From: Wei Dai <wei.dai@intel.com>
To: thomas@monjalon.net, ferruh.yigit@intel.com, qi.z.zhang@intel.com
Cc: dev@dpdk.org, Wei Dai <wei.dai@intel.com>
Subject: [dpdk-dev] [PATCH v6] ethdev: check Rx/Tx offloads
Date: Thu, 3 May 2018 09:30:40 +0800 [thread overview]
Message-ID: <1525311040-26694-1-git-send-email-wei.dai@intel.com> (raw)
In-Reply-To: <1524753466-17021-1-git-send-email-wei.dai@intel.com>
This patch check if a input requested offloading is valid or not.
Any reuqested offloading must be supported in the device capabilities.
Any offloading is disabled by default if it is not set in the parameter
dev_conf->[rt]xmode.offloads to rte_eth_dev_configure( ) and
[rt]x_conf->offloads to rte_eth_[rt]x_queue_setup().
>From application, a pure per-port offloading can only be enabled in
rte_eth_dev_configure().
Only supported per queue offloading can be sent to
rte_eth_[rt]x_queue_setup( ). A per queue offloading is
enabled only if it is enabled in rte_eth_dev_configure( ) OR
if it is enabled in rte_eth_[rt]x_queue_setup( ).
If a per queue offloading is enabled in rte_eth_dev_configure(),
it can't be disabled in rte_eth_[rt]x_queue_setup( ).
If a per queue offloading is disabled in rte_eth_dev_configure( ),
it can be enabled or disabled( ) in rte_eth_[rt]x_queue_setup( ).
This patch can make above such checking in a common way in rte_ethdev
layer to avoid same checking in underlying PMD.
Signed-off-by: Wei Dai <wei.dai@intel.com>
---
v6:
No need enable an offload in queue_setup( ) if it has already
been enabled in dev_configure( )
v5:
keep offload settings sent to PMD same as those from application
v4:
fix a wrong description in git log message.
v3:
rework according to dicision of offloading API in community
v2:
add offloads checking in rte_eth_dev_configure( ).
check if a requested offloading is supported.
---
lib/librte_ether/rte_ethdev.c | 70 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 70 insertions(+)
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index f0f53d4..39a0f0e 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -1196,6 +1196,28 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
ETHER_MAX_LEN;
}
+ /* Any requested offload must be within its device capability */
+ if ((local_conf.rxmode.offloads & dev_info.rx_offload_capa) !=
+ local_conf.rxmode.offloads) {
+ RTE_PMD_DEBUG_TRACE("ethdev port_id=%d requested Rx offloads "
+ "0x%" PRIx64 " doesn't match Rx offloads "
+ "capability 0x%" PRIx64 "\n",
+ port_id,
+ local_conf.rxmode.offloads,
+ dev_info.rx_offload_capa);
+ return -EINVAL;
+ }
+ if ((local_conf.txmode.offloads & dev_info.tx_offload_capa) !=
+ local_conf.txmode.offloads) {
+ RTE_PMD_DEBUG_TRACE("ethdev port_id=%d requested Tx offloads "
+ "0x%" PRIx64 " doesn't match Tx offloads "
+ "capability 0x%" PRIx64 "\n",
+ port_id,
+ local_conf.txmode.offloads,
+ dev_info.tx_offload_capa);
+ return -EINVAL;
+ }
+
/*
* Setup new number of RX/TX queues and reconfigure device.
*/
@@ -1547,6 +1569,30 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
&local_conf.offloads);
}
+ /*
+ * Only per-queue offload can be enabled from application.
+ * If any other offload is sent to this function, return -EINVAL
+ */
+ if ((local_conf.offloads & dev_info.rx_queue_offload_capa) !=
+ local_conf.offloads) {
+ RTE_PMD_DEBUG_TRACE("Ethdev port_id=%d rx_queue_id=%d "
+ "Requested offload 0x%" PRIx64 "doesn't "
+ "match per-queue capability 0x%" PRIx64
+ " in %s\n",
+ port_id,
+ rx_queue_id,
+ local_conf.offloads,
+ dev_info.rx_queue_offload_capa,
+ __func__);
+ return -EINVAL;
+ }
+
+ /*
+ * If an offload has already been enabled in rte_eth_dev_configure(),
+ * there is no need to enable it again in queue level.
+ */
+ local_conf.offloads &= ~dev->data->dev_conf.rxmode.offloads;
+
ret = (*dev->dev_ops->rx_queue_setup)(dev, rx_queue_id, nb_rx_desc,
socket_id, &local_conf, mp);
if (!ret) {
@@ -1681,6 +1727,30 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id,
&local_conf.offloads);
}
+ /*
+ * Only per-queue offload can be enabled from applcation.
+ * If any other offload is sent to this function, return -EINVAL
+ */
+ if ((local_conf.offloads & dev_info.tx_queue_offload_capa) !=
+ local_conf.offloads) {
+ RTE_PMD_DEBUG_TRACE("Ethdev port_id=%d tx_queue_id=%d "
+ "Requested offload 0x%" PRIx64 "doesn't "
+ "match per-queue capability 0x%" PRIx64
+ " in %s\n",
+ port_id,
+ tx_queue_id,
+ local_conf.offloads,
+ dev_info.tx_queue_offload_capa,
+ __func__);
+ return -EINVAL;
+ }
+
+ /*
+ * If an offload has already be enabled in rte_eth_dev_configure,
+ * there is no need to enable it in queue level again
+ */
+ local_conf.offloads &= ~dev->data->dev_conf.txmode.offloads;
+
return eth_err(port_id, (*dev->dev_ops->tx_queue_setup)(dev,
tx_queue_id, nb_tx_desc, socket_id, &local_conf));
}
--
2.7.5
next prev parent reply other threads:[~2018-05-03 1:49 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-01 13:53 [dpdk-dev] [PATCH] ethdev: check consistency of per port offloads Wei Dai
2018-03-28 8:57 ` [dpdk-dev] [PATCH v2] ethdev: check Rx/Tx offloads Wei Dai
2018-04-13 17:31 ` Ferruh Yigit
2018-04-15 10:37 ` Thomas Monjalon
2018-04-16 3:06 ` Dai, Wei
2018-04-25 11:26 ` [dpdk-dev] [PATCH] " Wei Dai
2018-04-25 11:31 ` [dpdk-dev] [PATCH v3] " Wei Dai
2018-04-25 11:49 ` Wei Dai
2018-04-25 11:50 ` [dpdk-dev] [PATCH v4] " Wei Dai
2018-04-25 17:04 ` Ferruh Yigit
2018-04-26 7:59 ` Zhang, Qi Z
2018-04-26 8:18 ` Thomas Monjalon
2018-04-26 8:51 ` Zhang, Qi Z
2018-04-26 14:45 ` Dai, Wei
2018-04-26 14:37 ` [dpdk-dev] [PATCH v5] " Wei Dai
2018-04-26 15:50 ` Ferruh Yigit
2018-04-26 15:56 ` Thomas Monjalon
2018-04-26 15:59 ` Ferruh Yigit
2018-04-26 16:11 ` Ferruh Yigit
2018-05-03 1:30 ` Wei Dai [this message]
2018-05-04 11:12 ` [dpdk-dev] [PATCH v6] " Ferruh Yigit
2018-05-04 14:02 ` [dpdk-dev] [PATCH v7] " Wei Dai
2018-05-04 14:42 ` Ferruh Yigit
2018-05-04 14:45 ` Ferruh Yigit
2018-05-05 18:59 ` Shahaf Shuler
2018-05-07 7:15 ` Dai, Wei
2018-05-08 10:58 ` Ferruh Yigit
2018-05-08 10:05 ` [dpdk-dev] [PATCH v8] " Wei Dai
2018-05-08 10:41 ` Andrew Rybchenko
2018-05-08 11:02 ` Ferruh Yigit
2018-05-08 11:22 ` Andrew Rybchenko
2018-05-08 11:37 ` Andrew Rybchenko
2018-05-08 12:34 ` Dai, Wei
2018-05-08 12:12 ` Ferruh Yigit
2018-05-09 12:45 ` Dai, Wei
2018-05-10 0:49 ` [dpdk-dev] [PATCH v9] ethdev: new Rx/Tx offloads API Wei Dai
2018-05-10 0:56 ` [dpdk-dev] [PATCH v10] " Wei Dai
2018-05-10 1:28 ` Ferruh Yigit
2018-05-10 2:35 ` Thomas Monjalon
2018-05-10 11:27 ` Dai, Wei
2018-05-10 9:25 ` Andrew Rybchenko
2018-05-10 19:47 ` Ferruh Yigit
2018-05-10 11:30 ` [dpdk-dev] [PATCH v11] " Wei Dai
2018-05-10 11:56 ` [dpdk-dev] [PATCH v12] " Wei Dai
2018-05-10 21:39 ` Thomas Monjalon
2018-05-14 8:37 ` Thomas Monjalon
2018-05-14 11:19 ` Dai, Wei
2018-05-10 21:48 ` Ferruh Yigit
2018-05-14 12:00 ` [dpdk-dev] [PATCH v13] " Wei Dai
2018-05-14 12:54 ` Thomas Monjalon
2018-05-14 13:26 ` Dai, Wei
2018-05-14 13:20 ` [dpdk-dev] [PATCH v14] " Wei Dai
2018-05-14 14:11 ` Thomas Monjalon
2018-05-14 14:46 ` Ferruh Yigit
2018-05-10 21:08 ` [dpdk-dev] [PATCH v10] " Ferruh Yigit
2018-05-08 10:10 ` [dpdk-dev] [PATCH v8] ethdev: check Rx/Tx offloads Wei Dai
2018-05-08 17:51 ` Andrew Rybchenko
2018-05-09 2:10 ` Dai, Wei
2018-05-09 14:11 ` Ferruh Yigit
2018-05-09 22:40 ` Ferruh Yigit
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=1525311040-26694-1-git-send-email-wei.dai@intel.com \
--to=wei.dai@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=qi.z.zhang@intel.com \
--cc=thomas@monjalon.net \
/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).