From: "Kulasek, TomaszX" <tomaszx.kulasek@intel.com>
To: Thomas Monjalon <thomas.monjalon@6wind.com>,
"Ananyev, Konstantin" <konstantin.ananyev@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] doc: announce ABI change for rte_eth_dev structure
Date: Wed, 20 Jul 2016 15:42:51 +0000 [thread overview]
Message-ID: <3042915272161B4EB253DA4D77EB373A14EEA916@IRSMSX102.ger.corp.intel.com> (raw)
In-Reply-To: <2792307.Hs7AniM9ZW@xps13>
> -----Original Message-----
> From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com]
> Sent: Wednesday, July 20, 2016 17:22
> To: Ananyev, Konstantin <konstantin.ananyev@intel.com>
> Cc: Kulasek, TomaszX <tomaszx.kulasek@intel.com>; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] doc: announce ABI change for rte_eth_dev
> structure
>
> 2016-07-20 15:13, Ananyev, Konstantin:
> > Hi Thomas,
> >
> > > Hi,
> > >
> > > This patch announces an interesting change in the DPDK design.
> > >
> > > 2016-07-20 16:24, Tomasz Kulasek:
> > > > This is an ABI deprecation notice for DPDK 16.11 in librte_ether
> > > > about changes in rte_eth_dev and rte_eth_desc_lim structures.
> > > >
> > > > In 16.11, we plan to introduce rte_eth_tx_prep() function to do
> > > > necessary preparations of packet burst to be safely transmitted on
> > > > device for desired HW offloads (set/reset checksum field according
> > > > to the hardware requirements) and check HW constraints (number of
> > > > segments per packet, etc).
> > > >
> > > > While the limitations and requirements may differ for devices, it
> > > > requires to extend rte_eth_dev structure with new function pointer
> > > > "tx_pkt_prep" which can be implemented in the driver to prepare
> > > > and verify packets, in devices specific way, before burst, what
> > > > should to prevent application to send malformed packets.
> > > >
> > > > Also new fields will be introduced in rte_eth_desc_lim: nb_seg_max
> > > > and nb_mtu_seg_max, providing an information about max segments in
> > > > TSO and non TSO packets acceptable by device.
> > >
> > > We cannot acknowledge such notice without a prior design discussion.
> > > Please explain why you plan to work on this change and give a draft of
> the new structures (a RFC patch would be ideal).
> >
> > I think it is not really a deprecation note, but announce ABI change for
> rte_ethdev.h structures.
>
> An ABI break requires a deprecation notice. So it is :)
>
> > The plan is to implement what was proposed & discussed the following
> thread:
> > http://dpdk.org/ml/archives/dev/2015-September/023603.html
>
> Please could you summarize it here?
Hi Thomas,
The implementation of rte_eth_tx_prep() will be similar to the rte_eth_tx_burst(), passing same arguments to the driver, so packets can be checked and modified before real burst will be done.
The API for new function will be implemented in the fallowed way:
+/**
+ * Process a burst of output packets on a transmit queue of an Ethernet device.
+ *
+ * The rte_eth_tx_prep() function is invoked to prepare output packets to be
+ * transmitted on the output queue *queue_id* of the Ethernet device designated
+ * by its *port_id*.
+ * The *nb_pkts* parameter is the number of packets to be prepared which are
+ * supplied in the *tx_pkts* array of *rte_mbuf* structures, each of them
+ * allocated from a pool created with rte_pktmbuf_pool_create().
+ * For each packet to send, the rte_eth_tx_prep() function performs
+ * the following operations:
+ *
+ * - Check if packet meets devices requirements for tx offloads.
+ *
+ * - Check limitations about number of segments.
+ *
+ * - Check additional requirements when debug is enabled.
+ *
+ * - Update and/or reset required checksums when tx offload is set for packet.
+ *
+ * The rte_eth_tx_prep() function returns the number of packets ready it
+ * actually sent. A return value equal to *nb_pkts* means that all packets
+ * are valid and ready to be sent.
+ *
+ * @param port_id
+ * The port identifier of the Ethernet device.
+ * @param queue_id
+ * The index of the transmit queue through which output packets must be
+ * sent.
+ * The value must be in the range [0, nb_tx_queue - 1] previously supplied
+ * to rte_eth_dev_configure().
+ * @param tx_pkts
+ * The address of an array of *nb_pkts* pointers to *rte_mbuf* structures
+ * which contain the output packets.
+ * @param nb_pkts
+ * The maximum number of packets to process.
+ * @return
+ * The number of packets correct and ready to be sent. The return value can be
+ * less than the value of the *tx_pkts* parameter when some packet doesn't
+ * meet devices requirements with rte_errno set appropriately.
+ */
+static inline uint16_t
+rte_eth_tx_prep(uint8_t port_id, uint16_t queue_id, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+
+ if (!dev->tx_pkt_prep) {
+ rte_errno = -ENOTSUP;
+ return 0;
+ }
+
+#ifdef RTE_LIBRTE_ETHDEV_DEBUG
+ if (queue_id >= dev->data->nb_tx_queues) {
+ RTE_PMD_DEBUG_TRACE("Invalid TX queue_id=%d\n", queue_id);
+ rte_errno = -EINVAL;
+ return 0;
+ }
+#endif
+
+ return (*dev->tx_pkt_prep)(dev->data->tx_queues[queue_id], tx_pkts, nb_pkts);
+}
Tomasz
next prev parent reply other threads:[~2016-07-20 15:42 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-20 14:24 Tomasz Kulasek
2016-07-20 15:01 ` Thomas Monjalon
2016-07-20 15:13 ` Ananyev, Konstantin
2016-07-20 15:22 ` Thomas Monjalon
2016-07-20 15:42 ` Kulasek, TomaszX [this message]
2016-07-21 15:24 ` [dpdk-dev] [PATCH v2] " Tomasz Kulasek
2016-07-21 22:48 ` Ananyev, Konstantin
2016-07-27 8:59 ` Thomas Monjalon
2016-07-27 17:10 ` Jerin Jacob
2016-07-27 17:33 ` Ananyev, Konstantin
2016-07-27 17:41 ` Jerin Jacob
2016-07-27 20:51 ` Ananyev, Konstantin
2016-07-28 2:13 ` Jerin Jacob
2016-07-28 10:36 ` Ananyev, Konstantin
2016-07-28 11:38 ` Jerin Jacob
2016-07-28 12:07 ` Avi Kivity
2016-07-28 13:01 ` Ananyev, Konstantin
2016-07-28 13:58 ` Olivier MATZ
2016-07-28 14:21 ` Ananyev, Konstantin
2016-07-28 13:59 ` Jerin Jacob
2016-07-28 14:52 ` Thomas Monjalon
2016-07-28 16:25 ` Jerin Jacob
2016-07-28 17:07 ` Thomas Monjalon
2016-07-31 7:50 ` Vlad Zolotarov
2016-07-28 12:04 ` Avi Kivity
2016-07-31 7:46 ` [dpdk-dev] [PATCH] " Vlad Zolotarov
2016-07-31 8:10 ` Vlad Zolotarov
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=3042915272161B4EB253DA4D77EB373A14EEA916@IRSMSX102.ger.corp.intel.com \
--to=tomaszx.kulasek@intel.com \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@intel.com \
--cc=thomas.monjalon@6wind.com \
/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).