From: Moti Haimovsky <motih@mellanox.com>
To: ferruh.yigit@intel.com, stephen@networkplumber.org
Cc: gaetan.rivet@6wind.com, dev@dpdk.org,
Moti Haimovsky <motih@mellanox.com>
Subject: [dpdk-dev] [PATCH v4 1/2] net/failsafe: use new Tx offloads API
Date: Wed, 17 Jan 2018 16:30:12 +0200 [thread overview]
Message-ID: <1516199413-134187-1-git-send-email-motih@mellanox.com> (raw)
In-Reply-To: <1515595223-36144-1-git-send-email-motih@mellanox.com>
Ethdev Tx offloads API has changed since:
commit cba7f53b717d ("ethdev: introduce Tx queue offloads API")
This commit adds support for the new Tx offloads API.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
---
V4:
Modifications according to inputs from Gaetan Rivet in reply to
1515595223-36144-1-git-send-email-motih@mellanox.com
V3:
Modifications according to inputs from Stephen Hemminger
* Removed unnecessary initialization of tx_queue_offload_capa
V2:
* Fixed coding style warnings.
---
drivers/net/failsafe/failsafe_ops.c | 50 +++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/drivers/net/failsafe/failsafe_ops.c b/drivers/net/failsafe/failsafe_ops.c
index fe957ad..53a242e 100644
--- a/drivers/net/failsafe/failsafe_ops.c
+++ b/drivers/net/failsafe/failsafe_ops.c
@@ -31,6 +31,7 @@
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <stdbool.h>
#include <stdint.h>
#include <rte_debug.h>
@@ -84,9 +85,20 @@
fs_dev_configure(struct rte_eth_dev *dev)
{
struct sub_device *sdev;
+ uint64_t supp_tx_offloads;
+ uint64_t tx_offloads;
uint8_t i;
int ret;
+ supp_tx_offloads = PRIV(dev)->infos.tx_offload_capa;
+ tx_offloads = dev->data->dev_conf.txmode.offloads;
+ if ((tx_offloads & supp_tx_offloads) != tx_offloads) {
+ rte_errno = ENOTSUP;
+ ERROR("Some Tx offloads are not supported, "
+ "requested 0x%" PRIx64 " supported 0x%" PRIx64,
+ tx_offloads, supp_tx_offloads);
+ return -rte_errno;
+ }
FOREACH_SUBDEV(sdev, i, dev) {
int rmv_interrupt = 0;
int lsc_interrupt = 0;
@@ -312,6 +324,25 @@
return ret;
}
+static bool
+fs_txq_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads)
+{
+ uint64_t port_offloads;
+ uint64_t queue_supp_offloads;
+ uint64_t port_supp_offloads;
+
+ port_offloads = dev->data->dev_conf.txmode.offloads;
+ queue_supp_offloads = PRIV(dev)->infos.tx_queue_offload_capa;
+ port_supp_offloads = PRIV(dev)->infos.tx_offload_capa;
+ if ((offloads & (queue_supp_offloads | port_supp_offloads)) !=
+ offloads)
+ return false;
+ /* Verify we have no conflict with port offloads */
+ if ((port_offloads ^ offloads) & port_supp_offloads)
+ return false;
+ return true;
+}
+
static void
fs_tx_queue_release(void *queue)
{
@@ -348,6 +379,23 @@
fs_tx_queue_release(txq);
dev->data->tx_queues[tx_queue_id] = NULL;
}
+ /*
+ * Don't verify queue offloads for applications which
+ * use the old API.
+ */
+ if (tx_conf != NULL &&
+ (tx_conf->txq_flags & ETH_TXQ_FLAGS_IGNORE) &&
+ fs_txq_offloads_valid(dev, tx_conf->offloads) == false) {
+ rte_errno = ENOTSUP;
+ ERROR("Tx queue offloads 0x%" PRIx64
+ " don't match port offloads 0x%" PRIx64
+ " or supported offloads 0x%" PRIx64,
+ tx_conf->offloads,
+ dev->data->dev_conf.txmode.offloads,
+ PRIV(dev)->infos.tx_offload_capa |
+ PRIV(dev)->infos.tx_queue_offload_capa);
+ return -rte_errno;
+ }
txq = rte_zmalloc("ethdev TX queue",
sizeof(*txq) +
sizeof(rte_atomic64_t) * PRIV(dev)->subs_tail,
@@ -560,6 +608,8 @@
PRIV(dev)->infos.rx_offload_capa = rx_offload_capa;
PRIV(dev)->infos.tx_offload_capa &=
default_infos.tx_offload_capa;
+ PRIV(dev)->infos.tx_queue_offload_capa &=
+ default_infos.tx_queue_offload_capa;
PRIV(dev)->infos.flow_type_rss_offloads &=
default_infos.flow_type_rss_offloads;
}
--
1.8.3.1
next prev parent reply other threads:[~2018-01-17 14:30 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-04 19:31 [dpdk-dev] [PATCH 0/2] net/failsafe: convert to new ethdev " Moti Haimovsky
2018-01-04 19:31 ` [dpdk-dev] [PATCH 1/2] net/failsafe: convert to new Tx " Moti Haimovsky
2018-01-04 19:50 ` [dpdk-dev] [PATCH V2 0/2] net/failsafe: convert to new ethdev " Moti Haimovsky
2018-01-04 19:50 ` [dpdk-dev] [PATCH V2 1/2] net/failsafe: convert to new Tx " Moti Haimovsky
2018-01-04 20:15 ` Stephen Hemminger
2018-01-10 14:40 ` [dpdk-dev] [PATCH V3 " Moti Haimovsky
2018-01-10 14:40 ` [dpdk-dev] [PATCH V3 2/2] net/failsafe: convert to new Rx " Moti Haimovsky
2018-01-15 16:02 ` Gaëtan Rivet
2018-01-15 15:57 ` [dpdk-dev] [PATCH V3 1/2] net/failsafe: convert to new Tx " Gaëtan Rivet
2018-01-17 14:30 ` Moti Haimovsky [this message]
2018-01-17 14:30 ` [dpdk-dev] [PATCH v4 2/2] net/failsafe: use new Rx " Moti Haimovsky
2018-01-17 17:30 ` [dpdk-dev] [PATCH v4 1/2] net/failsafe: use new Tx " Gaëtan Rivet
2018-01-17 19:24 ` Ferruh Yigit
2018-01-04 19:50 ` [dpdk-dev] [PATCH V2 2/2] net/failsafe: convert to new Rx " Moti Haimovsky
2018-01-04 19:31 ` [dpdk-dev] [PATCH " Moti Haimovsky
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=1516199413-134187-1-git-send-email-motih@mellanox.com \
--to=motih@mellanox.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=gaetan.rivet@6wind.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).