Skip to content

ksm: support tracking KSM-placed zero-pages

[email protected] linux-mm lkml 8 versions – Applied

Status from this message: [merged mm-stable] selftest-add-a-testcase-of-ksm-zero-pages.patch removed from -mm tree

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v10 Latest posting 2/25 patches 0 repliesApplied 5/5
  2. v10 posting 1/25 patches 1 replySuperseded
  3. v95 patches 10 repliesSuperseded
Earlier versions · 5
VersionPostedPatchesRepliesStatus
v86 patches11 repliesSuperseded
v76 patches1 replySuperseded
v66 patches16 repliesSuperseded
v56 patches11 repliesSuperseded
v46 patches0 repliesSuperseded

Changes in v10 from the cover letter

-------
(1) Fix a compile error due to [PATCH v8 3/5] when CONFIG_KSM is not set.

(2) Rename the function 'ksm_notify_unmap_zero_page' as 'ksm_might_unmap_zero_page'.

(3) In [PATCH 5/5], we get ksm_zero_pages from its own 'mm' instead of the global system.

(4) In [PATCH 5/5], we add a subject task of testing ksm zero pages when unmerging by triggering write fault.

Patches in v10 posting 2/2 All 5 applied

#Subject and filesSizeRepliesApplied
1/5ksm: support unsharing KSM-placed zero pagesinclude/linux/ksm.h mm/ksm.c+14 -30 repliesApplied
2/5ksm: count all zero pages placed by KSMDocumentation/admin-guide/mm/ksm.rst include/linux/ksm.h mm/khugepaged.c +2 more+37 -10 repliesApplied
3/5ksm: add ksm zero pages for each processfs/proc/base.c include/linux/ksm.h include/linux/mm_types.h +3 more+17 -80 repliesApplied
4/5ksm: consider KSM-placed zeropages when calculating KSM profitDocumentation/admin-guide/mm/ksm.rst mm/ksm.c+13 -90 repliesApplied
5/5selftest: add a testcase of ksm zero pagestools/testing/selftests/mm/ksm_functional_tests.c+97 -10 repliesApplied

Reviews trailers per patch

All 5 patches have a Reviewed-by or Acked-by.

PatchDavid HildenbrandXiaokai RanYang Yang
1/5A-b R-b R-b
2/5A-b R-b R-b
3/5R-b R-b
4/5A-b
5/5A-b R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 3 reviewers.

Read the v10 thread

Cover letter [PATCH RESEND v10 0/5] ksm: support tracking KSM-placed zero-pages

From: xu xin <[email protected]>

The core idea of this patch set is to enable users to perceive the number of any pages merged by KSM, regardless of whether use_zero_page switch has been turned on, so that users can know how much free memory increase is really due to their madvise(MERGEABLE) actions. But the problem is, when enabling use_zero_pages, all empty pages will be merged with kernel zero pages instead of with each other as use_zero_pages is disabled, and then these zero-pages are no longer monitored by KSM.

The motivations to do this is seen at:
https://lore.kernel.org/lkml/[email protected]/

In one word, we hope to implement the support for KSM-placed zero pages tracking without affecting the feature of use_zero_pages, so that app developer can also benefit from knowing the actual KSM profit by getting KSM-placed zero pages to optimize applications eventually when /sys/kernel/mm/ksm/use_zero_pages is enabled.

Change log
----------
v9->v10:
-------
(1) Fix a compile error due to [PATCH v8 3/5] when CONFIG_KSM is not set.

(2) Rename the function 'ksm_notify_unmap_zero_page' as 'ksm_might_unmap_zero_page'.

(3) In [PATCH 5/5], we get ksm_zero_pages from its own 'mm' instead of the global system.

(4) In [PATCH 5/5], we add a subject task of testing ksm zero pages when unmerging by triggering write fault.

v8->v9:
------
(1) The previous [PATCH v8 4/6] is squashed into the current [PATCH v9 2/5].

(2) Improve the codes as David's suggestions.

v7->v8:
-------
(1) Since [1] which fix the bug of pte_mkdirty on sparc64 that makes pte writable, then we can remove the architechture restrictions of our features.
(2) Improve the scheme of update ksm_zero_pages: add the handling case when khugepaged replaces a shared zeropage by a THP.

[1] https://lore.kernel.org/all/[email protected]/

v6->v7:
-------
This is an all-newed version which is different from v6 which relys on KSM's rmap_item. The patch series don't rely on rmap_item but pte_dirty, so the general handling of tracking KSM-placed zero-pages is simplified a lot.

For safety, we restrict this feature only to the tested and known-working architechtures (ARM, ARM64, and X86) fow now.

xu xin (5):
ksm: support unsharing KSM-placed zero pages
ksm: count all zero pages placed by KSM
ksm: add ksm zero pages for each process
ksm: consider KSM-placed zeropages when calculating KSM profit
selftest: add a testcase of ksm zero pages

 Documentation/admin-guide/mm/ksm.rst              | 25 ++++--
 fs/proc/base.c                                    |  1 +
 include/linux/ksm.h                               | 20 +++++
 include/linux/mm_types.h                          |  9 ++-
 mm/khugepaged.c                                   |  2 +
 mm/ksm.c                                          | 28 +++++--
 mm/memory.c                                       |  5 +-
 tools/testing/selftests/mm/ksm_functional_tests.c | 98 ++++++++++++++++++++++-
 8 files changed, 172 insertions(+), 16 deletions(-)
Signature · 1 line
2.15.2