Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2022-11-02 (i40e, iavf)

This series contains updates to i40e and iavf drivers.

Joe Damato adds tracepoint information to i40e_napi_poll to expose helpful
debug information for users who'd like to get a better understanding of
how their NIC is performing as they adjust various parameters and tuning
knobs.

Note: this does not touch any XDP related code paths. This
tracepoint will only work when not using XDP. Care has been taken to avoid
changing control flow in i40e_napi_poll with this change.

Alicja adds error messaging for unsupported duplex settings for i40e.

Ye Xingchen replaces use of __FUNCTION__ with __func__ for iavf.

Bartosz changes tense of device removal message to be more clear on the
action for iavf.

* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  iavf: Change information about device removal in dmesg
  iavf: Replace __FUNCTION__ with __func__
  i40e: Add appropriate error message logged for incorrect duplex setting
  i40e: Add i40e_napi_poll tracepoint
  i40e: Record number of RXes cleaned during NAPI
  i40e: Record number TXes cleaned during NAPI
  i40e: Store the irq number in i40e_q_vector
====================

Link: https://lore.kernel.org/r/20221102211011.2944983-1-anthony.l.nguyen@intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/intel/i40e/i40e.h

@@ -992,6 +992,7 @@ struct i40e_q_vector {
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
+	int irq_num;		/* IRQ assigned to this q_vector */
 } ____cacheline_internodealigned_in_smp;
 
 /* lan device */

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1287,8 +1287,10 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 	 * trying to set something that we do not support.
 	 */
 	if (memcmp(&copy_ks.base, &safe_ks.base,
-		   sizeof(struct ethtool_link_settings)))
+		   sizeof(struct ethtool_link_settings))) {
+		netdev_err(netdev, "Only speed and autoneg are supported.\n");
 		return -EOPNOTSUPP;
+	}
 
 	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
 		timeout--;

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -4123,6 +4123,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		}
 
 		/* register for affinity change notifications */
+		q_vector->irq_num = irq_num;
 		q_vector->affinity_notify.notify = i40e_irq_affinity_notify;
 		q_vector->affinity_notify.release = i40e_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);

drivers/net/ethernet/intel/i40e/i40e_trace.h

@@ -55,6 +55,55 @@
  * being built from shared code.
  */
 
+#define NO_DEV "(i40e no_device)"
+
+TRACE_EVENT(i40e_napi_poll,
+
+	TP_PROTO(struct napi_struct *napi, struct i40e_q_vector *q, int budget,
+		 int budget_per_ring, unsigned int rx_cleaned, unsigned int tx_cleaned,
+		 bool rx_clean_complete, bool tx_clean_complete),
+
+	TP_ARGS(napi, q, budget, budget_per_ring, rx_cleaned, tx_cleaned,
+		rx_clean_complete, tx_clean_complete),
+
+	TP_STRUCT__entry(
+		__field(int, budget)
+		__field(int, budget_per_ring)
+		__field(unsigned int, rx_cleaned)
+		__field(unsigned int, tx_cleaned)
+		__field(int, rx_clean_complete)
+		__field(int, tx_clean_complete)
+		__field(int, irq_num)
+		__field(int, curr_cpu)
+		__string(qname, q->name)
+		__string(dev_name, napi->dev ? napi->dev->name : NO_DEV)
+		__bitmask(irq_affinity,	nr_cpumask_bits)
+	),
+
+	TP_fast_assign(
+		__entry->budget = budget;
+		__entry->budget_per_ring = budget_per_ring;
+		__entry->rx_cleaned = rx_cleaned;
+		__entry->tx_cleaned = tx_cleaned;
+		__entry->rx_clean_complete = rx_clean_complete;
+		__entry->tx_clean_complete = tx_clean_complete;
+		__entry->irq_num = q->irq_num;
+		__entry->curr_cpu = get_cpu();
+		__assign_str(qname, q->name);
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+		__assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask),
+				 nr_cpumask_bits);
+	),
+
+	TP_printk("i40e_napi_poll on dev %s q %s irq %d irq_mask %s curr_cpu %d "
+		  "budget %d bpr %d rx_cleaned %u tx_cleaned %u "
+		  "rx_clean_complete %d tx_clean_complete %d",
+		__get_str(dev_name), __get_str(qname), __entry->irq_num,
+		__get_bitmask(irq_affinity), __entry->curr_cpu, __entry->budget,
+		__entry->budget_per_ring, __entry->rx_cleaned, __entry->tx_cleaned,
+		__entry->rx_clean_complete, __entry->tx_clean_complete)
+);
+
 /* Events related to a vsi & ring */
 DECLARE_EVENT_CLASS(
 	i40e_tx_template,

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -923,11 +923,13 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi)
  * @vsi: the VSI we care about
  * @tx_ring: Tx ring to clean
  * @napi_budget: Used to determine if we are in netpoll
+ * @tx_cleaned: Out parameter set to the number of TXes cleaned
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  **/
 static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
-			      struct i40e_ring *tx_ring, int napi_budget)
+			      struct i40e_ring *tx_ring, int napi_budget,
+			      unsigned int *tx_cleaned)
 {
 	int i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
@@ -1048,6 +1050,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		}
 	}
 
+	*tx_cleaned = total_packets;
 	return !!budget;
 }
 
@@ -2422,6 +2425,7 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring)
  * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
+ * @rx_cleaned: Out parameter of the number of packets processed
  *
  * This function provides a "bounce buffer" approach to Rx interrupt
  * processing.  The advantage to this is that on systems that have
@@ -2430,7 +2434,8 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring)
  *
  * Returns amount of work completed
  **/
-static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
+static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
+			     unsigned int *rx_cleaned)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0, frame_sz = 0;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
@@ -2567,6 +2572,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
+	*rx_cleaned = total_rx_packets;
+
 	/* guarantee a trip back through this routine if there was a failure */
 	return failure ? budget : (int)total_rx_packets;
 }
@@ -2689,6 +2696,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 			       container_of(napi, struct i40e_q_vector, napi);
 	struct i40e_vsi *vsi = q_vector->vsi;
 	struct i40e_ring *ring;
+	bool tx_clean_complete = true;
+	bool rx_clean_complete = true;
+	unsigned int tx_cleaned = 0;
+	unsigned int rx_cleaned = 0;
 	bool clean_complete = true;
 	bool arm_wb = false;
 	int budget_per_ring;
@@ -2705,10 +2716,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	i40e_for_each_ring(ring, q_vector->tx) {
 		bool wd = ring->xsk_pool ?
 			  i40e_clean_xdp_tx_irq(vsi, ring) :
-			  i40e_clean_tx_irq(vsi, ring, budget);
+			  i40e_clean_tx_irq(vsi, ring, budget, &tx_cleaned);
 
 		if (!wd) {
-			clean_complete = false;
+			clean_complete = tx_clean_complete = false;
 			continue;
 		}
 		arm_wb |= ring->arm_wb;
@@ -2733,14 +2744,18 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	i40e_for_each_ring(ring, q_vector->rx) {
 		int cleaned = ring->xsk_pool ?
 			      i40e_clean_rx_irq_zc(ring, budget_per_ring) :
-			      i40e_clean_rx_irq(ring, budget_per_ring);
+			      i40e_clean_rx_irq(ring, budget_per_ring, &rx_cleaned);
 
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */
 		if (cleaned >= budget_per_ring)
-			clean_complete = false;
+			clean_complete = rx_clean_complete = false;
 	}
 
+	if (!i40e_enabled_xdp_vsi(vsi))
+		trace_i40e_napi_poll(napi, q_vector, budget, budget_per_ring, rx_cleaned,
+				     tx_cleaned, rx_clean_complete, tx_clean_complete);
+
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
 		int cpu_id = smp_processor_id();

drivers/net/ethernet/intel/iavf/iavf_main.c

@@ -4820,7 +4820,7 @@ static void iavf_shutdown(struct pci_dev *pdev)
 		iavf_close(netdev);
 
 	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
-		dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__);
+		dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__);
 	/* Prevent the watchdog from running. */
 	iavf_change_state(adapter, __IAVF_REMOVE);
 	adapter->aq_required = 0;
@@ -5083,7 +5083,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	}
 
 	mutex_lock(&adapter->crit_lock);
-	dev_info(&adapter->pdev->dev, "Remove device\n");
+	dev_info(&adapter->pdev->dev, "Removing device\n");
 	iavf_change_state(adapter, __IAVF_REMOVE);
 
 	iavf_request_reset(adapter);