i40e/i40evf: Add tracepoints

This patch adds tracepoints to the i40e and i40evf drivers to which
BPF programs can be attached for feature testing and verification.
It's expected that an attached BPF program will identify and count or
log some interesting subset of traffic. The bcc-tools package is
helpful there for containing all the BPF arcana in a handy Python
wrapper. Though you can make these tracepoints log trace messages, the
messages themselves probably won't be very useful (other to verify the
tracepoint is being called while you're debugging your BPF program).

The idea here is that tracepoints have such low performance cost when
disabled that we can leave these in the upstream drivers. This may
eventually enable the instrumentation of unmodified customer systems
should the need arise to verify a NIC feature is working as expected.
In general this enables one set of feature verification tools to be
used on these drivers whether they're built with the kernel or
separately.

Users are advised against using these tracepoints for anything other
than a diagnostic tool. They have a performance impact when enabled,
and their exact placement and form may change as we see how well they
work in practice for the purposes above.

Change-ID: Id6014a7322c0e6d08068114dd20bd156f2f6435e
Signed-off-by: Scott Peterson <scott.d.peterson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

1 files changed, 9 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 843d7ffe1784..1531a0f9fcc6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -27,6 +27,7 @@
 #include <linux/prefetch.h>
 #include <net/busy_poll.h>
 #include "i40e.h"
+#include "i40e_trace.h"
 #include "i40e_prototype.h"
 
 static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
@@ -765,6 +766,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		/* prevent any other reads prior to eop_desc */
 		read_barrier_depends();
 
+		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)
 			break;
@@ -791,6 +793,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
+			i40e_trace(clean_tx_irq_unmap,
+				   tx_ring, tx_desc, tx_buf);
 
 			tx_buf++;
 			tx_desc++;
@@ -2005,6 +2009,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
+		i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
 
 		/* retrieve a buffer from the ring */
@@ -2057,6 +2062,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
+		i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 		skb = NULL;
 
@@ -3138,6 +3144,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	/* prefetch the data, we'll need it later */
 	prefetch(skb->data);
 
+	i40e_trace(xmit_frame_ring, skb, tx_ring);
+
 	count = i40e_xmit_descriptor_count(skb);
 	if (i40e_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb)) {
@@ -3216,6 +3224,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
+	i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring);
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
 	return NETDEV_TX_OK;