DPDK patches and discussions
 help / color / mirror / Atom feed
From: Huisong Li <lihuisong@huawei.com>
To: <dev@dpdk.org>
Cc: <ferruh.yigit@amd.com>, <andrew.rybchenko@oktetlabs.ru>,
	<3chas3@gmail.com>, <humin29@huawei.com>,
	<stephen@networkplumber.org>, <liudongdong3@huawei.com>,
	<huangdaode@huawei.com>, <lihuisong@huawei.com>
Subject: [PATCH V2] net/bonding: fix bond3 and bond4 process mbuf fast free
Date: Wed, 9 Nov 2022 10:22:37 +0800	[thread overview]
Message-ID: <20221109022237.49757-1-lihuisong@huawei.com> (raw)
In-Reply-To: <20221108084038.25136-1-lihuisong@huawei.com>

The RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE offload can't be used in bonding
mode Broadcast and mode 8023AD. Currently, bonding driver forcibly removes
from the dev->data->dev_conf.txmode.offloads and processes as success in
bond_ethdev_configure(). But this still cause that rte_eth_dev_configure()
fails to execute because of the failure of validating Tx offload in the
eth_dev_validate_offloads(). So this patch moves the modification of txmode
offlaods to the stage of adding slave device to report the correct txmode
offloads.

Fixes: 18c41457cbae ("net/bonding: fix mbuf fast free usage")
Cc: stable@dpdk.org

Signed-off-by: Huisong Li <lihuisong@huawei.com>
---
 -v2: report the correct txmode offloads based on bonding mode in the
      bonding driver, and not in testpmd.
---
 drivers/net/bonding/rte_eth_bond_api.c |  5 +++++
 drivers/net/bonding/rte_eth_bond_pmd.c | 11 -----------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/bonding/rte_eth_bond_api.c b/drivers/net/bonding/rte_eth_bond_api.c
index 694fe86115..c0178369b4 100644
--- a/drivers/net/bonding/rte_eth_bond_api.c
+++ b/drivers/net/bonding/rte_eth_bond_api.c
@@ -544,6 +544,11 @@ __eth_bond_slave_add_lock_free(uint16_t bonded_port_id, uint16_t slave_port_id)
 			return ret;
 	}
 
+	/* Bond mode Broadcast & 8023AD don't support MBUF_FAST_FREE offload. */
+	if (internals->mode == BONDING_MODE_8023AD ||
+	    internals->mode == BONDING_MODE_BROADCAST)
+		internals->tx_offload_capa &= ~RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE;
+
 	bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf &=
 			internals->flow_type_rss_offloads;
 
diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c b/drivers/net/bonding/rte_eth_bond_pmd.c
index 864e073db8..2efaad1e8e 100644
--- a/drivers/net/bonding/rte_eth_bond_pmd.c
+++ b/drivers/net/bonding/rte_eth_bond_pmd.c
@@ -3643,7 +3643,6 @@ bond_ethdev_configure(struct rte_eth_dev *dev)
 	const char *name = dev->device->name;
 	struct bond_dev_private *internals = dev->data->dev_private;
 	struct rte_kvargs *kvlist = internals->kvlist;
-	uint64_t offloads;
 	int arg_count;
 	uint16_t port_id = dev - rte_eth_devices;
 	uint32_t link_speeds;
@@ -3708,16 +3707,6 @@ bond_ethdev_configure(struct rte_eth_dev *dev)
 		}
 	}
 
-	offloads = dev->data->dev_conf.txmode.offloads;
-	if ((offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) &&
-			(internals->mode == BONDING_MODE_8023AD ||
-			internals->mode == BONDING_MODE_BROADCAST)) {
-		RTE_BOND_LOG(WARNING,
-			"bond mode broadcast & 8023AD don't support MBUF_FAST_FREE offload, force disable it.");
-		offloads &= ~RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE;
-		dev->data->dev_conf.txmode.offloads = offloads;
-	}
-
 	link_speeds = dev->data->dev_conf.link_speeds;
 	/*
 	 * The default value of 'link_speeds' is zero. From its definition,
-- 
2.33.0


  parent reply	other threads:[~2022-11-09  2:22 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-08  8:40 [PATCH 0/2] net/bonding: fix mbuf fast free for bond3 and bond4 Huisong Li
2022-11-08  8:40 ` [PATCH 1/2] net/bonding: fix bond3 and bond4 process mbuf fast free Huisong Li
2022-11-08  8:40 ` [PATCH 2/2] app/testpmd: remove fast free offload for bond3 and bond4 Huisong Li
2022-11-08 18:01   ` Stephen Hemminger
2022-11-09  1:11     ` lihuisong (C)
2022-11-09  2:22 ` Huisong Li [this message]
2022-11-09  3:24   ` [PATCH V2] net/bonding: fix bond3 and bond4 process mbuf fast free Stephen Hemminger
2022-11-09 10:37     ` Andrew Rybchenko

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=20221109022237.49757-1-lihuisong@huawei.com \
    --to=lihuisong@huawei.com \
    --cc=3chas3@gmail.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@amd.com \
    --cc=huangdaode@huawei.com \
    --cc=humin29@huawei.com \
    --cc=liudongdong3@huawei.com \
    --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).