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 09/19] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page
Date: Mon, 26 Oct 2020 22:51:04 +0800
Message-ID: <20201026145114.59424-10-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201026145114.59424-1-songmuchun@bytedance.com>

When we free a hugetlb page to the buddy, we should allocate the vmemmap
pages associated with it. We can do that in the __free_hugepage().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a5500c79e2df..cea580058a16 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1299,6 +1299,7 @@ static void __free_hugepage(struct hstate *h, struct page *page);
 
 #define RESERVE_VMEMMAP_NR	2U
 #define RESERVE_VMEMMAP_SIZE	(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define GFP_VMEMMAP_PAGE	(GFP_KERNEL | __GFP_NOFAIL | __GFP_MEMALLOC)
 
 #define page_huge_pte(page)	((page)->pmd_huge_pte)
 
@@ -1604,6 +1605,107 @@ static void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 	free_vmemmap_page_list(&free_pages);
 }
 
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					  unsigned long start,
+					  unsigned int nr_remap,
+					  struct list_head *remap_pages)
+{
+	void *from = (void *)page_private(reuse);
+	unsigned long addr, end = start + (nr_remap << PAGE_SHIFT);
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		void *to;
+		struct page *page;
+		pte_t entry, old = *ptep;
+
+		page = list_first_entry_or_null(remap_pages, struct page, lru);
+		list_del(&page->lru);
+		to = page_to_virt(page);
+		copy_page(to, from);
+
+		/*
+		 * Make sure that any data that writes to the @to is made
+		 * visible to the physical page.
+		 */
+		flush_kernel_vmap_range(to, PAGE_SIZE);
+
+		prepare_vmemmap_page(page);
+
+		entry = mk_pte(page, PAGE_KERNEL);
+		set_pte_at(&init_mm, addr, ptep++, entry);
+
+		VM_BUG_ON(!pte_present(old) || pte_page(old) != reuse);
+	}
+}
+
+static void __remap_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
+					  unsigned long addr,
+					  struct list_head *remap_pages)
+{
+	unsigned long next;
+	unsigned long start = addr + RESERVE_VMEMMAP_NR * PAGE_SIZE;
+	unsigned long end = addr + nr_vmemmap_size(h);
+	struct page *reuse = NULL;
+
+	addr = start;
+	do {
+		unsigned int nr_pages;
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse) {
+			reuse = pte_page(ptep[-1]);
+			set_page_private(reuse, addr - PAGE_SIZE);
+		}
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		nr_pages = (next - addr) >> PAGE_SHIFT;
+		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, nr_pages,
+					      remap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+	int i;
+
+	for (i = 0; i < nr_free_vmemmap(h); i++) {
+		struct page *page;
+
+		/* This should not fail */
+		page = alloc_page(GFP_VMEMMAP_PAGE);
+		list_add_tail(&page->lru, list);
+	}
+}
+
+static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	spinlock_t *ptl;
+	LIST_HEAD(remap_pages);
+
+	if (!nr_free_vmemmap(h))
+		return;
+
+	alloc_vmemmap_pages(h, &remap_pages);
+
+	pmd = vmemmap_to_pmd(head);
+	ptl = vmemmap_pmd_lockptr(pmd);
+
+	spin_lock(ptl);
+	__remap_huge_page_pmd_vmemmap(h, pmd, (unsigned long)head,
+				      &remap_pages);
+	if (!freed_vmemmap_hpage_dec(pmd_page(*pmd))) {
+		/*
+		 * Todo:
+		 * Merge pte to huge pmd if it has ever been split.
+		 */
+	}
+	spin_unlock(ptl);
+}
+
 /*
  * 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
@@ -1679,6 +1781,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
 
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
 static inline void __update_and_free_page(struct hstate *h, struct page *page)
 {
 	__free_hugepage(h, page);
@@ -1711,6 +1817,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 {
 	int i;
 
+	alloc_huge_page_vmemmap(h, page);
+
 	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 |
-- 
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 " 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 ` Muchun Song [this message]
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 ` [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=20201026145114.59424-10-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