DPDK patches and discussions
 help / color / mirror / Atom feed
From: Shai Brandes <shaibran@amazon.com>
To: <stephen@networkplumber.org>
Cc: <dev@dpdk.org>, Shai Brandes <shaibran@amazon.com>
Subject: [PATCH 01/21] net/ena/base: optimize Tx desc fields setting
Date: Wed, 15 Oct 2025 10:06:47 +0300	[thread overview]
Message-ID: <20251015070707.340-2-shaibran@amazon.com> (raw)
In-Reply-To: <20251015070707.340-1-shaibran@amazon.com>

Instead of erasing tx descriptor and later set all fields using or,
use set for the first value of each field of the descriptor.

Signed-off-by: Shai Brandes <shaibran@amazon.com>
Reviewed-by: Amit Bernstein <amitbern@amazon.com>
Reviewed-by: Yosef Raisman <yraisman@amazon.com>
---
 drivers/net/ena/base/ena_eth_com.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ena/base/ena_eth_com.c b/drivers/net/ena/base/ena_eth_com.c
index c6668238e5..c4fee7bb3c 100644
--- a/drivers/net/ena/base/ena_eth_com.c
+++ b/drivers/net/ena/base/ena_eth_com.c
@@ -516,26 +516,25 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
 	desc = get_sq_desc(io_sq);
 	if (unlikely(!desc))
 		return ENA_COM_FAULT;
-	memset(desc, 0x0, sizeof(struct ena_eth_io_tx_desc));
+
+	desc->len_ctrl = ENA_FIELD_PREP((u32)io_sq->phase,
+					ENA_ETH_IO_TX_DESC_PHASE_MASK,
+					ENA_ETH_IO_TX_DESC_PHASE_SHIFT);
 
 	/* Set first desc when we don't have meta descriptor */
 	if (!have_meta)
 		desc->len_ctrl |= ENA_ETH_IO_TX_DESC_FIRST_MASK;
 
-	desc->buff_addr_hi_hdr_sz |= ENA_FIELD_PREP((u32)header_len,
-						    ENA_ETH_IO_TX_DESC_HEADER_LENGTH_MASK,
-						    ENA_ETH_IO_TX_DESC_HEADER_LENGTH_SHIFT);
-
-	desc->len_ctrl |= ENA_FIELD_PREP((u32)io_sq->phase,
-					 ENA_ETH_IO_TX_DESC_PHASE_MASK,
-					 ENA_ETH_IO_TX_DESC_PHASE_SHIFT);
+	desc->buff_addr_hi_hdr_sz = ENA_FIELD_PREP((u32)header_len,
+						   ENA_ETH_IO_TX_DESC_HEADER_LENGTH_MASK,
+						   ENA_ETH_IO_TX_DESC_HEADER_LENGTH_SHIFT);
 
 	desc->len_ctrl |= ENA_ETH_IO_TX_DESC_COMP_REQ_MASK;
 
 	/* Bits 0-9 */
-	desc->meta_ctrl |= ENA_FIELD_PREP((u32)ena_tx_ctx->req_id,
-					  ENA_ETH_IO_TX_DESC_REQ_ID_LO_MASK,
-					  ENA_ETH_IO_TX_DESC_REQ_ID_LO_SHIFT);
+	desc->meta_ctrl = ENA_FIELD_PREP((u32)ena_tx_ctx->req_id,
+					 ENA_ETH_IO_TX_DESC_REQ_ID_LO_MASK,
+					 ENA_ETH_IO_TX_DESC_REQ_ID_LO_SHIFT);
 
 	desc->meta_ctrl |= ENA_FIELD_PREP(ena_tx_ctx->df,
 					  ENA_ETH_IO_TX_DESC_DF_MASK,
-- 
2.17.1


  reply	other threads:[~2025-10-15  7:07 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-15  7:06 [PATCH 00/21] net/ena: Release 2.14.0 Shai Brandes
2025-10-15  7:06 ` Shai Brandes [this message]
2025-10-15  7:06 ` [PATCH 02/21] net/ena/base: rework admin timeout handling Shai Brandes
2025-10-15  7:06 ` [PATCH 03/21] net/ena/base: add extended Tx cdesc support Shai Brandes
2025-10-15  7:06 ` [PATCH 04/21] net/ena/base: add IO ring helper functions Shai Brandes
2025-10-15  8:50 ` [PATCH 00/21] net/ena: Release 2.14.0 Brandes, Shai
2025-10-15 18:12 ` Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20251015070707.340-2-shaibran@amazon.com \
    --to=shaibran@amazon.com \
    --cc=dev@dpdk.org \
    --cc=stephen@networkplumber.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).