[PATCH net-next v3 07/15] ibmveth: Add RX queue register/deregister helpers for MQ

[Mingming Cao <mmc@linux.ibm.com>]

MQ RX replaces a single adapter-level register/free pair with a mixed
PHYP model: queue 0 via h_register_logical_lan*(), subordinates via
H_REG_LOGICAL_LAN_QUEUE. Subordinate registration returns queue handles
and hardware IRQ numbers that must be mapped to Linux virqs and unwound
on failure.

Add queue lifecycle helpers to isolate that control plane:

  ibmveth_register_logical_lan_queue()
  ibmveth_register_single_rx_queue()
  ibmveth_deregister_single_rx_queue()
  ibmveth_register_rx_queues()
  ibmveth_free_all_queues()
  ibmveth_dispose_subordinate_irq_mappings()

These helpers are called only when multi_queue is enabled (patch 11).
Until then open/close still use the legacy register and buffer hcall
path; legacy firmware is unchanged.

When multi_queue is enabled, queue 0 uses
h_register_logical_lan_with_handle() so all queues share the per-queue
buffer hcall path. register_rx_queues() registers with PHYP only;
interrupt delivery is enabled later from ibmveth_setup_rx_interrupts()
after request_irq(). Partial registration failure disposes subordinate virq
mappings before ibmveth_free_all_queues() clears handles;
free_all_queues() clears queue handles only — IRQ mappings are released
by dispose_subordinate_irq_mappings() or cleanup_rx_interrupts().
This commit also centralizes hcall accounting on the register/free paths.

Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
 drivers/net/ethernet/ibm/ibmveth.c | 337 ++++++++++++++++++++++++++++-
 1 file changed, 332 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 63b0184c622a..7fc11a4e1f61 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -21,6 +21,8 @@
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/ethtool.h>
@@ -399,6 +401,28 @@ ibmveth_enable_irq(struct ibmveth_adapter *adapter, int queue_index)
 	return ibmveth_toggle_irq(adapter, queue_index, true);
 }
 
+/**
+ * ibmveth_dispose_subordinate_irq_mappings - Drop virq mappings for queues 1..N
+ * @adapter: ibmveth adapter structure
+ *
+ * Subordinate queues get mappings from irq_create_mapping() during PHYP
+ * registration.  Queue 0 uses netdev->irq from device tree and is left alone.
+ * Call after free_irq() when handlers were installed, or alone when open
+ * fails during register_rx_queues() before request_irq().
+ */
+static void
+ibmveth_dispose_subordinate_irq_mappings(struct ibmveth_adapter *adapter)
+{
+	int i;
+
+	for (i = 1; i < adapter->num_rx_queues; i++) {
+		if (adapter->queue_irq[i]) {
+			irq_dispose_mapping(adapter->queue_irq[i]);
+			adapter->queue_irq[i] = 0;
+		}
+	}
+}
+
 /**
  * ibmveth_setup_rx_interrupts - Register IRQs and enable NAPI
  * @adapter: ibmveth adapter structure
@@ -1082,8 +1106,8 @@ ibmveth_free_tx_resources(struct ibmveth_adapter *adapter)
 }
 
 static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
-				   union ibmveth_buf_desc rxq_desc,
-				   u64 mac_address)
+					union ibmveth_buf_desc rxq_desc,
+					u64 mac_address)
 {
 	int rc, try_again = 1;
 
@@ -1093,13 +1117,29 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
 	 * try again, but only once.
 	 */
 retry:
-	rc = h_register_logical_lan(adapter->vdev->unit_address,
-				    adapter->buffer_list_dma[0], rxq_desc.desc,
-				    adapter->filter_list_dma, mac_address);
+	/* In multi-queue mode, obtain a queue handle for queue 0 so all RX
+	 * queues can use the same per-queue buffer hypercalls.
+	 */
+	if (adapter->multi_queue) {
+		rc = h_register_logical_lan_with_handle(adapter->vdev->unit_address,
+							adapter->buffer_list_dma[0],
+							rxq_desc.desc,
+							adapter->filter_list_dma,
+							mac_address,
+							&adapter->queue_handle[0]);
+	} else {
+		rc = h_register_logical_lan(adapter->vdev->unit_address,
+					    adapter->buffer_list_dma[0],
+					    rxq_desc.desc,
+					    adapter->filter_list_dma,
+					    mac_address);
+	}
+	adapter->hcall_stats.reg_lan++;
 
 	if (rc != H_SUCCESS && try_again) {
 		do {
 			rc = h_free_logical_lan(adapter->vdev->unit_address);
+			adapter->hcall_stats.free_lan++;
 		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
 
 		try_again = 0;
@@ -1136,6 +1176,293 @@ static void __maybe_unused ibmveth_free_rx_qstats(struct ibmveth_adapter *adapte
 	adapter->rx_qstats = NULL;
 }
 
+/**
+ * ibmveth_register_logical_lan_queue - Register subordinate queue with hypervisor
+ * @adapter: ibmveth adapter structure
+ * @rxq_desc: Receive queue descriptor
+ * @queue_index: RX queue index (1..N for subordinate queues)
+ *
+ * Registers a subordinate receive queue using H_REG_LOGICAL_LAN_QUEUE.
+ * On success, stores the queue handle and virtual IRQ in the adapter.
+ * Retries once if registration fails (handles kexec case).  If IRQ mapping
+ * fails after a successful hypervisor registration, the queue is freed
+ * before returning.
+ *
+ * Return: H_SUCCESS on success, negative errno on IRQ mapping failure,
+ *         hypervisor error code otherwise
+ */
+static int
+ibmveth_register_logical_lan_queue(struct ibmveth_adapter *adapter,
+				   union ibmveth_buf_desc rxq_desc,
+				   int queue_index)
+{
+	unsigned long handle, hwirq;
+	unsigned int virq;
+	long lpar_rc;
+	int try_again = 1;
+
+retry:
+	netdev_dbg(adapter->netdev,
+		   "Attempting to register queue %d: unit_addr=0x%x buffer_list_dma=0x%llx rxq_desc=0x%llx\n",
+		   queue_index, adapter->vdev->unit_address,
+		   (unsigned long long)adapter->buffer_list_dma[queue_index],
+		   (unsigned long long)rxq_desc.desc);
+
+	lpar_rc = h_reg_logical_lan_queue(adapter->vdev->unit_address,
+					  adapter->buffer_list_dma[queue_index],
+					  rxq_desc.desc, &handle, &hwirq);
+	adapter->hcall_stats.reg_lan_queue++;
+
+	if (lpar_rc == H_SUCCESS) {
+		virq = irq_create_mapping(NULL, hwirq);
+		if (!virq) {
+			unsigned long free_rc;
+
+			netdev_err(adapter->netdev,
+				   "Failed to map IRQ for queue %d (hwirq=%lu)\n",
+				   queue_index, hwirq);
+			do {
+				free_rc = h_free_logical_lan_queue(adapter->vdev->unit_address,
+								   handle);
+			} while (H_IS_LONG_BUSY(free_rc) || (free_rc == H_BUSY));
+			adapter->hcall_stats.free_lan_queue++;
+			if (free_rc != H_SUCCESS)
+				netdev_err(adapter->netdev,
+					   "h_free_logical_lan_queue failed for queue %d after IRQ map failure: rc=0x%lx\n",
+					   queue_index, free_rc);
+			return -EINVAL;
+		}
+
+		adapter->queue_handle[queue_index] = handle;
+		adapter->queue_irq[queue_index] = virq;
+
+		netdev_dbg(adapter->netdev,
+			   "queue %d registered: handle=0x%llx irq=%u\n",
+			   queue_index, adapter->queue_handle[queue_index],
+			   adapter->queue_irq[queue_index]);
+		return H_SUCCESS;
+	}
+
+	if (lpar_rc == H_FUNCTION) {
+		if (adapter->multi_queue) {
+			netdev_info(adapter->netdev,
+				    "Multi queue mode not supported by firmware, falling back to single queue\n");
+			adapter->multi_queue = 0;
+		} else {
+			netdev_err(adapter->netdev,
+				   "Unexpected H_FUNCTION for queue %d registration (MQ mode already disabled)\n",
+				   queue_index);
+		}
+		return lpar_rc;
+	}
+
+	if (try_again) {
+		try_again = 0;
+		goto retry;
+	}
+
+	netdev_err(adapter->netdev,
+		   "h_reg_logical_lan_queue failed with %ld after retry\n",
+		   lpar_rc);
+	netdev_err(adapter->netdev,
+		   "queue %d params: unit_addr=0x%x buffer_list_dma=0x%llx rxq_desc=0x%llx\n",
+		   queue_index, adapter->vdev->unit_address,
+		   (unsigned long long)adapter->buffer_list_dma[queue_index],
+		   (unsigned long long)rxq_desc.desc);
+
+	return lpar_rc;
+}
+
+/**
+ * ibmveth_register_single_rx_queue - Register one subordinate RX queue
+ * @adapter: ibmveth adapter structure
+ * @queue_idx: Queue index to register (1..N)
+ * @mac_address: MAC address (unused; reserved for API symmetry)
+ *
+ * Builds the queue descriptor and registers with the hypervisor via
+ * ibmveth_register_logical_lan_queue().
+ *
+ * Return: 0 on success, -EINVAL if @queue_idx is invalid, -EIO on failure
+ */
+static int
+ibmveth_register_single_rx_queue(struct ibmveth_adapter *adapter,
+				 int queue_idx, u64 mac_address)
+{
+	struct net_device *netdev = adapter->netdev;
+	union ibmveth_buf_desc rxq_desc;
+	long lpar_rc;
+
+	(void)mac_address;
+
+	if (WARN_ON(queue_idx < 1 || queue_idx >= IBMVETH_MAX_RX_QUEUES))
+		return -EINVAL;
+
+	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
+				    adapter->rx_queue[queue_idx].queue_len;
+	rxq_desc.fields.address = adapter->rx_queue[queue_idx].queue_dma;
+
+	lpar_rc = ibmveth_register_logical_lan_queue(adapter, rxq_desc,
+						     queue_idx);
+	if (lpar_rc != H_SUCCESS) {
+		netdev_err(netdev, "Failed to register queue %d: rc=0x%lx\n",
+			   queue_idx, lpar_rc);
+		return -EIO;
+	}
+
+	netdev_dbg(netdev, "Registered queue %d with handle 0x%llx\n",
+		   queue_idx, adapter->queue_handle[queue_idx]);
+
+	return 0;
+}
+
+/**
+ * ibmveth_deregister_single_rx_queue - Deregister one subordinate RX queue
+ * @adapter: ibmveth adapter structure
+ * @queue_idx: Queue index to deregister (1..N)
+ *
+ * Deregisters a single queue via H_FREE_LOGICAL_LAN_QUEUE and disposes
+ * the IRQ mapping for subordinate queues. Queue 0 is freed only through
+ * ibmveth_free_all_queues() (H_FREE_LOGICAL_LAN).
+ */
+static void __maybe_unused
+ibmveth_deregister_single_rx_queue(struct ibmveth_adapter *adapter,
+				   int queue_idx)
+{
+	unsigned long lpar_rc;
+
+	if (!adapter->queue_handle[queue_idx])
+		return;
+
+	do {
+		lpar_rc = h_free_logical_lan_queue(adapter->vdev->unit_address,
+						   adapter->queue_handle[queue_idx]);
+	} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
+
+	adapter->hcall_stats.free_lan_queue++;
+
+	if (lpar_rc != H_SUCCESS) {
+		netdev_err(adapter->netdev,
+			   "h_free_logical_lan_queue failed for queue %d: rc=0x%lx\n",
+			   queue_idx, lpar_rc);
+	}
+
+	adapter->queue_handle[queue_idx] = 0;
+
+	if (queue_idx > 0 && adapter->queue_irq[queue_idx]) {
+		irq_dispose_mapping(adapter->queue_irq[queue_idx]);
+		adapter->queue_irq[queue_idx] = 0;
+	}
+
+	netdev_dbg(adapter->netdev, "Deregistered queue %d\n", queue_idx);
+}
+
+/**
+ * ibmveth_free_all_queues - Free all RX queues at once
+ * @adapter: ibmveth adapter structure
+ *
+ * Uses H_FREE_LOGICAL_LAN to free all queues in one hypercall.
+ * Used during interface close and registration error cleanup.
+ *
+ * Clears queue handles only; queue_irq[] is released by
+ * ibmveth_cleanup_rx_interrupts() on close, or by
+ * ibmveth_dispose_subordinate_irq_mappings() on partial register failure.
+ */
+static void ibmveth_free_all_queues(struct ibmveth_adapter *adapter)
+{
+	unsigned long lpar_rc;
+	int i;
+
+	netdev_dbg(adapter->netdev, "freeing all RX queues at once\n");
+
+	do {
+		lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
+		adapter->hcall_stats.free_lan++;
+	} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
+
+	if (lpar_rc != H_SUCCESS) {
+		netdev_err(adapter->netdev,
+			   "h_free_logical_lan failed: %ld\n", lpar_rc);
+	}
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		adapter->queue_handle[i] = 0;
+}
+
+/**
+ * ibmveth_register_rx_queues - Register RX queues with hypervisor
+ * @adapter: ibmveth adapter structure
+ * @mac_address: MAC address for device registration
+ *
+ * Registers queue 0 via ibmveth_register_logical_lan(), then subordinate
+ * queues 1..N when multi-queue mode is enabled.
+ *
+ * Return: 0 on success, -ENONET if queue 0 registration fails, -EIO on
+ *         subordinate queue registration failure
+ */
+static int
+ibmveth_register_rx_queues(struct ibmveth_adapter *adapter, u64 mac_address)
+{
+	struct net_device *netdev = adapter->netdev;
+	union ibmveth_buf_desc rxq_desc;
+	unsigned long lpar_rc;
+	int i, rc;
+
+	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
+				    adapter->rx_queue[0].queue_len;
+	rxq_desc.fields.address = adapter->rx_queue[0].queue_dma;
+	adapter->queue_irq[0] = netdev->irq;
+
+	rc = ibmveth_disable_irq(adapter, 0);
+	if (rc != H_SUCCESS)
+		netdev_dbg(netdev,
+			   "Failed to disable IRQ for queue 0 before registration, rc=%d\n",
+			   rc);
+
+	lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);
+	if (lpar_rc != H_SUCCESS) {
+		netdev_err(netdev, "h_register_logical_lan failed: %ld\n", lpar_rc);
+		netdev_err(netdev,
+			   "buffer TCE:0x%llx filter TCE:0x%llx rxq desc:0x%llx MAC:0x%llx\n",
+			   adapter->buffer_list_dma[0],
+			   adapter->filter_list_dma,
+			   rxq_desc.desc, mac_address);
+		return -ENONET;
+	}
+
+	if (adapter->num_rx_queues == 1 || !adapter->multi_queue) {
+		netdev_dbg(netdev,
+			   "registered 1 RX queue with hypervisor (single-queue mode)\n");
+		return 0;
+	}
+
+	netdev_dbg(netdev, "Registering %d subordinate queues (1-%d)\n",
+		   adapter->num_rx_queues - 1, adapter->num_rx_queues - 1);
+
+	for (i = 1; i < adapter->num_rx_queues; i++) {
+		rc = ibmveth_register_single_rx_queue(adapter, i, mac_address);
+		if (rc) {
+			if (!adapter->queue_handle[i] || !adapter->queue_irq[i]) {
+				netdev_err(netdev,
+					   "Invalid hypervisor return for queue %d: handle=0x%llx irq=%u\n",
+					   i, adapter->queue_handle[i],
+					   adapter->queue_irq[i]);
+			}
+			goto err_unregister;
+		}
+	}
+
+	netdev_dbg(netdev,
+		   "registered %d RX queues with hypervisor (multi-queue mode)\n",
+		   adapter->num_rx_queues);
+
+	return 0;
+
+err_unregister:
+	ibmveth_dispose_subordinate_irq_mappings(adapter);
+	ibmveth_free_all_queues(adapter);
+	return rc;
+}
+
 static int ibmveth_open(struct net_device *netdev)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
-- 
2.39.3 (Apple Git-146)