[PATCH net-next v6 15/15] ibmveth: Complete set_channels down-path and mq_fallback max_rx cap

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

Patch 14 wires live ethtool -L rx. This patch completes the down-path
publish/rollback and get_channels() once mq_fallback is set.

When down: set TX queues first, then publish the desired RX count in
adapter->num_rx_queues and netdev->real_num_rx_queues (rx-N sysfs and
CMO desired change immediately). Do not allocate RX mappings, buffers
or IRQs while down. If RX set_real fails, restore the old TX real_num.

When up: resize RX, then the existing TX LTB
stop/alloc/set_real_num_tx/free/wake path. Skip that path when the TX
count is unchanged. If TX cannot reach the requested count, roll RX
back; that rollback is best-effort.

Validate tx_count before touching RX so a request the driver will
reject does not resize RX first. The ethtool core already range-checks
against the max_tx get_channels() reports; this is the driver's own
guard.

get_channels() always reports the live rx_count. When mq_fallback is
set it caps max_rx at that count. Understating rx_count would turn a
TX-only ethtool -L into a silent RX shrink. Capping max_rx blocks
growth in the core without misreporting what is configured.

i = old_tx before the TX alloc loop is readability; the old
for-initializer already defined i for the free walk.

Guard poll_controller() with adapter->opened so netpoll cannot walk
unallocated queue state while closed.

Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
Tested-by: Shaik Abdulla <shaik.abdulla1@ibm.com>
---

Changes in v6:
- get_channels() caps max_rx at the live rx_count when mq_fallback
  is set; rx_count stays live
- roll back TX real_num if down-path RX set_real fails
- poll_controller() returns if !opened
- noted: rx > 1 reject once mq_fallback is set is patch 14

Changes in v5:
- set_channels / resize_rx_channels read via get_num_rx_queues()
- Series renumber: mailed v4 13/14 set_channels -> tip P15 (end; 14->15)
- set_channels: gate on adapter->opened (not IFF_UP) for live RX resize
  vs while-down stash
- Down-path RX stash also refreshes CMO (publish + set_real_num_rx)
- When up: resize RX then TX; roll RX back if TX cannot reach goal

Changes in v4:
- On !IFF_UP, stash num_rx_queues only after TX set succeeds; do not
  allocate live subordinate IRQs/buffers while down.
- Initialize i = old_tx on the TX adjust path.
- Always return rc from set_channels().
- Split from the resize-helper patch (same split as v3) while keeping
  a live caller of resize_rx_channels() in the previous patch.

 drivers/net/ethernet/ibm/ibmveth.c | 143 +++++++++++++++++++++++------
 1 file changed, 117 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 5aef8a1f2c23..4cd00ff3d43e 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -3156,15 +3156,24 @@ static void ibmveth_get_channels(struct net_device *netdev,
 				 struct ethtool_channels *channels)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
+	unsigned int rx_count = ibmveth_get_num_rx_queues(adapter);
 
 	channels->max_tx = ibmveth_real_max_tx_queues();
 	channels->tx_count = netdev->real_num_tx_queues;
 
-	if (adapter->multi_queue)
+	/*
+	 * Always report the live RX count. ethtool -L is read-modify-
+	 * write, so a TX-only request echoes rx_count back at us; an
+	 * understated value would be applied as a silent RX shrink.
+	 * mq_fallback instead caps max_rx at the live count, which
+	 * blocks growth in the core without misreporting what is
+	 * currently configured.
+	 */
+	channels->rx_count = rx_count;
+	if (adapter->multi_queue && !adapter->mq_fallback)
 		channels->max_rx = IBMVETH_MAX_RX_QUEUES;
 	else
-		channels->max_rx = 1;
-	channels->rx_count = ibmveth_get_num_rx_queues(adapter);
+		channels->max_rx = rx_count;
 }
 
 /**
@@ -3233,28 +3242,83 @@ static int ibmveth_set_channels(struct net_device *netdev,
 				struct ethtool_channels *channels)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
-	unsigned int old = netdev->real_num_tx_queues,
-		     goal = channels->tx_count;
+	unsigned int old_rx = ibmveth_get_num_rx_queues(adapter);
+	unsigned int goal_rx = channels->rx_count;
+	unsigned int old_tx = netdev->real_num_tx_queues;
+	unsigned int goal_tx = channels->tx_count;
+	unsigned int want_tx = goal_tx;
+	bool rx_changed = false;
 	int rc, i;
 
-	/* Validate RX (and resize when opened) before the down-path
-	 * early return so MQ/range errors are reported here. Publishing
-	 * the desired RX count and CMO while down is the next patch.
-	 */
-	rc = ibmveth_resize_rx_channels(adapter, channels->rx_count);
+	if (goal_tx < 1 || goal_tx > ibmveth_real_max_tx_queues()) {
+		netdev_err(netdev,
+			   "Invalid TX queue count %u (must be 1-%u)\n",
+			   goal_tx, ibmveth_real_max_tx_queues());
+		return -EINVAL;
+	}
+
+	/* RX range / MQ checks live in ibmveth_resize_rx_channels(). */
+	rc = ibmveth_resize_rx_channels(adapter, goal_rx);
 	if (rc)
 		return rc;
 
-	if (!adapter->opened)
-		return netif_set_real_num_tx_queues(netdev, goal);
+	/* If RX resources are not live (never opened, or close+open failed
+	 * while IFF_UP stayed set), publish desired queue counts without
+	 * allocating.
+	 */
+	if (!adapter->opened) {
+		/* Apply TX first so a failure leaves the published RX
+		 * count unchanged.
+		 */
+		rc = netif_set_real_num_tx_queues(netdev, goal_tx);
+		if (rc)
+			return rc;
+
+		/* Publish desired RX count for next open() and refresh CMO;
+		 * do not allocate while down.
+		 */
+		if (goal_rx != ibmveth_get_num_rx_queues(adapter)) {
+			ibmveth_publish_num_rx_queues(adapter, goal_rx);
+			rc = netif_set_real_num_rx_queues(netdev, goal_rx);
+			if (rc) {
+				int tx_rc;
+
+				ibmveth_publish_num_rx_queues(adapter, old_rx);
+				tx_rc = netif_set_real_num_tx_queues(netdev,
+								     old_tx);
+				if (tx_rc)
+					netdev_err(netdev,
+						   "Failed to restore TX queues to %u after RX failure: %d\n",
+						   old_tx, tx_rc);
+				return rc;
+			}
+			if (firmware_has_feature(FW_FEATURE_CMO)) {
+				unsigned long dma;
+
+				dma = ibmveth_get_desired_dma(adapter->vdev);
+				vio_cmo_set_dev_desired(adapter->vdev, dma);
+			}
+		}
+		return 0;
+	}
+
+	if (goal_rx != old_rx)
+		rx_changed = true;
 
 	/* We have IBMVETH_MAX_QUEUES netdev_queue's allocated
 	 * but we may need to alloc/free the ltb's.
 	 */
+	if (goal_tx == old_tx)
+		return 0;
+
 	netif_tx_stop_all_queues(netdev);
 
-	/* Allocate any queue that we need */
-	for (i = old; i < goal; i++) {
+	/* Allocate any new TX LTBs. i starts at old_tx for the free walk
+	 * below when this loop body never runs (goal_tx == old_tx already
+	 * returned; goal_tx < old_tx is scale-down).
+	 */
+	i = old_tx;
+	for (; i < goal_tx; i++) {
 		if (adapter->tx_ltb_ptr[i])
 			continue;
 
@@ -3263,28 +3327,50 @@ static int ibmveth_set_channels(struct net_device *netdev,
 			continue;
 
 		/* if something goes wrong, free everything we just allocated */
-		netdev_err(netdev, "Failed to allocate more tx queues, returning to %d queues\n",
-			   old);
-		goal = old;
-		old = i;
+		netdev_err(netdev, "Failed to allocate more tx queues, returning to %u queues\n",
+			   old_tx);
+		goal_tx = old_tx;
+		old_tx = i;
 		break;
 	}
-	rc = netif_set_real_num_tx_queues(netdev, goal);
+	rc = netif_set_real_num_tx_queues(netdev, goal_tx);
 	if (rc) {
-		netdev_err(netdev, "Failed to set real tx queues, returning to %d queues\n",
-			   old);
-		goal = old;
-		old = i;
+		netdev_err(netdev, "Failed to set real tx queues, returning to %u queues\n",
+			   old_tx);
+		goal_tx = old_tx;
+		old_tx = i;
 	}
 	/* Free any that are no longer needed */
-	for (i = old; i > goal; i--) {
+	for (i = old_tx; i > goal_tx; i--) {
 		if (adapter->tx_ltb_ptr[i - 1])
 			ibmveth_free_tx_ltb(adapter, i - 1);
 	}
 
 	netif_tx_wake_all_queues(netdev);
 
-	return rc;
+	if (netdev->real_num_tx_queues != want_tx) {
+		if (rx_changed) {
+			/*
+			 * Only meaningful once RX is live. num_slots is
+			 * embedded in the adapter and outlives the DMA ring,
+			 * so reading it at function entry is safe but can
+			 * return a stale geometry from before the resize.
+			 */
+			int rxq_entries = adapter->rx_queue[0].num_slots;
+			int rb;
+
+			rb = ibmveth_resize_rx_queues_incremental(adapter,
+								  old_rx,
+								  rxq_entries);
+			if (rb)
+				netdev_err(netdev,
+					   "Failed to roll back RX queues to %u after TX failure: %d\n",
+					   old_rx, rb);
+		}
+		return rc ? rc : -ENOMEM;
+	}
+
+	return 0;
 }
 
 static const struct ethtool_ops netdev_ethtool_ops = {
@@ -3951,9 +4037,14 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
 static void ibmveth_poll_controller(struct net_device *dev)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(dev);
-	unsigned int num = ibmveth_get_num_rx_queues(adapter);
+	unsigned int num;
 	int i;
 
+	if (!adapter->opened)
+		return;
+
+	num = ibmveth_get_num_rx_queues(adapter);
+
 	for (i = 0; i < num; i++)
 		ibmveth_replenish_task(adapter, i);
 
-- 
2.50.1 (Apple Git-155)