Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
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>,
        Miaohe Lin <linmiaohe@huawei.com>,
        Chen Huang <chenhuang5@huawei.com>,
        Bodeddula Balasubramaniam <bodeddub@amazon.com>
Subject: [PATCH v21 3/9] mm: hugetlb: gather discrete indexes of tail page
Date:   Sun, 25 Apr 2021 15:07:46 +0800
Message-Id: <20210425070752.17783-4-songmuchun@bytedance.com>
In-Reply-To: <20210425070752.17783-1-songmuchun@bytedance.com>
References: <20210425070752.17783-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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>
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>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h        | 21 +++++++++++++++++++--
 include/linux/hugetlb_cgroup.h | 19 +++++++++++--------
 2 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b92f25ccef58..d523a345dc86 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -29,6 +29,23 @@ typedef struct { unsigned long pd; } hugepd_t;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+/*
+ * 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 gather these discrete indexes
+ * of tail struct page here.
+ */
+enum {
+	SUBPAGE_INDEX_SUBPOOL = 1,	/* reuse page->private */
+#ifdef CONFIG_CGROUP_HUGETLB
+	SUBPAGE_INDEX_CGROUP,		/* reuse page->private */
+	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
+	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
+#endif
+	__NR_USED_SUBPAGE,
+};
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
@@ -627,13 +644,13 @@ extern unsigned int default_hstate_idx;
  */
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
-	return (struct hugepage_subpool *)(hpage+1)->private;
+	return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
 }
 
 static inline void hugetlb_set_page_subpool(struct page *hpage,
 					struct hugepage_subpool *subpool)
 {
-	set_page_private(hpage+1, (unsigned long)subpool);
+	set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
 }
 
 static inline struct hstate *hstate_file(struct file *f)
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0bff345c4bc6..0b8d1fdda3a1 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -21,15 +21,16 @@ struct hugetlb_cgroup;
 struct resv_map;
 struct file_region;
 
+#ifdef CONFIG_CGROUP_HUGETLB
 /*
  * 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
+#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1)
 
-#ifdef CONFIG_CGROUP_HUGETLB
 enum hugetlb_memory_event {
 	HUGETLB_MAX,
 	HUGETLB_NR_MEMORY_EVENTS,
@@ -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;
 }
 
-- 
2.11.0