[patch 0/4] mm: de-skew page refcount

[Nick Piggin]

The following patchset (against 2.6.16-rc1 + migrate race fixes) uses the new
atomic ops to do away with the offset page refcounting, and simplify the race
that it was designed to cover.

This allows some nice optimisations, and in the page freeing path we end up
saving 2 atomic ops including a spin_lock_irqsave in the !PageLRU case, and 1
or 2 atomic ops in the PageLRU case.

Andrew's previous feedback has been incorporated (less BUG_ONs in fastpaths
and more detail in changelogs).

Anyone spot any holes or races?

Thanks,
Nick
-
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/