[v2,0/7] mm/autonuma: replace savedwrite infrastructure

Message

David Hildenbrand Nov. 8, 2022, 5:46 p.m. UTC

This series is based on mm-unstable.

As discussed in my talk at LPC, we can reuse the same mechanism for
deciding whether to map a pte writable when upgrading permissions via
mprotect() -- e.g., PROT_READ -> PROT_READ|PROT_WRITE -- to replace the
savedwrite infrastructure used for NUMA hinting faults (e.g., PROT_NONE
-> PROT_READ|PROT_WRITE).

Instead of maintaining previous write permissions for a pte/pmd, we
re-determine if the pte/pmd can be writable. The big benefit is that we
have a common logic for deciding whether we can map a pte/pmd writable on
protection changes.

For private mappings, there should be no difference -- from
what I understand, that is what autonuma benchmarks care about.

I ran autonumabench for v1 on a system with 2 NUMA nodes, 96 GiB each via:
	perf stat --null --repeat 10
The numa01 benchmark is quite noisy in my environment and I failed to
reduce the noise so far.

numa01:
	mm-unstable:   146.88 +- 6.54 seconds time elapsed  ( +-  4.45% )
	mm-unstable++: 147.45 +- 13.39 seconds time elapsed  ( +-  9.08% )

numa02:
	mm-unstable:   16.0300 +- 0.0624 seconds time elapsed  ( +-  0.39% )
	mm-unstable++: 16.1281 +- 0.0945 seconds time elapsed  ( +-  0.59% )

It is worth noting that for shared writable mappings that require
writenotify, we will only avoid write faults if the pte/pmd is dirty
(inherited from the older mprotect logic). If we ever care about optimizing
that further, we'd need a different mechanism to identify whether the FS
still needs to get notified on the next write access.

In any case, such an optimiztion will then not be autonuma-specific,
but mprotect() permission upgrades would similarly benefit from it.

Cc: Linus Torvalds <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Dave Chinner <[e-mail]>
Cc: Nadav Amit <[e-mail]>
Cc: Peter Xu <[e-mail]>
Cc: Andrea Arcangeli <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Mike Rapoport <[e-mail]>
Cc: Anshuman Khandual <[e-mail]>

v1 -> v2:
* "mm/mprotect: factor out check whether manual PTE write upgrades are
   required"
 -> Added
* "mm/autonuma: use can_change_(pte|pmd)_writable() to replace savedwrite"
 -> Simplify and don't opimize for failed migration
 -> Update patch description

RFC -> v1:
* "mm/mprotect: allow clean exclusive anon pages to be writable"
 -> Move comment change to patch #2
* "mm/mprotect: minor can_change_pte_writable() cleanups"
 -> Adjust comments
* "mm/huge_memory: try avoiding write faults when changing PMD protection"
 -> Fix wrong check
* "selftests/vm: anon_cow: add mprotect() optimiation tests"
 -> Add basic tests for the mprotect() optimization

David Hildenbrand (6):
  mm/mprotect: minor can_change_pte_writable() cleanups
  mm/huge_memory: try avoiding write faults when changing PMD protection
  mm/mprotect: factor out check whether manual PTE write upgrades are
    required
  mm/autonuma: use can_change_(pte|pmd)_writable() to replace savedwrite
  mm: remove unused savedwrite infrastructure
  selftests/vm: anon_cow: add mprotect() optimization tests

Nadav Amit (1):
  mm/mprotect: allow clean exclusive anon pages to be writable

 arch/powerpc/include/asm/book3s/64/pgtable.h | 80 +-------------------
 arch/powerpc/kvm/book3s_hv_rm_mmu.c          |  2 +-
 include/linux/mm.h                           | 18 ++++-
 include/linux/pgtable.h                      | 24 ------
 mm/debug_vm_pgtable.c                        | 32 --------
 mm/huge_memory.c                             | 64 ++++++++++++----
 mm/ksm.c                                     |  9 +--
 mm/memory.c                                  | 16 +++-
 mm/mprotect.c                                | 50 ++++++------
 tools/testing/selftests/vm/anon_cow.c        | 49 +++++++++++-
 10 files changed, 158 insertions(+), 186 deletions(-)