>So what? One wakes up, finds the same pointer it stashed away ==> Installs
>new page (changing pointer) via short way. Second wakes up, finds pointer
>changed ==> goes long way to do its job.
>
>Or am I overlooking something stupid?
What if the page that was at the start of the chain gets removed, the page
that we are allocing gets inserted and then the same page that gets
released before will be inserted again?
page0 -> page1
remove page 0
page1
anoher piece of code need ourpage and go to alloc it -> insert ourpage
ourpage -> page1
insert page0 again
page0 -> ourpage -> page1
Now we have alloced memory succesfully for ourpage and we are going to
insert it. page0 is still here and if we don't take the slow way we'll add
it twice:
ourpage -> page0 -> ourpage -> page1
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/