From: Wei Dai <wei.dai@intel.com>
To: thomas@monjalon.net, shahafs@mellanox.com
Cc: dev@dpdk.org, Wei Dai <wei.dai@intel.com>
Subject: [dpdk-dev] [PATCH] ethdev: check consistency of per port offloads
Date: Thu, 1 Feb 2018 21:53:06 +0800 [thread overview]
Message-ID: <1517493186-6687-1-git-send-email-wei.dai@intel.com> (raw)
A per port offloading feature should be enabled or
disabled at same time in both rte_eth_dev_configure( )
and rte_eth_rx_queue_setup( )/rte_eth_tx_queue_setup( ).
This patch check if a per port offloading flag has
same configuration in rte_eth_dev_configure( ) and
rte_eth_rx_queue_setup( )/rte_eth_tx_queue_setup( ).
This patch can make 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>
---
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 78bed1a..7945890 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -1404,6 +1404,44 @@ rte_eth_dev_is_removed(uint16_t port_id)
return ret;
}
+/**
+* Check if the Rx/Tx queue offloading settings is valid
+* @param queue_offloads
+* offloads input to rte_eth_rx_queue_setup( ) or rte_eth_tx_queue_setup( )
+* @param port_offloads
+* Rx or Tx offloads input to rte_eth_dev_configure( )
+* @param queue_offload_capa
+* rx_queue_offload_capa or tx_queue_offload_capa in struct rte_eth_dev_ifnfo
+* got from rte_eth_dev_info_get( )
+* @param all_offload_capa
+* rx_offload_capa or tx_offload_capa in struct rte_eth_dev_info
+* got from rte_eth_dev_info_get( )
+*
+* @return
+* Nonzero when per-queue offloading setting is valid
+*/
+static int
+rte_eth_check_queue_offloads(uint64_t queue_offloads,
+ uint64_t port_offloads,
+ uint64_t queue_offload_capa,
+ uint64_t all_offload_capa)
+{
+ uint64_t pure_port_capa = all_offload_capa ^ queue_offload_capa;
+
+ return !((port_offloads ^ queue_offloads) & pure_port_capa);
+}
+
+static int
+rte_eth_check_rx_queue_offloads(uint64_t rx_queue_offloads,
+ const struct rte_eth_rxmode *rxmode,
+ const struct rte_eth_dev_info *dev_info)
+{
+ return rte_eth_check_queue_offloads(rx_queue_offloads,
+ rxmode->offloads,
+ dev_info->rx_queue_offload_capa,
+ dev_info->rx_offload_capa);
+}
+
int
rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
uint16_t nb_rx_desc, unsigned int socket_id,
@@ -1446,6 +1484,7 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
(int) sizeof(struct rte_pktmbuf_pool_private));
return -ENOSPC;
}
+
mbp_buf_size = rte_pktmbuf_data_room_size(mp);
if ((mbp_buf_size - RTE_PKTMBUF_HEADROOM) < dev_info.min_rx_bufsize) {
@@ -1495,6 +1534,16 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
&local_conf.offloads);
}
+ if (!rte_eth_check_rx_queue_offloads(local_conf.offloads,
+ &dev->data->dev_conf.rxmode, &dev_info)) {
+ RTE_PMD_DEBUG_TRACE("%p : Rx queue offloads ox%" PRIx64
+ " don't match port offloads 0x%" PRIx64
+ " or supported offloads 0x%" PRIx64,
+ (void *)dev, local_conf.offloads,
+ dev_info.rx_offload_capa);
+ return -ENOTSUP;
+ }
+
ret = (*dev->dev_ops->rx_queue_setup)(dev, rx_queue_id, nb_rx_desc,
socket_id, &local_conf, mp);
if (!ret) {
@@ -1555,6 +1604,17 @@ rte_eth_convert_txq_offloads(const uint64_t tx_offloads, uint32_t *txq_flags)
*txq_flags = flags;
}
+static int
+rte_eth_check_tx_queue_offloads(uint64_t tx_queue_offloads,
+ const struct rte_eth_txmode *txmode,
+ const struct rte_eth_dev_info *dev_info)
+{
+ return rte_eth_check_queue_offloads(tx_queue_offloads,
+ txmode->offloads,
+ dev_info->tx_queue_offload_capa,
+ dev_info->tx_offload_capa);
+}
+
int
rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id,
uint16_t nb_tx_desc, unsigned int socket_id,
@@ -1622,6 +1682,16 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id,
&local_conf.offloads);
}
+ if (!rte_eth_check_tx_queue_offloads(local_conf.offloads,
+ &dev->data->dev_conf.txmode, &dev_info)) {
+ RTE_PMD_DEBUG_TRACE("%p : Tx queue offloads ox%" PRIx64
+ " don't match port offloads 0x%" PRIx64
+ " or supported offloads 0x%" PRIx64,
+ (void *)dev, local_conf.offloads,
+ dev_info.tx_offload_capa);
+ return -ENOTSUP;
+ }
+
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 reply other threads:[~2018-02-01 14:09 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-01 13:53 Wei Dai [this message]
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 ` [dpdk-dev] [PATCH v6] " Wei Dai
2018-05-04 11:12 ` 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=1517493186-6687-1-git-send-email-wei.dai@intel.com \
--to=wei.dai@intel.com \
--cc=dev@dpdk.org \
--cc=shahafs@mellanox.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).