linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dave Hansen <dave@sr71.net>
To: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org, kirill.shutemov@linux.intel.com,
	Dave Hansen <dave@sr71.net>
Subject: [PATCH 09/10] mm: pagewalk: use new locked walker for /proc/pid/smaps
Date: Mon, 02 Jun 2014 14:36:56 -0700	[thread overview]
Message-ID: <20140602213656.7AE8FDC7@viggo.jf.intel.com> (raw)
In-Reply-To: <20140602213644.925A26D0@viggo.jf.intel.com>


From: Dave Hansen <dave.hansen@linux.intel.com>

The diffstat tells the story here.  Using the new walker function
greatly simplifies the code.  One side-effect here is that we'll
call cond_resched() more often than we did before.  It used to be
called once per pte page, but now it's called on every pte.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
---

 b/fs/proc/task_mmu.c |   27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff -puN fs/proc/task_mmu.c~mm-pagewalk-use-locked-walker-smaps fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c~mm-pagewalk-use-locked-walker-smaps	2014-06-02 14:20:21.247895019 -0700
+++ b/fs/proc/task_mmu.c	2014-06-02 14:20:21.251895198 -0700
@@ -490,32 +490,15 @@ static void smaps_pte_entry(pte_t ptent,
 	}
 }
 
-static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+static int smaps_single_locked(pte_t *pte, unsigned long addr, unsigned long size,
 			   struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = walk->vma;
-	pte_t *pte;
-	spinlock_t *ptl;
-
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
-		spin_unlock(ptl);
+
+	if (size == HPAGE_PMD_SIZE)
 		mss->anonymous_thp += HPAGE_PMD_SIZE;
-		return 0;
-	}
 
-	if (pmd_trans_unstable(pmd))
-		return 0;
-	/*
-	 * The mmap_sem held all the way back in m_start() is what
-	 * keeps khugepaged out of here and from collapsing things
-	 * in here.
-	 */
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE)
-		smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
-	pte_unmap_unlock(pte - 1, ptl);
+	smaps_pte_entry(*pte, addr, size, walk);
 	cond_resched();
 	return 0;
 }
@@ -581,7 +564,7 @@ static int show_smap(struct seq_file *m,
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
-		.pmd_entry = smaps_pte_range,
+		.locked_single_entry = smaps_single_locked,
 		.mm = vma->vm_mm,
 		.private = &mss,
 	};
_

--
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>

  parent reply	other threads:[~2014-06-02 21:36 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-02 21:36 [PATCH 00/10] mm: pagewalk: huge page cleanups and VMA passing Dave Hansen
2014-06-02 21:36 ` [PATCH 01/10] mm: pagewalk: consolidate vma->vm_start checks Dave Hansen
2014-06-02 21:36 ` [PATCH 02/10] mm: pagewalk: always skip hugetlbfs except when explicitly handled Dave Hansen
2014-06-02 21:36 ` [PATCH 03/10] mm: pagewalk: have generic code keep track of VMA Dave Hansen
2014-06-02 21:36 ` [PATCH 04/10] mm: pagewalk: add page walker for mincore() Dave Hansen
2014-06-02 21:36 ` [PATCH 05/10] mm: mincore: clean up hugetlbfs handling (part 1) Dave Hansen
2014-06-02 21:36 ` [PATCH 06/10] mm: mincore: clean up hugetlbfs handler (part 2) Dave Hansen
2014-06-02 21:36 ` [PATCH 07/10] mm: pagewalk: kill check for hugetlbfs inside /proc pagemap code Dave Hansen
2014-06-02 21:36 ` [PATCH 08/10] mm: pagewalk: add locked pte walker Dave Hansen
2014-06-02 21:36 ` Dave Hansen [this message]
2014-06-02 21:36 ` [PATCH 10/10] mm: pagewalk: use locked walker for /proc/pid/numa_maps Dave Hansen
2014-06-02 21:52 ` [PATCH 00/10] mm: pagewalk: huge page cleanups and VMA passing Naoya Horiguchi
     [not found] ` <1401745925-l651h3s9@n-horiguchi@ah.jp.nec.com>
2014-06-02 21:53   ` Dave Hansen
2014-06-03  6:18     ` [PATCH -mm] mincore: apply page table walker on do_mincore() (Re: [PATCH 00/10] mm: pagewalk: huge page cleanups and VMA passing) Naoya Horiguchi
     [not found]     ` <1401776292-dn0fof8e@n-horiguchi@ah.jp.nec.com>
2014-06-03 15:55       ` Dave Hansen
2014-06-03 20:01         ` Naoya Horiguchi
2014-06-03 20:08           ` Naoya Horiguchi
     [not found]         ` <1401825676-8py0r32h@n-horiguchi@ah.jp.nec.com>
2014-06-03 20:33           ` Dave Hansen
2014-06-03 15:59       ` Dave Hansen
2014-06-03 16:22         ` Naoya Horiguchi

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=20140602213656.7AE8FDC7@viggo.jf.intel.com \
    --to=dave@sr71.net \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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).