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,
osalvador@suse.de, mhocko@suse.com
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 v4 10/21] mm/hugetlb: Defer freeing of hugetlb pages
Date: Fri, 13 Nov 2020 18:59:41 +0800 [thread overview]
Message-ID: <20201113105952.11638-11-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201113105952.11638-1-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 | 98 +++++++++++++++++++++++++++++++++++++++++++++-------
mm/hugetlb_vmemmap.c | 5 ---
mm/hugetlb_vmemmap.h | 10 ++++++
3 files changed, 96 insertions(+), 17 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a0ce6f33a717..4aabf12aca9b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1221,7 +1221,7 @@ static void destroy_compound_gigantic_page(struct page *page,
__ClearPageHead(page);
}
-static void free_gigantic_page(struct page *page, unsigned int order)
+static void __free_gigantic_page(struct page *page, unsigned int order)
{
/*
* If the page isn't allocated using the cma allocator,
@@ -1288,20 +1288,100 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
{
return NULL;
}
-static inline void free_gigantic_page(struct page *page, unsigned int order) { }
+static inline void __free_gigantic_page(struct page *page,
+ unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
unsigned int order) { }
#endif
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void __free_hugepage(struct hstate *h, struct page *page);
+
+/*
+ * 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)
{
- int i;
+ 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 (!free_vmemmap_pages_per_hpage(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);
+}
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+ __free_gigantic_page(page, huge_page_order(h));
+}
+#else
+static inline void free_gigantic_page(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)
+{
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 |
@@ -1313,14 +1393,8 @@ 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(h, page);
} else {
__free_pages(page, huge_page_order(h));
}
@@ -1761,7 +1835,7 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
if (vmemmap_pgtable_prealloc(h, page)) {
if (hstate_is_gigantic(h))
- free_gigantic_page(page, huge_page_order(h));
+ free_gigantic_page(h, page);
else
put_page(page);
return NULL;
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 937562a15f1e..e6fca02b57b2 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -115,11 +115,6 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
}
#endif
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-{
- return h->nr_free_vmemmap_pages;
-}
-
static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
{
return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index fb8b77659ed5..a23fb1375859 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -16,6 +16,11 @@ void __init hugetlb_vmemmap_init(struct hstate *h);
int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page);
void vmemmap_pgtable_free(struct page *page);
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+ return h->nr_free_vmemmap_pages;
+}
#else
static inline void hugetlb_vmemmap_init(struct hstate *h)
{
@@ -33,5 +38,10 @@ static inline void vmemmap_pgtable_free(struct page *page)
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:[~2020-11-13 11:17 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-13 10:59 [PATCH v4 00/21] Free some vmemmap pages of hugetlb page Muchun Song
2020-11-13 10:59 ` [PATCH v4 01/21] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-11-16 13:50 ` Oscar Salvador
2020-11-13 10:59 ` [PATCH v4 02/21] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-11-16 13:52 ` Oscar Salvador
2020-11-13 10:59 ` [PATCH v4 03/21] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-11-18 22:38 ` Mike Kravetz
2020-11-19 2:57 ` [External] " Muchun Song
2020-11-13 10:59 ` [PATCH v4 04/21] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-11-16 13:33 ` Oscar Salvador
2020-11-16 15:40 ` [External] " Muchun Song
2020-11-18 22:54 ` Mike Kravetz
2020-11-18 23:48 ` Mike Kravetz
2020-11-19 3:00 ` [External] " Muchun Song
2020-11-13 10:59 ` [PATCH v4 05/21] mm/hugetlb: Introduce pgtable allocation/freeing helpers Muchun Song
2020-11-17 15:06 ` Oscar Salvador
2020-11-17 15:29 ` [External] " Muchun Song
2020-11-19 6:17 ` Muchun Song
2020-11-19 23:21 ` Mike Kravetz
2020-11-20 2:52 ` Muchun Song
2020-11-19 23:37 ` Mike Kravetz
2020-11-13 10:59 ` [PATCH v4 06/21] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-11-13 10:59 ` [PATCH v4 07/21] mm/bootmem_info: Combine bootmem info and type into page->freelist Muchun Song
2020-11-13 10:59 ` [PATCH v4 08/21] mm/hugetlb: Initialize page table lock for vmemmap Muchun Song
2020-11-13 10:59 ` [PATCH v4 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-17 9:54 ` Song Bao Hua (Barry Song)
2020-11-17 10:26 ` [External] " Muchun Song
2020-11-18 3:21 ` Song Bao Hua (Barry Song)
2020-11-13 10:59 ` Muchun Song [this message]
2020-11-13 10:59 ` [PATCH v4 11/21] mm/hugetlb: Allocate " Muchun Song
2020-11-13 10:59 ` [PATCH v4 12/21] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-11-13 10:59 ` [PATCH v4 13/21] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-11-13 10:59 ` [PATCH v4 14/21] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-11-13 10:59 ` [PATCH v4 15/21] mm/hugetlb: Set the PageHWPoison to the raw error page Muchun Song
2020-11-13 10:59 ` [PATCH v4 16/21] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-11-13 10:59 ` [PATCH v4 17/21] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-11-13 10:59 ` [PATCH v4 18/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-11-13 10:59 ` [PATCH v4 19/21] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-11-13 10:59 ` [PATCH v4 20/21] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-11-13 10:59 ` [PATCH v4 21/21] mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two Muchun Song
2020-11-17 10:15 ` [PATCH v4 00/21] Free some vmemmap pages of hugetlb page Song Bao Hua (Barry Song)
2020-11-17 10:49 ` [External] " Muchun Song
2020-11-17 11:07 ` Song Bao Hua (Barry Song)
2020-11-17 16:29 ` Muchun Song
2020-11-17 19:22 ` Matthew Wilcox
2020-11-18 2:43 ` Muchun Song
2020-11-17 19:45 ` Oscar Salvador
2020-11-18 3:27 ` Muchun Song
2020-11-18 3:27 ` Song Bao Hua (Barry Song)
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=20201113105952.11638-11-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=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.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=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
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).