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 03/30] mm: thp: use single linked list for THP page table page deposit.
Date: Mon, 28 Sep 2020 13:54:01 -0400 [thread overview]
Message-ID: <20200928175428.4110504-4-zi.yan@sent.com> (raw)
In-Reply-To: <20200928175428.4110504-1-zi.yan@sent.com>
From: Zi Yan <ziy@nvidia.com>
The old design uses the double linked list page->lru to chain all
deposited page table pages when creating a THP and page->pmd_huge_pte
to point to the first page of the list. As the second pointer in
page->lru overlaps with page->pmd_huge_pte, the design prevents
multi-level page table page deposit, which is useful for PUD and higher
level THPs.
The new design uses single linked list, where deposit_head points to
a single linked list of deposited pages and deposit_node can be used to
deposit the page itself to another list. For example, this allows us to
have one PUD page points to a list of PMD pages, each of which points
a list of PTE pages to support PUD level THP.
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
include/linux/mm.h | 9 +++++----
include/linux/mm_types.h | 8 +++++---
kernel/fork.c | 4 ++--
mm/pgtable-generic.c | 15 +++++----------
4 files changed, 17 insertions(+), 19 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 17e712207d74..01b62da34794 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -10,6 +10,7 @@
#include <linux/gfp.h>
#include <linux/bug.h>
#include <linux/list.h>
+#include <linux/llist.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/atomic.h>
@@ -2249,7 +2250,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
static inline bool pmd_ptlock_init(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- page->pmd_huge_pte = NULL;
+ init_llist_head(&page->deposit_head);
#endif
return ptlock_init(page);
}
@@ -2257,12 +2258,12 @@ static inline bool pmd_ptlock_init(struct page *page)
static inline void pmd_ptlock_free(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
+ VM_BUG_ON_PAGE(!llist_empty(&page->deposit_head), page);
#endif
ptlock_free(page);
}
-#define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte)
+#define huge_pmd_deposit_head(mm, pmd) (pmd_to_page(pmd)->deposit_head)
#else
@@ -2274,7 +2275,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
static inline bool pmd_ptlock_init(struct page *page) { return true; }
static inline void pmd_ptlock_free(struct page *page) {}
-#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
+#define huge_pmd_deposit_head(mm, pmd) ((mm)->deposit_head_pmd)
#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 496c3ff97cce..be842926577a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -6,6 +6,7 @@
#include <linux/auxvec.h>
#include <linux/list.h>
+#include <linux/llist.h>
#include <linux/spinlock.h>
#include <linux/rbtree.h>
#include <linux/rwsem.h>
@@ -143,8 +144,8 @@ struct page {
struct list_head deferred_list;
};
struct { /* Page table pages */
- unsigned long _pt_pad_1; /* compound_head */
- pgtable_t pmd_huge_pte; /* protected by page->ptl */
+ struct llist_head deposit_head; /* pgtable deposit list head */
+ struct llist_node deposit_node; /* pgtable deposit list node */
unsigned long _pt_pad_2; /* mapping */
union {
struct mm_struct *pt_mm; /* x86 pgds only */
@@ -511,7 +512,8 @@ struct mm_struct {
struct mmu_notifier_subscriptions *notifier_subscriptions;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
- pgtable_t pmd_huge_pte; /* protected by page_table_lock */
+ /* pgtable deposit list head, protected by page_table_lock */
+ struct llist_head deposit_head_pmd;
#endif
#ifdef CONFIG_NUMA_BALANCING
/*
diff --git a/kernel/fork.c b/kernel/fork.c
index 138cd6ca50da..9c8e880538de 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -661,7 +661,7 @@ static void check_mm(struct mm_struct *mm)
mm_pgtables_bytes(mm));
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
- VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
+ VM_BUG_ON_MM(!llist_empty(&mm->deposit_head_pmd), mm);
#endif
}
@@ -1022,7 +1022,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mmu_notifier_subscriptions_init(mm);
init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
- mm->pmd_huge_pte = NULL;
+ init_llist_head(&mm->deposit_head_pmd);
#endif
mm_init_uprobes_state(mm);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9578db83e312..dbb0154165f1 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -164,11 +164,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
assert_spin_locked(pmd_lockptr(mm, pmdp));
/* FIFO */
- if (!pmd_huge_pte(mm, pmdp))
- INIT_LIST_HEAD(&pgtable->lru);
- else
- list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
- pmd_huge_pte(mm, pmdp) = pgtable;
+ llist_add(&pgtable->deposit_node, &huge_pmd_deposit_head(mm, pmdp));
}
#endif
@@ -180,12 +176,11 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
assert_spin_locked(pmd_lockptr(mm, pmdp));
+ /* only withdraw from a non empty list */
+ VM_BUG_ON(llist_empty(&huge_pmd_deposit_head(mm, pmdp)));
/* FIFO */
- pgtable = pmd_huge_pte(mm, pmdp);
- pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru,
- struct page, lru);
- if (pmd_huge_pte(mm, pmdp))
- list_del(&pgtable->lru);
+ pgtable = llist_entry(llist_del_first(&huge_pmd_deposit_head(mm, pmdp)),
+ struct page, deposit_node);
return pgtable;
}
#endif
--
2.28.0
next prev parent reply other threads:[~2020-09-28 17:55 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 ` Zi Yan [this message]
2020-09-28 19:34 ` [RFC PATCH v2 03/30] mm: thp: use single linked list for THP page table page deposit Matthew Wilcox
2020-09-28 20:34 ` Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 04/30] mm: add new helper functions to allocate one PMD page with 512 PTE pages Zi Yan
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=20200928175428.4110504-4-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).