From: Wei Hu <weh@linux.microsoft.com>
To: longli@kernel.org, kotaranov@microsoft.com, kuba@kernel.org,
davem@davemloft.net, pabeni@redhat.com, edumazet@google.com,
andrew+netdev@lunn.ch, jgg@ziepe.ca, leon@kernel.org,
haiyangz@microsoft.com, wei.liu@kernel.org, decui@microsoft.com,
shradhagupta@linux.microsoft.com, horms@kernel.org,
ernis@linux.microsoft.com, stephen@networkplumber.org
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
gargaditya@linux.microsoft.com, kees+treewide@kernel.org,
kees@kernel.org, mawasthi@linux.microsoft.com, weh@microsoft.com,
edumazet@kernel.org, shacharr@microsoft.com
Subject: [PATCH net-next v11 0/4] net: mana: concurrent HWC requests and dynamic queue depth
Date: Tue, 17 Nov 2026 16:00:57 +0000 [thread overview]
Message-ID: <cover.1794751992.git.weh@linux.microsoft.com> (raw)
This is v11 of Long Li's four-patch HWC series. I am carrying the series
forward with review fixes and integration work. Original authorship and
sign-offs are retained.
The series supports concurrent requests over the MANA hardware channel and
rebuilds its queues using the queue depth and message sizes required by
the PF. It prepares ownership and teardown, gives each message its own
completion, adds concurrent request tracking, and enables dynamic sizing.
Changes since v10:
- Rebase onto current net-next, including Erni Sri Satya Vennela's
6964ff21c5d8 ("net: mana: Allocate queue MSI-X vectors on demand").
Preserve the upstream allocation, affinity and shared-vector behavior.
- Distinguish a local HWC rejection from a command posted and then timed
out. Propagate that distinction through GDMA, Ethernet and RDMA cleanup
so a destroy that could not be sent does not release device-owned queue
memory, RX pages or RDMA pins. Retain relevant EQ/MSI-X references.
- Cover failed creation unwinds, transferred queue ownership and partial
multi-command DMA regions. Preserve verbs dependencies on rejection and
avoid repeating acknowledged RSS WQ destroys during a partial retry.
Keep previously retained CQ callback state until destruction succeeds.
- Wait on a full mixed pool while a healthy occupied slot can still make
progress, rather than failing merely because another slot was abandoned.
Keep quarantine, stop/cancellation wakeups and available-slot behavior.
- Preserve the specific private-bootstrap EQ-test failure diagnostic and
initialize the context drain waitqueue once in PCI/CDX probe.
- Correct the stale WARN and teardown/RCU comments. Add original-driver
Fixes lineage and dependency-complete backport guidance; do not mark the
whole feature stack for automatic stable pickup.
- Document nonzero PF-report validation and EPROTO, including fallback,
and the existing unchecked-doorbell fix. PF-directed geometry and
directional-size contracts are unchanged.
Independent pre-existing RX, CQ-lifetime and broader lifecycle findings
remain separate. The posted-command timeout/PF-error cleanup policy is
also unchanged. Unacknowledged DMA, pins and references may be deliberately
retained; this revision does not infer quiescence from a reset or delay,
or promise automatic reclamation.
Validation on this exact revision:
- Ten GCC/Clang W=1 MANA Ethernet/RDMA target builds: unmodified base plus
each of the four intermediate commits, with no compiler diagnostics.
- Thirteen inherited bounded actual-source regression suites and four
throttle/CQ/EQ lifetime suites.
- Eight new GCC/Clang ASan/UBSan suites exercise cleanup rejection,
callback/dependency retention, partial DMA creation, retries, healthy
controls and the unchanged posted-error policy. There are 175 new cases
and 25 negative controls per compiler.
- Source-cited local review following netdev/Sashiko criteria, including
the fault-state caller interactions and failed construction unwinds.
- Strict 80-column checks have no source diagnostics. Checkpatch reports
the retained Co-authored-by metadata warning once on each patch.
These are static/offline checks, not actual bot or hardware approval.
No new full-kernel, runtime or performance qualification is claimed.
Previous revision:
https://lore.kernel.org/all/cover.1794208055.git.weh@linux.microsoft.com/
Base: 6964ff21c5d8b75649211a52dbfd92753e605649
Long Li (4):
net: mana: prepare HWC ownership for safe reinitialization
net: mana: give each HWC message slot its own completion state
net: mana: support concurrent HWC requests
net: mana: add dynamic HWC queue depth with reinit path
drivers/infiniband/hw/mana/cq.c | 17 +-
drivers/infiniband/hw/mana/main.c | 91 +-
drivers/infiniband/hw/mana/mana_ib.h | 5 +-
drivers/infiniband/hw/mana/mr.c | 28 +-
drivers/infiniband/hw/mana/qp.c | 106 +-
drivers/infiniband/hw/mana/wq.c | 4 +-
.../net/ethernet/microsoft/mana/gdma_cdx.c | 6 +-
.../net/ethernet/microsoft/mana/gdma_main.c | 207 +++-
.../net/ethernet/microsoft/mana/gdma_pci.c | 20 +-
.../net/ethernet/microsoft/mana/hw_channel.c | 1021 ++++++++++++++---
drivers/net/ethernet/microsoft/mana/mana_en.c | 49 +-
.../net/ethernet/microsoft/mana/shm_channel.c | 58 +-
include/net/mana/gdma.h | 26 +-
include/net/mana/hw_channel.h | 70 +-
include/net/mana/mana.h | 4 +-
include/net/mana/shm_channel.h | 10 +-
16 files changed, 1404 insertions(+), 318 deletions(-)
base-commit: 6964ff21c5d8b75649211a52dbfd92753e605649
--
2.43.0
next reply other threads:[~2026-11-17 16:01 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-17 16:00 Wei Hu [this message]
2026-11-17 16:00 ` [PATCH net-next v11 1/4] net: mana: prepare HWC ownership for safe reinitialization Wei Hu
2026-11-17 16:00 ` [PATCH net-next v11 2/4] net: mana: give each HWC message slot its own completion state Wei Hu
2026-11-17 16:01 ` [PATCH net-next v11 3/4] net: mana: support concurrent HWC requests Wei Hu
2026-11-17 16:01 ` [PATCH net-next v11 4/4] net: mana: add dynamic HWC queue depth with reinit path Wei Hu
2026-11-17 16:03 ` [PATCH net-next v11 0/4] net: mana: concurrent HWC requests and dynamic queue depth netdev-bot+sinfo
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.1794751992.git.weh@linux.microsoft.com \
--to=weh@linux.microsoft.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=decui@microsoft.com \
--cc=edumazet@google.com \
--cc=edumazet@kernel.org \
--cc=ernis@linux.microsoft.com \
--cc=gargaditya@linux.microsoft.com \
--cc=haiyangz@microsoft.com \
--cc=horms@kernel.org \
--cc=jgg@ziepe.ca \
--cc=kees+treewide@kernel.org \
--cc=kees@kernel.org \
--cc=kotaranov@microsoft.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=longli@kernel.org \
--cc=mawasthi@linux.microsoft.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=shacharr@microsoft.com \
--cc=shradhagupta@linux.microsoft.com \
--cc=stephen@networkplumber.org \
--cc=weh@microsoft.com \
--cc=wei.liu@kernel.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
all inboxes | Powered by JetHome®