DPDK patches and discussions
 help / color / mirror / Atom feed
From: Shaokai Zhang <felix.zhang@jaguarmicro.com>
To: dev@dpdk.org
Cc: linville@tuxdriver.com, stable@dpdk.org,
	Joey Xing <joey.xing@jaguarmicro.com>
Subject: [PATCH] net/af_packet: register supported param fanout mode
Date: Thu, 20 Mar 2025 16:15:03 +0800	[thread overview]
Message-ID: <20250320081503.5505-1-felix.zhang@jaguarmicro.com> (raw)

Although af_packet PMD supports setting the fanout algorithm, it is not
explicitly declared during registration. Add fanout parameter registration
to facilitate users in quickly obtaining supported fanout algorithms.

Additionally, add configuration parameter printing during initialization.

Fixes: d3bc77ab05a4 ("net/af_packet: allow changing fanout mode")
Cc: stable@dpdk.org

Signed-off-by: Shaokai Zhang <felix.zhang@jaguarmicro.com>
Reviewed-by: Joey Xing <joey.xing@jaguarmicro.com>
---
 drivers/net/af_packet/rte_eth_af_packet.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c
index ab34285ed9..76f09dbe01 100644
--- a/drivers/net/af_packet/rte_eth_af_packet.c
+++ b/drivers/net/af_packet/rte_eth_af_packet.c
@@ -791,8 +791,8 @@ rte_pmd_init_internals(struct rte_vdev_device *dev,
                        unsigned int blockcnt,
                        unsigned int framesize,
                        unsigned int framecnt,
-		       unsigned int qdisc_bypass,
-		       const char *fanout_mode,
+                       unsigned int qdisc_bypass,
+                       const char *fanout_mode,
                        struct pmd_internals **internals,
                        struct rte_eth_dev **eth_dev,
                        struct rte_kvargs *kvlist)
@@ -1172,6 +1172,11 @@ rte_eth_from_packet(struct rte_vdev_device *dev,
 	PMD_LOG(INFO, "%s:\tblock count %d", name, blockcount);
 	PMD_LOG(INFO, "%s:\tframe size %d", name, framesize);
 	PMD_LOG(INFO, "%s:\tframe count %d", name, framecount);
+	PMD_LOG(INFO, "%s:\tqdisc bypass %d", name, qdisc_bypass);
+	if (fanout_mode)
+		PMD_LOG(INFO, "%s:\tfanout mode %s", name, fanout_mode);
+	else
+		PMD_LOG(INFO, "%s:\tfanout mode %s", name, "default PACKET_FANOUT_HASH");
 
 	if (rte_pmd_init_internals(dev, *sockfd, qpairs,
 				   blocksize, blockcount,
@@ -1274,4 +1279,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_af_packet,
 	"blocksz=<int> "
 	"framesz=<int> "
 	"framecnt=<int> "
-	"qdisc_bypass=<0|1>");
+	"qdisc_bypass=<0|1> "
+	"fanout_mode=<hash|lb|cpu|rollover|rnd|qm>");
-- 
2.47.1.windows.2


             reply	other threads:[~2025-03-20  8:15 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-20  8:15 Shaokai Zhang [this message]
2025-03-20  8:37 ` [PATCH v2 0/1] " Shaokai Zhang
2025-03-20  8:37   ` [PATCH v2 1/1] " Shaokai Zhang
2025-03-20 17:45     ` Stephen Hemminger
2025-03-21  3:05     ` [PATCH v3 0/1] " Shaokai Zhang
2025-03-21  3:05       ` [PATCH v3 1/1] " Shaokai Zhang

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=20250320081503.5505-1-felix.zhang@jaguarmicro.com \
    --to=felix.zhang@jaguarmicro.com \
    --cc=dev@dpdk.org \
    --cc=joey.xing@jaguarmicro.com \
    --cc=linville@tuxdriver.com \
    --cc=stable@dpdk.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).