Re: [PATCH 2/2] SHM_UNLOCK: fix Unevictable pages stranded afterswap

[KOSAKI Motohiro]

2012/1/6 Hugh Dickins <hughd@xxxxxxxxxx>:
> Commit cc39c6a9bbde "mm: account skipped entries to avoid looping in
> find_get_pages" correctly fixed an infinite loop; but left a problem
> that find_get_pages() on shmem would return 0 (appearing to callers
> to mean end of tree) when it meets a run of nr_pages swap entries.
>
> The only uses of find_get_pages() on shmem are via pagevec_lookup(),
> called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's
> scan_mapping_unevictable_pages().  The first is already commented,
> and not worth worrying about; but the second can leave pages on the
> Unevictable list after an unusual sequence of swapping and locking.
>
> Fix that by using shmem_find_get_pages_and_swap() (then ignoring
> the swap) instead of pagevec_lookup().
>
> But I don't want to contaminate vmscan.c with shmem internals, nor
> shmem.c with LRU locking.  So move scan_mapping_unevictable_pages()
> into shmem.c, renaming it shmem_unlock_mapping(); and rename
> check_move_unevictable_page() to check_move_unevictable_pages(),
> looping down an array of pages, oftentimes under the same lock.
>
> Leave out the "rotate unevictable list" block: that's a leftover
> from when this was used for /proc/sys/vm/scan_unevictable_pages,
> whose flawed handling involved looking at pages at tail of LRU.
>
> Was there significance to the sequence first ClearPageUnevictable,
> then test page_evictable, then SetPageUnevictable here?  I think
> not, we're under LRU lock, and have no barriers between those.

If I understand correctly, this is not exactly correct. Because of,
PG_mlocked operation is not protected by LRU lock. So, I think we
have three choice.

1) check_move_unevictable_pages() aimed retry logic and put pages back
   into correct lru.
2) check_move_unevictable_pages() unconditionally move the pages into
   evictable lru, and vmacan put them back into correct lru later.
3) To protect PG_mlock operation by lru lock.


other parts looks fine to me.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/