One of the things that commit 5574ff7b7b3d ("i40e: optimize AF_XDP Tx
completion path") introduced was the @xdp_tx_active field. Its usage
from i40e can be adjusted to ice driver and give us positive performance
results.
If the descriptor that @next_dd to points has been sent by HW (its DD
bit is set), then we are sure that there are ICE_TX_THRESH count of
descriptors ready to be cleaned. If @xdp_tx_active is 0 which means that
related xdp_ring is not used for XDP_{TX, REDIRECT} workloads, then we
know how many XSK entries should placed to completion queue, IOW walking
through the ring can be skipped.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx>
---
drivers/net/ethernet/intel/ice/ice_txrx.h | 1 +
drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 1 +
drivers/net/ethernet/intel/ice/ice_xsk.c | 7 +++++++
3 files changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index f2ebbe2158e7..8dd9c92662ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -332,6 +332,7 @@ struct ice_tx_ring {
struct ice_ptp_tx *tx_tstamps;
spinlock_t tx_lock;
u32 txq_teid; /* Added Tx queue TEID */
+ u16 xdp_tx_active;
#define ICE_TX_FLAGS_RING_XDP BIT(0)
u8 flags;
u8 dcb_tc; /* Traffic class of ring */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1dd7e84f41f8..f15c215c973c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -299,6 +299,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0,
size, 0);
+ xdp_ring->xdp_tx_active++;
i++;
if (i == xdp_ring->count) {
i = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a7f866b3fcd7..8949a7be45c6 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -684,6 +684,7 @@ static void
ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
{
xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
+ xdp_ring->xdp_tx_active--;
dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
dma_unmap_len_set(tx_buf, len, 0);
@@ -713,6 +714,11 @@ bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring)
again:
xsk_frames = 0;
+ if (likely(!xdp_ring->xdp_tx_active)) {
+ xsk_frames = ICE_TX_THRESH;
+ goto skip;
+ }
+
ntc = xdp_ring->next_to_clean;
for (i = 0; i < ICE_TX_THRESH; i++) {
@@ -729,6 +735,7 @@ bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring)
if (ntc >= xdp_ring->count)
ntc = 0;
}
+skip:
xdp_ring->next_to_clean += ICE_TX_THRESH;
if (xdp_ring->next_to_clean >= desc_cnt)
xdp_ring->next_to_clean -= desc_cnt;
--
2.33.1
