When VF receives a message from PF, it should check the return
value. But in i40evf_execute_vf_cmd the value is ignored and not
returned to the caller.
Fixes: 95cd21f45d1b ("i40evf: allocate virtchnl commands buffer per VF")
Signed-off-by: Wenzhuo Lu
---
drivers/net/i40e/i40e_ethdev.h| 2 +-
When using "show port xstats all" command to show xstats, the output
is usually too long to obtain what you really want, expecially when
multi-queue is enabled.
This patch refines this situation by skipping showing those with value
of zero.
Signed-off-by: Jianfeng Tan
---
app/test-pmd/config.c
On 12/20/2016 08:26 PM, Thomas Monjalon wrote:
Add a new macro RTE_PMD_REGISTER_KMOD_DEP() that allows a driver to
declare the list of kernel modules required to run properly.
Today, most PCI drivers require uio/vfio.
Signed-off-by: Olivier Matz
Acked-by: Fiona Trahe
Acked-by: Adrien Mazargu
Signed-off-by: Jerin Jacob
Acked-by: Bruce Richardson
---
lib/librte_eventdev/rte_eventdev.h | 38 +
lib/librte_eventdev/rte_eventdev_pmd.h | 294 +
2 files changed, 332 insertions(+)
create mode 100644 lib/librte_eventdev/rte_eventdev_pmd.h
diff --git
As previously discussed in RFC v1 [1], RFC v2 [2], with changes
described in [3] (also pasted below), here is the first non-draft series
for this new API.
[1] http://dpdk.org/ml/archives/dev/2016-August/045181.html
[2] http://dpdk.org/ml/archives/dev/2016-October/048592.html
[3] http://dpdk.org/ml
In a polling model, lcores poll ethdev ports and associated
rx queues directly to look for packet. In an event driven model,
by contrast, lcores call the scheduler that selects packets for
them based on programmer-specified criteria. Eventdev library
adds support for event driven programming model,
This patch implements northbound eventdev API interface using
southbond driver interface
Signed-off-by: Jerin Jacob
Acked-by: Bruce Richardson
---
config/common_base | 6 +
lib/Makefile | 1 +
lib/librte_eal/common/include/rte_log.h
This patch adds infrastructure for registering the vdev or
the PCI based event device.
Signed-off-by: Jerin Jacob
Acked-by: Bruce Richardson
---
lib/librte_eventdev/rte_eventdev.c | 236 +++
lib/librte_eventdev/rte_eventdev_pmd.h | 111 +
lib/
This commit adds basic unit tests for the eventdev API.
commands to run the test app:
./build/app/test -c 2
RTE>>eventdev_common_autotest
Signed-off-by: Jerin Jacob
Acked-by: Bruce Richardson
---
MAINTAINERS | 1 +
app/test/Makefile| 2 +
app/test/test_eventdev.c | 778
The skeleton driver facilitates, bootstrapping the new
eventdev driver and creates a platform to verify
the northbound eventdev common code.
The driver supports both VDEV and PCI based eventdev
devices.
Signed-off-by: Jerin Jacob
Acked-by: Bruce Richardson
---
MAINTAINERS
From: Jan Wickbom
Currently select() is used to monitor file descriptors for vhostuser
ports. This limits the number of ports possible to create since the
fd number is used as index in the fd_set and we have seen fds > 1023.
This patch changes select() to poll(). This way we can keep an
packed (p
On Tuesday 20 December 2016 04:41 PM, Jan Blunck wrote:
The drivers should not directly access the rte_eth_dev->pci_dev but use
a macro instead. This is a preparation for replacing the pci_dev with
a struct rte_device member in the future.
Signed-off-by: Jan Blunck
---
drivers/net/bnx2x/bnx2x_
On Tuesday 20 December 2016 04:41 PM, Jan Blunck wrote:
Only the device itself can decide its PCI or not.
Signed-off-by: Jan Blunck
---
drivers/net/bnx2x/bnx2x_ethdev.c| 1 +
drivers/net/bnxt/bnxt_ethdev.c | 2 ++
drivers/net/cxgbe/cxgbe_ethdev.c| 2 ++
drivers/net/e10
update ixgbe shared code to version 16.11.21 .
v2 changes:
modify subject line and message body of git log according to
feedbacks from communtiy.
split the 24th patch into 2 separate ones.
the 24th of v1 is net/ixgbe/base: add EEE support for DNL-controlled PHYs
the 24th of v2 is net/
Receive Address Register (RAR) entries, including SAN MAC address,
are cleared when VMDq pool bits are cleared.
Prevent SAN MAC address to be cleared.
Fixes: af75078fece3 ("first public release")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_common.c | 3 ++-
1 fi
PHY type ixgbe_phy_x550em_ext_t requires different check
to verify reset status.
Fixes: af75078fece3 ("first public release")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_phy.c | 29 -
1 file changed, 24 insertions(+), 5 deletions(-)
Send the driver version string to firmware through
the host interface command on x550 devices.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_api.c| 7 ++--
drivers/net/ixgbe/base/ixgbe_api.h| 2 +-
drivers/net/ixgbe/base/ixgbe_common.c | 4 ++-
drivers/net/ixgbe/base/ixgbe_c
This patch cleans up the code and clarifies the comment around
the X557 PHY link status check in ixgbe_check_link_t_x550em().
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 25 +++--
1 file changed, 11 insertions(+), 14 deletions(-)
diff --git a/drivers/net
Method to identify the CS4223/CS4227 is incorrect and unreliable.
Provide a new register to differentiate between these PHY SKUs.
Fixes: fc0559bdb5e3 ("net/ixgbe/base: add link MAC setup for X550a SFP+")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_phy.h | 5 +++
Devices that cannot go 10G speeds can safely select a faster
Management Data Input/Output (MDIO) speed.
Select fast MDIO clock speed for for those devices.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/
The variable checksum_last_word is used only for bounds check.
So remove this variable and use IXGBE_EEPROM_CHECKSUM directly.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x540.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ixgbe/base/ixgb
Enable the Link Alarm Status Interrupt (LASI) only for X552 devices
to receive notifications of the link configurations of the external
PHY and correspondingly support the configuration of the internal
iXFI link, since iXFI does not support auto-negotiation.
This is not required for X553 devices h
Add support to get the link active LED index via the LEDCTL register.
If the LEDCTL register does not have link active LED set then
use MAC default LED index.
Link active LED is used for adapter identify/blink support.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_common.c | 45 +++
The MAC register NW_MNG_IF_SEL fields have been redefined for X553.
These changes impact the iXFI driver code flow. Since iXFI is only
supported in X552, this patch adds X552 MAC check for iXFI flows.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_type.h | 4 ++--
drivers/net/ixgbe/bas
Return correct physical layer for some x550 devices.
Fixes: 76d5b807ff74 ("ixgbe/base: new X557 phy")
Fixes: d2e72774e58c ("ixgbe/base: support X550")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/driver
Fix ixgbe_setup_sgmii_m88 to set lane speed to autoneg instead of 1G
to prevent problems with link between PHYs
Fixes: d4b4c6845487 ("net/ixgbe/base: add X550em_a FW ALEF support")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 2 +-
1 file changed, 1 inse
Update ixgbe_setup_phy_link_generic that set/unset auto-negotiation.
Ensure that unsupported auto-negotiation speeds are unset.
This is necessary since the PHY NVM may advertise unsupported speeds.
Fixes: af75078fece3 ("first public release")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
dri
Remove some specific code for enabling/disabling Energy Efficient
Ethernet (EEE).
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 61 ++---
1 file changed, 10 insertions(+), 51 deletions(-)
diff --git a/drivers/net/ixgbe/base/ixgbe_x550.c
b/driv
Use the new firmware interface to access and control some PHYs.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_phy.c | 4 -
drivers/net/ixgbe/base/ixgbe_phy.h | 67 --
drivers/net/ixgbe/base/ixgbe_type.h | 2 +-
drivers/net/ixgbe/base/ixgbe_x550.c | 412 ++
This patch moves some of the extended speeds that come with X552
(5G, 2.5G, 10M) into the link check functions.
It also now returns speed_unknown for speeds that are not known
how to interpret.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/Makefile | 1 +
drivers/net/ixgbe/base/ixgbe_
Read and store NW_MNG_IF_SEL register because register fields are
used to determine SGMII link for busy SGMII register reads.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/base/ixgbe_x550.
Only X550 devices support 5Gb. MAC type checks for 5Gb should
be done only for X550 devices.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_common.c | 2 +-
drivers/net/ixgbe/base/ixgbe_hv_vf.c | 2 +-
drivers/net/ixgbe/base/ixgbe_vf.c | 2 +-
3 files changed, 3 insertions(+), 3 de
Implement support for new firmware commands to be used to access
and control some PHYs.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_common.h | 4 +-
drivers/net/ixgbe/base/ixgbe_osdep.h | 3 +-
drivers/net/ixgbe/base/ixgbe_type.h | 70 ++-
drivers/net/ixgbe/base/ixgbe
The "FW" PHY type now supports speeds 10M, 100M, and 1G.
Previously, only the 1G speed was reported for this PHY type.
Add reporting 10M and 100M speed options.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_type.h | 1 +
drivers/net/ixgbe/base/ixgbe_x550.c | 8 +++-
2 files changed
ixgbe_read_i2c_combined_generic_int() is only used by devices >= X550.
Set the initial value accordingly and remove the MAC type check.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_phy.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/net/ixgbe/base/ixgb
This patch removes the flow control conversion from Rx and Tx to pause
and asymmetric pause, as that is handled by the ixgbe_negotiate_fc().
Performing the conversion prior to ixgbe_negotiate_fc() results in
an incorrect fc mode if Rx only pause is selected when the link partner
is advertising Tx.
The first PHY ID for X550 was only used on original HW and
never released. So remove these unused PHY ID.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_phy.c | 1 -
drivers/net/ixgbe/base/ixgbe_type.h | 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/net/ixgbe/base/ixgbe_ph
remove unused enum type for master/slave control
in ixbge_type.h
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_type.h | 8
1 file changed, 8 deletions(-)
diff --git a/drivers/net/ixgbe/base/ixgbe_type.h
b/drivers/net/ixgbe/base/ixgbe_type.h
index 9ec17a9..f1761a3 100644
---
Remove unused old Energy Efficient Ethernet (EEE) code.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 113 +---
drivers/net/ixgbe/base/ixgbe_x550.h | 2 -
2 files changed, 1 insertion(+), 114 deletions(-)
diff --git a/drivers/net/ixgbe/base/i
This register was incorrect when compared to the data sheet.
Even though the driver doesn't currently use this register,
it is better to fix it upstream.
Fixes: af75078fece3 ("first public release")
CC: sta...@dpdk.org
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_type.h | 2 +-
1 fi
This patch adds Energy Efficient Ethernet (EEE) support for
some Marvell PHYs on some future platforms.
Because EEE capability or status was not indicated previously,
this patch simply assumes that it is supported.
As soon as there is a PHY that does not support EEE, there will
be defects in this
This patch updates the configuration of PHY from Inphi (www.inphi.com)
to flush the register write with a reg read.
The Inphi PHY is configured in ixgbe_setup_mac_link_sfp_x550a.
The Inphy PHY setup flow has been updated to read configuration reg,
write only linear/non-linear, and then read (write
For the PHY type SGMII, report the pyhsical layer.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/ixgbe_x550.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ixgbe/base/ixgbe_x550.c
b/drivers/net/ixgbe/base/ixgbe_x550.c
index a57ba74..782ca91 100644
--- a/drivers/net/ixgb
update the version of shared codes to cid-ixgbe.2016.11.21.tar.gz,
all files in net/ixgbe/base are developped by another team and
DPDK PMD uses them accordingly.
Signed-off-by: Wei Dai
---
drivers/net/ixgbe/base/README | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/driver
On Wednesday 21 December 2016 03:20 PM, Shreyansh Jain wrote:
On Tuesday 20 December 2016 04:41 PM, Jan Blunck wrote:
The drivers should not directly access the rte_eth_dev->pci_dev but use
a macro instead. This is a preparation for replacing the pci_dev with
a struct rte_device member in the fu
Hi Jan,
On Tuesday 20 December 2016 04:41 PM, Jan Blunck wrote:
This is a repost of the series I sent in November. I've addressed Shreyansh's
review comments about the PCI device users I've missed.
Jan Blunck (9):
eal: define container_of macro
ethdev: Helper to convert to struct rte_pci_de
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/Makefile| 1 +
drivers/net/mlx5/mlx5.h | 16 ++
drivers/net/mlx5/mlx5_fdir.c | 15 ++
drivers/net/mlx5/mlx5_flow.c | 122 +++
4 files changed, 154 insertions(+)
create mode 100644 dr
Introduce initial software validation for rte_flow rules.
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5.h | 2 +
drivers/net/mlx5/mlx5_flow.c| 202 ++--
drivers/net/mlx5/mlx5_trigger.c | 2 +
3 files changed, 177 insertions(+), 29 d
Convert Ethernet, IPv4, IPv6, TCP, UDP layers into ibv_flow and create
those rules when after validation (i.e. NIC supports the rule).
VLAN is still not supported in this commit.
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5.h | 3 +-
drivers/net/mlx5/mlx5_flow.c| 737
This series requires rte_flow [1].
It brings rte_flow support to the same level as flow director (FDIR) in mlx5.
[1] http://dpdk.org/ml/archives/dev/2016-December/052802.html
Changes in v2:
- Fix several issues.
- Support VLAN filtering.
Nelio Laranjeiro (4):
net/mlx5: add preliminary sup
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5_flow.c | 59 ++--
1 file changed, 57 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 44e2fb8..fec1950 100644
--- a/drivers/net/mlx5/mlx5_
On Mon, Dec 19, 2016 at 11:39:18AM +0530, Jianbo Liu wrote:
Hi Jianbo,
> vPMD will check 4 descriptors in one time, but the statuses are not consistent
> because the memory allocated for RX descriptors is cacheable huagepage.
Is it different in X86 case ?i.e Is x86 creating non cacheable hugepage
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, December 6, 2016 3:41 AM
> To: Dai, Wei ; Zhang, Helin ;
> Ananyev, Konstantin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 24/29] net/ixgbe/base: add EEE support for
> DNL-controlled PHYs
>
> On 12/4/2016 6:31 AM, Wei Dai
2016-12-19 15:52, Thomas Monjalon:
> Hi all,
>
> On Wednesday December 21, 2016, between 6:00 and 9:00 UTC, there will be
> an upgrade of our hosting platform.
> Unfortunately it is announced a downtime of an hour or more.
> It will affect every hosted services: web, mail, git, patchwork.
>
> It
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, December 6, 2016 3:41 AM
> To: Dai, Wei ; Zhang, Helin ;
> Ananyev, Konstantin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 27/29] net/ixgbe/base: add write flush required
> by Inphi
>
> On 12/4/2016 6:31 AM, Wei Dai wrote
Thanks for your correcting.
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, December 6, 2016 3:41 AM
> To: Dai, Wei ; Zhang, Helin ;
> Ananyev, Konstantin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 29/29] net/ixgbe/base: update version of
> basical
> codes in README
Hi Adrien,
You missed out the changes I suggested to the table_rte_flow_migration_fdir
which means that the pdf build is still broken. Also, the changes to
table_rte_flow_migration_l2tunnel also break the PDF bulid.
You can test as follows:
make doc-guides-pdf -j
I'd suggest the following t
On Wed, Dec 21, 2016 at 03:38:51PM +0530, Jerin Jacob wrote:
> On Mon, Dec 19, 2016 at 11:39:18AM +0530, Jianbo Liu wrote:
>
> Hi Jianbo,
>
> > vPMD will check 4 descriptors in one time, but the statuses are not
> > consistent
> > because the memory allocated for RX descriptors is cacheable huag
That's a good advice. Thanks.
-Original Message-
From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
Sent: Wednesday, December 21, 2016 10:37 AM
To: Yang, Qiming
Cc: dev@dpdk.org; Wu, Jingjing
Subject: Re: [dpdk-dev] [PATCH v3] app/testpmd: supported offload capabilities
query
On W
Hi John,
On Wed, Dec 21, 2016 at 10:55:39AM +, Mcnamara, John wrote:
> Hi Adrien,
>
> You missed out the changes I suggested to the table_rte_flow_migration_fdir
> which means that the pdf build is still broken. Also, the changes to
> table_rte_flow_migration_l2tunnel also break the PDF bulid
On Wed, Dec 21, 2016 at 12:21:14PM +0300, Andrew Rybchenko wrote:
> On 12/20/2016 08:26 PM, Thomas Monjalon wrote:
> > > > Add a new macro RTE_PMD_REGISTER_KMOD_DEP() that allows a driver to
> > > > declare the list of kernel modules required to run properly.
> > > >
> > > > Today, most PCI driver
On 12/21/2016 02:37 PM, Neil Horman wrote:
On Wed, Dec 21, 2016 at 12:21:14PM +0300, Andrew Rybchenko wrote:
On 12/20/2016 08:26 PM, Thomas Monjalon wrote:
Add a new macro RTE_PMD_REGISTER_KMOD_DEP() that allows a driver to
declare the list of kernel modules required to run properly.
Today, mo
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, December 2, 2016 2:16 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; De Lara Guarch, Pablo
> ; Griffin, John ;
> Jain, Deepak K ; Kusztal, ArkadiuszX
>
> Subject: [PATCH 0/3] Add DES capability to Intel QuickAssist Technology d
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, December 2, 2016 2:16 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; De Lara Guarch, Pablo
> ; Griffin, John ;
> Jain, Deepak K ; Kusztal, ArkadiuszX
>
> Subject: [PATCH 2/3] crypto/qat: add DES capability to Intel QAT driver
>
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, December 2, 2016 2:16 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; De Lara Guarch, Pablo
> ; Griffin, John ;
> Jain, Deepak K ; Kusztal, ArkadiuszX
>
> Subject: [PATCH 3/3] app/test: add DES tests to Intel QAT crypto test sui
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, December 2, 2016 2:16 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; De Lara Guarch, Pablo
> ; Griffin, John ;
> Jain, Deepak K ; Kusztal, ArkadiuszX
>
> Subject: [PATCH 1/3] lib/librte_cryptodev: add DES CBC cipher algorithm
>
Ping.
Best regards, Ilya Maximets.
On 21.11.2016 16:53, Ferruh Yigit wrote:
> On 10/19/2016 3:30 PM, Ferruh Yigit wrote:
>> On 10/19/2016 3:07 PM, Ilya Maximets wrote:
>>> Ilya Maximets (2):
>>> net/i40e: allow bulk alloc for the max size desc ring
>>> net/ixgbe: allow bulk alloc for the max
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Monday, December 05, 2016 12:56 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; eclan.dohe...@intel.com; De Lara
> Guarch, Pablo; hemant.agra...@nxp.com; Akhil Goyal
> Subject: [PATCH 6/8] crypto/dpaa2_se
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Monday, December 05, 2016 12:56 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; eclan.dohe...@intel.com; De Lara
> Guarch, Pablo; hemant.agra...@nxp.com; Akhil Goyal
> Subject: [PATCH 6/8] crypto/dpaa2_sec
The performance report for DPDK 16.11 on Intel Nics is now available. See:
http://dpdk.org/doc/
http://fast.dpdk.org/doc/perf/Intel_DPDK_R16_11_NIC_performance_report.pdf
We intend to have a similar report for each release and hope that some other
vendors will also add reports.
We also
2016-12-08 10:56, Aaron Conole:
> It's been a source of confusion in the past, and even with this update
> may continue to be a source of confusion. However, the original
> language seems to imply that the DPDK EAL will take ownership of the
> array passed in. Loosening the language up a bit migh
2016-12-09 15:14, Bruce Richardson:
> On Thu, Dec 08, 2016 at 07:19:41PM +0100, Thomas Monjalon wrote:
> > 2016-12-02 17:48, Jianfeng Tan:
> > > This patch uses pthread_getaffinity_np() to narrow down used
> > > cores when none of below options is specified:
> > > * coremask (-c)
> > > * coreli
2016-12-04 02:25, Jerin Jacob:
> v2:
> - No changes in eal: postpone vdev initialization
> - Added new patch "eal: rename dev init API for consistency" as
> suggested by Shreyansh Jain
> http://dpdk.org/dev/patchwork/patch/17096/
Let's forget this rename and apply the v1 instead.
These functions a
From 94f2eaed51e6e5402e8c03b80e0999a4fd420390 Mon Sep 17 00:00:00 2001
From: root
To:
Cc: , ,
Date: Wed, 21 Dec 2016 22:31:29 +0800
Subject: [PATCH] load_balancer Tx Flush Bug
We found a bug in use load_balancer example,and,This bug DPDK each version.
In IO tx flush, only flush port 0.
So,If I e
2016-11-20 13:30, Jerin Jacob:
> Some platform like octeontx may use pci and
> vdev based combined device to represent a logical
> dpdk functional device.In such case, postponing the
> vdev initialization after pci device
> initialization will provide the better view of
> the pci device resources i
Hi Zbigniew,
> -Original Message-
> From: zbigniew.bo...@caviumnetworks.com
> [mailto:zbigniew.bo...@caviumnetworks.com]
> Sent: Wednesday, December 07, 2016 2:33 AM
> To: De Lara Guarch, Pablo; jerin.ja...@caviumnetworks.com
> Cc: dev@dpdk.org; Zbigniew Bodek
> Subject: [PATCH v2 01/12] m
As previously discussed in RFC v1 [1], RFC v2 [2], with changes
described in [3] (also pasted below), here is the first non-draft series
for this new API.
Its capabilities are so generic that its name had to be vague, it may be
called "Generic flow API", "Generic flow interface" (possibly shortene
This new API supersedes all the legacy filter types described in
rte_eth_ctrl.h. It is slightly higher level and as a result relies more on
PMDs to process and validate flow rules.
Benefits:
- A unified API is easier to program for, applications do not have to be
written for a specific filter t
They are superseded by the generic flow API (rte_flow). Target release is
not defined yet.
Suggested-by: Kevin Traynor
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
doc/guides/rel_notes/deprecation.rst | 8
1 file changed, 8 insertions(+)
diff --git a/doc/guides/rel_notes/
Considering tokens must be hard-coded in a list part of the instruction
structure, context-dependent tokens cannot be expressed.
This commit adds support for building dynamic token lists through a
user-provided function, which is called when the static token list is empty
(a single NULL entry).
B
This documentation is based on the latest RFC submission, subsequently
updated according to feedback from the community.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
doc/guides/prog_guide/index.rst|1 +
doc/guides/prog_guide/rte_flow.rst | 2041 ++
Managing generic flow API functions from command line requires the use of
dynamic tokens for convenience as flow rules are not fixed and cannot be
defined statically.
This commit adds specific flexible parser code and object for a new "flow"
command in separate file.
Signed-off-by: Adrien Mazargu
This prevents sigbus errors on architectures that cannot handle unexpected
unaligned accesses to the output buffer.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
lib/librte_cmdline/cmdline_parse.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/lib/librte
Parse all integer types and handle conversion to network byte order in a
single function.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 148 +++
1 file changed, 148 insertions(+)
diff --git a/app/test-pmd/cmdline_flow
Add basic management functions for the generic flow API (validate, create,
destroy, flush, query and list). Flow rule objects and properties are
arranged in lists associated with each port.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline.c | 1 +
app/test-pmd
Syntax:
flow list {port_id} [group {group_id}] [...]
List configured flow rules on a port. Output can optionally be limited to a
given set of group identifiers.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline.c | 4 ++
app/test-pmd/cmdline_flow.c | 141 ++
Syntax:
flow destroy {port_id} rule {rule_id} [...]
Destroy a given set of flow rules associated with a port.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline.c | 3 ++
app/test-pmd/cmdline_flow.c | 106 ++-
2 files chan
Syntax:
flow flush {port_id}
Destroy all flow rules on a port.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline.c | 3 +++
app/test-pmd/cmdline_flow.c | 43 +++-
2 files changed, 45 insertions(+), 1 deletion(-)
diff --gi
Syntax:
flow (validate|create) {port_id}
[group {group_id}] [priority {level}] [ingress] [egress]
pattern {item} [/ {item} [...]] / end
actions {action} [/ {action} [...]] / end
Either check the validity of a flow rule or create it. Any number of
pattern items and actions can be prov
Syntax:
flow query {port_id} {rule_id} {action}
Query a specific action of an existing flow rule.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline.c | 3 +
app/test-pmd/cmdline_flow.c | 121 ++-
2 files changed, 123 inse
Generating bit-masks from prefix lengths is often more convenient than
providing them entirely (e.g. to define IPv4 and IPv6 subnets).
This commit adds the "prefix" operator that assigns generated bit-masks to
any pattern item specification field.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga S
Several rte_flow structures expose bit-fields that cannot be set in a
generic fashion at byte level. Add bit-mask support to handle them.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 70
1 file changed, 70 insert
Add parser code to fully set individual fields of pattern item
specification structures, using the following operators:
- fix: sets field and applies full bit-mask for perfect matching.
- spec: sets field without modifying its bit-mask.
- last: sets upper value of the spec => last range.
- mask: s
This pattern item matches any protocol in place of the current layer and
has two properties:
- min: minimum number of layers covered (0 or more).
- max: maximum number of layers covered (0 means infinity).
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 2
- PF: match packets addressed to the physical function.
- VF: match packets addressed to a virtual function ID.
- PORT: device-specific physical port index to use.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 53
These pattern items match basic Ethernet headers (source, destination and
type) and related 802.1Q/ad VLAN headers.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 126 +++
1 file changed, 126 insertions(+)
diff --git a
Matches arbitrary byte strings with properties:
- relative: look for pattern after the previous item.
- search: search pattern from offset (see also limit).
- offset: absolute or relative offset for pattern.
- limit: search area limit for start of pattern.
- length: pattern length.
- pattern: byte
Add the ability to match basic fields from IPv4 and IPv6 headers (source
and destination addresses only).
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/cmdline_flow.c | 177 +++
1 file changed, 177 insertions(+)
diff --git a/app/test-
Add the ability to match a few properties of common L4[.5] protocol
headers:
- ICMP: type and code.
- UDP: source and destination ports.
- TCP: source and destination ports.
- SCTP: source and destination ports.
- VXLAN: network identifier.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
-
- MARK: attach 32 bit value to packets.
- FLAG: flag packets.
- DROP: drop packets.
- COUNT: enable counters for a rule.
- PF: redirect packets to physical device function.
- VF: redirect packets to virtual device function.
Signed-off-by: Adrien Mazarguil
Acked-by: Olga Shern
---
app/test-pmd/c
1 - 100 of 181 matches
Mail list logo
