem core functions to bootmem_info.c Muchun Song
2021-05-10 3:00 ` [PATCH v23 2/9] mm: hugetlb: introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2021-05-10 3:00 ` [PATCH v23 3/9] mm: hugetlb: gather discrete indexes of tail page Muchun Song
2021-05-10 3:00 ` [PATCH v23 4/9] mm: hugetlb: free the vmemmap pages associated with each HugeTLB page Muchun Song
2021-05-10 3:00 ` Muchun Song [this message]
2021-05-10 10:23 ` [PATCH v23 5/9] mm: hugetlb: defer freeing of HugeTLB pages Oscar Salvador
2021-05-10 3:00 ` [PATCH v23 6/9] mm: hugetlb: alloc the vmemmap pages associated with each HugeTLB page Muchun Song
2021-05-10 10:45 ` Oscar Salvador
2021-05-10 12:19 ` [External] " Muchun Song
2021-05-11 1:10 ` Mike Kravetz
2021-05-11 8:07 ` Oscar Salvador
2021-05-10 3:00 ` [PATCH v23 7/9] mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap Muchun Song
2021-05-10 3:00 ` [PATCH v23 8/9] mm: memory_hotplug: disable memmap_on_memory when hugetlb_free_vmemmap enabled Muchun Song
2021-05-10 10:08 ` Oscar Salvador
2021-05-10 10:33 ` [External] " Muchun Song
2021-05-10 3:00 ` [PATCH v23 9/9] mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2021-06-25 17:21 ` [PATCH v23 0/9] Free some vmemmap pages of HugeTLB page Wali, Rohit
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=20210510030027.56044-6-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=david@redhat.com \
--cc=duanxiongchun@bytedance.com \
--cc=fam.zheng@bytedance.com \
--cc=hpa@zytor.com \
--cc=joao.m.martins@oracle.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=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.com \
--cc=naoya.horiguchi@nec.com \
--cc=oneukum@suse.com \
--cc=osalvador@suse.de \
--cc=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=song.bao.hua@hisilicon.com \
--cc=tglx@linutronix.de \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
--cc=zhengqi.arch@bytedance.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).