linux-cifs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Metzmacher <metze@samba.org>
To: linux-cifs@vger.kernel.org, samba-technical@lists.samba.org
Cc: metze@samba.org, Namjae Jeon <linkinjeon@kernel.org>,
	Steve French <smfrench@gmail.com>, Tom Talpey <tom@talpey.com>,
	Long Li <longli@microsoft.com>
Subject: [RFC PATCH 0/4] smb:smbdirect/server: introduce smb_direct_negotiate_recv_work
Date: Tue,  2 Dec 2025 22:15:23 +0100	[thread overview]
Message-ID: <cover.1764709225.git.metze@samba.org> (raw)

Hi,

here's a patchset that implements a better solution
to the problem that the initial recv completion might
arrive before the RDMA_CM_EVENT_ESTABLISHED event.

The last patch is not intended to be applied, but
it helps to see the event flow it generated,
see the commit message.

This is based on the 4 smbirect patches within
v6.19-rc-smb-fixes:

dc10cf1368af8cb816dcaa2502ba7d44fff20612
smb: client: relax WARN_ON_ONCE(SMBDIRECT_SOCKET_*) checks in recv_done() and smbd_conn_upcall()
425c32750b48956a6e156b6a4609d281ee471359
smb: server: relax WARN_ON_ONCE(SMBDIRECT_SOCKET_*) checks in recv_done() and smb_direct_cm_handler()
1adb2dab9727c5beaaf253f67bf4fc2c54ae70e7
smb: smbdirect: introduce SMBDIRECT_CHECK_STATUS_{WARN,DISCONNECT}()
1f3fd108c5c5a9885c6c276a2489c49b60a6b90d
smb: smbdirect: introduce SMBDIRECT_DEBUG_ERR_PTR() helper

I've tested them on top of v6.18 (without the other patches
in v6.19-rc-smb-fixes).

Sadly there are still problems with Mellanox setups
as well as irdma (in iwarp mode). I'm trying to
prepare patches to debug this next.

Stefan Metzmacher (4):
  smb: smbdirect: introduce smbdirect_socket.connect.{lock,work}
  smb: server: initialize recv_io->cqe.done = recv_done just once
  smb: server: defer the initial recv completion logic to
    smb_direct_negotiate_recv_work()
  fs/smb/server/transport_rdma.c TMP DEBUG connect work

 fs/smb/common/smbdirect/smbdirect_socket.h |  12 +
 fs/smb/server/transport_rdma.c             | 321 +++++++++++++++++++--
 2 files changed, 304 insertions(+), 29 deletions(-)

-- 
2.43.0


             reply	other threads:[~2025-12-02 21:15 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-02 21:15 Stefan Metzmacher [this message]
2025-12-02 21:15 ` [RFC PATCH 1/4] smb: smbdirect: introduce smbdirect_socket.connect.{lock,work} Stefan Metzmacher
2025-12-02 21:15 ` [RFC PATCH 2/4] smb: server: initialize recv_io->cqe.done = recv_done just once Stefan Metzmacher
2025-12-02 21:15 ` [RFC PATCH 3/4] smb: server: defer the initial recv completion logic to smb_direct_negotiate_recv_work() Stefan Metzmacher
2025-12-02 21:15 ` [RFC PATCH 4/4] fs/smb/server/transport_rdma.c TMP DEBUG connect work Stefan Metzmacher
2025-12-04  6:15 ` [RFC PATCH 0/4] smb:smbdirect/server: introduce smb_direct_negotiate_recv_work Namjae Jeon

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=cover.1764709225.git.metze@samba.org \
    --to=metze@samba.org \
    --cc=linkinjeon@kernel.org \
    --cc=linux-cifs@vger.kernel.org \
    --cc=longli@microsoft.com \
    --cc=samba-technical@lists.samba.org \
    --cc=smfrench@gmail.com \
    --cc=tom@talpey.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).