i40e: Add i40e_napi_poll tracepoint

Add a tracepoint for i40e_napi_poll that allows users to get detailed
information about the amount of work done. This information can help users
better tune the correct NAPI parameters (like weight and budget), as well
as debug NIC settings like rx-usecs and tx-usecs, etc.

When perf is attached, this tracepoint only fires when not in XDP mode.

An example of the output from this tracepoint:

$ sudo perf trace -e i40e:i40e_napi_poll -a --call-graph=fp --libtraceevent_print

[..snip..]

388.258 :0/0 i40e:i40e_napi_poll(i40e_napi_poll on dev eth2 q i40e-eth2-TxRx-9 irq 346 irq_mask 00000000,00000000,00000000,00000000,00000000,00800000 curr_cpu 23 budget 64 bpr 64 rx_cleaned 28 tx_cleaned 0 rx_clean_complete 1 tx_clean_complete 1)
	i40e_napi_poll ([i40e])
	i40e_napi_poll ([i40e])
	__napi_poll ([kernel.kallsyms])
	net_rx_action ([kernel.kallsyms])
	__do_softirq ([kernel.kallsyms])
	common_interrupt ([kernel.kallsyms])
	asm_common_interrupt ([kernel.kallsyms])
	intel_idle_irq ([kernel.kallsyms])
	cpuidle_enter_state ([kernel.kallsyms])
	cpuidle_enter ([kernel.kallsyms])
	do_idle ([kernel.kallsyms])
	cpu_startup_entry ([kernel.kallsyms])
	[0x243fd8] ([kernel.kallsyms])
	secondary_startup_64_no_verify ([kernel.kallsyms])
Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Acked-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Tested-by: Gurucharan <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

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

@@ -2752,6 +2752,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 			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();