Re: [PATCH 1/2] SHM_UNLOCK: fix long unpreemptible section

[KOSAKI Motohiro]

(1/6/12 4:10 PM), Hugh Dickins wrote:
> scan_mapping_unevictable_pages() is used to make SysV SHM_LOCKed pages
> evictable again once the shared memory is unlocked.  It does this with
> pagevec_lookup()s across the whole object (which might occupy most of
> memory), and takes 300ms to unlock 7GB here.  A cond_resched() every
> PAGEVEC_SIZE pages would be good.
>
> However, KOSAKI-san points out that this is called under shmem.c's
> info->lock, and it's also under shm.c's shm_lock(), both spinlocks.
> There is no strong reason for that: we need to take these pages off
> the unevictable list soonish, but those locks are not required for it.
>
> So move the call to scan_mapping_unevictable_pages() from shmem.c's
> unlock handling up to shm.c's unlock handling.  Remove the recently
> added barrier, not needed now we have spin_unlock() before the scan.
>
> Use get_file(), with subsequent fput(), to make sure we have a
> reference to mapping throughout scan_mapping_unevictable_pages():
> that's something that was previously guaranteed by the shm_lock().
>
> Remove shmctl's lru_add_drain_all(): we don't fault in pages at
> SHM_LOCK time, and we lazily discover them to be Unevictable later,
> so it serves no purpose for SHM_LOCK; and serves no purpose for
> SHM_UNLOCK, since pages still on pagevec are not marked Unevictable.
>
> The original code avoided redundant rescans by checking VM_LOCKED
> flag at its level: now avoid them by checking shp's SHM_LOCKED.
>
> The original code called scan_mapping_unevictable_pages() on a
> locked area at shm_destroy() time: perhaps we once had accounting
> cross-checks which required that, but not now, so skip the overhead
> and just let inode eviction deal with them.
>
> Put check_move_unevictable_page() and scan_mapping_unevictable_pages()
> under CONFIG_SHMEM (with stub for the TINY case when ramfs is used),
> more as comment than to save space; comment them used for SHM_UNLOCK.
>
> Signed-off-by: Hugh Dickins<hughd@xxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx [back to 2.6.32 but will need respins]

Looks completely make sense.
	Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>

--
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/