linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Song Liu <songliubraving@fb.com>
To: <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
	<akpm@linux-foundation.org>
Cc: <matthew.wilcox@oracle.com>, <kirill.shutemov@linux.intel.com>,
	<oleg@redhat.com>, <kernel-team@fb.com>,
	<william.kucharski@oracle.com>, <srikar@linux.vnet.ibm.com>,
	Song Liu <songliubraving@fb.com>
Subject: [PATCH v12 0/6] THP aware uprobe
Date: Wed, 7 Aug 2019 16:37:23 -0700	[thread overview]
Message-ID: <20190807233729.3899352-1-songliubraving@fb.com> (raw)

This set makes uprobe aware of THPs.

Currently, when uprobe is attached to text on THP, the page is split by
FOLL_SPLIT. As a result, uprobe eliminates the performance benefit of THP.

This set makes uprobe THP-aware. Instead of FOLL_SPLIT, we introduces
FOLL_SPLIT_PMD, which only split PMD for uprobe.

After all uprobes within the THP are removed, the PTE-mapped pages are
regrouped as huge PMD.

This set (plus a few THP patches) is also available at

   https://github.com/liu-song-6/linux/tree/uprobe-thp


Changes v11.4 => v12
1. Combine the first 4 patches with the rest 2 patches again in the same
   set.
2. Improve checks for the page in collapse_pte_mapped_thp() (Oleg).
3. Fixed build error w/o CONFIG_SHMEM.

v11.1 to v11.4 are only the last two patches.

Changes v11.3 => v11.4:
1. Simplify locking for pte_mapped_thp (Oleg).
2. Improve checks for the page in collapse_pte_mapped_thp() (Oleg).
3. Move HPAGE_PMD_MASK to collapse_pte_mapped_thp() (kbuild test robot).

Changes v11.2 => v11.3:
1. Update vma/pmd check in collapse_pte_mapped_thp() (Oleg).
2. Add Acked-by from Kirill

Changes v11.1 => v11.2:
1. Call collapse_pte_mapped_thp() directly from uprobe_write_opcode();
2. Add VM_BUG_ON() for addr alignment in khugepaged_add_pte_mapped_thp()
   and collapse_pte_mapped_thp().

Changes v9 => v10:
1. 2/4 incorporate suggestion by Oleg Nesterov.
2. Reword change log of 4/4.

Changes v8 => v9:
1. To replace with orig_page, only unmap old_page. Let the orig_page fault
   in (Oleg Nesterov).

Changes v7 => v8:
1. check PageUptodate() for orig_page (Oleg Nesterov).

Changes v6 => v7:
1. Include Acked-by from Kirill A. Shutemov for the first 4 patches;
2. Keep only the first 4 patches (while I working on improving the last 2).

Changes v5 => v6:
1. Enable khugepaged to collapse pmd for pte-mapped THP
   (Kirill A. Shutemov).
2. uprobe asks khuagepaged to collaspe pmd. (Kirill A. Shutemov)

Note: Theast two patches in v6 the set apply _after_ v7 of set "Enable THP
      for text section of non-shmem files"

Changes v4 => v5:
1. Propagate pte_alloc() error out of follow_pmd_mask().

Changes since v3:
1. Simplify FOLL_SPLIT_PMD case in follow_pmd_mask(), (Kirill A. Shutemov)
2. Fix try_collapse_huge_pmd() to match change in follow_pmd_mask().

Changes since v2:
1. For FOLL_SPLIT_PMD, populated the page table in follow_pmd_mask().
2. Simplify logic in uprobe_write_opcode. (Oleg Nesterov)
3. Fix page refcount handling with FOLL_SPLIT_PMD.
4. Much more testing, together with THP on ext4 and btrfs (sending in
   separate set).
5. Rebased.

Changes since v1:
1. introduces FOLL_SPLIT_PMD, instead of modifying split_huge_pmd*();
2. reuse pages_identical() from ksm.c;
3. rewrite most of try_collapse_huge_pmd().

Song Liu (6):
  mm: move memcmp_pages() and pages_identical()
  uprobe: use original page when all uprobes are removed
  mm, thp: introduce FOLL_SPLIT_PMD
  uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT
  khugepaged: enable collapse pmd for pte-mapped THP
  uprobe: collapse THP pmd after removing all uprobes

 include/linux/khugepaged.h |  12 ++++
 include/linux/mm.h         |   8 +++
 kernel/events/uprobes.c    |  81 ++++++++++++++++-----
 mm/gup.c                   |   8 ++-
 mm/khugepaged.c            | 140 ++++++++++++++++++++++++++++++++++++-
 mm/ksm.c                   |  18 -----
 mm/util.c                  |  13 ++++
 7 files changed, 240 insertions(+), 40 deletions(-)

--
2.17.1


             reply	other threads:[~2019-08-07 23:37 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-07 23:37 Song Liu [this message]
2019-08-07 23:37 ` [PATCH v12 1/6] mm: move memcmp_pages() and pages_identical() Song Liu
2019-08-07 23:37 ` [PATCH v12 2/6] uprobe: use original page when all uprobes are removed Song Liu
2019-08-07 23:37 ` [PATCH v12 3/6] mm, thp: introduce FOLL_SPLIT_PMD Song Liu
2019-08-08 16:37   ` Oleg Nesterov
2019-08-08 17:16     ` Song Liu
2019-08-09 16:35       ` Oleg Nesterov
2019-08-09 16:50         ` Song Liu
2019-08-07 23:37 ` [PATCH v12 4/6] uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT Song Liu
2019-08-07 23:37 ` [PATCH v12 5/6] khugepaged: enable collapse pmd for pte-mapped THP Song Liu
2019-08-08 16:33   ` Oleg Nesterov
2019-08-08 17:05     ` Song Liu
2019-08-09 15:24       ` Oleg Nesterov
2019-08-09 16:30         ` Song Liu
2019-08-09 18:01           ` Song Liu
2019-08-12 12:11             ` Kirill A. Shutemov
2019-08-12 13:22               ` Oleg Nesterov
2019-08-12 14:40                 ` Kirill A. Shutemov
2019-08-12 21:04                   ` Song Liu
2019-08-13 14:44                     ` Song Liu
2019-08-15 10:16                       ` Oleg Nesterov
2019-08-15 16:27                         ` Song Liu
2019-08-13 13:30                   ` Oleg Nesterov
2019-08-13 14:05                     ` Oleg Nesterov
2019-08-13 15:05                       ` Kirill A. Shutemov
2019-08-13 16:24                         ` Oleg Nesterov
2019-08-16 14:54                           ` Kirill A. Shutemov
2019-08-12 13:06             ` Oleg Nesterov
2019-08-12 14:36               ` Song Liu
2019-08-07 23:37 ` [PATCH v12 6/6] uprobe: collapse THP pmd after removing all uprobes Song Liu

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=20190807233729.3899352-1-songliubraving@fb.com \
    --to=songliubraving@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=kernel-team@fb.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=matthew.wilcox@oracle.com \
    --cc=oleg@redhat.com \
    --cc=srikar@linux.vnet.ibm.com \
    --cc=william.kucharski@oracle.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