dpdk.git
7 years agonet/tap: support segmented mbufs
Pascal Mazon [Thu, 16 Mar 2017 08:59:21 +0000 (09:59 +0100)]
net/tap: support segmented mbufs

Support for segmented packets (scatter/gather) is mandatory for most
purposes, regardless of the MTU size. Tx packets are often the result of
mbuf concatenation, and an mbuf is not necessarily large enough for Rx
packets to fit in a single one.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/tap: do not send packets larger than MTU
Pascal Mazon [Wed, 15 Mar 2017 15:09:08 +0000 (16:09 +0100)]
net/tap: do not send packets larger than MTU

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/thunderx: sync mailbox definitions with Linux PF driver
Jerin Jacob [Mon, 20 Mar 2017 14:10:40 +0000 (19:40 +0530)]
net/thunderx: sync mailbox definitions with Linux PF driver

- bgx_link_status mbox definition was changed in Linux
commit 1cc702591bae ("net: thunderx: Add ethtool support")
- NIC_MBOX_MSG_RES_BIT related changes were never part of Linux PF driver

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
7 years agonet/tap: add basic flow API patterns and actions
Pascal Mazon [Thu, 23 Mar 2017 08:33:57 +0000 (09:33 +0100)]
net/tap: add basic flow API patterns and actions

Supported flow rules are now mapped to TC rules on the tap netdevice.
The netlink message used for creating the TC rule is stored in struct
rte_flow. That way, by simply changing a metadata in it, we can require
for the rule deletion without further parsing.

Supported items:
- eth: src and dst (with variable masks), and eth_type (0xffff mask).
- vlan: vid, pcp, tpid, but not eid.
- ipv4/6: src and dst (with variable masks), and ip_proto (0xffff mask).
- udp/tcp: src and dst port (0xffff) mask.

Supported actions:
- DROP
- QUEUE
- PASSTHRU

It is generally not possible to provide a "last" item. However, if the
"last" item, once masked, is identical to the masked spec, then it is
supported.

Only IPv4/6 and MAC addresses can use a variable mask. All other
items need a full mask (exact match).

Support for VLAN requires kernel headers >= 4.9, checked using
auto-config.sh.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Olga Shern <olgas@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/tap: add netlink back-end for flow API
Pascal Mazon [Thu, 23 Mar 2017 08:33:56 +0000 (09:33 +0100)]
net/tap: add netlink back-end for flow API

Each kernel netdevice may have queueing disciplines set for it, which
determine how to handle the packet (mostly on egress). That's part of
the TC (Traffic Control) mechanism.

Through TC, it is possible to set filter rules that match specific
packets, and act according to what is in the rule. This is a perfect
candidate to implement the flow API for the tap PMD, as it has an
associated kernel netdevice automatically.

Each flow API rule will be translated into its TC counterpart.

To leverage TC, it is necessary to communicate with the kernel using
netlink. This patch introduces a library to help that communication.

Inside netlink.c, functions are generic for any netlink messaging.
Inside tcmsgs.c, functions are specific to deal with TC rules.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Olga Shern <olgas@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/tap: add preliminary support for flow API
Pascal Mazon [Thu, 23 Mar 2017 08:33:55 +0000 (09:33 +0100)]
net/tap: add preliminary support for flow API

The flow API provides the ability to classify packets received by a tap
netdevice.

This patch only implements skeleton functions for flow API support, no
patterns are supported yet.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Olga Shern <olgas@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/tap: move private elements to external header
Pascal Mazon [Thu, 23 Mar 2017 08:33:54 +0000 (09:33 +0100)]
net/tap: move private elements to external header

In the next patch, access to struct pmd_internals will be necessary in
tap_flow.c to store the flows.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Olga Shern <olgas@mellanox.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/mlx5: fix reusing Rx/Tx queues
Yongseok Koh [Tue, 21 Mar 2017 17:50:51 +0000 (10:50 -0700)]
net/mlx5: fix reusing Rx/Tx queues

When configuring Rx/Tx queue, if queue already exists, it is reused. But if
the queue size is changed, it must be resized to not access/overwrite
invalid memory.

Fixes: 2e22920b85d9 ("mlx5: support non-scattered Tx and Rx")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
7 years agonet/i40e: fix VLAN filter
Wenzhuo Lu [Wed, 22 Mar 2017 08:39:07 +0000 (16:39 +0800)]
net/i40e: fix VLAN filter

VLAN filter is not working on i40e because driver need to
disable the VLAN promiscuous mode and set the VLAN filter
table.

Fixes: 5f2b0e3f7656 ("net/i40e: set VF VLAN filter from PF")
Cc: stable@dpdk.org
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
7 years agonet/i40e/base: new AQ commands for cloud filter
Jingjing Wu [Wed, 22 Mar 2017 09:24:59 +0000 (17:24 +0800)]
net/i40e/base: new AQ commands for cloud filter

Add new admin queue function and extended fields for cloud filter:
 - Add admin queue function for Replace filter command (Opcode: 0x025F)
 - Define big buffer for extended general fields in Add/Remove
   Cloud filters command

Signed-off-by: Laura Stroe <laura.stroe@intel.com>
Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: add VF offload flags
Jingjing Wu [Wed, 22 Mar 2017 09:24:58 +0000 (17:24 +0800)]
net/i40e/base: add VF offload flags

This patch adds:
 - ENCAP offload negotiation flag. Use the existing ENCAP_CSUM offload
   flag to negotiate GSO_UDP_TUNNEL_CSUM capability and create new ENCAP
   flag for negotiating offloads for encapsulated packets
 - RX_ENCAP_CSUM offload negotiation flag for VF to negotiate RX
   checksum capability for tunnelled packet types.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: reduce wait time for adminq command
Jingjing Wu [Wed, 22 Mar 2017 09:24:57 +0000 (17:24 +0800)]
net/i40e/base: reduce wait time for adminq command

When sending an adminq command, we wait for the command to complete in
a loop. This loop waits for an entire millisecond, when in practice the
adminq command is processed often much faster.

Change the loop to use i40e_usec_delay instead, and wait for 50 usecs
each time instead. This appears to be about the minimum time required,
based on some manual observation and testing.

The primary benefit of this change is reducing latency of various
operations in the PF driver, especially when related to having a large
number of VFs enabled.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: new AQ commands for PPP
Jingjing Wu [Wed, 22 Mar 2017 09:24:56 +0000 (17:24 +0800)]
net/i40e/base: new AQ commands for PPP

Add admin queue functions for Pipeline Personalization Profile AQ
commands:
 - Write Recipe Command buffer (Opcode: 0x0270)
 - Get Applied Profiles list (Opcode: 0x0271)

Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: fix potential out of bound array access
Jingjing Wu [Wed, 22 Mar 2017 09:24:55 +0000 (17:24 +0800)]
net/i40e/base: fix potential out of bound array access

This is fix for klocwork issue where dcbcfg->numapps could
be greater than size of array (i.e dcbcfg->app[I40E_DCBX_MAX_APPS]).
The fix makes sure the array is not accessed past size of array
(i.e. I40E_DCBX_MAX_APPS).

Fixes: 166dceeeeafc ("i40e/base: add parsing for CEE DCBX TLVs")
Cc: stable@dpdk.org
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: control register read/write on X722
Jingjing Wu [Wed, 22 Mar 2017 09:24:54 +0000 (17:24 +0800)]
net/i40e/base: control register read/write on X722

The X722 doesn't support the AQ command to read/write the control
register so enable it to bypass the check and use the direct read/write
method.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/i40e/base: define bit for HW ATR evict control
Jingjing Wu [Wed, 22 Mar 2017 09:24:53 +0000 (17:24 +0800)]
net/i40e/base: define bit for HW ATR evict control

On X722, we can control whether or not the hardware performs ATR
eviction. Define the correct bit so we can twiddle it.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
7 years agonet/bonding: reduce slave starvation on Rx poll
Keith Wiles [Tue, 21 Mar 2017 15:12:12 +0000 (10:12 -0500)]
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>
7 years agonet/nfp: fix Rx interrupt
Alejandro Lucero [Tue, 21 Mar 2017 10:43:21 +0000 (10:43 +0000)]
net/nfp: fix Rx interrupt

Current code enables RX interrupts even if this it not
requested.

Fixes: ea121b28316d ("net/nfp: add Rx interrupts")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
7 years agonet/nfp: fix packet/data length conversion
Alejandro Lucero [Tue, 21 Mar 2017 10:43:20 +0000 (10:43 +0000)]
net/nfp: fix packet/data length conversion

Chained mbufs hold data_len as the length of that particular mbuf
and pkt_len as the full packet length including all the chained
mbufs. It is not clear from the mbuf definition if pkt_len should
be set for all the mbufs in a chain, but code there for handling
mbufs suggests just the first mbuf requires to have pkt_len set.

NFP PMD was assuming pkt_len is set in all the chained mbufs and
unit tests for gather dma were building mbufs with pkt_len always
set. This patch gets rid of that assumption.

Fixes: b812daadad0d ("nfp: add Rx and Tx")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
7 years agonet/nfp: clean Tx descriptor flags
Alejandro Lucero [Tue, 21 Mar 2017 10:43:19 +0000 (10:43 +0000)]
net/nfp: clean Tx descriptor flags

When LSO, not doing this can led to firmware disruption. It does
not show as error because TCP ends up sending data again later on.

Fixes: 9ba3d0ae2090 ("net/nfp: add TSO support")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
7 years agonet/qede/base: fix to use NULL pointer
Rasesh Mody [Sat, 18 Mar 2017 06:57:50 +0000 (23:57 -0700)]
net/qede/base: fix to use NULL pointer

Use OSAL NULL where appropriate

Fixes: 22d07d939c3c ("net/qede/base: update")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix resource lock minimum value
Rasesh Mody [Sat, 18 Mar 2017 06:57:49 +0000 (23:57 -0700)]
net/qede/base: fix resource lock minimum value

Fixes: ababb5203de2 ("net/qede/base: semantic/formatting changes")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix sriov typo
Rasesh Mody [Sat, 18 Mar 2017 06:53:34 +0000 (23:53 -0700)]
net/qede/base: fix sriov typo

Typo in ecore_sriov.c; Ending line with , instead of ;

Fixes: 379cbb2c446a ("net/qede/base: semantic change")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: refactor return path
Rasesh Mody [Sat, 18 Mar 2017 06:53:33 +0000 (23:53 -0700)]
net/qede/base: refactor return path

No need to return - base on return at end of function.

Fixes: 22d07d939c3c ("net/qede/base: update")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix typo
Rasesh Mody [Sat, 18 Mar 2017 06:53:32 +0000 (23:53 -0700)]
net/qede/base: fix typo

Fixes: 22d07d939c3c ("net/qede/base: update")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix first VF index calculation
Rasesh Mody [Sat, 18 Mar 2017 06:53:31 +0000 (23:53 -0700)]
net/qede/base: fix first VF index calculation

When a server doesn't support ARI, VF offsets begin at a much higher
number. As a result, ecore miscalculates the first_vf_in_pf and
initialization fails since base driver incorrectly learns there are
no SBs for its VF [as its VFs are out of range].

Fixes: 22d07d939c3c ("net/qede/base: update")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix remove the unneeded conversion to LE
Rasesh Mody [Sat, 18 Mar 2017 06:53:30 +0000 (23:53 -0700)]
net/qede/base: fix remove the unneeded conversion to LE

Remove the unneeded conversion to LE when writing to the 32-bit
XSDM_REG_OPERATION_GEN register

Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix to remove redundant memset
Rasesh Mody [Sat, 18 Mar 2017 06:53:29 +0000 (23:53 -0700)]
net/qede/base: fix to remove redundant memset

Fixes: 22d07d939c3c ("net/qede/base: update")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix out-of-bound memory access
Rasesh Mody [Sat, 18 Mar 2017 06:53:28 +0000 (23:53 -0700)]
net/qede/base: fix out-of-bound memory access

Fix out-of-bound memory access on Management FW interaction for
resource allocation

Fixes: 252b88b58f70 ("net/qede/base: add selftest and query sensor info")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix DORQ attention mask
Rasesh Mody [Sat, 18 Mar 2017 06:53:27 +0000 (23:53 -0700)]
net/qede/base: fix DORQ attention mask

Fix Doorbell Queue(DORQ) attention mask

Fixes: e6051bd6b07d ("qede: add interrupt handling support")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix printout
Rasesh Mody [Sat, 18 Mar 2017 06:53:26 +0000 (23:53 -0700)]
net/qede/base: fix printout

Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: add attention bits for AH chip
Rasesh Mody [Sat, 18 Mar 2017 06:53:25 +0000 (23:53 -0700)]
net/qede/base: add attention bits for AH chip

add attention bits for CHIP_NUM_AH_xxx

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix to prevent VF promisc config
Rasesh Mody [Sat, 18 Mar 2017 06:50:23 +0000 (23:50 -0700)]
net/qede/base: fix to prevent VF promisc config

VFs are seeing the number of MACs available to them as '0',
and as a result configure themselves as PROMISC. This fix is to
prevent that.

Fixes: 86a2265e59d7 ("qede: add SRIOV support")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix index printing of multi-bit attentions
Rasesh Mody [Sat, 18 Mar 2017 06:50:22 +0000 (23:50 -0700)]
net/qede/base: fix index printing of multi-bit attentions

Fix the logic for identifying which bit amongst the Multi-bit
attention sources is set.

Fixes: e6051bd6b07d ("qede: add interrupt handling support")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix numbering L2 VF queues
Rasesh Mody [Sat, 18 Mar 2017 06:50:21 +0000 (23:50 -0700)]
net/qede/base: fix numbering L2 VF queues

There are some constellations where Due to lack of resource allocation
in MFW, There would be an insufficient number of L2 queues for all the
VFs.

This introduces a new feature ECORE_VF_L2_QUE which correctly numbers
the number of VF queues. Notice it might be larger than the actual
number of VFs in configuration space, in which case its the ecore
client responsibility not to try activating that many.

As part of the fix, also correct the nubmering of the VF queues. As
their numbering is dependent on the SBs of the PF, which might only be
partially used by L2 [as half would be assigned for RDMA which doesn't
require L2 queues], we make the numbering consecutive with that of the
L2 queues only.

Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix VF init after malicious VF FLR
Rasesh Mody [Sat, 18 Mar 2017 06:50:20 +0000 (23:50 -0700)]
net/qede/base: fix VF init after malicious VF FLR

Fix VF init after malicious VF FLR.

Fixes: 40c926ba2626 ("net/qede/base: support to initiate PF FLR")
Fixes: 86a2265e59d7 ("qede: add SRIOV support")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix printout
Rasesh Mody [Sat, 18 Mar 2017 06:50:19 +0000 (23:50 -0700)]
net/qede/base: fix printout

Prints in ecore_get_dev_info showed only chip revision,
and did that as number instead of letter.
I.e.,  BB A0 --> BB0, BB B0 --> BB1, AH A0 --> AH0, AH A1 --> AH0.

Correct the printing scheme into
{AH, BB} {A, B}{0, 1}

Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix TM block ILT initialization
Rasesh Mody [Sat, 18 Mar 2017 06:50:18 +0000 (23:50 -0700)]
net/qede/base: fix TM block ILT initialization

Fix Timer(TM) block Internal Lookup Table(or ILT for logical to
physical address translation) initialization for SRIOV's coexistence
with other protocols.

Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix forcing driver default resc allocation
Rasesh Mody [Sat, 18 Mar 2017 06:50:17 +0000 (23:50 -0700)]
net/qede/base: fix forcing driver default resc allocation

Remove the forcing of the driver's default resource allocation.

Fixes: 77f7222124de ("net/qede: add PCI ids for new chip variant")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix to set pointers to NULL after freeing
Rasesh Mody [Sat, 18 Mar 2017 06:50:16 +0000 (23:50 -0700)]
net/qede/base: fix to set pointers to NULL after freeing

Set pointers to NULL after freeing the allocations. Change OSAL_FREE
macro to take care of this and cleanup relevant code.

Fixes: 26ae839d06e9 ("qede: add DCBX support")
Fixes: ec94dbc57362 ("qede: add base driver")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/qede/base: fix incorrect typecasting of flag
Rasesh Mody [Sat, 18 Mar 2017 06:48:36 +0000 (23:48 -0700)]
net/qede/base: fix incorrect typecasting of flag

dcbx-update-flag is incorrectly converted to boolean before assigining
it to ramrod data, fix this typecasting. Also, added more debug
messages in the dcbx code paths.

Fixes: 26ae839d06e9 ("qede: add DCBX support")

Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
7 years agonet/sfc: implement simple EF10 native Tx datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:19 +0000 (10:15 +0000)]
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>
7 years agonet/sfc: make multi-segment support a Tx datapath feature
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:18 +0000 (10:15 +0000)]
net/sfc: make multi-segment support a Tx datapath feature

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: implement EF10 native Tx datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:17 +0000 (10:15 +0000)]
net/sfc: implement EF10 native Tx datapath

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: David Riddoch <driddoch@solarflare.com>
7 years agonet/sfc: make TSO a datapath-dependent feature
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:16 +0000 (10:15 +0000)]
net/sfc: make TSO a datapath-dependent feature

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: make VLAN insertion a datapath-dependent feature
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:15 +0000 (10:15 +0000)]
net/sfc: make VLAN insertion a datapath-dependent feature

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: factor out libefx-based Tx datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:14 +0000 (10:15 +0000)]
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>
7 years agonet/sfc: implement EF10 native Rx datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:13 +0000 (10:15 +0000)]
net/sfc: implement EF10 native Rx datapath

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: David Riddoch <driddoch@solarflare.com>
7 years agonet/sfc: remove few conditions in Rx queue refill
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:12 +0000 (10:15 +0000)]
net/sfc: remove few conditions in Rx queue refill

If Rx refill threshold guarantees that refill happens for one or
more bulks, less checks may be done on refill.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: make Rx scatter a datapath-dependent feature
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:11 +0000 (10:15 +0000)]
net/sfc: make Rx scatter a datapath-dependent feature

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: factor out libefx-based Rx datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:10 +0000 (10:15 +0000)]
net/sfc: factor out libefx-based Rx datapath

Split control and datapath to make datapath substitutable and
possibly reusable with alternative control path.

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

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: do not use Rx queue control state on datapath
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:09 +0000 (10:15 +0000)]
net/sfc: do not use Rx queue control state on datapath

Rx queue flags should keep the information required on datapath.

It is a preparation to split control and data paths.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: emphasis that RSS hash flag is an Rx queue flag
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:08 +0000 (10:15 +0000)]
net/sfc: emphasis that RSS hash flag is an Rx queue flag

Style fix to establish namespace for Rx queue flag defines.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: use different callbacks for event queues
Andrew Rybchenko [Mon, 20 Mar 2017 10:15:07 +0000 (10:15 +0000)]
net/sfc: use different callbacks for event queues

Use different sets of libefx EvQ callbacks for management,
transmit and receive event queue. It makes event handling
more robust against unexpected events.

Also it is required for alternative datapath support.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/mlx4: support basic flow items and actions
Vasily Philipov [Sun, 5 Mar 2017 07:51:32 +0000 (09:51 +0200)]
net/mlx4: support basic flow items and actions

Adding support for the next items: eth, vlan, ipv4, udp, tcp and for the
next actions: queue, drop

Signed-off-by: Vasily Philipov <vasilyf@mellanox.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
7 years agonet/mlx4: split the definitions to the header file
Vasily Philipov [Sun, 5 Mar 2017 07:51:31 +0000 (09:51 +0200)]
net/mlx4: split the definitions to the header file

Make priv_lock/priv_unlock functions and some other structs/defines visible
from different source files by placing them into mlx4.h header.

Signed-off-by: Vasily Philipov <vasilyf@mellanox.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
7 years agonet/mlx4: update link status upon probing with LSC
Gaetan Rivet [Fri, 3 Mar 2017 15:39:56 +0000 (16:39 +0100)]
net/mlx4: update link status upon probing with LSC

If LSC interrupts are enabled, the application expects the link_update
ops to be executed by the PMD itself.

No link status change event is received upon probing, therefore the link
status update must be forced.

Fixes: c4da6caa426d ("mlx4: handle link status interrupts")
Cc: stable@dpdk.org
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
7 years agoconfig: enable thunderx nicvf
Jerin Jacob [Sun, 19 Mar 2017 14:48:48 +0000 (20:18 +0530)]
config: enable thunderx nicvf

Enable Thunderx nicvf PMD driver in the common
config as it does not have build dependency
with any external library and/or architecture.

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
7 years agonet/thunderx: fix build on FreeBSD
Jerin Jacob [Sun, 19 Mar 2017 14:48:47 +0000 (20:18 +0530)]
net/thunderx: fix build on FreeBSD

SIMPLEQ_* operations are not available in FreeBSD. Replacing
with equivalent STAILQ_* operations.

Fixes: f2546f8e51b8 ("net/thunderx/base: add functions to store qsets")

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
7 years agonet/thunderx: fix 32-bit build
Jerin Jacob [Sun, 19 Mar 2017 14:48:46 +0000 (20:18 +0530)]
net/thunderx: fix 32-bit build

Fixes: e438796617dc ("net/thunderx: add PMD skeleton")

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
7 years agonet/sfc: add missing BSD license line and update year
Andrew Rybchenko [Thu, 16 Mar 2017 12:41:08 +0000 (12:41 +0000)]
net/sfc: add missing BSD license line and update year

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/mlx5: add enhanced multi-packet send for ConnectX-5
Yongseok Koh [Wed, 15 Mar 2017 23:55:44 +0000 (16:55 -0700)]
net/mlx5: add enhanced multi-packet send for ConnectX-5

ConnectX-5 supports enhanced version of multi-packet send (MPS). An MPS Tx
descriptor can carry multiple packets either by including pointers of
packets or by inlining packets. Inlining packet data can be helpful to
better utilize PCIe bandwidth. In addition, Enhanced MPS supports hybrid
mode - mixing inlined packets and pointers in a descriptor. This feature is
enabled by default if supported by HW.

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
7 years agonet/mlx5: limit flow API rules to one tunnel
Nélio Laranjeiro [Wed, 15 Mar 2017 12:32:50 +0000 (13:32 +0100)]
net/mlx5: limit flow API rules to one tunnel

Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
7 years agonet/sfc: add callback to retrieve FW version
Ivan Malov [Thu, 16 Mar 2017 11:01:35 +0000 (11:01 +0000)]
net/sfc: add callback to retrieve FW version

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc/base: add advanced function to extract FW version
Ivan Malov [Thu, 16 Mar 2017 11:01:34 +0000 (11:01 +0000)]
net/sfc/base: add advanced function to extract FW version

Some libefx-based drivers might need this functionality to
indicate DPCPU FW IDs as part of FW version info to assist
experienced users.

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
7 years agonet/i40e: fix broadcast promiscuous mode setting
Wenzhuo Lu [Thu, 16 Mar 2017 03:09:45 +0000 (11:09 +0800)]
net/i40e: fix broadcast promiscuous mode setting

When setting up the VSIs, MAC filter is used for
receiving MAC broadcast packets.
We should follow it to implement the broadcast
promiscuous mode setting.

Fixes: 61fff9b4c68b ("net/i40e: set VF broadcast mode from PF")
Cc: stable@dpdk.org
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
7 years agonet/vmxnet3: fix queue size changes
Chas Williams [Wed, 15 Mar 2017 12:35:10 +0000 (08:35 -0400)]
net/vmxnet3: fix queue size changes

If the user reconfigures the queue size, then the previously allocated
memzone may potentially be too small.  Release the memzone when a queue
is released and allocate a new one each time a queue is setup.

While here convert to rte_eth_dma_zone_reserve() which does basically
the same things as the private function.

Fixes: dfaff37fc46d ("vmxnet3: import new vmxnet3 poll mode driver implementation")
Cc: stable@dpdk.org
Signed-off-by: Chas Williams <ciwillia@brocade.com>
Acked-by: Jan Blunck <jblunck@infradead.org>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
7 years agonet/tap: add flow control management
Pascal Mazon [Wed, 15 Mar 2017 14:48:19 +0000 (15:48 +0100)]
net/tap: add flow control management

A tap netdevice does not support flow control; ensure nothing but
RTE_FC_NONE mode can be set.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: add packet type management
Pascal Mazon [Wed, 15 Mar 2017 14:48:18 +0000 (15:48 +0100)]
net/tap: add packet type management

Advertise packet types supported by the librte_net.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: add multicast addresses management
Pascal Mazon [Wed, 15 Mar 2017 14:48:17 +0000 (15:48 +0100)]
net/tap: add multicast addresses management

A tap netdevice actually receives every packet, without any filtering
whatsoever. There is no need for any multicast address registration
to receive multicast packets.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: add speed capabilities
Pascal Mazon [Wed, 15 Mar 2017 14:48:16 +0000 (15:48 +0100)]
net/tap: add speed capabilities

Tap PMD is flexible, it supports any speed.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: add MTU management
Pascal Mazon [Wed, 15 Mar 2017 14:48:15 +0000 (15:48 +0100)]
net/tap: add MTU management

The MTU is assigned to the tap netdevice according to the argument, but
packet transmission and reception just write/read on an fd with the
default limit being the socket buffer size.

As a new rte_eth_dev_data is allocated during tap device init, ensure it
is set again dev->data->mtu.
Once the actual netdevice is created via tun_alloc(), make sure to apply
the desired MTU to the netdevice.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: add MAC address management
Pascal Mazon [Wed, 15 Mar 2017 14:48:14 +0000 (15:48 +0100)]
net/tap: add MAC address management

As soon as the netdevice is created, update pmd->mac_addr with its
actual MAC address.

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: refactor ioctl calls
Pascal Mazon [Wed, 15 Mar 2017 14:48:13 +0000 (15:48 +0100)]
net/tap: refactor ioctl calls

Create a socket for ioctl at tap device creation instead of opening it
and closing it every call to tap_link_set_flags().

Use a common tap_ioctl() function that can be extended for various uses
(such as MTU change, MAC address change, ...).

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/tap: remove NO-ARP setting
Pascal Mazon [Wed, 15 Mar 2017 14:48:12 +0000 (15:48 +0100)]
net/tap: remove NO-ARP setting

There is no reason not to support ARP on a tap netdevice. Remove
IFF_NOARP flags.
Focus on IFF_UP when a link status change is required.

Fixes: f457b472b1f2 ("net/tap: add link up and down operations")

Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/sfc: add VFs to the table of PCI IDs for supported NICs
Ivan Malov [Thu, 9 Mar 2017 17:23:03 +0000 (17:23 +0000)]
net/sfc: add VFs to the table of PCI IDs for supported NICs

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support MCDI proxy
Ivan Malov [Thu, 9 Mar 2017 17:23:02 +0000 (17:23 +0000)]
net/sfc: support MCDI proxy

The patch is to add support for MCDI proxy which comes in
useful, particularly, while running over VF: few commands
will normally fail with EPERM, but in some cases the host
driver (i.e. running over the corresponding PF, typically,
within a hypervisor) may set itself as a proxy to conduct
authorization for the commands coming from VFs; these are
forwarded to the corresponding access control application
which may decline or approve authorization by replying to
the requests; all in all, the guest driver has to process
the replies forwarded back by the firmware MC in order to
give up gracefully (by setting return code which could be
understood by 'libefx') or re-issue the original commands

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
7 years agonet/sfc: avoid failure on port start if Rx mode is rejected
Ivan Malov [Thu, 9 Mar 2017 17:23:01 +0000 (17:23 +0000)]
net/sfc: avoid failure on port start if Rx mode is rejected

If Rx mode is unacceptable, in particular, when promiscuous
or all-multicast filters are not allowed while running over
PCI function which is not a member of appropriate privilege
groups, the driver has to cope with the failures gracefully

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: poll MAC stats if periodic DMA is not supported
Ivan Malov [Thu, 9 Mar 2017 17:23:00 +0000 (17:23 +0000)]
net/sfc: poll MAC stats if periodic DMA is not supported

If periodic DMA statistics feature is absent (particularly,
while running over VF), the PMD must provide an ability to
cope with it using explicit update requests which are kept
restrained according to 'stats_update_period_ms' parameter

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
7 years agonet/sfc: add kvarg control for MAC statistics update period
Ivan Malov [Thu, 9 Mar 2017 17:22:59 +0000 (17:22 +0000)]
net/sfc: add kvarg control for MAC statistics update period

The patch is to make MAC statistics update interval tunable
by means of 'stats_update_period_ms' kvarg parameter making
it possible to use values different from 1000 ms in case of
SFN8xxx boards provided that firmware version is 6.2.1.1033

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc/base: do not ignore MAC stats update period
Andrew Rybchenko [Thu, 9 Mar 2017 17:22:58 +0000 (17:22 +0000)]
net/sfc/base: do not ignore MAC stats update period

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/ena: fix return of hash control flushing
Yong Wang [Tue, 14 Feb 2017 12:37:43 +0000 (07:37 -0500)]
net/ena: fix return of hash control flushing

In function ena_com_set_hash_ctrl(), the return value is assigned to
"ret" variable, but it is not returned. Fix it by adding the return.

Fixes: 99ecfbf845b3 ("ena: import communication layer")
Cc: stable@dpdk.org
Signed-off-by: Yong Wang <wang.yong19@zte.com.cn>
Acked-by: Jan Medala <jan@semihalf.com>
7 years agonet/ena: remove redundant variable
Yong Wang [Tue, 14 Feb 2017 12:37:42 +0000 (07:37 -0500)]
net/ena: remove redundant variable

Signed-off-by: Yong Wang <wang.yong19@zte.com.cn>
Acked-by: Jan Medala <jan@semihalf.com>
7 years agonet/pcap: fix using mbuf after freeing it
Johan Samuelsson [Mon, 13 Mar 2017 09:21:25 +0000 (10:21 +0100)]
net/pcap: fix using mbuf after freeing it

Fixes: 2269e7e815a2 ("pcap: add Rx and Tx byte counters")
Cc: stable@dpdk.org
Signed-off-by: Johan Samuelsson <johan.xb.samuelsson@ericsson.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
7 years agonet/i40e: fix error log in descriptor done function
Olivier Matz [Wed, 1 Mar 2017 14:45:29 +0000 (15:45 +0100)]
net/i40e: fix error log in descriptor done function

It's not queue identifier but a descriptor identifier.

Fixes: 4861cde46116 ("i40e: new poll mode driver")

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
7 years agonet/mlx5: support user space Rx interrupt event
Shahaf Shuler [Tue, 14 Mar 2017 13:03:09 +0000 (15:03 +0200)]
net/mlx5: support user space Rx interrupt event

Implement rxq interrupt callbacks

Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
7 years agoeal/linux: support external Rx interrupt
Shahaf Shuler [Tue, 14 Mar 2017 13:03:08 +0000 (15:03 +0200)]
eal/linux: support external Rx interrupt

Prior to this patch only UIO/VFIO interrupt handlers types were supported.
This patch adds support for the external interrupt handler type, allowing
external drivers to set their own fds with specific interrupt handlers.

Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
7 years agonet/tap: add Rx trigger
Adrien Mazarguil [Tue, 14 Mar 2017 12:51:58 +0000 (13:51 +0100)]
net/tap: add Rx trigger

This commit adds a signal-based trigger to the Rx burst function in order
to avoid unnecessary system calls while Rx queues are empty.

Triggered Rx bursts put less pressure on the kernel, free up CPU resources
for applications and result in a noticeable performance improvement when
sharing CPU threads with other PMDs.

Measuring the traffic forwarding rate between two physical devices in
testpmd (IO mode, single thread, 64B packets) before and after adding two
tap PMD instances (4 ports total) that do not process any traffic and
comparing results yields:

Without Rx trigger:

 -15% (--burst=32)
 -62% (--burst=1)

With Rx trigger:

 -0.3% (--burst=32)
 -6% (--burst=1)

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/tap: remove redundant syscall on Tx
Adrien Mazarguil [Tue, 14 Mar 2017 12:51:57 +0000 (13:51 +0100)]
net/tap: remove redundant syscall on Tx

Polling the Tx queue file descriptor before writing to it is not mandatory
since it is configured as non-blocking.

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
7 years agonet/thunderx: check data offset alignment requirement
Jerin Jacob [Mon, 13 Mar 2017 08:02:11 +0000 (13:32 +0530)]
net/thunderx: check data offset alignment requirement

nicvf HW expects the DMA address of the packet data to be
aligned with cache line size.

Packet data offset is a function of struct mbuf size,
mbuf private size and headroom. mbuf private size can
be changed from the application in pool creation, this
check detects HW alignment requirement constraint in pmd
start function.

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
7 years agonet/e1000: advertise offload capabilities for the EM PMD
Allain Legacy [Fri, 10 Mar 2017 14:38:21 +0000 (09:38 -0500)]
net/e1000: advertise offload capabilities for the EM PMD

The hardware offload capabilities are not being advertised for the EM PMD.
Because of this, applications that only enable these features if the device
advertises them will never do so.

Normally this is not an issue since normal packet processing should work
even if hardware offload is not available.  But, in older versions of
Virtual Box the e1000 device emulation (Intel PRO/1000 MT Desktop 82540EM)
assumes that it should enable VLAN stripping even if the driver does not
request it.  This means that any ingress packets that have a VLAN tag will
be stripped.  Since the application did not request to enable VLAN
stripping it is not expecting these packets so they are not processed as
VLAN packets.

Regardless of the Virtual Box issue, the driver should be advertising
supported capabilities as is done in other drivers.

Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
7 years agonet/sfc: set multicast address list in started state only
Ivan Malov [Thu, 9 Mar 2017 16:21:30 +0000 (16:21 +0000)]
net/sfc: set multicast address list in started state only

According to 'libefx' API requirements, one is allowed to
apply multicast address list to the port in started state
only, otherwise the new array should be copied to a local
storage in order to be applied during the next port start

Coverity issue: 141296
Fixes: 0fa0070e4391 ("net/sfc: support multicast addresses list controls")

Fixes: e9ddf37a507d ("net/sfc: fix setting empty multicast list")
Cc: stable@dpdk.org
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
7 years agonet/sfc: add unknown unicast/multicast match in flow API
Roman Zhukov [Thu, 9 Mar 2017 15:26:33 +0000 (15:26 +0000)]
net/sfc: add unknown unicast/multicast match in flow API

Support individual/group destination address match (unknown unicast
and all-multicast correspondingly in terms of firmware).

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support UDP in flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:32 +0000 (15:26 +0000)]
net/sfc: support UDP in flow API filters

Exact match of source and destination ports is supported by parser.
IP protocol match is enforced to UDP.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support TCP in flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:31 +0000 (15:26 +0000)]
net/sfc: support TCP in flow API filters

Exact match of source and destination ports is supported by parser.
IP protocol match is enforced to TCP.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support IPV6 in flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:30 +0000 (15:26 +0000)]
net/sfc: support IPV6 in flow API filters

Exact match of IP protocol, source and destination
addresses is supported by parser.
EtherType match is enforced to IPv6 EtherType.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support IPV4 in flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:29 +0000 (15:26 +0000)]
net/sfc: support IPV4 in flow API filters

Exact match of IP protocol, source and destination
addresses is supported by parser.
EtherType match is enforced to IPv4 EtherType.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support VLAN in flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:28 +0000 (15:26 +0000)]
net/sfc: support VLAN in flow API filters

Exact match of VLAN ID bits is supported only and required in VLAN item.
Mask to match VLAN ID bits only is required, default mask to match entire
TCI is not supported.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
7 years agonet/sfc: support flow API filters
Roman Zhukov [Thu, 9 Mar 2017 15:26:27 +0000 (15:26 +0000)]
net/sfc: support flow API filters

Only pattern items VOID, ETH and actions VOID, QUEUE is now
supported.

Signed-off-by: Roman Zhukov <roman.zhukov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
7 years agonet/sfc: provide a way to check if filter is supported
Andrew Rybchenko [Thu, 9 Mar 2017 15:26:26 +0000 (15:26 +0000)]
net/sfc: provide a way to check if filter is supported

The information is obtained from firmware on attach. It may
change after MC reboot (firmware version or variant change).
Cache should be refreshed after MC reboot when it is handled
properly (not yet).

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>