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 17/19] mm/hugetlb: Merge pte to huge pmd only for gigantic page
Date: Mon, 26 Oct 2020 22:51:12 +0800
Message-ID: <20201026145114.59424-18-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201026145114.59424-1-songmuchun@bytedance.com>

Merge pte to huge pmd if it has ever been split. Now only support
gigantic page which's vmemmap pages size is an integer multiple of
PMD_SIZE. This is the simplest case to handle.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/include/asm/hugetlb.h |   8 +++
 include/linux/hugetlb.h        |   7 +++
 mm/hugetlb.c                   | 106 ++++++++++++++++++++++++++++++++-
 3 files changed, 119 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 7c3eb60c2198..9f9e19dd0578 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -15,6 +15,14 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
 {
 	return pmd_large(*pmd);
 }
+
+#define vmemmap_pmd_mkhuge vmemmap_pmd_mkhuge
+static inline pmd_t vmemmap_pmd_mkhuge(struct page *page)
+{
+	pte_t entry = pfn_pte(page_to_pfn(page), PAGE_KERNEL_LARGE);
+
+	return __pmd(pte_val(entry));
+}
 #endif
 
 #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 695d3041ae7d..3a45199cc5c1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -611,6 +611,13 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
 }
 #endif
 
+#ifndef vmemmap_pmd_mkhuge
+static inline pmd_t vmemmap_pmd_mkhuge(struct page *page)
+{
+	return pmd_mkhuge(mk_pmd(page, PAGE_KERNEL));
+}
+#endif
+
 #ifndef VMEMMAP_HPAGE_SHIFT
 #define VMEMMAP_HPAGE_SHIFT		PMD_SHIFT
 #endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 82467d573fee..a526bcdb137b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1718,6 +1718,62 @@ static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 	}
 }
 
+static void __replace_huge_page_pte_vmemmap(pte_t *ptep, unsigned long start,
+					    unsigned int nr, struct page *huge,
+					    struct list_head *free_pages)
+{
+	unsigned long addr;
+	unsigned long end = start + (nr << PAGE_SHIFT);
+
+	for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
+		struct page *page;
+		pte_t old = *ptep;
+		pte_t entry;
+
+		prepare_vmemmap_page(huge);
+
+		entry = mk_pte(huge++, PAGE_KERNEL);
+		VM_WARN_ON(!pte_present(old));
+		page = pte_page(old);
+		list_add(&page->lru, free_pages);
+
+		set_pte_at(&init_mm, addr, ptep, entry);
+	}
+}
+
+static void replace_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					  struct page *huge,
+					  struct list_head *free_pages)
+{
+	unsigned long end = start + VMEMMAP_HPAGE_SIZE;
+
+	flush_cache_vunmap(start, end);
+	__replace_huge_page_pte_vmemmap(pte_offset_kernel(pmd, start), start,
+					VMEMMAP_HPAGE_NR, huge, free_pages);
+	flush_tlb_kernel_range(start, end);
+}
+
+static pte_t *merge_vmemmap_pte(pmd_t *pmdp, unsigned long addr)
+{
+	pte_t *pte;
+	struct page *page;
+
+	pte = pte_offset_kernel(pmdp, addr);
+	page = pte_page(*pte);
+	set_pmd(pmdp, vmemmap_pmd_mkhuge(page));
+
+	return pte;
+}
+
+static void merge_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					struct page *huge,
+					struct list_head *free_pages)
+{
+	replace_huge_page_pmd_vmemmap(pmd, start, huge, free_pages);
+	pte_free_kernel(&init_mm, merge_vmemmap_pte(pmd, start));
+	flush_tlb_kernel_range(start, start + VMEMMAP_HPAGE_SIZE);
+}
+
 static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
 {
 	int i;
@@ -1731,6 +1787,15 @@ static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
 	}
 }
 
+static inline void dissolve_compound_page(struct page *page, unsigned int order)
+{
+	int i;
+	unsigned int nr_pages = 1 << order;
+
+	for (i = 1; i < nr_pages; i++)
+		set_page_refcounted(page + i);
+}
+
 static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	pmd_t *pmd;
@@ -1750,10 +1815,47 @@ static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 				    __remap_huge_page_pte_vmemmap);
 	if (!freed_vmemmap_hpage_dec(pmd_page(*pmd)) && pmd_split(pmd)) {
 		/*
-		 * Todo:
-		 * Merge pte to huge pmd if it has ever been split.
+		 * Merge pte to huge pmd if it has ever been split. Now only
+		 * support gigantic page which's vmemmap pages size is an
+		 * integer multiple of PMD_SIZE. This is the simplest case
+		 * to handle.
 		 */
 		clear_pmd_split(pmd);
+
+		if (IS_ALIGNED(nr_vmemmap(h), VMEMMAP_HPAGE_NR)) {
+			unsigned long addr = (unsigned long)head;
+			unsigned long end = addr + nr_vmemmap_size(h);
+
+			spin_unlock(ptl);
+
+			for (; addr < end; addr += VMEMMAP_HPAGE_SIZE) {
+				void *to;
+				struct page *page;
+
+				page = alloc_pages(GFP_VMEMMAP_PAGE & ~__GFP_NOFAIL,
+						   VMEMMAP_HPAGE_ORDER);
+				dissolve_compound_page(page,
+						       VMEMMAP_HPAGE_ORDER);
+				if (!page)
+					goto out;
+
+				to = page_to_virt(page);
+				memcpy(to, (void *)addr, VMEMMAP_HPAGE_SIZE);
+
+				/*
+				 * Make sure that any data that writes to the
+				 * @to is made visible to the physical page.
+				 */
+				flush_kernel_vmap_range(to, VMEMMAP_HPAGE_SIZE);
+
+				merge_huge_page_pmd_vmemmap(pmd++, addr, page,
+							    &remap_pages);
+			}
+
+out:
+			free_vmemmap_page_list(&remap_pages);
+			return;
+		}
 	}
 	spin_unlock(ptl);
 }
-- 
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 ` Muchun Song [this message]
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=20201026145114.59424-18-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