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 18/19] mm/hugetlb: Gather discrete indexes of tail page
Date: Mon, 26 Oct 2020 22:51:13 +0800
Message-ID: <20201026145114.59424-19-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201026145114.59424-1-songmuchun@bytedance.com>

For hugetlb page, there are more metadata to save in the struct
page. But the head struct page cannot meet our needs, so we have
to abuse other tail struct page to store the metadata. In order
to avoid conflicts caused by subsequent use of more tail struct
pages, we can gather these discrete indexes of tail struct page
In this case, it will be easier to add a new tail page index later.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/hugetlb.h        | 13 +++++++++++++
 include/linux/hugetlb_cgroup.h | 15 +++++++++------
 mm/hugetlb.c                   | 18 +++++++++---------
 3 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3a45199cc5c1..6d377b6099f0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -28,6 +28,19 @@ typedef struct { unsigned long pd; } hugepd_t;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+enum {
+	SUBPAGE_INDEX_ACTIVE = 1,	/* reuse page flags of PG_private */
+	SUBPAGE_INDEX_TEMPORARY,	/* reuse page->mapping */
+#ifdef CONFIG_CGROUP_HUGETLB
+	SUBPAGE_INDEX_CGROUP = SUBPAGE_INDEX_TEMPORARY,/* reuse page->private */
+	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	SUBPAGE_INDEX_HWPOISON,		/* reuse page->private */
+#endif
+	NR_USED_SUBPAGE,
+};
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 2ad6e92f124a..3d3c1c49efe4 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -24,8 +24,9 @@ struct file_region;
 /*
  * Minimum page order trackable by hugetlb cgroup.
  * At least 4 pages are necessary for all the tracking information.
- * The second tail page (hpage[2]) is the fault usage cgroup.
- * The third tail page (hpage[3]) is the reservation usage cgroup.
+ * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
+ * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
+ * is the reservation usage cgroup.
  */
 #define HUGETLB_CGROUP_MIN_ORDER	2
 
@@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd)
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
 	if (rsvd)
-		return (struct hugetlb_cgroup *)page[3].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
 	else
-		return (struct hugetlb_cgroup *)page[2].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
 }
 
 static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
@@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page,
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return -1;
 	if (rsvd)
-		page[3].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
+				 (unsigned long)h_cg);
 	else
-		page[2].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP,
+				 (unsigned long)h_cg);
 	return 0;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a526bcdb137b..029b00ed52ed 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1925,17 +1925,17 @@ static inline void flush_free_huge_page_work(void)
 
 static inline bool subpage_hwpoison(struct page *head, struct page *page)
 {
-	return page_private(head + 4) == page - head;
+	return page_private(head + SUBPAGE_INDEX_HWPOISON) == page - head;
 }
 
 static inline void set_subpage_hwpoison(struct page *head, struct page *page)
 {
-	set_page_private(head + 4, page - head);
+	set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
 }
 
 static inline void clear_subpage_hwpoison(struct page *head)
 {
-	set_page_private(head + 4, 0);
+	set_page_private(head + SUBPAGE_INDEX_HWPOISON, 0);
 }
 
 static int __init early_hugetlb_free_vmemmap_param(char *buf)
@@ -2075,20 +2075,20 @@ struct hstate *size_to_hstate(unsigned long size)
 bool page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHead(page) && PagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /* never called for tail page */
 static void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	SetPagePrivate(&page[1]);
+	SetPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 static void clear_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	ClearPagePrivate(&page[1]);
+	ClearPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /*
@@ -2100,17 +2100,17 @@ static inline bool PageHugeTemporary(struct page *page)
 	if (!PageHuge(page))
 		return false;
 
-	return (unsigned long)page[2].mapping == -1U;
+	return (unsigned long)page[SUBPAGE_INDEX_TEMPORARY].mapping == -1U;
 }
 
 static inline void SetPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = (void *)-1U;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = (void *)-1U;
 }
 
 static inline void ClearPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = NULL;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = NULL;
 }
 
 static void __free_huge_page(struct page *page)
-- 
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 ` [PATCH v2 08/19] mm/hugetlb: Defer freeing of hugetlb pages Muchun Song
2020-10-26 14:51 ` [PATCH v2 09/19] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page 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 ` Muchun Song [this message]
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=20201026145114.59424-19-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