igc: Link queues to NAPI instances

Link queues to NAPI instances via netdev-genl API so that users can
query this information with netlink. Handle a few cases in the driver:
  1. Link/unlink the NAPIs when XDP is enabled/disabled
  2. Handle IGC_FLAG_QUEUE_PAIRS enabled and disabled

Example output when IGC_FLAG_QUEUE_PAIRS is enabled:

$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
                         --dump queue-get --json='{"ifindex": 2}'

[{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'},
 {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'rx'},
 {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'rx'},
 {'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'tx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'tx'},
 {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'tx'},
 {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'tx'}]

Since IGC_FLAG_QUEUE_PAIRS is enabled, you'll note that the same NAPI ID
is present for both rx and tx queues at the same index, for example
index 0:

{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'tx'},

To test IGC_FLAG_QUEUE_PAIRS disabled, a test system was booted using
the grub command line option "maxcpus=2" to force
igc_set_interrupt_capability to disable IGC_FLAG_QUEUE_PAIRS.

Example output when IGC_FLAG_QUEUE_PAIRS is disabled:

$ lscpu | grep "On-line CPU"
On-line CPU(s) list:      0,2

$ ethtool -l enp86s0  | tail -5
Current hardware settings:
RX:		n/a
TX:		n/a
Other:		1
Combined:	2

$ cat /proc/interrupts  | grep enp
 144: [...] enp86s0
 145: [...] enp86s0-rx-0
 146: [...] enp86s0-rx-1
 147: [...] enp86s0-tx-0
 148: [...] enp86s0-tx-1

1 "other" IRQ, and 2 IRQs for each of RX and Tx, so we expect netlink to
report 4 IRQs with unique NAPI IDs:

$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
                         --dump napi-get --json='{"ifindex": 2}'
[{'id': 8196, 'ifindex': 2, 'irq': 148},
 {'id': 8195, 'ifindex': 2, 'irq': 147},
 {'id': 8194, 'ifindex': 2, 'irq': 146},
 {'id': 8193, 'ifindex': 2, 'irq': 145}]

Now we examine which queues these NAPIs are associated with, expecting
that since IGC_FLAG_QUEUE_PAIRS is disabled each RX and TX queue will
have its own NAPI instance:

$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
                         --dump queue-get --json='{"ifindex": 2}'
[{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'},
 {'id': 0, 'ifindex': 2, 'napi-id': 8195, 'type': 'tx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8196, 'type': 'tx'}]

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250106221929.956999-15-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 47 insertions, 9 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index d9542015e871..56a35d58e7a6 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4942,6 +4942,22 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	return 0;
 }
 
+void igc_set_queue_napi(struct igc_adapter *adapter, int vector,
+			struct napi_struct *napi)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
@@ -4949,6 +4965,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i = 0;
 
 	/* hardware has been reset, we need to reload some things */
@@ -4956,8 +4973,11 @@ void igc_up(struct igc_adapter *adapter)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->msix_entries)
 		igc_configure_msix(adapter);
@@ -5186,6 +5206,7 @@ void igc_down(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igc_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
@@ -6015,6 +6036,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err = 0;
 	int i = 0;
 
@@ -6050,8 +6072,11 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(IGC_ICR);
@@ -7296,7 +7321,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int igc_resume(struct device *dev)
+static int __igc_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7339,7 +7364,11 @@ static int igc_resume(struct device *dev)
 	wr32(IGC_WUS, ~0);
 
 	if (netif_running(netdev)) {
+		if (!rpm)
+			rtnl_lock();
 		err = __igc_open(netdev, true);
+		if (!rpm)
+			rtnl_unlock();
 		if (!err)
 			netif_device_attach(netdev);
 	}
@@ -7347,9 +7376,14 @@ static int igc_resume(struct device *dev)
 	return err;
 }
 
+static int igc_resume(struct device *dev)
+{
+	return __igc_resume(dev, false);
+}
+
 static int igc_runtime_resume(struct device *dev)
 {
-	return igc_resume(dev);
+	return __igc_resume(dev, true);
 }
 
 static int igc_suspend(struct device *dev)
@@ -7394,14 +7428,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	if (state == pci_channel_io_perm_failure)
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
+	}
 
 	if (netif_running(netdev))
 		igc_down(adapter);
 	pci_disable_device(pdev);
+	rtnl_unlock();
 
 	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -7412,7 +7450,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igc_resume routine.
+ *  resembles the first-half of the __igc_resume routine.
  **/
 static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 {
@@ -7451,7 +7489,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igc_resume routine.
+ *  second-half of the __igc_resume routine.
  */
 static void igc_io_resume(struct pci_dev *pdev)
 {