iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ice: Make Tx threshold dependent on ring length

Browse Source 
XDP_TX workloads use a concept of Tx threshold that indicates the
interval of setting RS bit on descriptors which in turn tells the HW to
generate an interrupt to signal the completion of Tx on HW side. It is
currently based on a constant value of 32 which might not work out well
for various sizes of ring combined with for example batch size that can
be set via SO_BUSY_POLL_BUDGET.

Internal tests based on AF_XDP showed that most convenient setup of
mentioned threshold is when it is equal to quarter of a ring length.

Make use of recently introduced ICE_RING_QUARTER macro and use this
value as a substitute for ICE_TX_THRESH.

Align also ethtool -G callback so that next_dd/next_rs fields are up to
date in terms of the ring size.

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/20220125160446.78976-5-maciej.fijalkowski@intel.com
This commit is contained in:
Maciej Fijalkowski
2022-01-25 17:04:42 +01:00
committed by Daniel Borkmann
parent 3876ff525d
commit 3dd411efe1
4 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
drivers/net/ethernet/intel/ice/ice_txrx_lib.c
View File

@ -222,6 +222,7 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
{
unsigned int total_bytes = 0, total_pkts = 0;
u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
u16 ntc = xdp_ring->next_to_clean;
struct ice_tx_desc *next_dd_desc;
u16 next_dd = xdp_ring->next_dd;
@ -233,7 +234,7 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
return;
for (i = 0; i < ICE_TX_THRESH; i++) {
for (i = 0; i < tx_thresh; i++) {
tx_buf = &xdp_ring->tx_buf[ntc];
total_bytes += tx_buf->bytecount;
@ -254,9 +255,9 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
}
next_dd_desc->cmd_type_offset_bsz = 0;
xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH;
xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh;
if (xdp_ring->next_dd > xdp_ring->count)
xdp_ring->next_dd = ICE_TX_THRESH - 1;
xdp_ring->next_dd = tx_thresh - 1;
xdp_ring->next_to_clean = ntc;
ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes);
}
@ -269,12 +270,13 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
*/
int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
{
u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
u16 i = xdp_ring->next_to_use;
struct ice_tx_desc *tx_desc;
struct ice_tx_buf *tx_buf;
dma_addr_t dma;
if (ICE_DESC_UNUSED(xdp_ring) < ICE_TX_THRESH)
if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh)
ice_clean_xdp_irq(xdp_ring);
if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) {
@ -306,7 +308,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
tx_desc->cmd_type_offset_bsz |=
cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
xdp_ring->next_rs = ICE_TX_THRESH - 1;
xdp_ring->next_rs = tx_thresh - 1;
}
xdp_ring->next_to_use = i;
@ -314,7 +316,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
tx_desc->cmd_type_offset_bsz |=
cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
xdp_ring->next_rs += ICE_TX_THRESH;
xdp_ring->next_rs += tx_thresh;
}
return ICE_XDP_TX;