Re: [PATCH 00/18] mm: memcontrol: charge swapin pages on instantiation

[Alex Shi]

在 2020/4/21 上午6:11, Johannes Weiner 写道:
> This patch series reworks memcg to charge swapin pages directly at
> swapin time, rather than at fault time, which may be much later, or
> not happen at all.
> 
> The delayed charging scheme we have right now causes problems:
> 
> - Alex's per-cgroup lru_lock patches rely on pages that have been
>   isolated from the LRU to have a stable page->mem_cgroup; otherwise
>   the lock may change underneath him. Swapcache pages are charged only
>   after they are added to the LRU, and charging doesn't follow the LRU
>   isolation protocol.

Hi Johannes,

Thanks a lot! 
It looks all fine for me. I will rebase per cgroup lru_lock on this.
Thanks!

Alex

> 
> - Joonsoo's anon workingset patches need a suitable LRU at the time
>   the page enters the swap cache and displaces the non-resident
>   info. But the correct LRU is only available after charging.
> 
> - It's a containment hole / DoS vector. Users can trigger arbitrarily
>   large swap readahead using MADV_WILLNEED. The memory is never
>   charged unless somebody actually touches it.
> 
> - It complicates the page->mem_cgroup stabilization rules
> 
> In order to charge pages directly at swapin time, the memcg code base
> needs to be prepared, and several overdue cleanups become a necessity:
> 
> To charge pages at swapin time, we need to always have cgroup
> ownership tracking of swap records. We also cannot rely on
> page->mapping to tell apart page types at charge time, because that's
> only set up during a page fault.
> 
> To eliminate the page->mapping dependency, memcg needs to ditch its
> private page type counters (MEMCG_CACHE, MEMCG_RSS, NR_SHMEM) in favor
> of the generic vmstat counters and accounting sites, such as
> NR_FILE_PAGES, NR_ANON_MAPPED etc.
> 
> To switch to generic vmstat counters, the charge sequence must be
> adjusted such that page->mem_cgroup is set up by the time these
> counters are modified.
> 
> The series is structured as follows:
> 
> 1. Bug fixes
> 2. Decoupling charging from rmap
> 3. Swap controller integration into memcg
> 4. Direct swapin charging
> 
> The patches survive a simple swapout->swapin test inside a virtual
> machine. Because this is blocking two major patch sets, I'm sending
> these out early and will continue testing in parallel to the review.
> 
>  include/linux/memcontrol.h |  53 +----
>  include/linux/mm.h         |   4 +-
>  include/linux/swap.h       |   6 +-
>  init/Kconfig               |  17 +-
>  kernel/events/uprobes.c    |  10 +-
>  mm/filemap.c               |  43 ++---
>  mm/huge_memory.c           |  45 ++---
>  mm/khugepaged.c            |  25 +--
>  mm/memcontrol.c            | 448 ++++++++++++++-----------------------------
>  mm/memory.c                |  51 ++---
>  mm/migrate.c               |  20 +-
>  mm/rmap.c                  |  53 +++--
>  mm/shmem.c                 | 117 +++++------
>  mm/swap_cgroup.c           |   6 -
>  mm/swap_state.c            |  89 +++++----
>  mm/swapfile.c              |  25 +--
>  mm/userfaultfd.c           |   5 +-
>  17 files changed, 367 insertions(+), 650 deletions(-)
>