ice: xsk: Borrow xdp_tx_active logic from i40e

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 points to has been sent by HW (its DD
bit is set), then we are sure that at least quarter of the ring is 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@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220125160446.78976-9-maciej.fijalkowski@intel.com

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 666db35a291971fd098f4e3dd87c9cb97bb2e3ce..466253ac2ee146d2f37220f6cc9de5b8008ec57b 100644 (file)
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -333,6 +333,7 @@ struct ice_tx_ring {
        spinlock_t tx_lock;
        u32 txq_teid;                   /* Added Tx queue TEID */
        /* CL4 - 4th cacheline starts here */
+       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 9677cf880a4b0da086cedb5eae49fd750eeb966e..eb21cec1d772ac55111f4387081069bdd765547f 100644 (file)
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -302,6 +302,7 @@ 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 8b6acb4afb7fdf6504513575409c7636298db9a4..2976991c0ab290c465890676346eb9036c2ebd7c 100644 (file)
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -687,6 +687,7 @@ 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);
@@ -703,9 +704,8 @@ static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
 {
        u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
        int budget = napi_budget / tx_thresh;
-       u16 ntc = xdp_ring->next_to_clean;
        u16 next_dd = xdp_ring->next_dd;
-       u16 cleared_dds = 0;
+       u16 ntc, cleared_dds = 0;
 
        do {
                struct ice_tx_desc *next_dd_desc;
@@ -721,6 +721,12 @@ static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
 
                cleared_dds++;
                xsk_frames = 0;
+               if (likely(!xdp_ring->xdp_tx_active)) {
+                       xsk_frames = tx_thresh;
+                       goto skip;
+               }
+
+               ntc = xdp_ring->next_to_clean;
 
                for (i = 0; i < tx_thresh; i++) {
                        tx_buf = &xdp_ring->tx_buf[ntc];
@@ -736,6 +742,10 @@ static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
                        if (ntc >= xdp_ring->count)
                                ntc = 0;
                }
+skip:
+               xdp_ring->next_to_clean += tx_thresh;
+               if (xdp_ring->next_to_clean >= desc_cnt)
+                       xdp_ring->next_to_clean -= desc_cnt;
                if (xsk_frames)
                        xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
                next_dd_desc->cmd_type_offset_bsz = 0;
@@ -744,7 +754,6 @@ static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
                        next_dd = tx_thresh - 1;
        } while (budget--);
 
-       xdp_ring->next_to_clean = ntc;
        xdp_ring->next_dd = next_dd;
 
        return cleared_dds * tx_thresh;