2016-03-10 12:32, Yuanhan Liu:
> v3: - quite few minor changes, including using likely/unlikely
> when possible.
>
> - Added a new patch 8 to avoid desc dead loop chain
>
> The first 3 patches refactor 3 major functions at vhost_rxtx.c.
> It simplifies the code logic, making it more rea
2016-01-05 07:16, Xie, Huawei:
> On 1/5/2016 2:42 PM, Xie, Huawei wrote:
> > This patch removes the internal lockless enqueue implmentation.
> > DPDK doesn't support receiving/transmitting packets from/to the same
> > queue. Vhost PMD wraps vhost device as normal DPDK port. DPDK
> > applications no
2016-03-14 17:12, Yuanhan Liu:
> On Mon, Mar 14, 2016 at 05:53:32PM +0900, Tetsuya Mukawa wrote:
> > Currently, default values of kickfd and callfd are -1.
> > If the values are -1, current code guesses kickfd and callfd haven't
> > been initialized yet. Then vhost library will guess the virtqueue
On 3/14/2016 5:40 PM, Jay Rolette wrote:
> Is there some technical reason or is it just the push-back you are
> getting from some of the maintainers?
>
The majority of the discussion on the list was based on not having
kernel modules, which cloud the desired technical discussion.
As a result of t
Hi,
patch http://dpdk.org/dev/patchwork/patch/10202/
which was applied to dpdk-next-net/rel_16_04 tree changes filling
of items in rte_eth_link structure for szedata2 driver. These changes
for szedata2 driver are not compliant with changes in this patch series.
I'm not sure how it should be addres
Thanks for your reply! I used one patch solve my problem someone posted last
night in the mailing list.
At 2016-03-14 21:02:13, "Kyle Larose" wrote:
>Hello,
>
>On Sun, Mar 13, 2016 at 10:38 AM, ?? wrote:
>> Hi all,
>> When I use the dpdk lookup function, I met the segment fault problem. Can
Hi, Bruce
That is because another patch was applied before this one. I will rework it,
and send it soon.
Thanks
Jingjing
> -Original Message-
> From: Richardson, Bruce
> Sent: Monday, March 14, 2016 8:22 PM
> To: Wu, Jingjing
> Cc: dev at dpdk.org; Zhang, Helin; Tao, Zhe
> Subject: Re:
Thanks so much for your patch! Your patch exactly solves my bug. :)
At 2016-03-15 08:57:29, "Dhananjaya Eadala" wrote:
Hi
I looked at your info from gdb and source code.
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Tuesday, March 15, 2016 5:56 AM
> To: marcdevel at gmail.com; Richardson, Bruce ;
> Doherty, Declan ; Ananyev, Konstantin
> ; Lu, Wenzhuo ;
> Zhang, Helin ; Chen, Jing D intel.com>;
> harish.patil
Hi,
On 3/15/2016 1:14 AM, Ferruh Yigit wrote:
> On 3/14/2016 7:42 AM, Jianfeng Tan wrote:
>> Add a new API rte_eth_dev_get_supported_ptypes to query what packet types
>> can be filled by given already started device (or its pmd rx burst function
>> has already been decided).
>>
>> Signed-off-by: J
v6 changes:
- rebase on latest dpdk-next-net/rel_16_04 branch (commit 94d8f4bf963a)
- fix complie issue
v5 changes:
- doc rewording and format fixing.
v4 changes:
- rebase on latest dpdk-next-net/rel_16_04 branch (commit 0f9564a0e4f2)
v3 changes:
- commit log doc rewording.
- rebase on lat
Currently, i40evf PMD uses a global static buffer to send virtchnl
command to host driver. It is shared by multi VFs.
This patch changed to allocate virtchnl cmd buffer for each VF.
Signed-off-by: Jingjing Wu
Acked-by: Helin Zhang
---
drivers/net/i40e/i40e_ethdev.h| 2 +
drivers/net/i40e/
When Linux PF and DPDK VF are used for i40e PMD, In case of PF reset,
interrupt will go via adminq event, VF need be informed the event,
a callback mechanism is introduced by VF. This will allow VF to
invoke callback when reset happens.
Users can register a callback for this interrupt event like:
Add a new API rte_eth_dev_get_supported_ptypes to query what packet types
can be filled by given already started device (or its pmd rx burst function
has already been decided).
Signed-off-by: Jianfeng Tan
Acked-by: Konstantin Ananyev
Acked-by: Adrien Mazarguil
---
v9:
- Fix rte_ether_version.m
Tested-by: Min Cao
- Tested Commit: e702183bab5a13f6e7d77be0d414914319469020
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 24 cases, 24 passe
On 2016/03/14 21:02, Bruce Richardson wrote:
> On Mon, Mar 07, 2016 at 11:07:14AM +0900, Tetsuya Mukawa wrote:
>> The patch introduces a new PMD. This PMD is implemented as thin wrapper
>> of librte_vhost. It means librte_vhost is also needed to compile the PMD.
>> The vhost messages will be handle
On 03/14/2016 06:44 PM, Ferruh Yigit wrote:
> On 3/10/2016 1:15 PM, Panu Matilainen wrote:
>> There are two places that need -lm (test app and librte_sched) and
>> exactly one that needs -lrt (librte_sched). Add the relevant
>> DT_NEEDED entries to both, and eliminate the bogus discrepancy
>> betwe
Here is a patchset for little cleanups and a fix on newly introduced pci
ioport api.
The last patch fixes a regression reported by Mauricio V. [1].
[1]: http://dpdk.org/ml/archives/dev/2016-February/033922.html
--
David Marchand
David Marchand (4):
pci: explicitly call ioport handlers for ui
Prepare for fixes on x86 by separating igb_uio and uio_pci_generic cases.
Signed-off-by: David Marchand
---
lib/librte_eal/linuxapp/eal/eal_pci.c | 8
1 file changed, 8 insertions(+)
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c
b/lib/librte_eal/linuxapp/eal/eal_pci.c
index 9f752
Same idea as commit bd80d4730aca ("pci: rework ioport map error handling").
Signed-off-by: David Marchand
---
lib/librte_eal/linuxapp/eal/eal_pci.c | 5 +
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c
b/lib/librte_eal/linuxapp/eal/eal_pci
Commit b8eb345378bd ("pci: ignore devices already managed in Linux when
mapping x86 ioport") did not update other parts of the ioport api.
The application is not supposed to call these read/write/unmap ioport
functions if map call failed but I prefer aligning the code for the sake
of consistency.
uio_pci_generic does not offer the same sysfs helpers as igb_uio.
In this case, ioport number can only be retrieved by parsing /proc/ioports.
Fixes: 756ce64b1ecd ("eal: introduce PCI ioport API")
Reported-by: Mauricio V?squez
Signed-off-by: David Marchand
---
lib/librte_eal/linuxapp/eal/eal_pc
Tested-by: Min Cao
- Tested Commit: e45ef10c34540c3f543689d833db8bb7296d9e85
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 24 cases, 24 passe
Tested-by: Min Cao
- Tested Commit: e45ef10c34540c3f543689d833db8bb7296d9e85
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 23 cases, 23 passe
Tested-by: Min Cao
- Tested Commit: e45ef10c34540c3f543689d833db8bb7296d9e85
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 24 cases, 24 passe
Tested-by: Min Cao
- Tested Commit: e45ef10c34540c3f543689d833db8bb7296d9e85
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 24 cases, 24 passe
2016-03-15 01:04, Matej Vido:
> Hi,
>
> patch http://dpdk.org/dev/patchwork/patch/10202/
> which was applied to dpdk-next-net/rel_16_04 tree changes filling
> of items in rte_eth_link structure for szedata2 driver. These changes
> for szedata2 driver are not compliant with changes in this patch se
D?a 15.03.2016 o 08:12 Thomas Monjalon nap?sal(a):
> 2016-03-15 01:04, Matej Vido:
>> Hi,
>>
>> patch http://dpdk.org/dev/patchwork/patch/10202/
>> which was applied to dpdk-next-net/rel_16_04 tree changes filling
>> of items in rte_eth_link structure for szedata2 driver. These changes
>> for szeda
Tested-by: Min Cao
- Tested Commit: e45ef10c34540c3f543689d833db8bb7296d9e85
- OS: Fedora20 3.11.10-301.fc20.x86_64
- GCC: gcc (GCC) 4.8.3
- CPU: Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
- NIC: Niantic
- Default x86_64-native-linuxapp-gcc configuration
- Prerequisites:
- Total 24 cases, 24 passe
The patch introduces a new PMD. This PMD is implemented as thin wrapper
of librte_vhost.
PATCH v12 changes:
- Rebase on latest master.
- Add a missing documentation.
PATCH v11 changes:
- Rebase on latest master.
- Fix MAINTAINERS file.
- Fix Acked-by and Tested-by signatures of commit log.
This patch adds a below event type.
- RTE_ETH_EVENT_QUEUE_STATE_CHANGE
This event is used for notifying a queue state changed event.
Signed-off-by: Tetsuya Mukawa
Acked-by: Ferruh Yigit
Acked-by: Yuanhan Liu
Acked-by: Rich Lane
Tested-by: Rich Lane
---
lib/librte_ether/rte_ethdev.h | 2 ++
The patch introduces a new PMD. This PMD is implemented as thin wrapper
of librte_vhost. It means librte_vhost is also needed to compile the PMD.
The vhost messages will be handled only when a port is started. So start
a port first, then invoke QEMU.
The PMD has 2 parameters.
- iface: The parame
Hi Team,
We are facing an issue when we are trying to implement Layer 2 bridging
functionality over the Virtual function.
*Requirement:*
We need to create four VMs and each VM should run in promiscuous mode
for a specific VLAN, so that it can receive packets for that VLAN and all
the unic
On Mon, Mar 14, 2016 at 10:55:38PM +0100, Thomas Monjalon wrote:
> Re-spin of the Marc's patchset.
> The first version was sent 10 months ago!
> There are still too few tests and reviews but it is now time to move
> forward with this rework.
> Some issues were remaining in v9 and were difficult to
Hi
I am developing a network program using DPDK API. I want to extract the data
which is there is rte_mbuf structure.
Referred to rte_mbuf structure manual but confused with fields
uint16_t buf_len; /**< Length of segment buffer. */
uint16_t data_len;/**< Amount of data in segm
On Tue, Mar 15, 2016 at 09:06:12AM +, Vivek Gupta wrote:
> Hi
>
> I am developing a network program using DPDK API. I want to extract the data
> which is there is rte_mbuf structure.
>
> Referred to rte_mbuf structure manual but confused with fields
>
> uint16_t buf_len; /**< Lengt
Hi
Thanks for your prompt reply.
As per my understanding rte_mbuf structure contains information of many header
and their corresponding values.
Like Ethernet, IP and UDP Headers.
I would like to know what are the other headers information is available and
how to extract those information from p
It's useful for debug purposes to see the command line used by
autotest.py.
Signed-off-by: Olivier Matz
---
app/test/autotest_runner.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/app/test/autotest_runner.py b/app/test/autotest_runner.py
index eadfb7f..291a821 100644
--- a/app/test/autot
This test expects that a vdev is instanciated on the command
line. If it's not the case, just skip this part.
Signed-off-by: Olivier Matz
---
app/test/test_pmd_ring.c | 16 +---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/app/test/test_pmd_ring.c b/app/test/test_pm
Seen by trying to fix the func_reentrancy autotest. The test
was doing the following on several cores in parallel:
name = "common_name";
do several times {
obj = allocate_an_object(name) // obj = ring, mempool, hash, lpm, ...
if (obj == NULL && lookup(name) == NULL)
ret
Internal lpm structures are not properly freed. Seen with the
lpm6 autotest.
Signed-off-by: Olivier Matz
---
lib/librte_lpm/rte_lpm.c | 3 +++
lib/librte_lpm/rte_lpm6.c | 1 +
2 files changed, 4 insertions(+)
diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
index dd62f9b..d28e9
This patch series adds link speed API changes to szedata2 driver
based on current dpdk-next-net/rel_16_04 tree.
Changes are split into commits as in v10 of patch series:
http://dpdk.org/ml/archives/dev/2016-March/035731.html
Matej Vido (4):
szedata2: use constants for link state
szedata2: ren
Use ETH_LINK_UP and ETH_LINK_DOWN constants.
Signed-off-by: Matej Vido
---
drivers/net/szedata2/rte_eth_szedata2.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/szedata2/rte_eth_szedata2.c
b/drivers/net/szedata2/rte_eth_szedata2.c
index 81c806e..c65067e 100644
The speed numbers ETH_LINK_SPEED_ are renamed ETH_SPEED_NUM_.
Signed-off-by: Matej Vido
---
drivers/net/szedata2/rte_eth_szedata2.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/szedata2/rte_eth_szedata2.c
b/drivers/net/szedata2/rte_eth_szedata2.c
index
This patch sets value of flag link_autoneg in struct rte_eth_link
to ETH_LINK_SPEED_FIXED.
Signed-off-by: Matej Vido
---
drivers/net/szedata2/rte_eth_szedata2.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/szedata2/rte_eth_szedata2.c
b/drivers/net/szedata2/rte_eth_szedata2.
Temporary 10G constant is replaced with 100G constant.
Item speed_capa from struct rte_eth_dev_info is set with 100G flag.
Signed-off-by: Matej Vido
---
drivers/net/szedata2/rte_eth_szedata2.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/szedata2/rte_eth_szed
Thanks for the series completing the ethdev rework with the same splitting.
2016-03-15 14:12, Matej Vido:
> Temporary 10G constant is replaced with 100G constant.
> Item speed_capa from struct rte_eth_dev_info is set with 100G flag.
[...]
> @@ -1161,7 +1162,7 @@ eth_link_update(struct rte_eth_dev
D?a 15.03.2016 o 14:41 Thomas Monjalon nap?sal(a):
> Thanks for the series completing the ethdev rework with the same splitting.
>
> 2016-03-15 14:12, Matej Vido:
>> Temporary 10G constant is replaced with 100G constant.
>> Item speed_capa from struct rte_eth_dev_info is set with 100G flag.
> [..
D?a 15.03.2016 o 14:41 Thomas Monjalon nap?sal(a):
> Thanks for the series completing the ethdev rework with the same splitting.
>
> 2016-03-15 14:12, Matej Vido:
>> Temporary 10G constant is replaced with 100G constant.
>> Item speed_capa from struct rte_eth_dev_info is set with 100G flag.
> [..
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Kulasek, TomaszX
> Sent: Friday, March 11, 2016 18:49
> To: Thomas Monjalon ; Maciej Czekaj
>
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] examples/l3fwd: em path performance fix
>
>
>
> > ---
v3:
Additional features for Amazon ENA:
* Low Latenycy Queue (LLQ) for Tx
* RSS
v4:
* Improved doc
* Improved style according to checkpatch script
* Fixed build problems on: i686, clang, +shared, +debug
v5:
* Removed 'cvos' environment code from ena Makefile
* Driver symbol version fixed to DPDK_16
Signed-off-by: Alexander Matushevsky
Signed-off-by: Jan Medala
Signed-off-by: Jakub Palider
---
MAINTAINERS | 8 ++
doc/guides/nics/ena.rst | 251 +++
doc/guides/nics/index.rst| 1 +
doc/guides/nics/overview.rst | 116 +++
Low level common abstraction for ENA device communication.
Signed-off-by: Netanel Belgazal
Signed-off-by: Jan Medala
Signed-off-by: Jakub Palider
---
drivers/net/ena/base/ena_com.c | 2809 +++
drivers/net/ena/base/ena_com.h | 1052 +
This is a PMD for the Amazon ethernet ENA family.
The driver operates variety of ENA adapters through feature negotiation
with the adapter and upgradable commands set.
ENA driver handles PCI Physical and Virtual ENA functions.
Signed-off-by: Evgeny Schemeilin
Signed-off-by: Jan Medala
Signed-off
Implementation of platform specific code for ENA communication layer.
Signed-off-by: Evgeny Schemeilin
Signed-off-by: Jan Medala
Signed-off-by: Jakub Palider
---
drivers/net/ena/base/ena_plat_dpdk.h | 217 +++
1 file changed, 217 insertions(+)
create mode 10064
2016-03-15 14:31, Kulasek, TomaszX:
> From: Kulasek, TomaszX
> > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > There is an error:
> > > examples/l3fwd/l3fwd_em_hlm_sse.h:72:38: error:
> > > incompatible type for argument 2 of ?_mm_and_si128?
> >
> > It's caused by
> >
> > co
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Tuesday, March 15, 2016 15:50
> To: Kulasek, TomaszX ; Maciej Czekaj
>
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] examples/l3fwd: em path performance fix
>
> 2016-03-15 14:31, Kula
Issuing a zero objects dequeue with a single consumer has no effect.
Doing so with multiple consumers, can get more than one thread to succeed
the compare-and-set operation and observe starvation or even deadlock in
the while loop that checks for preceding dequeues. The problematic piece
of code w
Od: Kulasek, TomaszX
Wys?ane: 15 marca 2016 17:06
Do: Thomas Monjalon; Czekaj, Maciej
DW: dev at dpdk.org
Temat: RE: [dpdk-dev] [PATCH v3] examples/l3fwd: em path performance fix
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalo
From: Maciej Czekaj
v2:
* Fixed compilation issue with HASH_MULTI_LOOKUP
Maciej Czekaj (1):
l3fwd: Fix compilation & enable exact match mode on ARM.
examples/l3fwd/l3fwd.h| 4 ++-
examples/l3fwd/l3fwd_em.c | 72 ---
examples/l3fwd/l3f
From: Maciej Czekaj
Enable NEON support in exact match mode.
l3fwd example did not compile on ARM due to SSE2 instrincics used
in generic part.
Some instrinsins were used to initialize data structures and those were
replaced by ordinary structure initalization.
All SSE2 intrinsics used in forward
2016-01-12 18:08, Yong Wang:
> + /* Drop non-TSO packet that is excessively fragmented */
> + if (unlikely(!tso && count > VMXNET3_MAX_TXD_PER_PKT)) {
> + PMD_TX_LOG(ERROR, "Non-TSO packet cannot occupy more
> than %d tx "
> +
2016-03-04 13:09, John Daley:
> +#ifdef RTE_NEXT_ABI
> + pkt_err_flags |= PKT_RX_MAC_ERR;
> +#else
> + pkt_err_flags |= PKT_EXT_RX_PKT_ERROR;
> +#endif
> + }
> +
> + /* Check for bad FCS. MAC error isn't quite, but no other choice */
> + if (!enic_cq_rx
Hi Maciej,
2016-03-15 21:05, Maciej.Czekaj at caviumnetworks.com:
> v2:
> * Fixed compilation issue with HASH_MULTI_LOOKUP
2 comments:
- your patch v1 is already applied, so now we need a standalone fix
- you do not need to send a cover letter for an unique patch
Thanks
2016-03-15 14:50, Matej Vido:
>
> D?a 15.03.2016 o 14:41 Thomas Monjalon nap?sal(a):
> > Thanks for the series completing the ethdev rework with the same splitting.
> >
> > 2016-03-15 14:12, Matej Vido:
> >> Temporary 10G constant is replaced with 100G constant.
> >> Item speed_capa from struct rt
Od: Thomas Monjalon
Wys?ane: 15 marca 2016 21:49
Do: Czekaj, Maciej
DW: dev at dpdk.org; tomaszx.kulasek at intel.com
Temat: Re: [PATCH v2] l3fwd: Fix compilation & enable exact match mode on ARM.
Hi Maciej,
2016-03-15 21:05, Maciej.Czekaj at caviumnetw
66 matches
Mail list logo
