Re: [PATCH][RFC][0/4] InfiniBand userspace verbs implementation

[Timur Tabi]

Arjan van de Ven wrote:

> you just said that you didn't care that it got munlock'd. So you don't
> care that it gets freed either. And then reused.

Well, I can live with the app being able to call munlock(), because the apps that our 
customers use don't call munlock().  What I can't live with is a bug in the kernel that 
causes pinned pages to be swapped or moved.

Obviously, I would rather call get_user_pages() instead of mlock(), but I can't, because 
get_user_pages doesn't work.  The page doesn't stay pinned at the physical address, but it 
does if I call mlock() and get_user_pages().

Actually, in our tests, calling mlock() appears to be good enough, but I'll update our 
code to call get_user_pages() as well.

--
Timur Tabi
Staff Software Engineer
timur.tabi@xxxxxxxxxxx
-
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/