[PATCH net-next v4 12/13] net: mana: keep the surviving queues when the channel count is reduced

[Long Li]

Split the live set into a kept prefix and a retiring tail. Reductions
allocate only pointer arrays and steering tables, retaining the kept
queues' page pools, buffers, NAPI state and XDP references.

After publication, wait for TX-selection readers before freeing the old
containers, then retire only the tail. Failed publication discards the
new containers without freeing shared queues.

Signed-off-by: Long Li <longli@xxxxxxxxxxxxx>
---
Changes in v4:
  - Wait for TX-selection readers before freeing old containers.
  - Correct the allocation and shared-queue ownership descriptions;
    shorten comments and the commit message.

 drivers/net/ethernet/microsoft/mana/mana_en.c | 112 +++++++++++++++++-
 .../ethernet/microsoft/mana/mana_ethtool.c    |  30 +++++
 include/net/mana/mana.h                       |   4 +
 3 files changed, 143 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 78be88b29c99ba2a349df6b43e13487db8c69be1..158f9a6ce42157ad7afd45ec642405fbd81f0bac 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -4146,6 +4146,114 @@ void mana_qset_scratch_free(struct mana_port_context *scratch)
 	kvfree(scratch);
 }
 
+/* Split into kept queues and a retiring tail without changing live ownership.
+ * Queue i retains EQ i.
+ */
+int mana_split_qset(struct mana_port_context *apc,
+		    struct mana_port_context *scratch, unsigned int new_count,
+		    struct mana_qset *out_new, struct mana_qset *out_tail)
+{
+	unsigned int old_count = apc->num_queues;
+	struct mana_tx_qp **new_tx, **tail_tx;
+	struct mana_rxq **new_rx, **tail_rx;
+	unsigned int tail_count;
+	bool indir_lost;
+	unsigned int i;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (WARN_ON(new_count == 0 || new_count >= old_count))
+		return -EINVAL;
+	if (WARN_ON(!apc->tx_qp || !apc->rxqs))
+		return -EINVAL;
+
+	tail_count = old_count - new_count;
+
+	/* Build steering separately so it cannot index beyond the shortened RX
+	 * array.
+	 */
+	scratch->num_queues = new_count;
+	err = mana_rss_table_alloc(scratch);
+	if (err)
+		return err;
+
+	if (mana_rss_table_keep(apc, new_count, &indir_lost))
+		memcpy(scratch->indir_table, apc->indir_table,
+		       apc->indir_table_sz * sizeof(*apc->indir_table));
+	else
+		mana_rss_table_init(scratch);
+
+	new_tx = kzalloc_objs(struct mana_tx_qp *, new_count);
+	new_rx = kzalloc_objs(struct mana_rxq *, new_count);
+	tail_tx = kzalloc_objs(struct mana_tx_qp *, tail_count);
+	tail_rx = kzalloc_objs(struct mana_rxq *, tail_count);
+	if (!new_tx || !new_rx || !tail_tx || !tail_rx) {
+		err = -ENOMEM;
+		goto free_arrays;
+	}
+
+	for (i = 0; i < new_count; i++) {
+		new_tx[i] = apc->tx_qp[i];
+		new_rx[i] = apc->rxqs[i];
+	}
+	for (i = 0; i < tail_count; i++) {
+		tail_tx[i] = apc->tx_qp[new_count + i];
+		tail_rx[i] = apc->rxqs[new_count + i];
+	}
+
+	out_new->tx_qp		= new_tx;
+	out_new->rxqs		= new_rx;
+	out_new->indir_table	= scratch->indir_table;
+	out_new->indir_table_sz	= scratch->indir_table_sz;
+	out_new->rxobj_table	= scratch->rxobj_table;
+	out_new->default_rxobj	= apc->rxqs[0]->rxobj;
+	out_new->num_queues	= new_count;
+	out_new->rx_queue_size	= apc->rx_queue_size;
+	out_new->tx_queue_size	= apc->tx_queue_size;
+	out_new->priv_flags	= apc->priv_flags;
+	out_new->mtu		= apc->configured_mtu;
+	out_new->bpf_prog	= apc->bpf_prog;
+	out_new->rxfh_indir_lost = indir_lost;
+
+	scratch->indir_table	= NULL;
+	scratch->rxobj_table	= NULL;
+
+	memset(out_tail, 0, sizeof(*out_tail));
+	out_tail->tx_qp		= tail_tx;
+	out_tail->rxqs		= tail_rx;
+	out_tail->default_rxobj	= INVALID_MANA_HANDLE;
+	out_tail->num_queues	= tail_count;
+	out_tail->rx_queue_size	= apc->rx_queue_size;
+	out_tail->tx_queue_size	= apc->tx_queue_size;
+	out_tail->priv_flags	= apc->priv_flags;
+	out_tail->mtu		= apc->configured_mtu;
+	out_tail->bpf_prog	= apc->bpf_prog;
+
+	return 0;
+
+free_arrays:
+	kfree(new_tx);
+	kfree(new_rx);
+	kfree(tail_tx);
+	kfree(tail_rx);
+	mana_cleanup_indir_table(scratch);
+	return err;
+}
+
+/* Free containers only; the live port still owns the queues. */
+void mana_discard_split(struct mana_qset *newq, struct mana_qset *tailq)
+{
+	kfree(newq->tx_qp);
+	kfree(newq->rxqs);
+	kfree(newq->indir_table);
+	kfree(newq->rxobj_table);
+	kfree(tailq->tx_qp);
+	kfree(tailq->rxqs);
+	memset(newq, 0, sizeof(*newq));
+	memset(tailq, 0, sizeof(*tailq));
+}
+
 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,
@@ -4351,9 +4459,7 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq,
 	if (err)
 		goto rollback;
 
-	/* Install XDP and per-RXQ references before steering reaches new
-	 * queues.
-	 */
+	/* Install XDP before steering reaches the incoming RXQs. */
 	mana_chn_setxdp(apc, mana_xdp_get(apc));
 
 	err = mana_config_rss(apc, TRI_STATE_TRUE, true, true);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index acc82fa9f0057120920b5a09bbb2bc7185707e65..0b8c2f61d6263c65a8119b94426f794b218ad55f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -737,6 +737,36 @@ static int mana_set_channels(struct net_device *ndev,
 		goto clear_flag;
 	}
 
+	if (new_count < apc->num_queues) {
+		struct mana_qset tailq;
+
+		err = mana_split_qset(apc, scratch, new_count, &newq, &tailq);
+		if (err)
+			goto free_scratch;
+
+		err = mana_publish_qset(apc, &newq, &oldq);
+		if (err) {
+			/* Discard containers only; their queues still belong to
+			 * the old set.
+			 */
+			mana_discard_split(&newq, &tailq);
+			goto free_scratch;
+		}
+
+		/* Wait for ndo_select_queue() readers of oldq.indir_table. Free
+		 * only containers; the queues belong to the kept set or tail.
+		 */
+		synchronize_net();
+
+		kfree(oldq.tx_qp);
+		kfree(oldq.rxqs);
+		kfree(oldq.indir_table);
+		kfree(oldq.rxobj_table);
+
+		mana_free_qset(scratch, &tailq);
+		goto free_scratch;
+	}
+
 	err = mana_alloc_qset(apc, scratch, new_count, apc->rx_queue_size,
 			      apc->tx_queue_size, apc->priv_flags,
 			      apc->configured_mtu, apc->bpf_prog, &newq);
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 84b8151f0693c7e7ef06a558c69e2d207b445921..5ec75de0b644569acdf697e997c262d999295a06 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -743,6 +743,10 @@ int mana_alloc_qset(struct mana_port_context *apc,
 		    unsigned int rx_queue_size, unsigned int tx_queue_size,
 		    u32 priv_flags, int mtu, struct bpf_prog *bpf_prog,
 		    struct mana_qset *out);
+int mana_split_qset(struct mana_port_context *apc,
+		    struct mana_port_context *scratch, unsigned int new_count,
+		    struct mana_qset *out_new, struct mana_qset *out_tail);
+void mana_discard_split(struct mana_qset *newq, struct mana_qset *tailq);
 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