From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>,
Hugh Dickins <hughd@google.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>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH 02/19] thp: cluster split_huge_page* code together
Date: Wed, 5 Nov 2014 16:49:37 +0200 [thread overview]
Message-ID: <1415198994-15252-3-git-send-email-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <1415198994-15252-1-git-send-email-kirill.shutemov@linux.intel.com>
Rearrange code in mm/huge_memory.c to make future changes somewhat
easier.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
mm/huge_memory.c | 223 +++++++++++++++++++++++++++----------------------------
1 file changed, 111 insertions(+), 112 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8efe27b86370..52973809777f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1600,6 +1600,117 @@ unlock:
return NULL;
}
+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;
+
+ pmdp_clear_flush(vma, haddr, pmd);
+ /* leave pmd empty until pte is filled */
+
+ 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();
+}
+
+void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd)
+{
+ spinlock_t *ptl;
+ struct page *page;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long haddr = address & HPAGE_PMD_MASK;
+ unsigned long mmun_start; /* For mmu_notifiers */
+ unsigned long mmun_end; /* For mmu_notifiers */
+
+ BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE);
+
+ mmun_start = haddr;
+ mmun_end = haddr + HPAGE_PMD_SIZE;
+again:
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+ ptl = pmd_lock(mm, pmd);
+ if (unlikely(!pmd_trans_huge(*pmd))) {
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+ return;
+ }
+ if (is_huge_zero_pmd(*pmd)) {
+ __split_huge_zero_page_pmd(vma, haddr, pmd);
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+ return;
+ }
+ page = pmd_page(*pmd);
+ VM_BUG_ON_PAGE(!page_count(page), page);
+ get_page(page);
+ spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+
+ split_huge_page(page);
+
+ put_page(page);
+
+ /*
+ * We don't always have down_write of mmap_sem here: a racing
+ * do_huge_pmd_wp_page() might have copied-on-write to another
+ * huge page before our split_huge_page() got the anon_vma lock.
+ */
+ if (unlikely(pmd_trans_huge(*pmd)))
+ goto again;
+}
+
+void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
+ pmd_t *pmd)
+{
+ struct vm_area_struct *vma;
+
+ vma = find_vma(mm, address);
+ BUG_ON(vma == NULL);
+ split_huge_page_pmd(vma, address, pmd);
+}
+
+static void split_huge_page_address(struct mm_struct *mm,
+ unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
+
+ pgd = pgd_offset(mm, address);
+ if (!pgd_present(*pgd))
+ return;
+
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return;
+
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
+ return;
+ /*
+ * Caller holds the mmap_sem write mode, so a huge pmd cannot
+ * materialize from under us.
+ */
+ split_huge_page_pmd_mm(mm, address, pmd);
+}
static int __split_huge_page_splitting(struct page *page,
struct vm_area_struct *vma,
unsigned long address)
@@ -2808,118 +2919,6 @@ 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;
-
- pmdp_clear_flush(vma, haddr, pmd);
- /* leave pmd empty until pte is filled */
-
- 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();
-}
-
-void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
- pmd_t *pmd)
-{
- spinlock_t *ptl;
- struct page *page;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long haddr = address & HPAGE_PMD_MASK;
- unsigned long mmun_start; /* For mmu_notifiers */
- unsigned long mmun_end; /* For mmu_notifiers */
-
- BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE);
-
- mmun_start = haddr;
- mmun_end = haddr + HPAGE_PMD_SIZE;
-again:
- mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
- ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_trans_huge(*pmd))) {
- spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- return;
- }
- if (is_huge_zero_pmd(*pmd)) {
- __split_huge_zero_page_pmd(vma, haddr, pmd);
- spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- return;
- }
- page = pmd_page(*pmd);
- VM_BUG_ON_PAGE(!page_count(page), page);
- get_page(page);
- spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-
- split_huge_page(page);
-
- put_page(page);
-
- /*
- * We don't always have down_write of mmap_sem here: a racing
- * do_huge_pmd_wp_page() might have copied-on-write to another
- * huge page before our split_huge_page() got the anon_vma lock.
- */
- if (unlikely(pmd_trans_huge(*pmd)))
- goto again;
-}
-
-void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd)
-{
- struct vm_area_struct *vma;
-
- vma = find_vma(mm, address);
- BUG_ON(vma == NULL);
- split_huge_page_pmd(vma, address, pmd);
-}
-
-static void split_huge_page_address(struct mm_struct *mm,
- unsigned long address)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
-
- VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
-
- pgd = pgd_offset(mm, address);
- if (!pgd_present(*pgd))
- return;
-
- pud = pud_offset(pgd, address);
- if (!pud_present(*pud))
- return;
-
- pmd = pmd_offset(pud, address);
- if (!pmd_present(*pmd))
- return;
- /*
- * Caller holds the mmap_sem write mode, so a huge pmd cannot
- * materialize from under us.
- */
- split_huge_page_pmd_mm(mm, address, pmd);
-}
-
void __vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
--
2.1.1
--
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:[~2014-11-05 14:50 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-05 14:49 [PATCHv2 RFC 00/19] THP refcounting redesign Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 01/19] mm, thp: drop FOLL_SPLIT Kirill A. Shutemov
2014-11-25 3:01 ` Naoya Horiguchi
2014-11-25 14:04 ` Kirill A. Shutemov
2014-11-05 14:49 ` Kirill A. Shutemov [this message]
2014-11-05 14:49 ` [PATCH 03/19] mm: change PageAnon() to work on tail pages Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 04/19] mm: avoid PG_locked " Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 05/19] rmap: add argument to charge compound page Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 06/19] mm: store mapcount for compound page separate Kirill A. Shutemov
2014-11-18 8:43 ` Naoya Horiguchi
2014-11-18 9:58 ` Kirill A. Shutemov
2014-11-18 23:41 ` Naoya Horiguchi
2014-11-19 0:54 ` Kirill A. Shutemov
2014-11-21 6:41 ` Aneesh Kumar K.V
2014-11-21 11:47 ` Kirill A. Shutemov
2014-11-19 10:51 ` Jerome Marchand
2014-11-19 13:00 ` Kirill A. Shutemov
2014-11-19 13:15 ` Jerome Marchand
2014-11-20 20:06 ` Christoph Lameter
2014-11-21 12:01 ` Kirill A. Shutemov
2014-11-21 6:12 ` Aneesh Kumar K.V
2014-11-21 12:02 ` Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 07/19] mm, thp: adjust conditions when we can reuse the page on WP fault Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 08/19] mm: prepare migration code for new THP refcounting Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 09/19] thp: rename split_huge_page_pmd() to split_huge_pmd() Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 10/19] thp: PMD splitting without splitting compound page Kirill A. Shutemov
2014-11-19 6:57 ` Naoya Horiguchi
2014-11-19 13:02 ` Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 11/19] mm, vmstats: new THP splitting event Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 12/19] thp: implement new split_huge_page() Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 13/19] mm, thp: remove infrastructure for handling splitting PMDs Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 14/19] x86, thp: remove " Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 15/19] futex, thp: remove special case for THP in get_futex_key Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 16/19] thp: update documentation Kirill A. Shutemov
2014-11-19 8:07 ` Naoya Horiguchi
2014-11-19 13:11 ` Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 17/19] mlock, thp: HACK: split all pages in VM_LOCKED vma Kirill A. Shutemov
2014-11-19 9:02 ` Naoya Horiguchi
2014-11-19 13:08 ` Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 18/19] tho, mm: use migration entries to freeze page counts on split Kirill A. Shutemov
2014-11-05 14:49 ` [PATCH 19/19] mm, thp: remove compound_lock 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=1415198994-15252-3-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=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=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).