net: ena: optimize data access in fast-path code

This tweaks several small places to improve the data access in fast
path:

* Remove duplicates of first_interrupt flag and surround it with
  WRITE/READ_ONCE macros:

  The flag is used to detect HW disorders in its
  interrupt communication with the driver. The flag is set when an
  interrupt is received and used in the health check function
  (ena_timer_service()) to help it find irregularities.

* Reorder some fields in ena_napi struct to take better advantage of
  cache access pattern.

* Move XDP TX queue number to a variable to save its calculation for
  every packet.

* Use likely in a condition to improve branch prediction

The 'first_interrupt' and 'interrupt_masked' flags were moved to reside
in the same cache line as the first fields of 'napi' struct. This
placement ensures that all memory accessed during upper-half handler
reside in the same cacheline (napi_schedule_irqoff() only accesses
'state' and 'poll_list' fields which are at the beginning of napi
struct).

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 4 deletions

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 74af15d62ee1..21758707a929 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -135,12 +135,12 @@ struct ena_irq {
 };
 
 struct ena_napi {
-	struct napi_struct napi ____cacheline_aligned;
+	u8 first_interrupt ____cacheline_aligned;
+	u8 interrupts_masked;
+	struct napi_struct napi;
 	struct ena_ring *tx_ring;
 	struct ena_ring *rx_ring;
 	struct ena_ring *xdp_ring;
-	bool first_interrupt;
-	bool interrupts_masked;
 	u32 qid;
 	struct dim dim;
 };
@@ -259,6 +259,10 @@ struct ena_ring {
 	struct bpf_prog *xdp_bpf_prog;
 	struct xdp_rxq_info xdp_rxq;
 	spinlock_t xdp_tx_lock;	/* synchronize XDP TX/Redirect traffic */
+	/* Used for rx queues only to point to the xdp tx ring, to
+	 * which traffic should be redirected from this rx ring.
+	 */
+	struct ena_ring *xdp_ring;
 
 	u16 next_to_use;
 	u16 next_to_clean;
@@ -271,7 +275,6 @@ struct ena_ring {
 	/* The maximum header length the device can handle */
 	u8 tx_max_header_size;
 
-	bool first_interrupt;
 	bool disable_meta_caching;
 	u16 no_interrupt_event_cnt;