linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / 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,
	osalvador@suse.de, mhocko@suse.com
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 v4 05/21] mm/hugetlb: Introduce pgtable allocation/freeing helpers
Date: Fri, 13 Nov 2020 18:59:36 +0800	[thread overview]
Message-ID: <20201113105952.11638-6-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201113105952.11638-1-songmuchun@bytedance.com>

On x86_64, vmemmap is always PMD mapped if the machine has hugepages
support and if we have 2MB contiguos pages and PMD aligned. If we want
to free the unused vmemmap pages, we have to split the huge pmd firstly.
So we should pre-allocate pgtable to split PMD to PTE.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h | 12 +++++++++
 2 files changed, 85 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index a6c9948302e2..b7dfa97b4ea9 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -71,6 +71,8 @@
  */
 #define pr_fmt(fmt)	"HugeTLB Vmemmap: " fmt
 
+#include <linux/list.h>
+#include <asm/pgalloc.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -83,6 +85,77 @@
  */
 #define RESERVE_VMEMMAP_NR		2U
 
+#ifndef VMEMMAP_HPAGE_SHIFT
+#define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
+#endif
+#define VMEMMAP_HPAGE_ORDER		(VMEMMAP_HPAGE_SHIFT - PAGE_SHIFT)
+#define VMEMMAP_HPAGE_NR		(1 << VMEMMAP_HPAGE_ORDER)
+#define VMEMMAP_HPAGE_SIZE		((1UL) << VMEMMAP_HPAGE_SHIFT)
+#define VMEMMAP_HPAGE_MASK		(~(VMEMMAP_HPAGE_SIZE - 1))
+
+#define page_huge_pte(page)		((page)->pmd_huge_pte)
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
+
+static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
+}
+
+static inline unsigned long vmemmap_pages_size_per_hpage(struct hstate *h)
+{
+	return (unsigned long)vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
+}
+
+static inline unsigned int pgtable_pages_to_prealloc_per_hpage(struct hstate *h)
+{
+	unsigned long vmemmap_size = vmemmap_pages_size_per_hpage(h);
+
+	/*
+	 * No need pre-allocate page tables when there is no vmemmap pages
+	 * to free.
+	 */
+	if (!free_vmemmap_pages_per_hpage(h))
+		return 0;
+
+	return ALIGN(vmemmap_size, VMEMMAP_HPAGE_SIZE) >> VMEMMAP_HPAGE_SHIFT;
+}
+
+void vmemmap_pgtable_free(struct page *page)
+{
+	struct page *pte_page, *t_page;
+
+	list_for_each_entry_safe(pte_page, t_page, &page->lru, lru) {
+		list_del(&pte_page->lru);
+		pte_free_kernel(&init_mm, page_to_virt(pte_page));
+	}
+}
+
+int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
+{
+	unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+
+	/* Store preallocated pages on huge page lru list */
+	INIT_LIST_HEAD(&page->lru);
+
+	while (nr--) {
+		pte_t *pte_p;
+
+		pte_p = pte_alloc_one_kernel(&init_mm);
+		if (!pte_p)
+			goto out;
+		list_add(&virt_to_page(pte_p)->lru, &page->lru);
+	}
+
+	return 0;
+out:
+	vmemmap_pgtable_free(page);
+	return -ENOMEM;
+}
+
 void __init hugetlb_vmemmap_init(struct hstate *h)
 {
 	unsigned int order = huge_page_order(h);
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 40c0c7dfb60d..2a72d2f62411 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -9,12 +9,24 @@
 #ifndef _LINUX_HUGETLB_VMEMMAP_H
 #define _LINUX_HUGETLB_VMEMMAP_H
 #include <linux/hugetlb.h>
+#include <linux/mm.h>
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page);
+void vmemmap_pgtable_free(struct page *page);
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
+
+static inline int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
+{
+	return 0;
+}
+
+static inline void vmemmap_pgtable_free(struct page *page)
+{
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0


  parent reply	other threads:[~2020-11-13 11:18 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-13 10:59 [PATCH v4 00/21] Free some vmemmap pages of hugetlb page Muchun Song
2020-11-13 10:59 ` [PATCH v4 01/21] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-11-16 13:50   ` Oscar Salvador
2020-11-13 10:59 ` [PATCH v4 02/21] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-11-16 13:52   ` Oscar Salvador
2020-11-13 10:59 ` [PATCH v4 03/21] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-11-18 22:38   ` Mike Kravetz
2020-11-19  2:57     ` [External] " Muchun Song
2020-11-13 10:59 ` [PATCH v4 04/21] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-11-16 13:33   ` Oscar Salvador
2020-11-16 15:40     ` [External] " Muchun Song
2020-11-18 22:54     ` Mike Kravetz
2020-11-18 23:48   ` Mike Kravetz
2020-11-19  3:00     ` [External] " Muchun Song
2020-11-13 10:59 ` Muchun Song [this message]
2020-11-17 15:06   ` [PATCH v4 05/21] mm/hugetlb: Introduce pgtable allocation/freeing helpers Oscar Salvador
2020-11-17 15:29     ` [External] " Muchun Song
2020-11-19  6:17     ` Muchun Song
2020-11-19 23:21       ` Mike Kravetz
2020-11-20  2:52         ` Muchun Song
2020-11-19 23:37   ` Mike Kravetz
2020-11-13 10:59 ` [PATCH v4 06/21] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-11-13 10:59 ` [PATCH v4 07/21] mm/bootmem_info: Combine bootmem info and type into page->freelist Muchun Song
2020-11-13 10:59 ` [PATCH v4 08/21] mm/hugetlb: Initialize page table lock for vmemmap Muchun Song
2020-11-13 10:59 ` [PATCH v4 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-17  9:54   ` Song Bao Hua (Barry Song)
2020-11-17 10:26     ` [External] " Muchun Song
2020-11-18  3:21       ` Song Bao Hua (Barry Song)
2020-11-13 10:59 ` [PATCH v4 10/21] mm/hugetlb: Defer freeing of hugetlb pages Muchun Song
2020-11-13 10:59 ` [PATCH v4 11/21] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-13 10:59 ` [PATCH v4 12/21] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-11-13 10:59 ` [PATCH v4 13/21] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-11-13 10:59 ` [PATCH v4 14/21] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-11-13 10:59 ` [PATCH v4 15/21] mm/hugetlb: Set the PageHWPoison to the raw error page Muchun Song
2020-11-13 10:59 ` [PATCH v4 16/21] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-11-13 10:59 ` [PATCH v4 17/21] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-11-13 10:59 ` [PATCH v4 18/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-11-13 10:59 ` [PATCH v4 19/21] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-11-13 10:59 ` [PATCH v4 20/21] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-11-13 10:59 ` [PATCH v4 21/21] mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two Muchun Song
2020-11-17 10:15 ` [PATCH v4 00/21] Free some vmemmap pages of hugetlb page Song Bao Hua (Barry Song)
2020-11-17 10:49   ` [External] " Muchun Song
2020-11-17 11:07     ` Song Bao Hua (Barry Song)
2020-11-17 16:29       ` Muchun Song
2020-11-17 19:22         ` Matthew Wilcox
2020-11-18  2:43           ` Muchun Song
2020-11-17 19:45         ` Oscar Salvador
2020-11-18  3:27           ` Muchun Song
2020-11-18  3:27           ` Song Bao Hua (Barry Song)

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=20201113105952.11638-6-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=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=mingo@redhat.com \
    --cc=oneukum@suse.com \
    --cc=osalvador@suse.de \
    --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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).