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

From: Timur Tabi
Date: Sun Apr 24 2005 - 09:26:42 EST

Andrew Morton wrote:

If your theory is correct then it should be able to demonstrate this
problem without any special hardware at all: pin some user memory, then
generate memory pressure then check the contents of those pinned pages.

I tried that, but I couldn't get it to fail. But that was a while ago, and I've learned a few things since then, so I'll try again.

But if, for the DMA transfer, you're using the array of page*'s which were
originally obtained from get_user_pages() then it's rather hard to see how
the kernel could alter the page's contents.

Then again, if mlock() fixes it then something's up. Very odd.

With mlock(), we don't need to use get_user_pages() at all. Arjan tells me the only time an mlocked page can move is with hot (un)plug of memory, but that isn't supported on the systems that we support. We actually prefer mlock() over get_user_pages(), because if the process dies, the locks automatically go away too.

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at