From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>, Mel Gorman <mgorman@suse.de>,
Rik van Riel <riel@redhat.com>, Vlastimil Babka <vbabka@suse.cz>,
Christoph Lameter <cl@gentwo.org>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
Steve Capper <steve.capper@linaro.org>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@suse.cz>,
Jerome Marchand <jmarchan@redhat.com>,
Sasha Levin <sasha.levin@oracle.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv12 29/37] thp: implement split_huge_pmd()
Date: Tue, 6 Oct 2015 18:23:56 +0300 [thread overview]
Message-ID: <1444145044-72349-30-git-send-email-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <1444145044-72349-1-git-send-email-kirill.shutemov@linux.intel.com>
Original split_huge_page() combined two operations: splitting PMDs into
tables of PTEs and splitting underlying compound page. This patch
implements split_huge_pmd() which split given PMD without splitting
other PMDs this page mapped with or underlying compound page.
Without tail page refcounting, implementation of split_huge_pmd() is
pretty straight-forward.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
---
include/linux/huge_mm.h | 11 ++++-
mm/huge_memory.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 134 insertions(+), 1 deletion(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b82c0c2a96f6..60b5448bf37d 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -96,7 +96,16 @@ extern unsigned long transparent_hugepage_flags;
#define split_huge_page_to_list(page, list) BUILD_BUG()
#define split_huge_page(page) BUILD_BUG()
-#define split_huge_pmd(__vma, __pmd, __address) BUILD_BUG()
+
+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address);
+
+#define split_huge_pmd(__vma, __pmd, __address) \
+ do { \
+ pmd_t *____pmd = (__pmd); \
+ if (pmd_trans_huge(*____pmd)) \
+ __split_huge_pmd(__vma, __pmd, __address); \
+ } while (0)
#if HPAGE_PMD_ORDER >= MAX_ORDER
#error "hugepages can't be allocated by the buddy allocator"
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a5da7807985e..d2a86df4dd00 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2777,6 +2777,130 @@ static int khugepaged(void *none)
return 0;
}
+static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
+ unsigned long haddr, pmd_t *pmd)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pgtable_t pgtable;
+ pmd_t _pmd;
+ int i;
+
+ /* leave pmd empty until pte is filled */
+ pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+ pmd_populate(mm, &_pmd, pgtable);
+
+ for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ pte_t *pte, entry;
+ entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
+ entry = pte_mkspecial(entry);
+ pte = pte_offset_map(&_pmd, haddr);
+ VM_BUG_ON(!pte_none(*pte));
+ set_pte_at(mm, haddr, pte, entry);
+ pte_unmap(pte);
+ }
+ smp_wmb(); /* make pte visible before pmd */
+ pmd_populate(mm, pmd, pgtable);
+ put_huge_zero_page();
+}
+
+static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long haddr)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct page *page;
+ pgtable_t pgtable;
+ pmd_t _pmd;
+ bool young, write;
+ int i;
+
+ VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
+ VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+ VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
+ VM_BUG_ON(!pmd_trans_huge(*pmd));
+
+ count_vm_event(THP_SPLIT_PMD);
+
+ if (vma_is_dax(vma)) {
+ pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+ if (is_huge_zero_pmd(_pmd))
+ put_huge_zero_page();
+ return;
+ } else if (is_huge_zero_pmd(*pmd)) {
+ return __split_huge_zero_page_pmd(vma, haddr, pmd);
+ }
+
+ page = pmd_page(*pmd);
+ VM_BUG_ON_PAGE(!page_count(page), page);
+ atomic_add(HPAGE_PMD_NR - 1, &page->_count);
+ write = pmd_write(*pmd);
+ young = pmd_young(*pmd);
+
+ /* leave pmd empty until pte is filled */
+ pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+ pmd_populate(mm, &_pmd, pgtable);
+
+ for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ pte_t entry, *pte;
+ /*
+ * Note that NUMA hinting access restrictions are not
+ * transferred to avoid any possibility of altering
+ * permissions across VMAs.
+ */
+ entry = mk_pte(page + i, vma->vm_page_prot);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ if (!write)
+ entry = pte_wrprotect(entry);
+ if (!young)
+ entry = pte_mkold(entry);
+ pte = pte_offset_map(&_pmd, haddr);
+ BUG_ON(!pte_none(*pte));
+ set_pte_at(mm, haddr, pte, entry);
+ atomic_inc(&page[i]._mapcount);
+ pte_unmap(pte);
+ }
+
+ /*
+ * Set PG_double_map before dropping compound_mapcount to avoid
+ * false-negative page_mapped().
+ */
+ if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
+ for (i = 0; i < HPAGE_PMD_NR; i++)
+ atomic_inc(&page[i]._mapcount);
+ }
+
+ if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+ /* Last compound_mapcount is gone. */
+ __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+ if (TestClearPageDoubleMap(page)) {
+ /* No need in mapcount reference anymore */
+ for (i = 0; i < HPAGE_PMD_NR; i++)
+ atomic_dec(&page[i]._mapcount);
+ }
+ }
+
+ smp_wmb(); /* make pte visible before pmd */
+ pmd_populate(mm, pmd, pgtable);
+}
+
+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address)
+{
+ spinlock_t *ptl;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long haddr = address & HPAGE_PMD_MASK;
+
+ mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
+ ptl = pmd_lock(mm, pmd);
+ if (likely(pmd_trans_huge(*pmd)))
+ __split_huge_pmd_locked(vma, pmd, haddr);
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
+}
+
static void split_huge_pmd_address(struct vm_area_struct *vma,
unsigned long address)
{
--
2.5.3
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-10-06 15:30 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-06 15:23 [PATCHv12 00/37] THP refcounting redesign Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 01/37] mm, proc: adjust PSS calculation Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 02/37] rmap: add argument to charge compound page Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 03/37] memcg: adjust to support new THP refcounting Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 04/37] mm, thp: adjust conditions when we can reuse the page on WP fault Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 05/37] mm: adjust FOLL_SPLIT for new refcounting Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 06/37] mm: handle PTE-mapped tail pages in gerneric fast gup implementaiton Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 07/37] thp, mlock: do not allow huge pages in mlocked area Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 08/37] khugepaged: ignore pmd tables with THP mapped with ptes Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 09/37] thp: rename split_huge_page_pmd() to split_huge_pmd() Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 10/37] mm, vmstats: new THP splitting event Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 11/37] mm: temporally mark THP broken Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 12/37] thp: drop all split_huge_page()-related code Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 13/37] mm: drop tail page refcounting Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 14/37] futex, thp: remove special case for THP in get_futex_key Kirill A. Shutemov
2015-10-22 8:24 ` Artem Savkov
2015-10-22 9:49 ` Kirill A. Shutemov
2015-10-22 10:33 ` Artem Savkov
2015-10-06 15:23 ` [PATCHv12 15/37] ksm: prepare to new THP semantics Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 16/37] mm, thp: remove compound_lock Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 17/37] arm64, thp: remove infrastructure for handling splitting PMDs Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 18/37] arm, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 19/37] mips, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 20/37] powerpc, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 21/37] s390, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 22/37] sparc, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 23/37] tile, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 24/37] x86, " Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 25/37] mm, " Kirill A. Shutemov
2015-10-08 8:52 ` Vineet Gupta
2015-10-09 9:25 ` Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 26/37] mm: rework mapcount accounting to enable 4k mapping of THPs Kirill A. Shutemov
2015-10-27 6:18 ` Naoya Horiguchi
2015-10-27 9:30 ` Kirill A. Shutemov
2015-10-27 23:24 ` Naoya Horiguchi
2015-10-29 21:50 ` Kirill A. Shutemov
2015-10-30 8:33 ` Naoya Horiguchi
2015-10-29 8:19 ` Naoya Horiguchi
2015-10-29 21:20 ` Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 27/37] mm: differentiate page_mapped() from page_mapcount() for compound pages Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 28/37] mm, numa: skip PTE-mapped THP on numa fault Kirill A. Shutemov
2015-10-06 15:23 ` Kirill A. Shutemov [this message]
2015-10-06 15:23 ` [PATCHv12 30/37] thp: add option to setup migration entries during PMD split Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 31/37] thp, mm: split_huge_page(): caller need to lock page Kirill A. Shutemov
2015-10-06 15:23 ` [PATCHv12 32/37] thp: reintroduce split_huge_page() Kirill A. Shutemov
2015-11-18 16:24 ` Sasha Levin
2015-11-18 19:05 ` Kirill A. Shutemov
2015-11-27 4:26 ` Sasha Levin
2015-10-06 15:24 ` [PATCHv12 33/37] migrate_pages: try to split pages on qeueuing Kirill A. Shutemov
2015-10-06 15:24 ` [PATCHv12 34/37] thp: introduce deferred_split_huge_page() Kirill A. Shutemov
2016-01-21 1:22 ` Andrea Arcangeli
2016-01-21 12:09 ` [PATCH 0/3] Couple of fixes for deferred_split_huge_page() Kirill A. Shutemov
2016-01-21 12:09 ` [PATCH 1/3] thp: make split_queue per-node Kirill A. Shutemov
2016-01-21 12:09 ` [PATCH 2/3] thp: change deferred_split_count() to return number of THP in queue Kirill A. Shutemov
2016-01-22 14:31 ` Andrea Arcangeli
2016-01-22 15:20 ` Kirill A. Shutemov
2016-01-21 12:09 ` [PATCH 3/3] thp: limit number of object to scan on deferred_split_scan() Kirill A. Shutemov
2016-02-04 13:11 ` Kirill A. Shutemov
2016-01-21 22:52 ` [PATCH 0/3] Couple of fixes for deferred_split_huge_page() Andrea Arcangeli
2015-10-06 15:24 ` [PATCHv12 35/37] mm: re-enable THP Kirill A. Shutemov
2015-10-06 15:24 ` [PATCHv12 36/37] thp: update documentation Kirill A. Shutemov
2015-10-06 15:24 ` [PATCHv12 37/37] thp: allow mlocked THP again Kirill A. Shutemov
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=1444145044-72349-30-git-send-email-kirill.shutemov@linux.intel.com \
--to=kirill.shutemov@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=cl@gentwo.org \
--cc=dave.hansen@intel.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jmarchan@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.cz \
--cc=n-horiguchi@ah.jp.nec.com \
--cc=riel@redhat.com \
--cc=sasha.levin@oracle.com \
--cc=steve.capper@linaro.org \
--cc=vbabka@suse.cz \
/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).