From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Adalbert Lazăr" <alazar@bitdefender.com>
Cc: linux-mm@kvack.org, linux-api@vger.kernel.org,
"Andrew Morton" <akpm@linux-foundation.org>,
"Alexander Graf" <graf@amazon.com>,
"Stefan Hajnoczi" <stefanha@redhat.com>,
"Jerome Glisse" <jglisse@redhat.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Mihai Donțu" <mdontu@bitdefender.com>,
"Mircea Cirjaliu" <mcirjaliu@bitdefender.com>,
"Andy Lutomirski" <luto@kernel.org>,
"Arnd Bergmann" <arnd@arndb.de>,
"Sargun Dhillon" <sargun@sargun.me>,
"Aleksa Sarai" <cyphar@cyphar.com>,
"Oleg Nesterov" <oleg@redhat.com>, "Jann Horn" <jannh@google.com>,
"Kees Cook" <keescook@chromium.org>,
"Matthew Wilcox" <willy@infradead.org>,
"Christian Brauner" <christian.brauner@ubuntu.com>
Subject: Re: [RESEND RFC PATCH 0/5] Remote mapping
Date: Fri, 4 Sep 2020 09:11:48 -0300 [thread overview]
Message-ID: <20200904121148.GR24045@ziepe.ca> (raw)
In-Reply-To: <20200904113116.20648-1-alazar@bitdefender.com>
On Fri, Sep 04, 2020 at 02:31:11PM +0300, Adalbert Lazăr wrote:
> VMAs obtained by mmap()ing memory access fds mirror the contents of the remote
> process address space within the specified range. Pages are installed in the
> current process page tables at fault time and removed by the mmu_interval_notifier
> invalidate callbck. No further memory management is involved.
> On attempts to access a hole, or if a mapping was removed by PIDFD_MEM_UNMAP,
> or if the remote process address space was reaped by OOM, the remote mapping
> fault handler returns VM_FAULT_SIGBUS.
I still think anything along these lines needs to meet the XPMEM use
cases as well, we have to have more general solutions for such MM
stuff:
https://gitlab.com/hjelmn/xpmem
However, I think this fundamentally falls into some of the same bad
direction as xpmem.
I would much rather see this design copy & clone the VMA's than try to
mirror the PTEs inside the VMAs from the remote into a single giant
VMA and somehow split/mirror the VMA ops.
This is just too weird and fragile to be maintaible over a long
term.
For instance, one of the major bugs in things like xpmem was that they
are incompatible with get_user_pages(), largely because of this issue.
I feel like I said this already..
Jason
next prev parent reply other threads:[~2020-09-04 12:11 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-04 11:31 [RESEND RFC PATCH 0/5] Remote mapping Adalbert Lazăr
2020-09-04 11:31 ` [RESEND RFC PATCH 1/5] mm: add atomic capability to zap_details Adalbert Lazăr
2020-09-04 11:31 ` [RESEND RFC PATCH 2/5] mm: let the VMA decide how zap_pte_range() acts on mapped pages Adalbert Lazăr
2020-09-04 11:31 ` [RESEND RFC PATCH 3/5] mm/mmu_notifier: remove lockdep map, allow mmu notifier to be used in nested scenarios Adalbert Lazăr
2020-09-04 12:03 ` Jason Gunthorpe
2020-09-04 11:31 ` [RESEND RFC PATCH 4/5] mm/remote_mapping: use a pidfd to access memory belonging to unrelated process Adalbert Lazăr
2020-09-04 17:55 ` Oleg Nesterov
2020-09-07 14:30 ` Oleg Nesterov
2020-09-07 15:16 ` Adalbert Lazăr
2020-09-09 8:32 ` Mircea CIRJALIU - MELIU
2020-09-10 16:43 ` Oleg Nesterov
2020-09-07 15:02 ` Christian Brauner
2020-09-07 16:04 ` Mircea CIRJALIU - MELIU
2020-09-04 11:31 ` [RESEND RFC PATCH 5/5] pidfd_mem: implemented remote memory mapping system call Adalbert Lazăr
2020-09-04 19:18 ` Florian Weimer
2020-09-07 14:55 ` Christian Brauner
2020-09-04 12:11 ` Jason Gunthorpe [this message]
2020-09-04 13:24 ` [RESEND RFC PATCH 0/5] Remote mapping Mircea CIRJALIU - MELIU
2020-09-04 13:39 ` Jason Gunthorpe
2020-09-04 14:18 ` Mircea CIRJALIU - MELIU
2020-09-04 14:39 ` Jason Gunthorpe
2020-09-04 15:40 ` Mircea CIRJALIU - MELIU
2020-09-04 16:11 ` Jason Gunthorpe
2020-09-04 19:41 ` Matthew Wilcox
2020-09-04 19:49 ` Jason Gunthorpe
2020-09-04 20:08 ` Paolo Bonzini
2020-12-01 18:01 ` Jason Gunthorpe
2020-09-04 19:19 ` Florian Weimer
2020-09-04 20:18 ` Paolo Bonzini
2020-09-07 8:33 ` Christian Brauner
2020-09-04 19:39 ` Andy Lutomirski
2020-09-04 20:09 ` Paolo Bonzini
2020-09-04 20:34 ` Andy Lutomirski
2020-09-04 21:58 ` Paolo Bonzini
2020-09-04 23:17 ` Andy Lutomirski
2020-09-05 18:27 ` Paolo Bonzini
2020-09-07 8:38 ` Christian Brauner
2020-09-07 12:41 ` Mircea CIRJALIU - MELIU
2020-09-07 7:05 ` Christoph Hellwig
2020-09-07 8:44 ` Paolo Bonzini
2020-09-07 10:25 ` Mircea CIRJALIU - MELIU
2020-09-07 15:05 ` Christian Brauner
2020-09-07 20:43 ` Andy Lutomirski
2020-09-09 11:38 ` Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200904121148.GR24045@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=akpm@linux-foundation.org \
--cc=alazar@bitdefender.com \
--cc=arnd@arndb.de \
--cc=christian.brauner@ubuntu.com \
--cc=cyphar@cyphar.com \
--cc=graf@amazon.com \
--cc=jannh@google.com \
--cc=jglisse@redhat.com \
--cc=keescook@chromium.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mcirjaliu@bitdefender.com \
--cc=mdontu@bitdefender.com \
--cc=oleg@redhat.com \
--cc=pbonzini@redhat.com \
--cc=sargun@sargun.me \
--cc=stefanha@redhat.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).