From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
Roman Gushchin <guro@fb.com>, Rik van Riel <riel@surriel.com>,
Matthew Wilcox <willy@infradead.org>,
Shakeel Butt <shakeelb@google.com>,
Yang Shi <shy828301@gmail.com>, Jason Gunthorpe <jgg@nvidia.com>,
Mike Kravetz <mike.kravetz@oracle.com>,
Michal Hocko <mhocko@suse.com>,
David Hildenbrand <david@redhat.com>,
William Kucharski <william.kucharski@oracle.com>,
Andrea Arcangeli <aarcange@redhat.com>,
John Hubbard <jhubbard@nvidia.com>,
David Nellans <dnellans@nvidia.com>,
linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH v2 04/30] mm: add new helper functions to allocate one PMD page with 512 PTE pages.
Date: Mon, 28 Sep 2020 13:54:02 -0400 [thread overview]
Message-ID: <20200928175428.4110504-5-zi.yan@sent.com> (raw)
In-Reply-To: <20200928175428.4110504-1-zi.yan@sent.com>
From: Zi Yan <ziy@nvidia.com>
This prepares for PUD THP support, which allocates 512 of such PMD pages
when creating a PUD THP. These page table pages will be withdrawn during
THP split.
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
arch/x86/include/asm/pgalloc.h | 60 ++++++++++++++++++++++++++++++++++
arch/x86/mm/pgtable.c | 25 ++++++++++++++
include/linux/huge_mm.h | 3 ++
3 files changed, 88 insertions(+)
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 62ad61d6fefc..b24284522973 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -52,6 +52,19 @@ extern pgd_t *pgd_alloc(struct mm_struct *);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
extern pgtable_t pte_alloc_one(struct mm_struct *);
+extern pgtable_t pte_alloc_order(struct mm_struct *mm, unsigned long address,
+ int order);
+
+static inline void pte_free_order(struct mm_struct *mm, struct page *pte,
+ int order)
+{
+ int i;
+
+ for (i = 0; i < (1<<order); i++) {
+ pgtable_pte_page_dtor(&pte[i]);
+ __free_page(&pte[i]);
+ }
+}
extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
@@ -87,6 +100,53 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
#define pmd_pgtable(pmd) pmd_page(pmd)
#if CONFIG_PGTABLE_LEVELS > 2
+static inline pmd_t *pmd_alloc_one_page_with_ptes(struct mm_struct *mm, unsigned long addr)
+{
+ pgtable_t pte_pgtables;
+ pmd_t *pmd;
+ spinlock_t *pmd_ptl;
+ int i;
+
+ pte_pgtables = pte_alloc_order(mm, addr,
+ HPAGE_PUD_ORDER - HPAGE_PMD_ORDER);
+ if (!pte_pgtables)
+ return NULL;
+
+ pmd = pmd_alloc_one(mm, addr);
+ if (unlikely(!pmd)) {
+ pte_free_order(mm, pte_pgtables,
+ HPAGE_PUD_ORDER - HPAGE_PMD_ORDER);
+ return NULL;
+ }
+ pmd_ptl = pmd_lock(mm, pmd);
+
+ for (i = 0; i < (1<<(HPAGE_PUD_ORDER - HPAGE_PMD_ORDER)); i++)
+ pgtable_trans_huge_deposit(mm, pmd, pte_pgtables + i);
+
+ spin_unlock(pmd_ptl);
+
+ return pmd;
+}
+
+static inline void pmd_free_page_with_ptes(struct mm_struct *mm, pmd_t *pmd)
+{
+ spinlock_t *pmd_ptl;
+ int i;
+
+ BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+ pmd_ptl = pmd_lock(mm, pmd);
+
+ for (i = 0; i < (1<<(HPAGE_PUD_ORDER - HPAGE_PMD_ORDER)); i++) {
+ pgtable_t pte_pgtable;
+
+ pte_pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+ pte_free(mm, pte_pgtable);
+ }
+
+ spin_unlock(pmd_ptl);
+ pmd_free(mm, pmd);
+}
+
extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfd82f51ba66..7be73aee6183 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -33,6 +33,31 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
return __pte_alloc_one(mm, __userpte_alloc_gfp);
}
+pgtable_t pte_alloc_order(struct mm_struct *mm, unsigned long address, int order)
+{
+ struct page *pte;
+ int i;
+
+ pte = alloc_pages(__userpte_alloc_gfp, order);
+ if (!pte)
+ return NULL;
+ split_page(pte, order);
+ for (i = 1; i < (1 << order); i++)
+ set_page_private(pte + i, 0);
+
+ for (i = 0; i < (1<<order); i++) {
+ if (!pgtable_pte_page_ctor(&pte[i])) {
+ __free_page(&pte[i]);
+ while (--i >= 0) {
+ pgtable_pte_page_dtor(&pte[i]);
+ __free_page(&pte[i]);
+ }
+ return NULL;
+ }
+ }
+ return pte;
+}
+
static int __init setup_userpte(char *arg)
{
if (!arg)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8a8bc46a2432..e9d228d4fc69 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -115,6 +115,9 @@ extern struct kobj_attribute shmem_enabled_attr;
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER)
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define HPAGE_PMD_SHIFT PMD_SHIFT
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
--
2.28.0
next prev parent reply other threads:[~2020-09-28 18:01 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-28 17:53 [RFC PATCH v2 00/30] 1GB PUD THP support on x86_64 Zi Yan
2020-09-28 17:53 ` [RFC PATCH v2 01/30] mm/pagewalk: use READ_ONCE when reading the PUD entry unlocked Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 02/30] mm: pagewalk: use READ_ONCE when reading the PMD " Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 03/30] mm: thp: use single linked list for THP page table page deposit Zi Yan
2020-09-28 19:34 ` Matthew Wilcox
2020-09-28 20:34 ` Zi Yan
2020-09-28 17:54 ` Zi Yan [this message]
2020-09-28 17:54 ` [RFC PATCH v2 05/30] mm: thp: add page table deposit/withdraw functions for PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 06/30] mm: change thp_order and thp_nr as we will have not just PMD THPs Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 07/30] mm: thp: add anonymous PUD THP page fault support without enabling it Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 08/30] mm: thp: add PUD THP support for copy_huge_pud Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 09/30] mm: thp: add PUD THP support to zap_huge_pud Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 10/30] fs: proc: add PUD THP kpageflag Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 11/30] mm: thp: handling PUD THP reference bit Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 12/30] mm: rmap: add mappped/unmapped page order to anonymous page rmap functions Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 13/30] mm: rmap: add map_order to page_remove_anon_compound_rmap Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 14/30] mm: thp: add PUD THP split_huge_pud_page() function Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 15/30] mm: thp: add PUD THP to deferred split list when PUD mapping is gone Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 16/30] mm: debug: adapt dump_page to PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 17/30] mm: thp: PUD THP COW splits PUD page and falls back to PMD page Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 18/30] mm: thp: PUD THP follow_p*d_page() support Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 19/30] mm: stats: make smap stats understand PUD THPs Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 20/30] mm: page_vma_walk: teach it about PMD-mapped PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 21/30] mm: thp: PUD THP support in try_to_unmap() Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 22/30] mm: thp: split PUD THPs at page reclaim Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 23/30] mm: support PUD THP pagemap support Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 24/30] mm: madvise: add page size options to MADV_HUGEPAGE and MADV_NOHUGEPAGE Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 25/30] mm: vma: add VM_HUGEPAGE_PUD to vm_flags at bit 37 Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 26/30] mm: thp: add a global knob to enable/disable PUD THPs Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 27/30] mm: thp: make PUD THP size public Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 28/30] hugetlb: cma: move cma reserve function to cma.c Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 29/30] mm: thp: use cma reservation for pud thp allocation Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 30/30] mm: thp: enable anonymous PUD THP at page fault path Zi Yan
2020-09-30 11:55 ` [RFC PATCH v2 00/30] 1GB PUD THP support on x86_64 Michal Hocko
2020-10-01 15:14 ` Zi Yan
2020-10-02 7:32 ` Michal Hocko
2020-10-02 7:50 ` David Hildenbrand
2020-10-02 8:10 ` Michal Hocko
2020-10-02 8:30 ` David Hildenbrand
2020-10-05 15:03 ` Zi Yan
2020-10-05 15:55 ` Matthew Wilcox
2020-10-05 17:04 ` Roman Gushchin
2020-10-05 19:12 ` Zi Yan
2020-10-05 19:37 ` Matthew Wilcox
2020-10-05 17:16 ` Roman Gushchin
2020-10-05 17:27 ` David Hildenbrand
2020-10-05 18:25 ` Roman Gushchin
2020-10-05 18:33 ` David Hildenbrand
2020-10-05 19:11 ` Roman Gushchin
2020-10-06 8:25 ` David Hildenbrand
2020-10-05 17:39 ` David Hildenbrand
2020-10-05 18:05 ` Zi Yan
2020-10-05 18:48 ` David Hildenbrand
2020-10-06 11:59 ` Michal Hocko
2020-10-05 15:34 ` Zi Yan
2020-10-05 17:30 ` David Hildenbrand
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=20200928175428.4110504-5-zi.yan@sent.com \
--to=zi.yan@sent.com \
--cc=aarcange@redhat.com \
--cc=david@redhat.com \
--cc=dnellans@nvidia.com \
--cc=guro@fb.com \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=riel@surriel.com \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=william.kucharski@oracle.com \
--cc=willy@infradead.org \
--cc=ziy@nvidia.com \
/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).