i40e, xsk: remove HW descriptor prefetch in AF_XDP path

The software prefetching of HW descriptors has a negative impact on
the performance. Therefore, it is now removed.

Performance for the rx_drop benchmark increased with 2%.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

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

@@ -2295,6 +2295,19 @@ void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res)
 	}
 }
 
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+	prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
 /**
  * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on

drivers/net/ethernet/intel/i40e/i40e_txrx_common.h

@@ -99,19 +99,6 @@ static inline bool i40e_rx_is_programming_status(u64 qword1)
 	return qword1 & I40E_RXD_QW1_LENGTH_SPH_MASK;
 }
 
-/**
- * i40e_inc_ntc: Advance the next_to_clean index
- * @rx_ring: Rx ring
- **/
-static inline void i40e_inc_ntc(struct i40e_ring *rx_ring)
-{
-	u32 ntc = rx_ring->next_to_clean + 1;
-
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
-}
-
 void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
 void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi);

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -257,6 +257,18 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 	return skb;
 }
 
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+}
+
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring