Commit Graph

26 Commits

Author SHA1 Message Date
Andrew Rybchenko
9aa0afd1e9 net/sfc: advertise offload capabilities by Tx datapaths
Tx datapath feature bits were useful on migration from the old offload API
to the new one. However, right now it just adds indirection which
complicates code reading and understanding. Also addition of a new
offloads requires addition of a new feature bits and makes patches longer
and harder to understand. So, remove feature bits which correspond to Tx
offloads and simply advertise device and per-queue offloads directly.
Generic code could still mask some offloads if running HW or FW does not
support it.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Reviewed-by: Ivan Malov <ivan.malov@oktetlabs.ru>
2019-06-13 23:54:29 +09:00
Ivan Malov
c1ce2ba218 net/sfc: support tunnel TSO on EF10 native Tx datapath
Handle VXLAN and GENEVE TSO on EF10 native Tx datapath.

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-04-05 17:45:22 +02:00
Igor Romanov
9b70500cf2 net/sfc: add TSO header length check to Tx prepare
Make Tx prepare function able to detect packets with invalid header
size when header linearization is required.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-04-05 17:45:22 +02:00
Igor Romanov
f7a66f9365 net/sfc: introduce descriptor space check in Tx prepare
Add descriptor space check to Tx prepare function to inform a caller
that a packet that needs more than maximum Tx descriptors of a queue
can not be sent.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-04-05 17:45:22 +02:00
Igor Romanov
a3895ef38c net/sfc: move TSO header checks from Tx burst to Tx prepare
Tx offloads checks should be done in Tx prepare.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-04-05 17:45:22 +02:00
Igor Romanov
07685524c9 net/sfc: support Tx preparation in EFX datapath
Implement generic checks in Tx prepare function and update Tx burst
function accordingly.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-04-05 17:45:22 +02:00
Igor Romanov
9dbd28df2d net/sfc: use NIC min number of Tx descs instead of define
Min limit is not common for all NIC families. Use the variable from
NIC configuration instead of deprecated define.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-02-08 11:35:41 +01:00
Andrew Rybchenko
3cf4b9c24b net/sfc: support Tx descriptor status in secondary process
If Tx datapath supports multi-process, secondary process should be
able to use Tx descriptor status API.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2019-02-07 16:06:30 +01:00
Igor Romanov
6bc985e411 net/sfc: support TSO in EF10 Tx datapath
Implementation includes following limitations:

1) Packet's header length must be less than 256 (SFC_TSOH_STD_LEN);
2) Offset of the TCP header must be less than 208
   (EF10_TCP_HEADER_OFFSET_LIMIT);
3) Number of Tx descriptors must be not less than number of descriptors
   needed for TSO settings plus header plus one data segment.

If above conditions are not met, the packet is dropped.

If the maximum descriptor space is insufficient to hold entire TSO packet,
only a part of the packet is sent.

Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2018-10-11 18:53:49 +02:00
Ferruh Yigit
ab3ce1e0c1 ethdev: remove old offload API
In DPDK 17.11, the ethdev offloads API has changed:
	commit cba7f53b71 ("ethdev: introduce Tx queue offloads API")
	commit ce17eddefc ("ethdev: introduce Rx queue offloads API")
The new API is documented in the programmer's guide:
	http://doc.dpdk.org/guides/prog_guide/poll_mode_drv.html#hardware-offload

For reminder, the main concepts in the new API were:
	- All offloads are disabled by default
	- Distinction between per port and per queue offloads.

The transition bits are now removed:
	- Translation of the old API in ethdev
	- rte_eth_conf.rxmode.ignore_offload_bitfield
	- ETH_TXQ_FLAGS_IGNORE

The old API bits are now removed:
	- Rx per-port rte_eth_conf.rxmode.[bit-fields]
	- Tx per-queue rte_eth_txconf.txq_flags
	- ETH_TXQ_FLAGS_NO*

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Shahaf Shuler <shahafs@mellanox.com>
2018-07-04 21:50:32 +02:00
Andrew Rybchenko
714bff55a4 net/sfc: support runtime VI window size
Medford2 uses a configurable VI window size, and requires
updates to register accesses to use a runtime VI window size
rather than the *_STEP register constants used for earlier
controllers.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
2018-03-30 14:08:44 +02:00
Ferruh Yigit
ffc905f3b8 ethdev: separate driver APIs
Create a rte_ethdev_driver.h file and move PMD specific APIs here.
Drivers updated to include this new header file.

There is no update in header content and since ethdev.h included by
ethdev_driver.h, nothing changed from driver point of view, only
logically grouping of APIs. From applications point of view they can't
access to driver specific APIs anymore and they shouldn't.

More PMD specific data structures still remain in ethdev.h because of
inline functions in header use them. Those will be handled separately.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
2018-01-22 01:26:49 +01:00
Ivan Malov
c78d280e88 net/sfc: convert to new Tx offload API
Ethdev Tx offloads API has changed since:
commit cba7f53b71 ("ethdev: introduce Tx queue offloads API")
This commit support the new Tx offloads API.

The code which fills in txq_flags in default_txconf is preserved
because rte_eth_dev_info_get() lacks conversion between offloads
and txq_flags fields which means that a legacy application which
relies on default_txconf will fail to configure Tx queues in the
case when some bits in txq_flags are mandatory.

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2018-01-21 15:51:52 +01:00
Andrew Rybchenko
44c0947bae net/sfc: change license to BSD-3-Clause
Change license from BSD-2-Clause to BSD-3-Clause.
Bump copyright year.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
2018-01-16 18:47:49 +01:00
Andrew Rybchenko
c7dadc9fb5 net/sfc: support more options for a number of Tx descriptors
The number of Tx descriptors is not used as HW Tx ring size any more.
It simply defines maximum fill level.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
2018-01-16 18:47:49 +01:00
Andrew Rybchenko
eaab5d96c4 net/sfc: use Tx queue max fill level calculated on init
Prepare to support more options for number of Tx descriptors.

libefx-based datapath is updated just for completeness to
make code more readable and less error-prone.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
2018-01-16 18:47:49 +01:00
Andrew Rybchenko
420efecb54 net/sfc: make Tx free threshold check datapath specific
EFX_TXQ_LIMIT is libefx-specifics and it should not be used
for other Tx datapaths implementations (e.g. EF10 native).

EF10 native Tx datapath has its own understanding of the maximum
TxQ fill level imposed by EvQ clear strategy and space reserved
for Tx error and flush events.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
2018-01-16 18:47:49 +01:00
Ivan Malov
093e1afa24 net/sfc: free mbufs in bulks on simple EF10 Tx reap
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-10-06 02:49:48 +02:00
Ivan Malov
7df6f8542d net/sfc: support Tx descriptor status API
Support for the feature is added to EFX Tx datapath

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-10-06 02:49:47 +02:00
Andrew Rybchenko
f28ede500c net/sfc: support multi-process
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
2017-06-12 10:41:26 +01:00
Andrew Rybchenko
5688520075 net/sfc: implement simple EF10 native Tx datapath
The datapath does not support VLAN insertion, TSO and multi-segment
mbufs.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-04-04 18:59:43 +02:00
Andrew Rybchenko
ea2ed84c2f net/sfc: make multi-segment support a Tx datapath feature
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-04-04 18:59:43 +02:00
Andrew Rybchenko
8b00f426eb net/sfc: implement EF10 native Tx datapath
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: David Riddoch <driddoch@solarflare.com>
2017-04-04 18:59:43 +02:00
Andrew Rybchenko
7a4d44a639 net/sfc: make TSO a datapath-dependent feature
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-04-04 18:59:43 +02:00
Andrew Rybchenko
45cbb96c06 net/sfc: make VLAN insertion a datapath-dependent feature
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-04-04 18:59:43 +02:00
Andrew Rybchenko
dbdc82416b net/sfc: factor out libefx-based Tx datapath
Split control and datapath to make datapath substitutable and
possibly reusable with alternative control path.

libefx-based Tx datapath is bound to libefx control path, but
it should be possible to use other datapaths with alternative
control path(s).

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
2017-04-04 18:59:43 +02:00