[dpdk-dev] [PATCH v9 0/4] ethdev: add speed capabilities and refactor link API

[Nélio Laranjeiro]

On Wed, Mar 09, 2016 at 10:29:38AM +0100, Nélio Laranjeiro wrote:
> On Tue, Mar 08, 2016 at 05:53:05PM +0100, Nélio Laranjeiro wrote:
> > On Tue, Mar 08, 2016 at 04:00:29PM +0100, Marc Sune wrote:
> > > 2016-03-01 1:45 GMT+01:00 Marc Sune <marcdevel at gmail.com>:
> > > 
> > > > The current rte_eth_dev_info abstraction does not provide any mechanism to
> > > > get the supported speed(s) of an ethdev.
> > > >
> > > > For some drivers (e.g. ixgbe), an educated guess could be done based on the
> > > > driver's name (driver_name in rte_eth_dev_info), see:
> > > >
> > > > http://dpdk.org/ml/archives/dev/2013-August/000412.html
> > > >
> > > > However, i) doing string comparisons is annoying, and can silently
> > > > break existing applications if PMDs change their names ii) it does not
> > > > provide all the supported capabilities of the ethdev iii) for some drivers
> > > > it
> > > > is impossible determine correctly the (max) speed by the application
> > > > (e.g. in i40, distinguish between XL710 and X710).
> > > >
> > > > In addition, the link APIs do not allow to define a set of advertised link
> > > > speeds for autonegociation.
> > > >
> > > > This series of patches adds the following capabilities:
> > > >
> > > > * speed_capa bitmap in rte_eth_dev_info, which is filled by the PMDs
> > > >   according to the physical device capabilities.
> > > > * refactors link API in ethdev to allow the definition of the advertised
> > > >   link speeds, fix speed (no auto-negociation) or advertise all supported
> > > >   speeds (default).
> > > >
> > > > WARNING: this patch series, specifically 3/4, is NOT tested for most of the
> > > > PMDs, due to the lack of hardware. Only generic EM is tested (VM).
> > > > Reviewing
> > > > and testing required by PMD maintainers.
> > > >
> > > > * * * * *
> > > >
> > > > v2: rebase, converted speed_capa into 32 bits bitmap, fixed alignment
> > > >     (checkpatch).
> > > >
> > > > v3: rebase to v2.1. unified ETH_LINK_SPEED and ETH_SPEED_CAP into
> > > > ETH_SPEED.
> > > >     Converted field speed in struct rte_eth_conf to speed, to allow a
> > > > bitmap
> > > >     for defining the announced speeds, as suggested M. Brorup. Fixed
> > > > spelling
> > > >     issues.
> > > >
> > > > v4: fixed errata in the documentation of field speeds of rte_eth_conf, and
> > > >     commit 1/2 message. rebased to v2.1.0. v3 was incorrectly based on
> > > >     ~2.1.0-rc1.
> > > >
> > > > v5: revert to v2 speed capabilities patch. Fixed MLX4 speed capabilities
> > > >     (thanks N. Laranjeiro). Refactored link speed API to allow setting
> > > >     advertised speeds (3/4). Added NO_AUTONEG option to explicitely disable
> > > >     auto-negociation. Updated 2.2 rel. notes (4/4). Rebased to current
> > > > HEAD.
> > > >
> > > > v6: Move link_duplex to be part of bitfield. Fixed i40 autoneg flag link
> > > >     update code. Added rte_eth_speed_to_bm_flag() to .map file. Fixed other
> > > >     spelling issues. Rebased to current HEAD.
> > > >
> > > > v7: Rebased to current HEAD. Moved documentation to v2.3. Still needs
> > > > testing
> > > >     from PMD maintainers.
> > > >
> > > > v8: Rebased to current HEAD. Modified em driver impl. to not touch base
> > > > files.
> > > >     Merged patch 5 into 3 (map file). Changed numeric speed to a 64 bit
> > > > value.
> > > >     Filled-in speed capabilities for drivers bnx2x, cxgbe, mlx5 and nfp in
> > > >     addition to the ones of previous patch sets.
> > > >
> > > > v9: rebased to current HEAD. Reverted numeric speed to 32 bit in struct
> > > >     rte_eth_link (no atomic link get > 64bit). Fixed mlx5 driver
> > > > compilation
> > > >     and link speeds. Moved documentation to release_16_04.rst and fixed
> > > > several
> > > >     issues. Upgrade NIC notes with speed capabilities.
> > > >
> > > 
> > > Anyone interested in reviewing and _testing_ this series?
> > > 
> > > Thank you
> > > Marc
> > 
> > Hi Marc,
> > 
> > I will take a look tomorrow morning and run test on Mellanox NICs
> > (ConnectX 3 and 4).
> > 
> > I do not have access to the others NICs, if those who have can do
> > it, could be really great.
> > 
> > Regards,
> 
> It works as expected with Mellanox NICs.
> 
> Regards,
> 
> -- 
> Nélio Laranjeiro
> 6WIND

Tested-by: Nelio Laranjeiro <nelio.laranjeiro at 6wind.com>

- OS/Kernel: Debian 8/3.16.0-4-amd64
- GCC: gcc (Debian 4.9.2-10) 4.9.2
- CPU: Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz
- MLNX OFED: 3.2-2.0.0.0
- NIC: ConnectX 4 100G

- OS/Kernel: Debian 7/3.16.0-0.bpo.4-amd64
- GCC: gcc (Debian 4.7.2-5) 4.7.2
- CPU: Intel(R) Xeon(R) CPU E5-2648L 0 @ 1.80GHz
- MLNX OFED: 3.2-2.0.0.0
- NIC: ConnectX 3 Pro


1. Link displayed at the correct negotiated speed:
   - 40Gbps for ConnectX3 Pro
   - 100Gbps for ConnectX4 100G
   - 40Gbps for ConnectX4 100G on a 40G link.

2. Configuring speed:
   - Not supported yet for Mellanox as expected.

-- 
Nélio Laranjeiro
6WIND