From: Cornelia Huck <cohuck@redhat.com>
To: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Cc: qemu-devel@nongnu.org, peter.maydell@linaro.org,
yuval.shaia@oracle.com, pjp@fedoraproject.org
Subject: Re: [Qemu-devel] [PATCH PULL 02/31] contrib/rdmacm-mux: Add implementation of RDMA User MAD multiplexer
Date: Mon, 7 Jan 2019 18:54:17 +0100 [thread overview]
Message-ID: <20190107185417.6d6dbe59.cohuck@redhat.com> (raw)
In-Reply-To: <bed8bcb6-67ca-b8c5-ffbe-684241fe2b70@gmail.com>
On Mon, 7 Jan 2019 19:28:10 +0200
Marcel Apfelbaum <marcel.apfelbaum@gmail.com> wrote:
> On 1/3/19 12:34 PM, Cornelia Huck wrote:
> > On Sat, 22 Dec 2018 11:50:07 +0200
> > Marcel Apfelbaum <marcel.apfelbaum@gmail.com> wrote:
> >
> >> From: Yuval Shaia <yuval.shaia@oracle.com>
> >>
> >> RDMA MAD kernel module (ibcm) disallow more than one MAD-agent for a
> >> given MAD class.
> >> This does not go hand-by-hand with qemu pvrdma device's requirements
> >> where each VM is MAD agent.
> >> Fix it by adding implementation of RDMA MAD multiplexer service which on
> >> one hand register as a sole MAD agent with the kernel module and on the
> >> other hand gives service to more than one VM.
> >>
> >> Design Overview:
> >> Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
> >> ----------------
> >> A server process is registered to UMAD framework (for this to work the
> >> rdma_cm kernel module needs to be unloaded) and creates a unix socket to
> >> listen to incoming request from clients.
> >> A client process (such as QEMU) connects to this unix socket and
> >> registers with its own GID.
> >>
> >> TX:
> >> ----
> >> When client needs to send rdma_cm MAD message it construct it the same
> >> way as without this multiplexer, i.e. creates a umad packet but this
> >> time it writes its content to the socket instead of calling umad_send().
> >> The server, upon receiving such a message fetch local_comm_id from it so
> >> a context for this session can be maintain and relay the message to UMAD
> >> layer by calling umad_send().
> >>
> >> RX:
> >> ----
> >> The server creates a worker thread to process incoming rdma_cm MAD
> >> messages. When an incoming message arrived (umad_recv()) the server,
> >> depending on the message type (attr_id) looks for target client by
> >> either searching in gid->fd table or in local_comm_id->fd table. With
> >> the extracted fd the server relays to incoming message to the client.
> >>
> >> Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
> >> Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
> >> Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
> >>
> >> Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
> >> ---
> >> MAINTAINERS | 1 +
> >> Makefile | 3 +
> >> Makefile.objs | 1 +
> >> contrib/rdmacm-mux/Makefile.objs | 4 +
> >> contrib/rdmacm-mux/main.c | 798 +++++++++++++++++++++++++++++++
> >> contrib/rdmacm-mux/rdmacm-mux.h | 61 +++
> >> 6 files changed, 868 insertions(+)
> >> create mode 100644 contrib/rdmacm-mux/Makefile.objs
> >> create mode 100644 contrib/rdmacm-mux/main.c
> >> create mode 100644 contrib/rdmacm-mux/rdmacm-mux.h
> > This commit breaks building with clang on Fedora 28 for me; I get a
> > bunch of
> >
>
> Hi Cornelia,
> Thanks for spotting the issue.
>
> > clang-6.0: error: -libumad: 'linker' input unused [-Werror,-Wunused-command-line-argument]
>
> Is really strange, the rdma-mux is part of the contrib directory
> and is not even compiled by default.
>
> > Explicitly passing --disable-pvrdma to configure disables the offending
> > code.
> >
> > Let me know if you need more information.
>
> Can you please send the exact steps you are using to configure and
> compile QEMU,
> are you compiling on a x86 machine?
Yes, this is on my laptop (up-to-date F28). I can reproduce on current
master, configured with
../configure --target-list="s390x-softmmu s390x-linux-user i386-softmmu x86_64-softmmu cris-softmmu arm-softmmu ppc64-softmmu" --enable-linux-aio --enable-virtfs --enable-trace-backends=simple --cc=clang --enable-rdma --enable-pvrdma
It compiles if I pass --disable-pvrdma instead. It also compiles if I
drop --cc=clang.
I'm building in a build subdirectory; I have already tried purging it
before rebuilding, without luck.
clang --version says
clang version 6.0.1 (tags/RELEASE_601/final)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /usr/bin
next prev parent reply other threads:[~2019-01-07 17:54 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-22 9:50 [Qemu-devel] [PATCH PULL 00/31] RDMA queue Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 01/31] hw/pvrdma: Check the correct return value Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 02/31] contrib/rdmacm-mux: Add implementation of RDMA User MAD multiplexer Marcel Apfelbaum
2019-01-03 10:34 ` Cornelia Huck
2019-01-07 17:28 ` Marcel Apfelbaum
2019-01-07 17:54 ` Cornelia Huck [this message]
2019-01-08 8:41 ` Marcel Apfelbaum
2019-01-08 9:18 ` Cornelia Huck
2019-01-12 9:46 ` Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 03/31] hw/rdma: Add ability to force notification without re-arm Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 04/31] hw/rdma: Return qpn 1 if ibqp is NULL Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 05/31] hw/rdma: Abort send-op if fail to create addr handler Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 06/31] hw/rdma: Add support for MAD packets Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 07/31] hw/pvrdma: Make function reset_device return void Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 08/31] hw/pvrdma: Make default pkey 0xFFFF Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 09/31] hw/pvrdma: Set the correct opcode for recv completion Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 10/31] hw/pvrdma: Set the correct opcode for send completion Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 11/31] qapi: Define new QMP message for pvrdma Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 12/31] hw/pvrdma: Add support to allow guest to configure GID table Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 13/31] vmxnet3: Move some definitions to header file Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 14/31] hw/pvrdma: Make sure PCI function 0 is vmxnet3 Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 15/31] hw/rdma: Initialize node_guid from vmxnet3 mac address Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 16/31] hw/pvrdma: Make device state depend on Ethernet function state Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 17/31] hw/pvrdma: Fill all CQE fields Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 18/31] hw/pvrdma: Fill error code in command's response Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 19/31] hw/rdma: Remove unneeded code that handles more that one port Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 20/31] vl: Introduce shutdown_notifiers Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 21/31] hw/pvrdma: Clean device's resource when system is shutdown Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 22/31] hw/rdma: Do not use bitmap_zero_extend to free bitmap Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 23/31] hw/rdma: Do not call rdma_backend_del_gid on an empty gid Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 24/31] docs: Update pvrdma device documentation Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 25/31] pvrdma: release device resources in case of an error Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 26/31] rdma: check num_sge does not exceed MAX_SGE Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 27/31] pvrdma: add uar_read routine Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 28/31] pvrdma: check number of pages when creating rings Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 29/31] pvrdma: release ring object in case of an error Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 30/31] rdma: remove unused VENDOR_ERR_NO_SGE macro Marcel Apfelbaum
2018-12-22 9:50 ` [Qemu-devel] [PATCH PULL 31/31] pvrdma: check return value from pvrdma_idx_ring_has_ routines Marcel Apfelbaum
2018-12-22 13:59 ` [Qemu-devel] [PATCH PULL 00/31] RDMA queue Peter Maydell
2018-12-22 14:30 ` Marcel Apfelbaum
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=20190107185417.6d6dbe59.cohuck@redhat.com \
--to=cohuck@redhat.com \
--cc=marcel.apfelbaum@gmail.com \
--cc=peter.maydell@linaro.org \
--cc=pjp@fedoraproject.org \
--cc=qemu-devel@nongnu.org \
--cc=yuval.shaia@oracle.com \
/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).