From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 25 Jan 2022 17:04:46 +0100
Subject: ice: xsk: Borrow xdp_tx_active logic from i40e
Patch-mainline: v5.18-rc1
Git-commit: 59e92bfe4df71a833678a94b9947843a4c9f55bb
References: jsc#PED-376
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
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
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 | 15 ++++++++++++---
3 files changed, 14 insertions(+), 3 deletions(-)
--- 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 */
--- 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 si
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;
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -691,6 +691,7 @@ 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);
@@ -707,9 +708,8 @@ static u16 ice_clean_xdp_irq_zc(struct i
{
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;
@@ -725,6 +725,12 @@ static u16 ice_clean_xdp_irq_zc(struct i
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];
@@ -740,6 +746,10 @@ static u16 ice_clean_xdp_irq_zc(struct i
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;
@@ -748,7 +758,6 @@ static u16 ice_clean_xdp_irq_zc(struct i
next_dd = tx_thresh - 1;
} while (budget--);
- xdp_ring->next_to_clean = ntc;
xdp_ring->next_dd = next_dd;
return cleared_dds * tx_thresh;