Commit Graph

233 Commits

Author SHA1 Message Date
Ferruh Yigit
dd2c630a5f drivers/net: remove unnecessary macro for unused variables
remove __rte_unused instances that are not required.

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Allain Legacy <allain.legacy@windriver.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
2017-06-12 10:41:25 +01:00
Thomas Monjalon
2f6fec5390 vdev: remove eal prefix
The VDEV code will move to the bus drivers directory.
Rename functions from rte_eal_vdev_ to rte_vdev_
to prepare the move of the driver out of EAL.

The prefix rte_eal_vdrv_ is also renamed to rte_vdev_.
It was used for registration of vdev drivers.

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2017-05-05 14:38:35 +02:00
Wei Wang
210903803f net/bonding: fix updating slave link status
We need to update dev->data->dev_link before handling LSC event.
Otherwise it will still have the initial value after the startup of
the program before interrupt callback was executed.

Fixes: 414b202343 ("bonding: fix initial link status of slave")
Cc: stable@dpdk.org

Signed-off-by: Wei Wang <lnykww@gmail.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2017-04-28 14:46:18 +02:00
Ilya Maximets
c32c2c06bc net/bonding: allow configuring jumbo frames without slaves
Currently, 'rte_eth_dev_configure' fails on attempt to setup
max_rx_pkt_len > 2048 if no slaves was added to bonded device.

For example:

	rte_eth_dev_attach("eth_bond0,slave=05:00.0,mode=l34", &id)
	conf.rxmode.jumbo_frame = 1;
	conf.rxmode.max_rx_pkt_len = 9000;
	rte_eth_dev_configure(id, 1, 1, &conf)

Result:
	EAL: Initializing pmd_bond for eth_bond0
	EAL: Create bonded device eth_bond0 on port 4 in mode 2 on socket 0.
	rte_eth_dev_configure: ethdev port_id=4 \
		max_rx_pkt_len 9018 > max valid value 2048

It's expected that slaves will be added to bonded device inside
'rte_eth_dev_configure' and proper 'max_rx_pktlen' configured
for all of them.

Failure happens because of hardcoded low value of 'max_rx_pktlen'.
Increasing of this value to ETHER_MAX_JUMBO_FRAME_LEN will allow
above scenario (attach + configure).

It is important because it is the way OVS wants to work with
all DPDK devices (including virtual).
Changing the default hardcoded value makes no harm because
all the slaves' related code uses only 'candidate_max_rx_pktlen'
variable.

Fixes: 6cfc6a4f0d ("net/bonding: inherit maximum Rx packet length")
CC: stable@dpdk.org

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2017-04-19 15:37:37 +02:00
Ilya Maximets
01c0eae742 net/bonding: remove all slaves on close
Some applications like OVS knows nothing about the
device type and wants to use same API to work with
all of them. But bond_pmd, unlike other pmds, requires
additional step (removing of all the slaves) before
closing the device.

In fact that bond_pmd automatically adds all the
devices from kvargs to bonding on configuration it
also should remove all of them on close.

This change is intended to have the same API for physical
and virtual devices. It allows us to handle virtual
devices in OVS in a common way.

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2017-04-19 15:37:37 +02:00
Jan Blunck
050fe6e9ff drivers/net: use ethdev allocation helper for vdev
Signed-off-by: Jan Blunck <jblunck@infradead.org>
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2017-04-18 19:04:49 +02:00
Jan Blunck
68451eb669 net/bonding: call through EAL on create/free
To properly embed the generic rte_device into the rte_eth_dev this reworks
the bonding API to call through rte_eal_vdev_init().

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
2017-04-18 19:00:01 +02:00
Jan Blunck
5d2aa461cb vdev: use generic vdev struct for probe and remove
This is a preparation to embed the generic rte_device into the rte_eth_dev
also for virtual devices.

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
2017-04-14 15:41:50 +02:00
Keith Wiles
ae2a04864a net/bonding: reduce slave starvation on Rx poll
When polling the bonded ports for RX packets the old driver would
always start with the first slave in the list. If the requested
number of packets is filled on the first port in a two port config
then the second port could be starved or have larger number of
missed packet errors.

The code attempts to start with a different slave each time RX poll
is done to help eliminate starvation of slave ports. The effect of
the previous code was much lower performance for two slaves in the
bond then just the one slave.

The performance drop was detected when the application can not poll
the rings of Rx packets fast enough and the packets per second for
two or more ports was at the threshold throughput of the application.
At this threshold the slaves would see very little or no drops in
the case of one slave. Then enable the second slave you would see
a large drop rate on the two slave bond and reduction in throughput.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2017-04-04 18:59:45 +02:00
Bruce Richardson
ecaed092b6 ring: return remaining entry count when dequeuing
Add an extra parameter to the ring dequeue burst/bulk functions so that
those functions can optionally return the amount of remaining objs in the
ring. This information can be used by applications in a number of ways,
for instance, with single-consumer queues, it provides a max
dequeue size which is guaranteed to work.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
2017-03-29 22:32:20 +02:00
Olivier Matz
feb9f680cd mk: optimize directory dependencies
Before this patch, the management of dependencies between directories
had several issues:

- the generation of .depdirs, done at configuration is slow: it can take
  more than one minute on some slow targets (usually ~10s on a standard
  PC without -j).

- for instance, it is possible to express a dependency like:
  - app/foo depends on lib/librte_foo
  - and lib/librte_foo depends on app/bar
  But this won't work because the directories are traversed with a
  depth-first algorithm, so we have to choose between doing 'app' before
  or after 'lib'.

- the script depdirs-rule.sh is too complex.

- we cannot use "make -d" for debug, because the output of make is used for
  the generation of .depdirs.

This patch moves the DEPDIRS-* variables in the upper Makefile, making
the dependencies much easier to calculate. A DEPDIRS variable is still
used to process library dependencies in LDLIBS.

After this commit, "make config" is almost immediate.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Tested-by: Robin Jarry <robin.jarry@6wind.com>
Tested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
2017-03-27 23:28:43 +02:00
Hemant Agrawal
5a11168d9b mbuf: use pktmbuf helper to create the pool
When possible, replace the uses of rte_mempool_create() with
the helper provided in librte_mbuf: rte_pktmbuf_pool_create().

This is the preferred way to create a mbuf pool.

This also updates the documentation.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
2017-03-15 13:48:02 +01:00
Emmanuel Roullit
2e056ec0dc net/bonding: remove useless assignment
Found with clang static analysis:
drivers/net/bonding/rte_eth_bond_pmd.c:903:3:
warning: Value stored to 'num_not_send' is never read
        num_not_send += slave_bufs_pkts[RTE_MAX_ETHPORTS] - num_send;
        ^               ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fixes: 06fe78b98c ("bond: add mode 6")
Cc: stable@dpdk.org

Signed-off-by: Emmanuel Roullit <emmanuel.roullit@gmail.com>
2017-01-30 22:18:26 +01:00
David Marchand
73db5badb0 net: align ethdev and eal driver names
Some virtual pmds report a different name than the vdev driver name
registered in eal.
While it does not hurt, let's try to be consistent.

Signed-off-by: David Marchand <david.marchand@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2017-01-17 19:36:47 +01:00
Jan Blunck
eac901ce29 ethdev: decouple from PCI device
This makes struct rte_eth_dev independent of struct rte_pci_device by
replacing it with a pointer to the generic struct rte_device.

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
2016-12-25 23:30:19 +01:00
Stephen Hemminger
74343fa77d drivers: remove useless reset of PCI device pointer
Since rte_eth_dev_info_get does memset() on dev_info before
calling device specific code, the explicit assignment of NULL
in all these virtual drivers has no effect.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jan Blunck <jblunck@infradead.org>
2016-12-24 18:47:19 +01:00
Ilya Maximets
1e2eff64f5 net/bonding: reconfigure all slave queues every time
This reverts commit 5b7bb2bda5.

It is necessary to reconfigure all queues every time because configuration
can be changed.

For example, if we're reconfiguring bonding device with new memory pool,
already configured queues will still use the old one. And if the old
mempool be freed, application likely will panic in attempt to use
freed mempool.

This happens when we use the bonding device with OVS 2.6 while MTU
reconfiguration:

PANIC in rte_mempool_get_ops():
assert "(ops_index >= 0) && (ops_index < RTE_MEMPOOL_MAX_OPS_IDX)" failed

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Acked-by: Jan Blunck <jblunck@infradead.org>
2016-12-21 18:47:53 +01:00
Jan Blunck
601319ae24 net/bonding: force reconfiguration of removed slaves
After a slave interface is removed from a bond group it still has the
configuration of the bond interface. Lets enforce that the slave interface
is reconfigured after removal by resetting it.

Signed-off-by: Jan Blunck <jblunck@infradead.org>
2016-12-21 18:47:53 +01:00
Jan Blunck
75aca7997e ethdev: initialize more fields on allocation
This moves the non-PCI related initialization of the link state interrupt
callback list and the setting of the default MTU to rte_eth_dev_allocate()
so that drivers only need to set non-default values.

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2016-12-21 17:32:17 +01:00
Jan Blunck
7f95f78a8a ethdev: clear data when allocating device
Lets clear the eth_dev->data when allocating a new rte_eth_dev so that
drivers only need to set non-zero values.

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2016-12-21 17:30:27 +01:00
Haifeng Lin
9ed2c8a299 net/bonding: handle only LACP slow packets
We should not drop the slow packets which subtype is
not marker or lacp. Because slow packets have other subtype
like OAM,OSSP,user defined and so on.

Signed-off-by: Haifeng Lin <haifeng.lin@huawei.com>
Reviewed-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
2016-11-07 21:19:57 +01:00
Jan Blunck
9fa80cb26b net: register aliases for renamed vdev drivers
This registers the legacy names of the driver being renamed in
commit 2f45703c17 ("drivers: make driver names consistent").

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Reviewed-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
2016-10-25 18:49:18 +02:00
Bernard Iremonger
c1ceaf3ad0 ethdev: add an argument to internal callback function
add cb_arg parameter to the _rte_eth_dev_callback_process function.

Adding a parameter to this function allows passing information
to the application when an eth device event occurs such as
a VF to PF message.
This allows the application to decide if a particular function
is permitted.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Signed-off-by: Alex Zelezniak <alexz@att.com>
2016-10-14 02:01:52 +02:00
Shreyansh Jain
01f1922786 drivers: rename register macro prefix
All macros related to driver registeration renamed from DRIVER_*
to RTE_PMD_*

This includes:

 DRIVER_REGISTER_PCI -> RTE_PMD_REGISTER_PCI
 DRIVER_REGISTER_PCI_TABLE -> RTE_PMD_REGISTER_PCI_TABLE
 DRIVER_REGISTER_VDEV -> RTE_PMD_REGISTER_VDEV
 DRIVER_REGISTER_PARAM_STRING -> RTE_PMD_REGISTER_PARAM_STRING
 DRIVER_EXPORT_* -> RTE_PMD_EXPORT_*

Fix PMDINFOGEN tool to look for matches of RTE_PMD_REGISTER_*.

Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2016-10-14 01:49:32 +02:00
Eric Kinzie
c771e4ef38 net/bonding: enable slave VLAN filter
SR-IOV virtual functions cannot rely on promiscuous mode for the reception
of VLAN tagged frames. Program the VLAN filter for each slave when a
VLAN is configured for the bonding master.

Signed-off-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
2016-10-13 15:30:59 +02:00
Eric Kinzie
b4092cacf6 net/bonding: validate speed after link up
It's possible for the bonding driver to mistakenly reject an interface
based in it's, as yet, unnegotiated link speed and duplex. Always allow
the interface to be added to the bonding interface but require link
properties validation to succeed before slave is activated.

Fixes: 2efb58cbab ("bond: new link bonding library")

Signed-off-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
2016-10-13 15:30:59 +02:00
Shreyansh Jain
50a3345fa9 vdev: rename init/uninit ops to probe/remove
Inline with PCI probe and remove, VDEV probe and remove hooks provide
a uniform naming.
PCI probe represents scan and driver initialization. For VDEV, it will
represent argument parsing and initialization.

Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
2016-10-06 16:02:14 +02:00
Jan Viktorin
2695c6df69 eal: remove unused PMD types
- All devices register themselfs by calling a kind of DRIVER_REGISTER_XXX.
  The PMD_REGISTER_DRIVER is not used anymore.
- PMD_VDEV type is also not being used - can be removed from all VDEVs.

Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: David Marchand <david.marchand@6wind.com>
2016-10-03 16:33:51 +02:00
Jan Viktorin
fe363dd425 drivers: use vdev registration
All PMD_VDEV drivers can now use rte_vdev_driver instead of the
rte_driver (which is embedded in the rte_vdev_driver).

Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: David Marchand <david.marchand@6wind.com>
2016-10-03 16:33:48 +02:00
David Marchand
6751f6deb7 ethdev: get rid of device type
Now that hotplug has been moved to eal, there is no reason to keep the
device type in this layer.

Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Shreyansh Jain <shreyansh.jain@nxp.com>
2016-10-03 16:33:39 +02:00
Pablo de Lara
2f45703c17 drivers: make driver names consistent
As discussed in the past release, driver names are modified
to be more consistent, and the future driver should follow
this new convention.

Driver names consist of:
"driver category"_"driver folder name"_"optional extra name".

For example:
- Crypto null driver       -> "crypto_null"
- Network IXGBE VF driver  -> "net_ixgbe_vf"

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
2016-09-16 11:55:59 +02:00
Christian Ehrhardt
2bf4c83555 net/bonding: fix exported symbol versioning
The older versions of rte_eth_bond_8023ad_conf_get and
rte_eth_bond_8023ad_setup were available in the old way since 2.0 - at
least according to the map file.

But versioning in the code was set to 16.04.
That breaks compatibility checks for 2.0 on that library.

For example with the dpdk abi checker:
http://people.canonical.com/~paelzer/compat_report.html

To fix, version the old symbols on the 2.0 version as they were
initially added to the map file.

See http://people.canonical.com/~paelzer/compat_report.html

Fixes: dc40f17a ("net/bonding: allow external state machine in mode 4")

Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
2016-07-11 14:56:51 +02:00
Pablo de Lara
419f2add3b net/bonding: fix range of mode parameter
The range of the supported bonding modes is 0-6, instead of 0-4.

Fixes: cb6696d220 ("drivers: update registration macro usage")

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
2016-07-10 14:51:09 +02:00
Pablo de Lara
65eca099f4 drivers: split parameters infos in multiple lines
Driver arguments shown with DRIVER_REGISTER_PARAM_STRING
have been separated in multiple lines and indented to
ease their readability.

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
2016-07-10 14:51:09 +02:00
Pablo de Lara
bae696ebd4 drivers: remove static driver names
Since now the PMD_REGISTER_DRIVER macro sets the driver names,
there is no need to have the rte_driver structure setting it
statically, as it will get overridden.

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
2016-07-10 14:51:09 +02:00
Pablo de Lara
1586ff4cef drivers: revert vdev driver names to original
In order to avoid API breakage, the driver names of the virtual devices
have been renamed to their original name, before the modification
of the PMD_REGISTER_DRIVER macro, which sets now the driver names.

Fixes: cb6696d220 ("drivers: update registration macro usage")

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
2016-07-10 14:51:09 +02:00
Neil Horman
cb6696d220 drivers: update registration macro usage
Modify the PMD_REGISTER_DRIVER macro, adding a name argument to it.  The
addition of a name argument creates a token that can be used for subsequent
macros in the creation of unique symbol names to export additional bits of
information for use by the pmdinfogen tool.  For example:

PMD_REGISTER_DRIVER(ena_driver, ena);

registers the ena_driver struct as it always did, and creates a symbol
const char this_pmd_name0[] __attribute__((used)) = "ena";

which pmdinfogen can search for and extract.  The subsequent macro

DRIVER_REGISTER_PCI_TABLE(ena, ena_pci_id_map);

creates a symbol const char ena_pci_tbl_export[] __attribute__((used)) =
"ena_pci_id_map";

Which allows pmdinfogen to find the pci table of this driver

Using this pattern, we can export arbitrary bits of information.

pmdinfo uses this information to extract hardware support from an object
file and create a json string to make hardware support info discoverable
later.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Panu Matilainen <pmatilai@redhat.com>
Acked-by: Remy Horton <remy.horton@intel.com>
2016-07-06 23:21:40 +02:00
Eric Kinzie
dc40f17a36 net/bonding: allow external state machine in mode 4
Provide functions to allow an external 802.3ad state machine to transmit
and receive LACPDUs and to set the collection/distribution flags on
slave interfaces.

Signed-off-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-06-20 18:40:44 +02:00
Eric Kinzie
6cfc6a4f0d net/bonding: inherit maximum Rx packet length
Instead of a hard-coded maximum receive length, allow the bonded interface
to inherit this limit from the slave interfaces.  This allows
an application that uses jumbo frames to pass realistic values to
rte_eth_dev_configure without causing an error.

Before the bonding interface is configured, allow slaves with any
max_rx_pktlen to be added and remember the lowest of these values as
a candidate value.  During dev_configure, set the bond device's
max_rx_pktlen to the candidate value.  After this point only slaves
with a max_rx_pktlen greater or equal to that of the bonding device
can be added.

If all slaves are removed, the bond device's pktlen is cleared.

Signed-off-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-06-20 18:36:47 +02:00
Michal Jastrzebski
08719a8417 net/bonding: replace panic with errno code return
This patch modifies bond_mode_alb_enable function.
When mempool allocation fails errno code is returned
instead of rte_panic. This allow to decide on application level
if it should quit or retry for mempool allocation.

Signed-off-by: Michal Jastrzebski <michalx.k.jastrzebski@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
2016-06-20 17:21:48 +02:00
Christian Ehrhardt
6cbf4f75e0 mk: fix missing internal dependencies
This patch adds missing DEPDIRS to avoid any library referring to
symbols they are not linked against.

Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
2016-06-13 16:17:56 +02:00
Mauricio Vasquez B
1414dabc1b ethdev: use dedicated macro to check port id
The RTE_ETH_VALID_PORTID_OR_ERR_RET macro is used in some places
to check if a port id is valid or not. This commit makes use of it in
some new parts of the code.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquezbernal@studenti.polito.it>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2016-05-24 15:30:08 +02:00
Thomas Monjalon
50705e8e3c eal: add assert macro for debug
The macro RTE_VERIFY always checks a condition.
It is optimized with "unlikely" hint.
While this macro is well suited for test applications, it is preferred
in libraries and examples to enable such check in debug mode.
That's why the macro RTE_ASSERT is introduced to call RTE_VERIFY only
if built with debug logs enabled.

A lot of assert macros were duplicated and enabled with a specific flag.
Removing these #ifdef allows to test these code branches more easily
and avoid dead code pitfalls.

The ENA_ASSERT is kept (in debug mode only) because it has more
parameters to log.

Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2016-05-02 15:31:17 +02:00
Thomas Monjalon
a61dc000d5 ethdev: remove deprecated statistics
Some statistics were deprecated since release 2.1 (49f386542a).
The last deprecated counter to be used was imcasts.

The VF loopback statistics are also removed as they are used only
in igb and duplicated in extended statistics.

The new counters should be added to extended statistics.

Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Remy Horton <remy.horton@intel.com>
2016-04-20 13:49:31 +02:00
Marc Sune
82113036e4 ethdev: redesign link speed config
This patch redesigns the API to set the link speed/s configuration
of an ethernet port. Specifically:

- it allows to define a set of advertised speeds for
  auto-negociation.
- it allows to disable link auto-negociation (single fixed speed).
- default: auto-negociate all supported speeds.

A flag autoneg in struct rte_eth_link indicates if link speed was a
result of auto-negociation or was fixed by configuration.

Signed-off-by: Marc Sune <marcdevel@gmail.com>
Tested-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Tested-by: Beilei Xing <beilei.xing@intel.com>
Tested-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
2016-04-01 21:38:34 +02:00
Marc Sune
39fd068a27 ethdev: rename link speed constants
The speed numbers ETH_LINK_SPEED_ are renamed ETH_SPEED_NUM_.
The prefix ETH_LINK_SPEED_ is kept for AUTONEG and will be used
for bit flags in next patch.

Signed-off-by: Marc Sune <marcdevel@gmail.com>
2016-04-01 21:38:34 +02:00
Thomas Monjalon
09419f235e ethdev: use constants for link state
Define and use ETH_LINK_UP and ETH_LINK_DOWN where appropriate.

Signed-off-by: Marc Sune <marcdevel@gmail.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2016-04-01 21:38:34 +02:00
Vladyslav Buslov
aea2af182c bonding: fix loop boundary condition
Loop that calculates total number of tx descriptors in slave tx queues
should iterate up to nb_tx_queues, not nb_rx_queues.

Fixes: 3ef7955700 ("bonding: fix LACP mempool size")

Signed-off-by: Vladyslav Buslov <vladyslav.buslov@harmonicinc.com>
2016-04-01 15:29:40 +02:00
Nelson Escobar
44bf37a702 bonding: fix link detect in non-interrupt mode
Stopping then re-starting a bond interface containing slaves that
used polling for link detection caused the bond to think all slave
links were down and inactive.

Move the start of the polling for link from slave_add() to
bond_ethdev_start() and in bond_ethdev_stop() make sure we clear
the last_link_status of the slaves.

Fixes: a45b288ef2 ("bond: support link status polling")

Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-04-01 15:07:53 +02:00
Eric Kinzie
5b7bb2bda5 bonding: use existing enslaved device queues
This solves issues when an active device is added to a bond.

If a device to be enslaved already has transmit and/or receive queues
allocated, use those and then create any additional queues that are
necessary.

Fixes: 2efb58cbab ("bond: new link bonding library")

Signed-off-by: Eric Kinzie <ehkinzie@gmail.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
2016-03-25 19:03:48 +01:00
Bernard Iremonger
e0665f9809 bonding: fix current primary port
The current_primary_port is initialised to an invalid value
during bonded device creation.
It must be set to a valid value later.
This fix sets it to a valid value when the first slave port
is added to the bonding device.

Fixes: 2efb58cbab ("bond: new link bonding library")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2016-03-25 19:03:48 +01:00
Stephen Hemminger
89b890df3f drivers: make struct of networking operations const
This structure has immutable function pointers.
Also fix indentation.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2016-03-25 19:01:37 +01:00
Bernard Iremonger
2186fff367 bonding: fix crash when no slave device
If a bonded device is created when there are no slave devices
there is a loop in bond_ethdev_promiscuous_enable() which results
in a segmentation fault.

The solution is to initialise the current_primary_port to an
invalid port value when the bonded port is created.

Fixes: 2efb58cbab ("bond: new link bonding library")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
2016-03-16 19:05:47 +01:00
Eric Kinzie
7a7122edf1 bonding: do not activate slave twice
The current code for detecting link during slave addition can cause a
slave interface to be activated twice -- once during slave_configure()
and again at the end of __eth_bond_slave_add_lock_free().  This will
either cause the active slave count to be incorrect or will cause the
802.3ad activation function to panic.  Ensure that the interface is not
activated more than once.

Fixes: 46fb436836 ("bond: add mode 4")

Signed-off-by: Eric Kinzie <ekinzie@brocade.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Eric Kinzie
8997a10bfc bonding: fix active slaves with no primary
If the link state of a slave is "up" when added, it is added to the list
of active slaves but, even if it is the only slave, is not selected as
the primary interface.  Generally, handling of link state interrupts
selects an interface to be primary, but only if the active count is zero.
This change avoids the situation where there are active slaves but
no primary.

Fixes: 2efb58cbab ("bond: new link bonding library")

Signed-off-by: Eric Kinzie <ekinzie@brocade.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Eric Kinzie
6698820b5f bonding: do not ignore multicast in mode 4
The bonding PMD in mode 4 puts all enslaved interfaces into promiscuous
mode in order to receive LACPDUs and must filter unwanted packets
after the traffic has been "collected".  Allow broadcast and multicast
through so that ARP and IPv6 neighbor discovery continue to work.

Fixes: 46fb436836 ("bond: add mode 4")

Signed-off-by: Eric Kinzie <ekinzie@brocade.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Eric Kinzie
786c990a11 bonding: copy entire config structure in mode 4
Copy all needed fields from the mode8023ad_private structure in
bond_mode_8023ad_conf_get().  This help ensure that a subsequent call
to rte_eth_bond_8023ad_setup() is not passed uninitialized data that
would result in either incorrect behavior or a failed sanity check.

Fixes: 46fb436836 ("bond: add mode 4")

Signed-off-by: Eric Kinzie <ekinzie@brocade.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Bernard Iremonger
df3e8ad73f bonding: fix detach of slave devices
Ensure that a bonded slave device is not detached,
until it is removed from the bonded device.

Fixes: 2efb58cbab ("bond: new link bonding library")
Fixes: a45b288ef2 ("bond: support link status polling")
Fixes: 494adb7f63 ("ethdev: add device fields from PCI layer")
Fixes: b1fb53a39d ("ethdev: remove some PCI specific handling")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Bernard Iremonger
6e02723754 bonding: fix detach of bonded device
Check that the bonded device has no slaves before detaching it.

Fixes: 8d30fe7fa7 ("bonding: support port hotplug")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2016-03-16 19:05:47 +01:00
Huawei Xie
693f715da4 remove extra parentheses in return statement
fix the error reported by checkpatch:
  "ERROR: return is not a function, parentheses are not required"

remove parentheses in return like:
  "return (logical expressions)"

remove parentheses in return a function like:
  "return (rte_mempool_lookup(...))"

Fixes: 6307b909b8 ("lib: remove extra parenthesis after return")

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
2016-02-10 15:47:50 +01:00
Andriy Berestovskyy
1d63c314b7 bonding: fix reordering of IP fragments
Fragmented IPv4 packets have no TCP/UDP headers, so we hashed
random data introducing reordering of the fragments.

Signed-off-by: Andriy Berestovskyy <aber@semihalf.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-12-14 22:53:17 +01:00
Andriy Berestovskyy
3ef7955700 bonding: fix LACP mempool size
The following messages might appear after some idle time:
"PMD: Failed to allocate LACP packet from pool"

The fix ensures the mempool size is greater than the sum
of TX descriptors.

Signed-off-by: Andriy Berestovskyy <aber@semihalf.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-12-14 22:53:10 +01:00
Bernard Iremonger
3de5105468 bonding: fix link state interrupt flag
replace RTE_PCI_DRV_INTR_LSC with RTE_ETH_DEV_INTR_LSC

Fixes: 71ba84b1cc ("bonding: remove fake pci interface")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-12-07 01:03:13 +01:00
Stephen Hemminger
f528a67fc5 bonding: add depencency on cmdline library
Parallel build of bonding driver can fail because of
missing dependency.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-12-03 00:02:53 +01:00
Stephen Hemminger
476e41929f bonding: do not sum deprecated statistics
These statistics are marked deprecated, leave them alone.
Also keep track of imissed across all ports.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
2015-11-12 23:05:10 +01:00
Tomasz Kulasek
6b6a94ee17 bonding: fix build with icc
ICC complains about enumerated types being mixed in link bonding driver,
as ETH_MQ_RX_RSS is an enum type of mq_mode and not a bitmask as it was
being treated.

Fixes: 734ce47f71 ("bonding: support RSS dynamic configuration")

Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
2015-11-12 00:22:26 +01:00
Raslsn Darawsheh
32b12e7567 bonding: fix freeing with no queue
In case of creating bond device without add any slaves and
quit from testpmd, application crashed since rx/tx queues
are NULL.

Add checking of this parameters before trying to free.

Signed-off-by: Raslsn Darawsheh <rdarawsheh@asaltech.com>
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-11-04 23:44:58 +01:00
Bernard Iremonger
71ba84b1cc bonding: remove fake pci interface
remove pci_dev, pci_drv, rte_bond_pmd and pci_id_table.
handle numa_node for vdevs
handle RTE_ETH_DEV_INTR_LSC for vdevs
rename the function valid_bonded_device to check_for_bonded_device
remove branches on pci_dev

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
2015-11-03 18:48:24 +01:00
Bernard Iremonger
8fb9e2bbf9 drivers: copy fake PCI device info to ethdev data
Initialise dev_flags, driver, kdrv, drv_name and numa_node fields
in eth_dev data.

for the following vdevs:
null
ring
pcap
af_packet
xenvirt
mpipe
bonding

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2015-11-03 18:39:42 +01:00
Tomasz Kulasek
55587b01cc bonding: support stats per queue
This patch adds fills bonding port's stats with a sum of corresponding
values taken from bonded slaves, when stats are requested for bonding port.

Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-11-01 18:10:55 +01:00
Tomasz Kulasek
734ce47f71 bonding: support RSS dynamic configuration
Bonding device implements independent management of RSS settings. It
stores its own copies of settings i.e. RETA, RSS hash function and RSS
key. It’s required to ensure consistency.

1) RSS hash function set for bonding device is maximal set of RSS hash
functions supported by all bonded devices. That mean, to have RSS support
for bonding, all slaves should be RSS-capable.

2) RSS key is propagated over the slaves "as is".

3) RETA for bonding is an internal table managed by bonding API, and is
used as a pattern to set up slaves. Its size is GCD of all RETA sizes, so
it can be easily used as a pattern providing expected behavior, even if
slaves RETA sizes are different.

Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-11-01 18:10:48 +01:00
Bernard Iremonger
c45c8bd9b9 bonding: fix device initialisation error handling
If the name parameter to rte_eth_bond_create() was NULL,
there was a segmentation fault because eth_dev was also NULL.
Add error handling of mac_addrs memory allocation.
Add call to rte_eth_dev_release_port() in error handling.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Tested-by: Marvin Liu <yong.liu@intel.com>
Acked-by: Michal Jastrzebski <michalx.k.jastrzebski@intel.com>
2015-08-10 02:05:42 +02:00
Sergey Balabanov
85cc012ddd bonding: fix socket id for LACP slave
On slave activation in LACP (8023AD) SOCKET_ANY_ID (which is -1)
is being casted to unsigned char and then to signed int.
The result is that socket_id has value of 255, not -1.
This results to memory allocation failure.

Fixes: 46fb436836 ("bond: add mode 4")

Signed-off-by: Sergey Balabanov <balabanovsv@ecotelecom.ru>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
2015-08-10 01:56:05 +02:00
Bernard Iremonger
d1d1e664c6 bonding: free queue memory when closing
Add function bond_ethdev_free_queues() and call from the
bond_ethdev_close() function.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
2015-07-27 19:20:44 +02:00
Bernard Iremonger
8d30fe7fa7 bonding: support port hotplug
This patch depends on the Port Hotplug Framework.
It implements the rte_dev_uninit_t() function for the link bonding pmd.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-07-27 19:20:44 +02:00
Stephen Hemminger
fa8cc60774 bonding: fix name and port validation
Cleanup the code in bonding that checks ports.
  * Use standard rte_eth_dev_is_valid_port
  * Change name of driver string to avoid variable namespace conflicts
  * Get rid of unnecessary string comparison stuff. A simple pointer
    check is enough here.
  * Get rid of unnecessary assignment of driver_name, it is already
    done by common code.
  * Don't generate unnecessary log messages on error.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-07-20 02:47:38 +02:00
Sergio Gonzalez Monroy
2f9d47013e mem: move librte_malloc to eal/common
Move malloc inside eal and create a new section in MAINTAINERS file for
Memory Allocation in EAL.

Create a dummy malloc library to avoid breaking applications that have
librte_malloc in their DT_NEEDED entries.

This is the first step towards using malloc to allocate memory directly
from memsegs. Thus, memzones would allocate memory through malloc,
allowing to free memzones.

Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
2015-07-16 13:44:48 +02:00
Stephen Hemminger
3379b158b2 bonding: initialize backpointer from pci device to driver
Add missing initialization of to pci_dev driver
The link from pci_dev back to the ethernet driver was not being set.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
2015-06-29 12:13:37 +02:00
Jan Blunck
af63759a53 bonding: fix crash when stopping inactive slave
When stopping the bond device we don't need to try and free up the LACPDU's
from deactivated devices since this is covered by
bond_mode_8023ad_deactivate_slave().

This fixes the following:
[    0.100569] PANIC in bond_ethdev_stop():
[    0.100589] line 1172        assert "port->rx_ring != NULL" failed

Signed-off-by: Jan Blunck <jblunck@infradead.org>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-06-29 00:33:50 +02:00
Tomasz Kulasek
414b202343 bonding: fix initial link status of slave
On Fortville NIC, link status change interrupt callback is not executed when
slave in bonding is (re-)started. It causes that slave's NIC is inactive even
if its link status is up on the start.

This patch invokes lsc callback, just after port's start, to check its initial
link status and manage properly.

Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
2015-06-29 00:30:55 +02:00
Cyril Chemparathy
7621d6a8d0 eal: add and use unaligned integer types
On machines that are strict on pointer alignment, current code breaks
on GCC's -Wcast-align checks on casts from narrower to wider types.
This patch introduces new unaligned_uint(16|32|64)_t types, which
correctly retain alignment in such cases.  Strict alignment
architectures will need to define CONFIG_RTE_ARCH_STRICT_ALIGN in
order to effect these new types.

Signed-off-by: Cyril Chemparathy <cchemparathy@ezchip.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
2015-06-24 12:00:41 +02:00
Stephen Hemminger
e46e3ba5f0 bonding: remove useless memset
Remove 2 unneeded memset's.  The info area is already cleared rte_eth_dev_info_get
and the statistics buffer is cleared by rte_eth_stats_get

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2015-06-04 10:46:45 +02:00
Bruce Richardson
3eb6bdd89e bond: move to drivers/net/
Move bonded ethdev pmd to drivers/net

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
2015-05-22 15:51:38 +02:00