From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
To: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, longli@microsoft.com, andrew+netdev@lunn.ch,
davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, kotaranov@microsoft.com, horms@kernel.org,
ernis@linux.microsoft.com, dipayanroy@linux.microsoft.com,
kees@kernel.org, linux-hyperv@vger.kernel.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-rdma@vger.kernel.org
Subject: [PATCH net-next] net: mana: Cache MANA_QUERY_LINK_CONFIG result to avoid repeated HWC queries
Date: Thu, 28 May 2026 11:07:51 -0700 [thread overview]
Message-ID: <20260528180757.1536640-1-ernis@linux.microsoft.com> (raw)
mana_query_link_cfg() sends an HWC command to firmware on every call,
but the link speed and QoS values it returns only change when the
driver explicitly calls mana_set_bw_clamp(). This function is called
not only by userspace via ethtool get_link_ksettings, but also
periodically by hv_netvsc through netvsc_get_link_ksettings and by
the sysfs speed_show attribute via dev_attr_show, resulting in
unnecessary HWC traffic every few minutes.
Add a link_cfg_error field to mana_port_context to cache the query
result. The field uses three states: 1 (not yet queried, initial
value set during mana_probe_port), 0 (success, speed/max_speed are
valid), or a negative errno for permanent errors like -EOPNOTSUPP
when the hardware does not support the command. Transient errors and
qos_unconfigured responses are not cached so that subsequent calls
will retry.
To prevent a concurrent mana_set_bw_clamp() from racing with an
in-flight query and publishing stale pre-clamp speed/max_speed,
serialize the firmware transaction and the cache update under a new
per-port mutex (link_cfg_mutex). The mutex covers both the HWC
request and the subsequent stores in mana_query_link_cfg(), and the
HWC request and invalidation in mana_set_bw_clamp(). With this lock
held, two queries can no longer interleave their speed/max_speed
stores, and an invalidation can no longer slip in between a query's
response and its publish.
Invalidate the cache inside mana_set_bw_clamp() on success, so all
current and future callers that change the link configuration
automatically trigger a fresh query on the next mana_query_link_cfg()
call. Also reset link_cfg_error during resume in mana_probe() under
link_cfg_mutex, so that any slow-path query already in flight cannot
later store 0 and silently overwrite the post-resume invalidation.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 41 +++++++++++++++----
include/net/mana/mana.h | 4 ++
2 files changed, 36 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 82f1461a48e9..43018bc13dc1 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1456,6 +1456,12 @@ int mana_query_link_cfg(struct mana_port_context *apc)
struct mana_query_link_config_req req = {};
int err;
+ mutex_lock(&apc->link_cfg_mutex);
+
+ err = apc->link_cfg_error;
+ if (err <= 0)
+ goto out;
+
mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG,
sizeof(req), sizeof(resp));
@@ -1468,10 +1474,11 @@ int mana_query_link_cfg(struct mana_port_context *apc)
if (err) {
if (err == -EOPNOTSUPP) {
netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
- return err;
+ apc->link_cfg_error = err;
+ goto out;
}
netdev_err(ndev, "Failed to query link config: %d\n", err);
- return err;
+ goto out;
}
err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG,
@@ -1482,16 +1489,20 @@ int mana_query_link_cfg(struct mana_port_context *apc)
resp.hdr.status);
if (!err)
err = -EOPNOTSUPP;
- return err;
+ goto out;
}
if (resp.qos_unconfigured) {
err = -EINVAL;
- return err;
+ goto out;
}
apc->speed = resp.link_speed_mbps;
apc->max_speed = resp.qos_speed_mbps;
- return 0;
+ apc->link_cfg_error = 0;
+ err = 0;
+out:
+ mutex_unlock(&apc->link_cfg_mutex);
+ return err;
}
int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
@@ -1508,17 +1519,19 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
req.link_speed_mbps = speed;
req.enable_clamping = enable_clamping;
+ mutex_lock(&apc->link_cfg_mutex);
+
err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
sizeof(resp));
if (err) {
if (err == -EOPNOTSUPP) {
netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
- return err;
+ goto out;
}
netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
speed, err);
- return err;
+ goto out;
}
err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP,
@@ -1529,13 +1542,18 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
resp.hdr.status);
if (!err)
err = -EOPNOTSUPP;
- return err;
+ goto out;
}
if (resp.qos_unconfigured)
netdev_info(ndev, "QoS is unconfigured\n");
- return 0;
+ /* Invalidate the cache; next query will re-fetch from firmware. */
+ apc->link_cfg_error = 1;
+ err = 0;
+out:
+ mutex_unlock(&apc->link_cfg_mutex);
+ return err;
}
int mana_create_wq_obj(struct mana_port_context *apc,
@@ -3430,6 +3448,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
apc->port_handle = INVALID_MANA_HANDLE;
apc->pf_filter_handle = INVALID_MANA_HANDLE;
apc->port_idx = port_idx;
+ apc->link_cfg_error = 1;
+ mutex_init(&apc->link_cfg_mutex);
apc->cqe_coalescing_enable = 0;
mutex_init(&apc->vport_mutex);
@@ -3750,6 +3770,9 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
rtnl_lock();
apc = netdev_priv(ac->ports[i]);
enable_work(&apc->queue_reset_work);
+ mutex_lock(&apc->link_cfg_mutex);
+ apc->link_cfg_error = 1;
+ mutex_unlock(&apc->link_cfg_mutex);
err = mana_attach(ac->ports[i]);
rtnl_unlock();
/* Log the port for which the attach failed, stop
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index d9c27310fd04..af772b7297ec 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -555,6 +555,10 @@ struct mana_port_context {
u32 speed;
/* Maximum speed supported by the SKU (mbps) */
u32 max_speed;
+ /* 1 = not queried, 0 = cached success, negative = permanent error */
+ int link_cfg_error;
+ /* Serializes mana_query_link_cfg() and mana_set_bw_clamp(). */
+ struct mutex link_cfg_mutex;
bool port_is_up;
bool port_st_save; /* Saved port state */
--
2.34.1
reply other threads:[~2026-05-28 18:08 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20260528180757.1536640-1-ernis@linux.microsoft.com \
--to=ernis@linux.microsoft.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=decui@microsoft.com \
--cc=dipayanroy@linux.microsoft.com \
--cc=edumazet@google.com \
--cc=haiyangz@microsoft.com \
--cc=horms@kernel.org \
--cc=kees@kernel.org \
--cc=kotaranov@microsoft.com \
--cc=kuba@kernel.org \
--cc=kys@microsoft.com \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=longli@microsoft.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.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