mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
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,
	dipayanroy@linux.microsoft.com, bpf@vger.kernel.org,
	sdf@fomichev.me, daniel@iogearbox.net, hawk@kernel.org,
	ast@kernel.org, john.fastabend@gmail.com, weh@microsoft.com
Subject: [PATCH net-next v6 01/13] net: mana: add queue-set allocation and teardown helpers
Date: Fri,  9 Oct 2026 14:41:12 +0000	[thread overview]
Message-ID: <24eeca6a691150407d5ce94650d3ee51cf11b620.1790795005.git.weh@linux.microsoft.com> (raw)
In-Reply-To: <cover.1790795005.git.weh@linux.microsoft.com>

From: Long Li <longli@microsoft.com>

Add queue-set allocation and teardown helpers using a scratch port
context without releasing the vport. These prepare reconfiguration
to retain its running queues if replacement allocation fails.

Leave ordinary mana_dealloc_queues() byte-identical to the pinned
base. Do not introduce reset generations, sibling-port rebuilds, or
an incomplete independent failed-FLR TX-buffer policy change.

Queue-set retirement itself performs no function reset. Its caller
must drain old published TX queues before publishing a replacement;
unpublished sets have never admitted TX. The first live-swap commit
adds that nonresetting pre-publication wait. These helpers have no
live replacement callers yet.

Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
---
 .../net/ethernet/microsoft/mana/mana_bpf.c    |  24 +++
 drivers/net/ethernet/microsoft/mana/mana_en.c | 184 +++++++++++++++++-
 include/net/mana/mana.h                       |  31 +++
 3 files changed, 236 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
index 9ef42b74048b..ff54f8966825 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
@@ -263,3 +263,27 @@ int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
 		return -EOPNOTSUPP;
 	}
 }
+
+struct bpf_prog *mana_chn_xdp_peek(struct mana_port_context *apc)
+{
+	ASSERT_RTNL();
+
+	if (!apc->rxqs || !apc->rxqs[0])
+		return NULL;
+
+	return rtnl_dereference(apc->rxqs[0]->bpf_prog);
+}
+
+/* Keep the per-queue program pointers until RX polling stops. */
+void mana_chn_xdp_release(struct bpf_prog *prog, unsigned int num_queues)
+{
+	unsigned int i;
+
+	ASSERT_RTNL();
+
+	if (!prog)
+		return;
+
+	for (i = 0; i < num_queues; i++)
+		bpf_prog_put(prog);
+}
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 591fb4191d90..d4b8bb4e1f53 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2018,7 +2018,8 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	/* Ensure checking txq_stopped before apc->port_is_up. */
 	smp_rmb();
 
-	if (txq_stopped && apc->port_is_up && avail_space >= MAX_TX_WQE_SIZE) {
+	if (txq_stopped && !READ_ONCE(txq->retiring) && apc->port_is_up &&
+	    avail_space >= MAX_TX_WQE_SIZE) {
 		netif_tx_wake_queue(net_txq);
 		apc->eth_stats.wake_queue++;
 	}
@@ -3013,11 +3014,11 @@ static int mana_push_wqe(struct mana_rxq *rxq)
 
 static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 {
-	struct mana_port_context *mpc = netdev_priv(rxq->ndev);
 	struct page_pool_params pprm = {};
 	int ret;
 
-	pprm.pool_size = mpc->rx_queue_size / rxq->frag_count + 1;
+	/* Size the pool for this RX queue, not the live configuration. */
+	pprm.pool_size = rxq->num_rx_buf / rxq->frag_count + 1;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
@@ -3767,6 +3768,179 @@ static int mana_dealloc_queues(struct net_device *ndev)
 	return 0;
 }
 
+static void mana_qset_snapshot(const struct mana_port_context *ctx,
+			       struct mana_qset *out)
+{
+	out->eqs		= ctx->eqs;
+	out->tx_qp		= ctx->tx_qp;
+	out->rxqs		= ctx->rxqs;
+	out->indir_table	= ctx->indir_table;
+	out->indir_table_sz	= ctx->indir_table_sz;
+	out->rxobj_table	= ctx->rxobj_table;
+	out->default_rxobj	= ctx->default_rxobj;
+	out->num_queues		= ctx->num_queues;
+	out->rx_queue_size	= ctx->rx_queue_size;
+	out->tx_queue_size	= ctx->tx_queue_size;
+	out->priv_flags		= ctx->priv_flags;
+}
+
+/* Vport identity and port debugfs outlive queue sets. */
+static void mana_qset_install(struct mana_port_context *ctx,
+			      const struct mana_qset *qset)
+{
+	ctx->eqs		= qset->eqs;
+	ctx->tx_qp		= qset->tx_qp;
+	ctx->rxqs		= qset->rxqs;
+	ctx->indir_table	= qset->indir_table;
+	ctx->indir_table_sz	= qset->indir_table_sz;
+	ctx->rxobj_table	= qset->rxobj_table;
+	ctx->default_rxobj	= qset->default_rxobj;
+	ctx->num_queues		= qset->num_queues;
+	ctx->rx_queue_size	= qset->rx_queue_size;
+	ctx->tx_queue_size	= qset->tx_queue_size;
+	ctx->priv_flags		= qset->priv_flags;
+}
+
+/* Copy the vport identity without borrowing the live queues. */
+struct mana_port_context *mana_qset_scratch_alloc(struct mana_port_context *apc)
+{
+	struct mana_port_context *scratch;
+
+	scratch = kvzalloc_obj(*scratch, GFP_KERNEL);
+	if (!scratch)
+		return NULL;
+
+	*scratch = *apc;
+
+	scratch->eqs		= NULL;
+	scratch->tx_qp		= NULL;
+	scratch->rxqs		= NULL;
+	scratch->indir_table	= NULL;
+	scratch->rxobj_table	= NULL;
+	scratch->default_rxobj	= INVALID_MANA_HANDLE;
+	scratch->mana_eqs_debugfs = NULL;
+
+	/* Do not consume the live set's pre-allocated RX buffers. */
+	scratch->rxbufs_pre	= NULL;
+	scratch->das_pre	= NULL;
+	scratch->rxbpre_total	= 0;
+
+	/* Suppress debugfs names that would collide with the live set. */
+	scratch->mana_port_debugfs = ERR_PTR(-ENODEV);
+
+	return scratch;
+}
+
+void mana_qset_scratch_free(struct mana_port_context *scratch)
+{
+	kvfree(scratch);
+}
+
+int mana_alloc_qset(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)
+{
+	struct net_device *ndev = scratch->ndev;
+	int err;
+
+	ASSERT_RTNL();
+
+	scratch->num_queues	= num_queues;
+	scratch->rx_queue_size	= rx_queue_size;
+	scratch->tx_queue_size	= tx_queue_size;
+	scratch->priv_flags	= priv_flags;
+
+	err = mana_init_port_context(scratch);
+	if (err)
+		goto out_err;
+
+	err = mana_rss_table_alloc(scratch);
+	if (err)
+		goto cleanup_rxq_array;
+
+	err = mana_create_eq(scratch);
+	if (err)
+		goto cleanup_rss;
+
+	err = mana_create_txq(scratch, ndev);
+	if (err)
+		goto cleanup_eq;
+
+	err = mana_add_rx_queues(scratch, ndev);
+	if (err)
+		goto cleanup_rxq;
+
+	mana_rss_table_init(scratch);
+
+	mana_qset_snapshot(scratch, out);
+	return 0;
+
+cleanup_rxq:
+	mana_destroy_rxqs(scratch);
+	mana_destroy_txq(scratch);
+cleanup_eq:
+	mana_destroy_eq(scratch);
+cleanup_rss:
+	mana_cleanup_indir_table(scratch);
+cleanup_rxq_array:
+	kfree(scratch->rxqs);
+	scratch->rxqs = NULL;
+out_err:
+	netdev_err(ndev, "%s(num_queues=%u) failed: %d\n", __func__,
+		   num_queues, err);
+	return err;
+}
+
+/* Under RTNL, free only queues no longer shared with the installed set. */
+void mana_free_qset(struct mana_port_context *scratch, struct mana_qset *qset)
+{
+	struct bpf_prog *retiring_prog;
+	unsigned int retiring_queues;
+
+	ASSERT_RTNL();
+
+	if (!qset->rxqs && !qset->tx_qp && !qset->eqs)
+		return;
+
+	if (qset->tx_qp) {
+		unsigned int q;
+
+		for (q = 0; q < qset->num_queues; q++) {
+			if (qset->tx_qp[q])
+				WRITE_ONCE(qset->tx_qp[q]->txq.retiring, true);
+		}
+	}
+
+	/* Keep retired queues and arrays through this grace period; local NAPI
+	 * synchronization does not drain other devices' XDP.
+	 */
+	synchronize_net();
+
+	mana_qset_install(scratch, qset);
+
+	/* Keep retiring RXQs' XDP programs and references until RX teardown. */
+	retiring_prog = mana_chn_xdp_peek(scratch);
+	retiring_queues = scratch->num_queues;
+
+	/* Published queues were drained before the swap; unpublished queues
+	 * have never admitted TX.
+	 */
+	/* Fence RQs before unmapping, but teardown proceeds on errors. */
+	mana_fence_rqs(scratch);
+
+	mana_destroy_rxqs(scratch);
+
+	mana_chn_xdp_release(retiring_prog, retiring_queues);
+
+	mana_destroy_txq(scratch);
+	mana_destroy_eq(scratch);
+	mana_cleanup_indir_table(scratch);
+	kfree(scratch->rxqs);
+	scratch->rxqs = NULL;
+
+	memset(qset, 0, sizeof(*qset));
+}
+
 int mana_detach(struct net_device *ndev, bool from_close)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
@@ -4245,6 +4419,10 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 		unregister_netdevice(ndev);
 		mana_cleanup_indir_table(apc);
 
+		/* Remove the port from reset walks before freeing its netdev.
+		 */
+		ac->ports[i] = NULL;
+
 		rtnl_unlock();
 
 		free_netdev(ndev);
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 83b7eff4646e..6a407b34fd68 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -143,6 +143,9 @@ struct mana_txq {
 
 	bool napi_initialized;
 
+	/* Suppress completion wakeups on the replacement's netdev queue. */
+	bool retiring;
+
 	struct mana_stats_tx stats;
 };
 
@@ -537,6 +540,7 @@ struct mana_context {
 	u8 bm_hostmode;
 
 	struct mana_ethtool_hc_stats hc_stats;
+
 	struct workqueue_struct *per_port_queue_reset_wq;
 	/* Workqueue for querying hardware stats */
 	struct delayed_work gf_stats_work;
@@ -661,6 +665,23 @@ struct mana_port_context {
 	u32 steer_cqe_coalescing;
 };
 
+struct mana_qset {
+	struct mana_eq		*eqs;
+	struct mana_tx_qp	**tx_qp;
+	struct mana_rxq		**rxqs;
+
+	u32			*indir_table;
+	u32			indir_table_sz;
+	mana_handle_t		*rxobj_table;
+	mana_handle_t		default_rxobj;
+
+	unsigned int		num_queues;
+	unsigned int		rx_queue_size;
+	unsigned int		tx_queue_size;
+	u32			priv_flags;
+
+};
+
 netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx,
 		    bool update_hash, bool update_tab);
@@ -670,6 +691,14 @@ int mana_alloc_queues(struct net_device *ndev);
 int mana_attach(struct net_device *ndev);
 int mana_detach(struct net_device *ndev, bool from_close);
 
+struct mana_port_context *
+mana_qset_scratch_alloc(struct mana_port_context *apc);
+void mana_qset_scratch_free(struct mana_port_context *scratch);
+int mana_alloc_qset(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);
+void mana_free_qset(struct mana_port_context *scratch, struct mana_qset *qset);
+
 void mana_dim_change(struct mana_cq *cq, bool enable);
 
 int mana_probe(struct gdma_dev *gd, bool resuming);
@@ -685,6 +714,8 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
 		 struct xdp_buff *xdp, void *buf_va, uint pkt_len);
 struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
 void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
+struct bpf_prog *mana_chn_xdp_peek(struct mana_port_context *apc);
+void mana_chn_xdp_release(struct bpf_prog *prog, unsigned int num_queues);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 int mana_query_gf_stats(struct mana_context *ac);
 int mana_query_link_cfg(struct mana_port_context *apc);

  reply	other threads:[~2026-10-09 14:41 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-09 14:41 [PATCH net-next v6 00/13] net: mana: reconfigure by replacing the queue set Wei Hu
2026-10-09 14:41 ` Wei Hu [this message]
2026-10-09 14:41 ` [PATCH net-next v6 02/13] net: mana: share the EQ pool across a queue-set swap Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 03/13] net: mana: keep per-queue statistics in the port context Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 04/13] net: mana: swap queue sets in mana_set_channels Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 05/13] net: mana: swap queue sets in mana_set_ringparam Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 06/13] net: mana: swap queue sets in mana_set_priv_flags Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 07/13] net: mana: swap queue sets in mana_change_mtu Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 08/13] net: mana: swap queue sets in mana_xdp_set Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 09/13] net: mana: do not bail out of mana_detach on dealloc failure Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 10/13] net: mana: release EQs left idle by a channel-count reduction Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 11/13] net: mana: keep a user-configured RSS table across a queue rebuild Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 12/13] net: mana: keep the surviving queues when the channel count is reduced Wei Hu
2026-10-09 14:41 ` [PATCH net-next v6 13/13] net: mana: keep the existing queues when the channel count is raised Wei Hu

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=24eeca6a691150407d5ce94650d3ee51cf11b620.1790795005.git.weh@linux.microsoft.com \
    --to=weh@linux.microsoft.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=decui@microsoft.com \
    --cc=dipayanroy@linux.microsoft.com \
    --cc=edumazet@google.com \
    --cc=ernis@linux.microsoft.com \
    --cc=haiyangz@microsoft.com \
    --cc=hawk@kernel.org \
    --cc=horms@kernel.org \
    --cc=jgg@ziepe.ca \
    --cc=john.fastabend@gmail.com \
    --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=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    --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®