Re: [RFC PATCH 0/8] mm/madvise: support process_madvise(MADV_DONTNEED)

From: Nadav Amit
Date: Mon Sep 27 2021 - 15:12:52 EST

> On Sep 27, 2021, at 5:16 AM, Michal Hocko <mhocko@xxxxxxxx> wrote:
> On Mon 27-09-21 05:00:11, Nadav Amit wrote:
> [...]
>> The manager is notified on memory regions that it should monitor
>> (through PTRACE/LD_PRELOAD/explicit-API). It then monitors these regions
>> using the remote-userfaultfd that you saw on the second thread. When it wants
>> to reclaim (anonymous) memory, it:
>> 1. Uses UFFD-WP to protect that memory (and for this matter I got a vectored
>> UFFD-WP to do so efficiently, a patch which I did not send yet).
>> 2. Calls process_vm_readv() to read that memory of that process.
>> 3. Write it back to “swap”.
>> 4. Calls process_madvise(MADV_DONTNEED) to zap it.
> Why cannot you use MADV_PAGEOUT/MADV_COLD for this usecase?

Providing hints to the kernel takes you so far to a certain extent.
The kernel does not want to (for a good reason) to be completely
configurable when it comes to reclaim and prefetch policies. Doing
so from userspace allows you to be fully configurable.

> MADV_DONTNEED on a remote process has been proposed in the past several
> times and it has always been rejected because it is a free ticket to all
> sorts of hard to debug problems as it is just a free ticket for a remote
> memory corruption. An additional capability requirement might reduce the
> risk to some degree but I still do not think this is a good idea.

I would argue that there is nothing bad that remote MADV_DONTNEED can do
that process_vm_writev() cannot do as well (putting aside ptrace).

process_vm_writev() is checking:

mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS)

Wouldn't adding such a condition suffice?