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 12/19] mm/hugetlb: Support freeing vmemmap pages of gigantic page
Date: Mon, 26 Oct 2020 22:51:07 +0800
Message-ID: <20201026145114.59424-13-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201026145114.59424-1-songmuchun@bytedance.com>

The gigantic page is allocated by bootmem, if we want to free the
unused vmemmap pages. We also should allocate the page table. So
we also allocate page tables from bootmem.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            | 57 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 919f47d77117..695d3041ae7d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -506,6 +506,9 @@ struct hstate {
 struct huge_bootmem_page {
 	struct list_head list;
 	struct hstate *hstate;
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	pte_t *vmemmap_pgtable;
+#endif
 };
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f75b93fb4c07..d98b55ad1a90 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1410,6 +1410,48 @@ static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
 		pte_free_kernel(&init_mm, pte_p);
 }
 
+static unsigned long __init gather_vmemmap_pgtable_prealloc(void)
+{
+	struct huge_bootmem_page *m, *tmp;
+	unsigned long nr_free = 0;
+
+	list_for_each_entry_safe(m, tmp, &huge_boot_pages, list) {
+		struct hstate *h = m->hstate;
+		unsigned int pgtable_size = nr_pgtable(h) << PAGE_SHIFT;
+
+		if (!pgtable_size)
+			continue;
+
+		m->vmemmap_pgtable = memblock_alloc_try_nid(pgtable_size,
+				PAGE_SIZE, 0, MEMBLOCK_ALLOC_ACCESSIBLE,
+				NUMA_NO_NODE);
+		if (!m->vmemmap_pgtable) {
+			nr_free++;
+			list_del(&m->list);
+			memblock_free_early(__pa(m), huge_page_size(h));
+		}
+	}
+
+	return nr_free;
+}
+
+static void __init gather_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+					       struct page *page)
+{
+	int i;
+	struct hstate *h = m->hstate;
+	unsigned long pgtable = (unsigned long)m->vmemmap_pgtable;
+	unsigned int nr = nr_pgtable(h);
+
+	if (!nr)
+		return;
+
+	vmemmap_pgtable_init(page);
+
+	for (i = 0; i < nr; i++, pgtable += PAGE_SIZE)
+		vmemmap_pgtable_deposit(page, (pte_t *)pgtable);
+}
+
 static void __init hugetlb_vmemmap_init(struct hstate *h)
 {
 	unsigned int order = huge_page_order(h);
@@ -1778,6 +1820,16 @@ static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
 {
 }
 
+static inline unsigned long gather_vmemmap_pgtable_prealloc(void)
+{
+	return 0;
+}
+
+static inline void gather_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+					       struct page *page)
+{
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
@@ -3039,6 +3091,7 @@ static void __init gather_bootmem_prealloc(void)
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
 		WARN_ON(PageReserved(page));
+		gather_vmemmap_pgtable_init(m, page);
 		prep_new_huge_page(h, page, page_to_nid(page));
 		put_page(page); /* free it into the hugepage allocator */
 
@@ -3091,6 +3144,10 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 			break;
 		cond_resched();
 	}
+
+	if (hstate_is_gigantic(h))
+		i -= gather_vmemmap_pgtable_prealloc();
+
 	if (i < h->max_huge_pages) {
 		char buf[32];
 
-- 
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 ` Muchun Song [this message]
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 ` [PATCH v2 18/19] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
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=20201026145114.59424-13-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