From: Long Li <longli@microsoft.com>
To: Long Li <longli@microsoft.com>, Long Li <longli@kernel.org>,
Konstantin Taranov <kotaranov@microsoft.com>,
Jakub Kicinski <kuba@kernel.org>,
"David S . Miller" <davem@davemloft.net>,
Paolo Abeni <pabeni@redhat.com>,
Eric Dumazet <edumazet@google.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
Jason Gunthorpe <jgg@ziepe.ca>, Leon Romanovsky <leon@kernel.org>,
Haiyang Zhang <haiyangz@microsoft.com>,
"K . Y . Srinivasan" <kys@microsoft.com>,
Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>,
shradhagupta@linux.microsoft.com, Simon Horman <horms@kernel.org>,
ernis@linux.microsoft.com, stephen@networkplumber.org,
shirazsaleem@microsoft.com
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH net-next v5 06/13] net: mana: swap queue sets in mana_change_mtu
Date: Wed, 9 Sep 2026 15:24:09 -0700 [thread overview]
Message-ID: <20260909222416.884246-7-longli@microsoft.com> (raw)
In-Reply-To: <20260909222416.884246-1-longli@microsoft.com>
Carry the MTU in the queue set and size replacement RX buffers from it.
Publish ndev->mtu after RSS configuration succeeds; allocation failure
leaves the live queues and advertised MTU unchanged.
This still rebuilds all queues, requiring both sets' SQ/RQ/CQ objects
and RX buffers temporarily. Resource limits can therefore reject an MTU
change that detach/attach previously accepted.
Signed-off-by: Long Li <longli@microsoft.com>
---
Changes in v5:
- Rebased onto current net-next; no changes to this patch.
Changes in v4:
- Document the two-set resource peak and possible allocation refusal
at high queue counts; shorten comments.
drivers/net/ethernet/microsoft/mana/mana_en.c | 53 ++++++++++++-------
.../ethernet/microsoft/mana/mana_ethtool.c | 10 ++--
include/net/mana/mana.h | 7 ++-
3 files changed, 46 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index bb9ef4e634a6edaf097bc85f2248c2ceea88fc05..7f7833f3e1aad43d250b15ddb35f59907d01929e 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -902,32 +902,37 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
static int mana_change_mtu(struct net_device *ndev, int new_mtu)
{
struct mana_port_context *mpc = netdev_priv(ndev);
- unsigned int old_mtu = ndev->mtu;
+ struct mana_port_context *scratch;
+ struct mana_qset newq, oldq;
int err;
- /* Pre-allocate buffers to prevent failure in mana_attach later */
- err = mana_pre_alloc_rxbufs(mpc, new_mtu, mpc->num_queues);
- if (err) {
- netdev_err(ndev, "Insufficient memory for new MTU\n");
- return err;
+ if (!mpc->port_is_up) {
+ mpc->configured_mtu = new_mtu;
+ WRITE_ONCE(ndev->mtu, new_mtu);
+ return 0;
}
- err = mana_detach(ndev, false);
- if (err) {
- netdev_err(ndev, "mana_detach failed: %d\n", err);
- goto out;
- }
+ scratch = mana_qset_scratch_alloc(mpc);
+ if (!scratch)
+ return -ENOMEM;
- WRITE_ONCE(ndev->mtu, new_mtu);
+ err = mana_alloc_qset(mpc, scratch, mpc->num_queues,
+ mpc->rx_queue_size, mpc->tx_queue_size,
+ mpc->priv_flags, new_mtu, &newq);
+ if (err)
+ goto free_scratch;
- err = mana_attach(ndev);
+ err = mana_publish_qset(mpc, &newq, &oldq);
if (err) {
- netdev_err(ndev, "mana_attach failed: %d\n", err);
- WRITE_ONCE(ndev->mtu, old_mtu);
+ mana_free_qset(scratch, &newq);
+ goto free_scratch;
}
-out:
- mana_pre_dealloc_rxbufs(mpc);
+ mana_free_qset(scratch, &oldq);
+
+free_scratch:
+ mana_publish_close_if_needed(mpc);
+ mana_qset_scratch_free(scratch);
return err;
}
@@ -3153,7 +3158,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
rxq->rxq_idx = rxq_idx;
rxq->rxobj = INVALID_MANA_HANDLE;
- mana_get_rxbuf_cfg(apc, ndev->mtu, &rxq->datasize, &rxq->alloc_size,
+ mana_get_rxbuf_cfg(apc, apc->configured_mtu, &rxq->datasize,
+ &rxq->alloc_size,
&rxq->headroom, &rxq->frag_count);
/* Create page pool for RX queue */
err = mana_create_page_pool(rxq, gc);
@@ -3909,6 +3915,7 @@ static void mana_qset_snapshot(const struct mana_port_context *ctx,
out->rx_queue_size = ctx->rx_queue_size;
out->tx_queue_size = ctx->tx_queue_size;
out->priv_flags = ctx->priv_flags;
+ out->mtu = ctx->configured_mtu;
}
/* Vport identity and port debugfs outlive queue sets. */
@@ -3925,6 +3932,7 @@ static void mana_qset_install(struct mana_port_context *ctx,
ctx->rx_queue_size = qset->rx_queue_size;
ctx->tx_queue_size = qset->tx_queue_size;
ctx->priv_flags = qset->priv_flags;
+ ctx->configured_mtu = qset->mtu;
}
/* Scratch starts without SQs/RQs and borrows the port's EQ pool. Never call
@@ -3965,7 +3973,7 @@ void mana_qset_scratch_free(struct mana_port_context *scratch)
int mana_alloc_qset(struct mana_port_context *apc,
struct mana_port_context *scratch, unsigned int num_queues,
unsigned int rx_queue_size, unsigned int tx_queue_size,
- u32 priv_flags, struct mana_qset *out)
+ u32 priv_flags, int mtu, struct mana_qset *out)
{
struct net_device *ndev = scratch->ndev;
int err;
@@ -3977,6 +3985,8 @@ int mana_alloc_qset(struct mana_port_context *apc,
scratch->tx_queue_size = tx_queue_size;
scratch->priv_flags = priv_flags;
+ scratch->configured_mtu = mtu;
+
err = mana_init_port_context(scratch);
if (err)
goto out_err;
@@ -4153,6 +4163,8 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq,
if (err)
goto rollback;
+ WRITE_ONCE(ndev->mtu, apc->configured_mtu);
+
/* Publish fields before opening the gate; pair with TX/XDP read
* barriers. The post-gate full barrier cannot replace this.
*/
@@ -4192,6 +4204,8 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq,
return err;
}
+ WRITE_ONCE(ndev->mtu, apc->configured_mtu);
+
/* Publish restored fields before reopening the gate, as on success. */
smp_wmb();
@@ -4362,6 +4376,7 @@ 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->configured_mtu = ndev->mtu;
apc->link_cfg_error = 1;
apc->cqe_coalescing_enable = 0;
apc->cqe8_coalescing_enable = 0;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index adc65b9146c7e74703db587a619678439ff0d84b..c03944f95cf84dcbaa866e92f6c7d67100215b7b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -708,7 +708,8 @@ static int mana_set_channels(struct net_device *ndev,
}
err = mana_alloc_qset(apc, scratch, new_count, apc->rx_queue_size,
- apc->tx_queue_size, apc->priv_flags, &newq);
+ apc->tx_queue_size, apc->priv_flags,
+ apc->configured_mtu, &newq);
if (err)
goto free_scratch;
@@ -797,7 +798,7 @@ static int mana_set_ringparam(struct net_device *ndev,
}
err = mana_alloc_qset(apc, scratch, apc->num_queues, new_rx, new_tx,
- apc->priv_flags, &newq);
+ apc->priv_flags, apc->configured_mtu, &newq);
if (err) {
NL_SET_ERR_MSG_FMT(extack, "failed to change ring params: %d",
err);
@@ -885,8 +886,9 @@ static int mana_set_priv_flags(struct net_device *ndev, u32 priv_flags)
goto clear_flag;
}
- err = mana_alloc_qset(apc, scratch, apc->num_queues, apc->rx_queue_size,
- apc->tx_queue_size, priv_flags, &newq);
+ err = mana_alloc_qset(apc, scratch, apc->num_queues,
+ apc->rx_queue_size, apc->tx_queue_size,
+ priv_flags, apc->configured_mtu, &newq);
if (err)
goto free_scratch;
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index e965d86b4d8502408f175bdbee5d77fb2e406df3..02d60a6b7be423ae55a93fa21e53717e40918eb7 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -616,6 +616,10 @@ struct mana_port_context {
unsigned int rx_queue_size;
unsigned int tx_queue_size;
+ /* MTU used to size RX buffers, independent of ndev->mtu during a swap.
+ */
+ int configured_mtu;
+
mana_handle_t port_handle;
mana_handle_t pf_filter_handle;
@@ -693,6 +697,7 @@ struct mana_qset {
unsigned int tx_queue_size;
u32 priv_flags;
+ int mtu;
};
netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev);
@@ -710,7 +715,7 @@ void mana_qset_scratch_free(struct mana_port_context *scratch);
int mana_alloc_qset(struct mana_port_context *apc,
struct mana_port_context *scratch, unsigned int num_queues,
unsigned int rx_queue_size, unsigned int tx_queue_size,
- u32 priv_flags, struct mana_qset *out);
+ u32 priv_flags, int mtu, struct mana_qset *out);
int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq,
struct mana_qset *out_old);
void mana_publish_close_if_needed(struct mana_port_context *apc);
--
2.43.0
next prev parent reply other threads:[~2026-09-09 22:25 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-09 22:24 [PATCH net-next v5 00/13] net: mana: reconfigure by replacing the queue set Long Li
2026-09-09 22:24 ` [PATCH net-next v5 01/13] net: mana: add queue-set allocation and teardown helpers Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 02/13] net: mana: share the EQ pool across a queue-set swap Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 03/13] net: mana: swap queue sets in mana_set_channels Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 04/13] net: mana: swap queue sets in mana_set_ringparam Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 05/13] net: mana: swap queue sets in mana_set_priv_flags Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` Long Li [this message]
2026-09-10 22:25 ` [PATCH net-next v5 06/13] net: mana: swap queue sets in mana_change_mtu sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 07/13] net: mana: swap queue sets in mana_xdp_set Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 08/13] net: mana: do not bail out of mana_detach on dealloc failure Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 09/13] net: mana: keep per-queue statistics in the port context Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 10/13] net: mana: release EQs left idle by a channel-count reduction Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 11/13] net: mana: keep a user-configured RSS table across a queue rebuild Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 12/13] net: mana: keep the surviving queues when the channel count is reduced Long Li
2026-09-10 22:25 ` sashiko-bot
2026-09-09 22:24 ` [PATCH net-next v5 13/13] net: mana: keep the existing queues when the channel count is raised Long Li
2026-09-10 22:25 ` sashiko-bot
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=20260909222416.884246-7-longli@microsoft.com \
--to=longli@microsoft.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=decui@microsoft.com \
--cc=edumazet@google.com \
--cc=ernis@linux.microsoft.com \
--cc=haiyangz@microsoft.com \
--cc=horms@kernel.org \
--cc=jgg@ziepe.ca \
--cc=kotaranov@microsoft.com \
--cc=kuba@kernel.org \
--cc=kys@microsoft.com \
--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=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=shirazsaleem@microsoft.com \
--cc=shradhagupta@linux.microsoft.com \
--cc=stephen@networkplumber.org \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.