This patch adds two sample configuration files to ipsec-secgw sample
application. The sample configuration files show how to setup
back-to-back systems that would forward traffic through an IPsec
tunnel.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Fan Zhang [Wed, 21 Sep 2016 12:05:18 +0000 (13:05 +0100)]
examples/ipsec-secgw: support configuration file
This patch adds the configuration file support to ipsec_secgw
sample application. Instead of hard-coded rules, the users can
specify their own SP, SA, and routing rules in the configuration
file. A command line option "-f" is added to pass the
configuration file location to the application.
Cleanup of unused code.
Rename and simplify a badly named struct element, was aes, but
used for all types of ciphers.
Print correct error msg (Unsupported rather than Undefined)
for all ciphers not supported by QAT PMD.
Pablo de Lara [Wed, 21 Sep 2016 01:45:18 +0000 (02:45 +0100)]
crypto: rename some SNOW 3G references
SNOW 3G algorithm has all uppercase letters in its name
and a space between SNOW and 3G, but some references of it
had some lowercase letters or no space.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Deepak Kumar Jain <deepak.k.jain@intel.com>
In file rte_crypto_sym.h, GMAC API comments need to be changed
to comply with the GMAC specification. Main areas of change are
aad pointer and aad len, which now will be used to
provide plaintext.
Added Galois Message Authentication Code (GMAC) capability to
QuickAssist Technology symmetric cryptographic driver.
GMAC is authentication only variant of Galois Counter Mode (GCM)
where all plaintext is provided with AAD pointer only.
John Griffin [Thu, 4 Aug 2016 15:46:23 +0000 (16:46 +0100)]
crypto/qat: make the session struct variable in size
This patch changes the qat firmware session data structure from a fixed
size to a variable size which is dependent on the size of the chosen
algorithm.
This reduces the amount of bytes which are transferred across
PCIe and thus helps to increase qat performance when the
accelerator is bound by PCIe.
Signed-off-by: John Griffin <john.griffin@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Shreyansh Jain [Thu, 6 Oct 2016 13:54:03 +0000 (19:24 +0530)]
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.
When compiled with EXTRA_CFLAGS="-O1", the compiler is not
able to detect that size is always initialized when used, and
issues a wrong warning:
eal_memory.c: In function ‘rte_eal_hugepage_attach’:
eal_memory.c:1684:3: error: ‘size’ may be used uninitialized in this
function [-Werror=maybe-uninitialized]
munmap(hp, size);
^
Workaround this issue by initializing size to 0.
Seen on gcc (Debian 5.4.1-1) 5.4.1 20160803.
net/bnxt: update struct definitions for 1.5.1 HWRM API
Update the PMD to use the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - a onetime change owing to the usage of a different auto generated
file.
Update the PMD to use packet filtering related structures as per the
1.5.1 version of the HWRM API. Most of the changes in the patch are
white spaces and rearrangement of the lines - a onetime change owing to
the usage of a different auto generated file.
Update the PMD to use HWRM ring related structures as per the 1.5.1
version of the HWRM API. Most of the changes in the patch are white
spaces and rearrangement of the lines - a onetime change owing to the
usage of a different auto generated file.
Update the PMD to use VNIC related structures as per the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - a onetime change owing to the usage of a different
auto generated file.
Update the PMD to use the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - a onetime change owing to the usage of a different
auto generated file.
Update the PMD to use the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - a onetime change owing to the usage of a different
auto generated file.
Structures being updated in this patch:
input, output, hwrm_ver_get_input, hwrm_ver_get_output,
hwrm_func_reset_input, hwrm_func_reset_output, hwrm_func_qcaps_input,
hwrm_func_qcaps_output
Update the PMD to use structures as per the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - hopefully a onetime change owing to the usage of a different
auto generated file.
Update the PMD to use the 1.5.1 HWRM API.
Most of the changes in the patch are white spaces and rearrangement of the
lines - hopefully a onetime change owing to the usage of a different
auto generated file.
Structures updated in this patch:
tx_bd_short, tx_bd_long, tx_bd_long_hi, rx_prod_pkt_bd
Update the PMD to use the 1.5.1 HWRM API.
Most of the changes in this patch and the following patches are
white spaces and rearrangement of the lines - hopefully a onetime change
owing to the usage of a different auto generated file.
Other than that, the following fields have been renamed:
1) rx_err_pkts and tx_err_pkts are now rx_discard_pkts and tx_discard_pkts
in struct ctx_hw_stats64
2) the perm_mac_addr field in the response of bnxt_hwrm_func_qcaps has
changed to mac_addr.
Add support to the bnxt PMD to load on a PCI VF.
1) VF cannot change parameters like - speed, autoneg and pause
2) If the VF MAC address shows up as all 0's it has to be provisioned
by the PF in the hypervisor.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Reviewed-by: David Christensen <david.christensen@broadcom.com>
Update doc/guides/nics/bnxt.rst to indicate that the bnxt PMD driver
supports Broadcom NetXtreme-C/NetXtreme-E BCM5730X/BCM5740X family of
network controllers and Broadcom StrataGX BCM5871X family of
communications processors.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Acked-by: John McNamara <john.mcnamara@intel.com>
More PCI Device IDs for Cumulus, Cumulus+ and Whitney, Whitney+ SKUs.
The NPAR model supported by firmware has been altered. It now allocates a
unique Device ID for each NPAR partition for each device. In addition,
ASIC's that are capable of supporting dual media have a unique DID
depending whether they are configured in copper or fiber mode.
This patch adds the necessary DIDs.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Reviewed-by: David Christensen <david.christensen@broadcom.com>
Adding code to enable support for NIC Partitioning or NPAR 1.0
As a part of NPAR, we don't allow port settings like speed or flow
control to be changed.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Reviewed-by: Stephen Hurd <stephen.hurd@broadcom.com> Reviewed-by: David Christensen <david.christensen@broadcom.com>
This patch adds support for the Broadcom StrataGX® BCM5871X
series of Communications Processors.
These ARM based processors target a broad range of networking
applications including virtual CPE (vCPE) and NFV appliances,
10G service routers and gateways, control plane processing for
Ethernet switches, and network attached storage (NAS).
Other than adding the PCI Id for supporting the device,
the patch also adds a memory barrier before the Tx doorbell
and Completing ring doorbell is written to. Since ARM has a
weakly ordered memory model this enforces a strict ordering
of the descriptor writes before the doorbell writes happen.
Signed-off-by: John Carney <john.carney@broadcom.com> Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:15 +0000 (17:00 +0800)]
net/ixgbe/base: fix skipping PHY config
By exiting early we could skip the PHY configuration and as such
the driver may not configure the PHY correctly for SFP+.
This patch removes the logic which would previously skip the PHY
configuration in the case where we are already at the requested
speed in ixgbe_setup_mac_link_multispeed_fiber().
Fixes: f3430431abaf ("ixgbe/base: add SFP+ dual-speed support") Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:14 +0000 (17:00 +0800)]
net/ixgbe/base: remove unneeded flow control code
Support for flow control auto negotiation is defeatured from X550em_a
fiber when connected to speeds lower than 10Gbps. This patch cleans up
the code path which is mostly dead to begin with.
- add device IDs check in ixgbe_device_supports_autoneg_fc().
- ixgbe_fc_autoneg_fiber_x550em_a() is now used only to pass the user
settings to ixgbe_fc_enable_generic().
- make sure that start_hw does not fail when setup_fc is not implemented.
- small fix in the debug message when ixgbe_device_supports_autoneg_fc()
returns false.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:12 +0000 (17:00 +0800)]
net/ixgbe/base: fix possible corruption of shadow RAM
Currently, not all shadow RAM accesses are being done under the
protection of a semaphore, which could result in corruption.
Refactor the code so that it is possible to hold the semaphore
around ixgbe_host_interface_command by introducing an unlocked form.
This patch also eliminates the function ixgbe_read_ee_hostif_data_X550
in favor of the function ixgbe_read_ee_hostif_X550.
The new arrangement is able to get both the management interface semaphore
and the EEPROM semaphore at the same time instead of separately.
Fixes: af75078fece3 ("first public release") Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:11 +0000 (17:00 +0800)]
net/ixgbe/base: add two MAC ops for Hyper-V
This patch adds negotiate_api_version and set_rlpml into mac_ops. With the
introduction of Hyper-V functionality, we can have separate functions to
accommodate different implementations without have one break the other.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:10 +0000 (17:00 +0800)]
net/ixgbe/base: add X550em_a FW ALEF support
This patch adds X550em_a FW ALEF support. ALEF is the new unified FW.
The driver uses the KRM_PMD_RX_FLEX_PORT/FLX_MASK_ST20 registers to
configure the lane mode.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
This patch adds missing FDIRSCTPM mask setting for tunneled packets.
It should be set the same way as FDIRTCPM and FDIRUDPM so that SCTP
packets can be filtered correctly.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:02 +0000 (17:00 +0800)]
net/ixgbe/base: set default autoneg speed at reset
This patch avoids the situation where we initialize an adapter but have not
yet set up phy.autoneg_advertised speeds. In that case we could end
up with having no autoneg speeds enabled and therefore get no link until we
reset the link and set the autoneg speeds correctly.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 09:00:01 +0000 (17:00 +0800)]
net/ixgbe/base: use default check link for X550em_a
This patch removes the X550em_a specific check link function and uses
ixgbe_check_mac_link_generic instead. It is not necessary to
check both the MAC link register and external PHY registers when
checking the link.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:58 +0000 (16:59 +0800)]
net/ixgbe/base: support X550em_a SGMII FC autoneg
Create flow control (FC) setup and enable functions to configure PHY
registers. These registers advertise FC settings according to the user
requested mode. On link establishment, these settings are negotiated
with the link partner to agree on the settings to use: RX and TX enabled,
TX only enabled, or FC disabled and RX enabled (which also enables TX).
Remove the part of code that performs FC auto-negotiation (AN) in
ixgbe_setup_m88 and put it in a new function to maintain consistency
with other FC AN implementations so far. Add function pointers to the
setup-fc and enable-fc functions so that they get called during init
to perform FC AN.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:57 +0000 (16:59 +0800)]
net/ixgbe/base: bypass checking link for crosstalk
When HW starts, first read the NVM to see if the crosstalk fix should
be used on the given HW and cache that information in the HW structure.
When we check_link we first see if 1) NVM requests this fix 2) if
we are an SFP+ device 3) see if a module is not in the SFP+ cage.
If all the above are true then don't bother checking the link, just
say it is down.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:55 +0000 (16:59 +0800)]
net/ixgbe/base: fix check for NACK
Previously we checked return buffer for
(IXGBE_VF_SET_MACVLAN | IXGBE_VT_MSGTYPE_NACK), but this would not
work if index is not 0 and as a result NACK will not be detected.
Fixes: af75078fece3 ("first public release") Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:54 +0000 (16:59 +0800)]
net/ixgbe/base: access IOSF by host interface
This patch makes sure that we access IOSF registers through the
host interface command (HIC) for the majority of X550em devices.
All devices with NVM are capable of using the HIC.
For consistency all instances where the ixgbe_write_phy_reg_mdi is called
directly are converted to function pointer calls.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:52 +0000 (16:59 +0800)]
net/ixgbe/base: report VF MTU setting failure
Propagate return value when trying to set the maximum packet length. A
PF driver could return a NACK for this request, and the VF driver will
need to know this.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:51 +0000 (16:59 +0800)]
net/ixgbe/base: fix function comments about X550
Some function comments are obviously wrong, this patch rewords them.
Fixes: d2e72774e58c ("ixgbe/base: support X550") Fixes: 0790adeb5675 ("ixgbe/base: support X550em_a device") Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:48 +0000 (16:59 +0800)]
net/ixgbe/base: add flow control autoneg for X550em_a fiber
This patch adds a separate function for enabling Flow Control (FC)
auto-negotiation on X550em_a:
- rename ixgbe_fc_autoneg_x550a() to ixgbe_fc_autoneg_backplane_x550em_a().
- create ixgbe_fc_autoneg_fiber_x550em_a() specifically for fiber.
- add definitions for KRM_PCS_KX_AN_LP register and related bits.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:47 +0000 (16:59 +0800)]
net/ixgbe/base: add flow control for X550em_a fiber
This patch adds a separate function for setting up Flow Control (FC)
on X550em_a fiber:
- rename ixgbe_setup_fc_x550a() to ixgbe_setup_fc_backplane_x550em_a().
- create ixgbe_setup_fc_fiber_x550em_a() to configure FC for fiber.
- add definitions for KRM_AN_CNTL_4 and KRM_PCS_KX_AN along with related
definitions.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:45 +0000 (16:59 +0800)]
net/ixgbe/base: rework X550em_a 1G PHY init
Fully initialize X550em_a 1G PHYs; move the PHY definitions from
ixgbe_x550.h to ixgbe_phy.h, where they really belong; define
register numbers in decimal because that is how they are in the spec.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:44 +0000 (16:59 +0800)]
net/ixgbe/base: extract PHY probing function
Move the PHY probe code into a separate function so that it can be
reused. A subsequent patch will use it for configurations that
provide the PHY address explicitly.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:43 +0000 (16:59 +0800)]
net/ixgbe/base: move X550 MAC ops init into functions
This patch introduces new init_ops functions for X550EM_a and X550EM_x.
This makes it easier to assign function pointers with specific
dependencies (like media type) for each MAC.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Xiao Wang [Sun, 25 Sep 2016 08:59:41 +0000 (16:59 +0800)]
net/ixgbe/base: support X550em_a 10G PHY
This patch uses the shared Management Data Input/output (MDIO)
functions ixgbe_read_phy_reg_x550a and ixgbe_write_phy_reg_x550a
for X550em_a 10G PHY which supports flow control auto-negotiation.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Using device ID to check PHY capability is not extensible.
Now we are using PHY type to detect PHY capability.
All link speeds supported by the device are encoded into PHY type,
and PHY type value can be read by admin queue "get_phy_capability"
command at initialization stage.
John Daley [Thu, 22 Sep 2016 17:02:46 +0000 (10:02 -0700)]
net/enic: support scatter Rx in MTU update
Re-initialize Rq's when MTU is changed. This allows for more
efficient use of mbufs when moving from an MTU that is greater
than the mbuf size to one that is less. Also move to using Rx
scatter mode when moving from an MTU less than the mbuf size
to one that is greater.
Signed-off-by: Nelson Escobar <neescoba@cisco.com> Signed-off-by: John Daley <johndale@cisco.com>
Nelson Escobar [Thu, 22 Sep 2016 17:02:45 +0000 (10:02 -0700)]
net/enic: fix freeing memory for descriptor ring
The function vnic_dev_free_desc_ring() didn't actually free memory. Fix
this by first changing vnic_dev_alloc_desc_ring() to use the common
allocation function, then in vnic_dev_free_desc_ring call the common
free function.
Fixes: fefed3d1e62c ("enic: new driver") Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Nelson Escobar [Mon, 19 Sep 2016 18:50:09 +0000 (11:50 -0700)]
net/enic: unregister interrupt handler when stopping
enic_disable() wasn't calling rte_intr_disable() or
rte_intr_callback_unregister(). stopping/starting a port would
result in the same interrupt callback being registered multiple
times, which would then cause it to be called multiple times on
every interrupt.
Fixes: fefed3d1e62c ("enic: new driver") Signed-off-by: Nelson Escobar <neescoba@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
git.droids-corp.org / dpdk.git / log