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,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
Muchun Song <songmuchun@bytedance.com>,
Miaohe Lin <linmiaohe@huawei.com>,
Chen Huang <chenhuang5@huawei.com>,
Bodeddula Balasubramaniam <bodeddub@amazon.com>
Subject: [PATCH v20 9/9] mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate
Date: Thu, 15 Apr 2021 16:40:05 +0800 [thread overview]
Message-ID: <20210415084005.25049-10-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210415084005.25049-1-songmuchun@bytedance.com>
All the infrastructure is ready, so we introduce nr_free_vmemmap_pages
field in the hstate to indicate how many vmemmap pages associated with
a HugeTLB page that can be freed to buddy allocator. And initialize it
in the hugetlb_vmemmap_init(). This patch is actual enablement of the
feature.
There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Tested-by: Chen Huang <chenhuang5@huawei.com>
Tested-by: Bodeddula Balasubramaniam <bodeddub@amazon.com>
---
include/linux/hugetlb.h | 3 +++
mm/hugetlb.c | 1 +
mm/hugetlb_vmemmap.c | 33 +++++++++++++++++++++++++++++++++
mm/hugetlb_vmemmap.h | 10 ++++++----
4 files changed, 43 insertions(+), 4 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 4015cedacf91..710d821fbca6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -602,6 +602,9 @@ struct hstate {
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+ unsigned int nr_free_vmemmap_pages;
+#endif
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files_dfl[7];
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1c37f0098e00..8adf52f4c7e4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3361,6 +3361,7 @@ void __init hugetlb_add_hstate(unsigned int order)
h->next_nid_to_free = first_memory_node;
snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
huge_page_size(h)/1024);
+ hugetlb_vmemmap_init(h);
parsed_hstate = h;
}
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 3070e1465b1b..f9f9bb212319 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -262,3 +262,36 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
SetHPageVmemmapOptimized(head);
}
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+ unsigned int nr_pages = pages_per_huge_page(h);
+ unsigned int vmemmap_pages;
+
+ /*
+ * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
+ * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
+ * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
+ */
+ BUILD_BUG_ON(__NR_USED_SUBPAGE >=
+ RESERVE_VMEMMAP_SIZE / sizeof(struct page));
+
+ if (!hugetlb_free_vmemmap_enabled)
+ return;
+
+ vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
+ /*
+ * The head page and the first tail page are not to be freed to buddy
+ * allocator, the other pages will map to the first tail page, so they
+ * can be freed.
+ *
+ * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true
+ * on some architectures (e.g. aarch64). See Documentation/arm64/
+ * hugetlbpage.rst for more details.
+ */
+ if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+ h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+ pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+ h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index a37771b0b82a..cb2bef8f9e73 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,17 +13,15 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
int alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+void hugetlb_vmemmap_init(struct hstate *h);
/*
* 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;
+ return h->nr_free_vmemmap_pages;
}
#else
static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
@@ -35,6 +33,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
{
return 0;
--
2.11.0
next prev parent reply other threads:[~2021-04-15 8:44 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-15 8:39 [PATCH v20 0/9] Free some vmemmap pages of HugeTLB page Muchun Song
2021-04-15 8:39 ` [PATCH v20 1/9] mm: memory_hotplug: factor out bootmem core functions to bootmem_info.c Muchun Song
2021-04-15 8:39 ` [PATCH v20 2/9] mm: hugetlb: introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2021-04-15 8:39 ` [PATCH v20 3/9] mm: hugetlb: gather discrete indexes of tail page Muchun Song
2021-04-16 18:54 ` Mike Kravetz
2021-04-15 8:40 ` [PATCH v20 4/9] mm: hugetlb: free the vmemmap pages associated with each HugeTLB page Muchun Song
2021-04-16 21:10 ` Mike Kravetz
2021-04-17 2:55 ` [External] " Muchun Song
2021-04-15 8:40 ` [PATCH v20 5/9] mm: hugetlb: defer freeing of HugeTLB pages Muchun Song
2021-04-16 23:55 ` Mike Kravetz
2021-04-17 4:13 ` [External] " Muchun Song
2021-04-15 8:40 ` [PATCH v20 7/9] mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap Muchun Song
2021-04-19 23:41 ` Mike Kravetz
2021-04-15 8:40 ` [PATCH v20 8/9] mm: memory_hotplug: disable memmap_on_memory when hugetlb_free_vmemmap enabled Muchun Song
2021-04-20 10:35 ` Oscar Salvador
2021-04-21 3:41 ` [External] " Muchun Song
2021-04-21 7:33 ` Oscar Salvador
2021-04-21 9:06 ` Muchun Song
2021-04-15 8:40 ` Muchun Song [this message]
[not found] ` <20210415084005.25049-7-songmuchun@bytedance.com>
2021-04-19 23:19 ` [PATCH v20 6/9] mm: hugetlb: alloc the vmemmap pages associated with each HugeTLB page Mike Kravetz
2021-04-20 8:46 ` [External] " Muchun Song
2021-04-20 17:48 ` Mike Kravetz
2021-04-21 3:42 ` Muchun 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=20210415084005.25049-10-songmuchun@bytedance.com \
--to=songmuchun@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=almasrymina@google.com \
--cc=anshuman.khandual@arm.com \
--cc=bodeddub@amazon.com \
--cc=bp@alien8.de \
--cc=chenhuang5@huawei.com \
--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=linmiaohe@huawei.com \
--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 \
/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).