Hi Jerin,
> -Original Message-
> From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> Sent: Tuesday, June 21, 2016 10:29 PM
> To: Ananyev, Konstantin
> Cc: Lu, Wenzhuo; Stephen Hemminger; dev at dpdk.org; Richardson, Bruce; Chen,
> Jing D; Liang, Cunming; Wu, Jingjing; Zhang, Hel
On Wed, Jun 22, 2016 at 01:35:37AM +, Lu, Wenzhuo wrote:
> Hi Jerin,
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> > Sent: Tuesday, June 21, 2016 10:29 PM
> > To: Ananyev, Konstantin
> > Cc: Lu, Wenzhuo; Stephen Hemminger; dev at dpdk.org;
In current i40e codebase, if single VLAN header is added in a packet,
it's treated as inner VLAN. Generally, a single VLAN header is
treated as the outer VLAN header. So change corresponding register
for single VLAN.
Fixes: 19b16e2f6442 ("ethdev: add vlan type when setting ether type")
Signed-off
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Mahdi Moradmand
> Badie
> Sent: Wednesday, June 22, 2016 5:21 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] Assembly code
>
> Dear All,
>
> I used the default format of Makefile (as follow) which is availabl
On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote:
> Hi Jerin,
Hi Thomas,
>
> I wanted to push this patch which is now a dependency of ThunderX
> but I do not fully understand it.
>
> 2016-03-31 02:21, Jerin Jacob:
> > - added VXLAN, GENEVE and NVGRE tunnel flow types
> > - added
Hi Jerin,
> -Original Message-
> From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> Sent: Wednesday, June 22, 2016 10:38 AM
> To: Lu, Wenzhuo
> Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson,
> Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang, H
On Wed, Jun 22, 2016 at 03:32:16AM +, Lu, Wenzhuo wrote:
> Hi Jerin,
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> > Sent: Wednesday, June 22, 2016 10:38 AM
> > To: Lu, Wenzhuo
> > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org
> -Original Message-
> From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> Sent: Wednesday, June 22, 2016 12:15 PM
> To: Lu, Wenzhuo
> Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson,
> Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang, Helin;
> t
On Wed, Jun 22, 2016 at 05:05:14AM +, Lu, Wenzhuo wrote:
>
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> > Sent: Wednesday, June 22, 2016 12:15 PM
> > To: Lu, Wenzhuo
> > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richard
hi,
i just looked at the CID: 127350 which raises a STRING_OVERFLOW bug
for pdump_prepare_client_request(...)
callers of pdump_prepare_client_request(...) pass 'device' parameter which
is always of DEVICE_ID_SIZE (64) bytes long. hence it is not possible to
overflow pdump_request.data.en_v1.devic
Hi Jerin,
> -Original Message-
> From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> Sent: Wednesday, June 22, 2016 2:10 PM
> To: Lu, Wenzhuo
> Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson,
> Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang, H
2016-06-22 09:00, Jerin Jacob:
> On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote:
> > Hi Jerin,
>
> Hi Thomas,
>
> >
> > I wanted to push this patch which is now a dependency of ThunderX
> > but I do not fully understand it.
> >
> > 2016-03-31 02:21, Jerin Jacob:
> > > - added V
> if (!strcmp(key, PDUMP_RX_DEV_ARG)) {
> - strncpy(pt->rx_dev, value, strlen(value));
> + strncpy(pt->rx_dev, value, sizeof(pt->rx_dev)-1);
I guess size-1 is to give room for terminating null byte, but for this
case is it guarantied that pt->rx_dev last byte is NULL?
On 2016-06-21 15:11, Ferruh Yigit wrote:
> On 6/20/2016 5:19 PM, Stephen Hemminger wrote:
>> On Mon, 20 Jun 2016 12:44:35 +0200
>> Simon Kagstrom wrote:
>>
>>> I.e., avoid dump messages with double 0x0x, e.g.,
>>>
>>> dump mbuf at 0x0x7fac7b17c800, phys=17b17c880, buf_len=2176
>>> pkt_len=20
On Wed, Jun 22, 2016 at 08:43:52AM +0200, Thomas Monjalon wrote:
> 2016-06-22 09:00, Jerin Jacob:
> > On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote:
> > > Hi Jerin,
> >
> > Hi Thomas,
> >
> > >
> > > I wanted to push this patch which is now a dependency of ThunderX
> > > but I
On Tue, Jun 21, 2016 at 05:42:42PM +0100, Ferruh Yigit wrote:
> On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote:
> > The intent is to replace the remaining compile-time options and environment
> > variables with a common mean of runtime configuration. This commit only
> > adds the kvargs handling code
2016-06-22 12:45, Jerin Jacob:
> On Wed, Jun 22, 2016 at 08:43:52AM +0200, Thomas Monjalon wrote:
> > 2016-06-22 09:00, Jerin Jacob:
> > > On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote:
> > > > 2016-03-31 02:21, Jerin Jacob:
> > > > > +#define RTE_ETH_FLOW_PORT 18
>
2016-06-19 13:05, David Hunt:
> v15 changes:
>
> * Changed rte_mempool_ops_get() to rte_mempool_get_ops()
I don't find this change in the patch.
But I wonder wether it is really needed.
On Wed, Jun 22, 2016 at 06:42:43AM +, Lu, Wenzhuo wrote:
> Hi Jerin,
>
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> > Sent: Wednesday, June 22, 2016 2:10 PM
> > To: Lu, Wenzhuo
> > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.o
Hi Ferruh,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, June 21, 2016 5:56 PM
> To: Pattan, Reshma ; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 1/3] pdump: check getenv return value
>
> On 6/21/2016 4:18 PM, Reshma Pattan wrote:
> > dir = client_socket_dir
2016-06-22 09:56, Thomas Monjalon:
> 2016-06-19 13:05, David Hunt:
> > v15 changes:
> >
> > * Changed rte_mempool_ops_get() to rte_mempool_get_ops()
>
> I don't find this change in the patch.
> But I wonder wether it is really needed.
If we assume that rte_mempool_ops_* are wrappers on top of h
On 17 June 2016 at 18:30, Thomas Monjalon wrote:
> 2016-05-19 17:56, Thomas Monjalon:
>> 2016-05-19 21:48, Jianbo Liu:
>> > On 13 May 2016 at 23:49, Thomas Monjalon
>> > wrote:
>> > > 2016-05-10 14:01, Jianbo Liu:
>> > >> Other APP may call rte_memcpy by function pointer,
>> > >> so change it to
2016-06-22 13:29, Jerin Jacob:
> Thomas,
> As a librte_ether maintainer any comments on this?
+1 for adding details and make sure naming is good.
I don't really need to comment here because I have already done this
comment earlier:
http://dpdk.org/ml/archives/dev/2016-June/041845.html
Than
Note that if we remove rte_eth_dev_get_reg_length() then it will break
all of the drivers that implement it. Shall I remove it all leave it and
modify only ethtool to use rte_eth_dev_get_regs() to get reg size? In
the end the drivers will have to implement the part of setting the size
in reg_in
On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote:
> On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote:
> > Enhance mlx5 with a data path that bypasses Verbs.
> >
> > The first half of this patchset removes support for functionality completely
> > rewritten in the second half (scatter/gather
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, June 22, 2016 4:17 PM
> To: Jerin Jacob
> Cc: Lu, Wenzhuo; Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org;
> Richardson, Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingj
2016-06-22 10:19, Zyta Szpak:
> Note that if we remove rte_eth_dev_get_reg_length() then it will break
> all of the drivers that implement it. Shall I remove it all leave it and
> modify only ethtool to use rte_eth_dev_get_regs() to get reg size? In
> the end the drivers will have to implement t
>-Original Message-
>From: Dumitrescu, Cristian
>Sent: Tuesday, June 21, 2016 7:44 PM
>To: Mrzyglod, DanielX T ; Singh, Jasvinder
>
>Cc: dev at dpdk.org
>Subject: RE: [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8
>
>
>
>> -Original Message-
>> From: Mrzyglod, Daniel
>From: Mrzyglod, DanielX T
>Sent: Tuesday, June 21, 2016 11:36 AM
>To: Singh, Jasvinder ; Dumitrescu, Cristian
>
>Cc: dev at dpdk.org; Mrzyglod, DanielX T
>Subject: [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8
>
>This patch fixes a maybe-uninitialized warning when compiling DPDK wi
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jasvinder Singh
> Sent: Thursday, June 16, 2016 10:05 AM
> To: dev at dpdk.org
> Cc: Dumitrescu, Cristian
> Subject: [dpdk-dev] [PATCH] ip_pipeline: fix parsing error in TM port section
>
> Replace APP_PARAM_
Enhance mlx5 with a data path that bypasses Verbs.
The first half of this patchset removes support for functionality completely
rewritten in the second half (scatter/gather, inline send), while the data
path is refactored without Verbs.
The PMD remains usable during the transition.
This patchset
Fixes: 701c8d80c820 ("pci: support class id probing")
Signed-off-by: Nelio Laranjeiro
---
drivers/crypto/qat/rte_qat_cryptodev.c | 5 +
drivers/net/mlx4/mlx4.c| 18 ++
drivers/net/mlx5/mlx5.c| 24
drivers/net/nfp/nfp_n
Except for the first time when memory registration occurs, the lkey is
always cached. Since memory registration is slow and performs system calls,
performance can be improved by moving that code to its own function outside
of the data path so only the lookup code is left in the original inlined
fun
This is done in preparation of bypassing Verbs entirely for the data path
as a performance improvement. TX gather cannot be maintained during the
transition and will be reimplemented later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_ethdev.c | 2
* Original patch series is from David Marchand [1], [2].
* Cover letter text has been modified to make it author agnostic
David created the original patchset based on the discussions on list [3].
Being a large piece of work, this patchset introduces first level of changes
for generalizing the driv
This is done in preparation of bypassing Verbs entirely for the data path
as a performance improvement. RX scatter cannot be maintained during the
transition and will be reimplemented later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_ethdev.c | 31
There is no scatter/gather support anymore, CONFIG_RTE_LIBRTE_MLX5_SGE_WR_N
has no purpose and can be removed.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
config/common_base | 1 -
doc/guides/nics/mlx5.rst | 7 ---
drivers/net/mlx5/Makefile| 4
Inline TX will be fully managed by the PMD after Verbs is bypassed in the
data path. Remove the current code until then.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
config/common_base | 1 -
doc/guides/nics/mlx5.rst | 10 --
drivers/net/mlx5/Makefile
To keep the data path as efficient as possible, move fields only useful to
the control path into new structure rxq_ctrl.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.c | 6 +-
drivers/net/mlx5/mlx5_fdir.c | 8 +-
drivers/net/mlx5/mlx5_rxq.c
To keep the data path as efficient as possible, move fields only useful to
the control path into new structure txq_ctrl.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.c| 21 +++--
drivers/net/mlx5/mlx5_ethdev.c | 28 +++---
drivers/net/mlx5/
The latest version of Mellanox OFED exposes hardware definitions necessary
to implement data path operation bypassing Verbs. Update the minimum
version requirement to MLNX_OFED >= 3.3 and clean up compatibility checks
for previous releases.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Ma
These structures and macros extend those exposed by libmlx5 (in mlx5_hw.h)
to let the PMD manage work queue and completion queue elements directly.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_prm.h | 163
These lists can be initialized once and for all at build time.
With this, those lists are only manipulated in a common place
(and we could even make them private).
A nice side effect is that pci drivers can now register in constructors.
Signed-off-by: David Marchand
Reviewed-by: Jan Viktorin
Si
These wrappers are meant to prevent code duplication later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.h| 2 ++
drivers/net/mlx5/mlx5_ethdev.c | 34 --
drivers/net/mlx5/mlx5_txq.c| 2 +-
3 files changed
The intent is to replace the remaining compile-time options and environment
variables with a common mean of runtime configuration. This commit only
adds the kvargs handling code, subsequent commits will update the rest.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers
Bypass Verbs to improve RX performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Yaacov Hazan
Signed-off-by: Adrien Mazarguil
Signed-off-by: Vasily Philipov
---
drivers/net/mlx5/mlx5_ethdev.c | 4 +-
drivers/net/mlx5/mlx5_fdir.c | 2 +-
drivers/net/mlx5/mlx5_rxq.c| 303 +++
Bypass Verbs to improve Tx performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Yaacov Hazan
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/Makefile | 5 -
drivers/net/mlx5/mlx5_ethdev.c | 10 +-
drivers/net/mlx5/mlx5_mr.c | 4 +-
drivers/net/mlx5/mlx5_rxtx.c | 359
Mini (compressed) CQEs are returned by the NIC when PCI back pressure is
detected, in which case the first CQE64 contains common packet information
followed by a number of CQE8 providing the rest, followed by a matching
number of empty CQE64 entries to be used by software for decompression.
Before
This information is not used and just adds noise.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_cryptodev/rte_cryptodev.c | 8 +++-
lib/librte_cryptodev/rte_cryptodev.h | 2 --
lib/librte_cryptodev/rte_cryptodev_pmd.h | 3 +--
3 files changed, 4 insertio
From: Adrien Mazarguil
Replacing the variable countdown (which depends on the number of
descriptors) with a fixed relative threshold known at compile time improves
performance by reducing the TX queue structure footprint and the amount of
code to manage completions during a burst.
Completions ar
Pure coding style, but it might make it easier later if we want to move
fields in rte_cryptodev_driver and eth_driver structures.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
drivers/crypto/qat/rte_qat_cryptodev.c | 2 +-
drivers/net/ena/ena_ethdev.c | 2 +-
drivers
From: Yaacov Hazan
Implement send inline feature which copies packet data directly into WQEs
for improved latency. The maximum packet size and the minimum number of Tx
queues to qualify for inline send are user-configurable.
This feature is effective when HW causes a performance bottleneck.
Sig
rte_eal_dev_init is declared in both eal_private.h and rte_dev.h since its
introduction.
This function has been exported in ABI, so remove it from eal_private.h
Fixes: e57f20e05177 ("eal: make vdev init path generic for both virtual and pci
devices")
Signed-off-by: David Marchand
Signed-off-by:
This feature enables the TX burst function to emit up to 5 packets using
only two WQEs on devices that support it. Saves PCI bandwidth and improves
performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
Signed-off-by: Olga Shern
---
doc/guides/nics/mlx5.rst | 10 ++
From: Adrien Mazarguil
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_txq.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 4f17fb0..bae9f3d 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_t
Introduce a RTE_INIT macro used to mark an init function as a constructor.
Current eal macros have been converted to use this (no functional impact).
RTE_EAL_PCI_REGISTER is added as a helper for pci drivers.
Suggested-by: Jan Viktorin
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
From: Adrien Mazarguil
The space necessary to store segmented packets cannot be known in advance
and must be verified for each of them.
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_rxtx.c | 136 ++-
1 file changed, 70 insertions(+), 66 delet
Preparing for getting rid of rte_cryptodev_driver, here are two wrappers
that can be used by pci drivers that assume a 1 to 1 association between
pci resource and upper interface.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_cryptodev/rte_cryptodev.c | 16
Simplify crypto and ethdev pci drivers init by using newly introduced
init macros and helpers.
Those drivers then don't need to register as "rte_driver"s anymore.
virtio and mlx* drivers use the general purpose RTE_INIT macro, as they both
need some special stuff to be done before registering a pc
From: Adrien Mazarguil
The primary purpose of rxq_rehash() function is to stop and restart
reception on a queue after re-posting buffers. This may fail if the array
that temporarily stores existing buffers for reuse cannot be allocated.
Update rxq_rehash() to work on the target queue directly (n
From: Adrien Mazarguil
This commit brings back Rx scatter and related support by the MTU update
function. The maximum number of segments per packet is not a fixed value
anymore (previously MLX5_PMD_SGE_WR_N, set to 4 by default) as it caused
performance issues when fewer segments were actually ne
Now that all pdev are pci drivers, we don't need to register ethdev drivers
through a dedicated channel.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_ether/rte_ethdev.c | 22 --
lib/librte_ether/rte_ethdev.h | 12
Now that all pdev are pci drivers, we don't need to register crypto drivers
through a dedicated channel.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_cryptodev/rte_cryptodev.c | 22 ---
lib/librte_cryptodev/rte_cryptodev_pmd.h | 30 -
Now that virtio pci driver is initialized in a constructor, iopl() stuff
happens early enough so that interrupt thread can be created right after
plugin loading.
This way, chelsio driver should be happy again [1].
[1] http://dpdk.org/ml/archives/dev/2015-November/028289.html
Signed-off-by: David
From: Adrien Mazarguil
Since commit "mlx5: resurrect Tx gather support", older GCC versions (such
as 4.8.5) may complain about the following:
mlx5_rxtx.c: In function `mlx5_tx_burst':
mlx5_rxtx.c:705:25: error: `wqe' may be used uninitialized in this
function [-Werror=maybe-uninitialized]
Preparing for getting rid of eth_drv, here are two wrappers that can be
used by pci drivers that assume a 1 to 1 association between pci resource and
upper interface.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_ether/rte_ethdev.c | 14 +++---
lib/
From: Adrien Mazarguil
Toggling RX checksum offloads is already done at initialization time. This
code does not belong in rxq_rehash().
Signed-off-by: Adrien Mazarguil
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5_rxq.c | 10 --
1 file changed, 10 deletions(-)
diff --git
eal is a better place than crypto / ethdev for naming resources.
Add a helper in eal and make use of it in crypto / ethdev.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_cryptodev/rte_cryptodev.c| 27 ---
lib/librte_eal/common/include/rte
This helper updates a pci device object with latest information it can
find.
It will be used mainly for hotplug code.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_eal/bsdapp/eal/eal_pci.c | 49 +
lib/librte_eal/common/eal_common_
No need to scan all devices, we only need to update the device being
attached.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_eal/common/eal_common_pci.c | 11 ---
lib/librte_ether/rte_ethdev.c | 3 ---
2 files changed, 8 insertions(+), 6 deletions(
Remove bus logic from ethdev hotplug by using eal for this.
Current api is preserved:
- the last port that has been created is tracked to return it to the
application when attaching,
- the internal device name is reused when detaching.
We can not get rid of ethdev hotplug yet since we still nee
From: Adrien Mazarguil
Compared to its previous incarnation, the software limit on the number of
mbuf segments is no more (previously MLX5_PMD_SGE_WR_N, set to 4 by
default) hence no need for linearization code and related buffers that
permanently consumed a non negligible amount of memory to han
hotplug which deals with resources should come from the layer that already
handles them, i.e. eal.
For both attach and detach operations, 'name' is used to select the bus
that will handle the request.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
lib/librte_eal/bsdapp/eal/rte
Now that hotplug has been moved to eal, there is no reason to keep the device
type in this layer.
Signed-off-by: David Marchand
Signed-off-by: Shreyansh Jain
---
app/test/virtual_pmd.c| 2 +-
drivers/net/af_packet/rte_eth_af_packet.c | 2 +-
drivers/net/bonding/rte_eth_bon
2016-06-22 08:25, Lu, Wenzhuo:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2016-06-22 13:29, Jerin Jacob:
> > > Thomas,
> > > As a librte_ether maintainer any comments on this?
> >
> > +1 for adding details and make sure naming is good.
> > I don't really need to comment here
On Wed, Jun 22, 2016 at 10:20:54AM +0200, Adrien Mazarguil wrote:
> On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote:
> > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote:
> > > Enhance mlx5 with a data path that bypasses Verbs.
> > >
> > > The first half of this patchset removes support f
On Wed, Jun 22, 2016 at 12:16:27PM +0530, Anupam Kapoor wrote:
> > if (!strcmp(key, PDUMP_RX_DEV_ARG)) {
> > - strncpy(pt->rx_dev, value, strlen(value));
> > + strncpy(pt->rx_dev, value, sizeof(pt->rx_dev)-1);
>
> I guess size-1 is to give room for terminating null by
Hi,
> -Original Message-
> From: Richardson, Bruce
> Sent: Wednesday, June 22, 2016 10:22 AM
> To: Anupam Kapoor
> Cc: Yigit, Ferruh ; Pattan, Reshma
> ; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 3/3] app/pdump: fix string overflow
>
> On Wed, Jun 22, 2016 at 12:16:27PM +0530, Anu
Here's the latest version of the Mempool Handler patch set.
It's re-based on top of the latest head as of 20/6/2016, including
Olivier's 35-part patch series on mempool re-org [1]
[1] http://dpdk.org/ml/archives/dev/2016-May/039229.html
v16 changes:
* Changed rte_mempool_ops_get() to rte_mempoo
Until now, the objects stored in a mempool were internally stored in a
ring. This patch introduces the possibility to register external handlers
replacing the ring.
The default behavior remains unchanged, but calling the new function
rte_mempool_set_ops_byname() right after rte_mempool_create_empt
Create a minimal custom mempool handler and check that it
passes basic mempool autotests.
Signed-off-by: Olivier Matz
Signed-off-by: David Hunt
Reviewed-by: Jan Viktorin
Acked-by: Shreyansh Jain
Acked-by: Olivier Matz
---
app/test/test_mempool.c | 122
By default, the mempool ops used for mbuf allocations is a multi
producer and multi consumer ring. We could imagine a target (maybe some
network processors?) that provides an hardware-assisted pool
mechanism. In this case, the default configuration for this architecture
would contain a different va
On Wed, Jun 22, 2016 at 10:19:14AM +0100, Bruce Richardson wrote:
> On Wed, Jun 22, 2016 at 10:20:54AM +0200, Adrien Mazarguil wrote:
> > On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote:
> > > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote:
> > > > Enhance mlx5 with a data path that bypa
On Wed, Jun 22, 2016 at 11:18:21AM +0200, Thomas Monjalon wrote:
> 2016-06-22 08:25, Lu, Wenzhuo:
> > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > 2016-06-22 13:29, Jerin Jacob:
> > > > Thomas,
> > > > As a librte_ether maintainer any comments on this?
> > >
> > > +1 for addin
Commit 9fc37d1c071c is missing a conditional in the dependencies,
causing builds to fail when KNI is not enabled:
== Build lib/librte_port
LD librte_port.so.3
/usr/bin/ld: cannot find -lrte_kni
collect2: error: ld returned 1 exit status
Fixes: 9fc37d1c071c ("port: support KNI")
2016-06-22 14:34, Panu Matilainen:
> --- a/lib/librte_port/Makefile
> +++ b/lib/librte_port/Makefile
> @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool
> DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ether
> DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ip_frag
> DEP
Hi Thomas,
On 06/22/2016 01:49 PM, Thomas Monjalon wrote:
> 2016-06-22 14:34, Panu Matilainen:
>> --- a/lib/librte_port/Makefile
>> +++ b/lib/librte_port/Makefile
>> @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool
>> DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ether
2016-06-22 13:57, Olivier Matz:
> Hi Thomas,
>
> On 06/22/2016 01:49 PM, Thomas Monjalon wrote:
> > 2016-06-22 14:34, Panu Matilainen:
> >> --- a/lib/librte_port/Makefile
> >> +++ b/lib/librte_port/Makefile
> >> @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool
> >> DEPDIR
All,
I am trying to debug a problem:
I am running testpmd in a VM.
The stack trace is below.
Running uio_pci_generic. kvm-qemu 2.5.3, Centos 7
CentOS Linux release 7.2.1511 (Core)
Problem can be reproduced using either igb_uio or virtio_pci kernel drivers.
Currently running 3.18.35 kernel bu
Hi Cristian, Chao,
I have encountered a compilation failure on IBM Power8 when compiling
master branch with EXTRA_CFLAGS='-O0 -g':
/root/nl/dpdk.org/build/lib/librte_meter.a(rte_meter.o): In function
`rte_meter_get_tb_params':
/root/nl/dpdk.org/lib/librte_meter/rte_meter.c:57: undefined refe
2016-06-22 17:49, Gadre Nayan:
> I need to get the interface speed though standard IOCTL call:
[...]
>
> However, for 10G interface I do not read a correct speed, since it may
> not be supported.
Yes
> Out 1G cards are I350 and 10G card is I40.
[...]
> There is no support for 1base. So to ge
v1..v2
- Added cover letter
- Corrected typo in RET_ETH_FLOW_VXLAN name
- Updated test-pmd application to access newly defined RSS offload flags
v2..v3
-testpmd document update(Suggested by John and Pablo)
v3..v4
- Added doxgen comments for new FLOW types(Suggested by Thomas)
Jerin Jacob (2):
- added VXLAN, GENEVE and NVGRE tunnel flow types
- added PORT flow type for accounting physical/virtual
port or channel number in flow creation
Signed-off-by: Jerin Jacob
---
app/test-pmd/cmdline.c | 18 +++---
app/test-pmd/config.c | 9 ++
Signed-off-by: Jerin Jacob
---
lib/librte_ether/rte_ethdev.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 1579cb0..6cf4c58 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -477,6 +477,7 @@
On Wed, Jun 22, 2016 at 02:36:28PM +0530, Shreyansh Jain wrote:
> Now that all pdev are pci drivers, we don't need to register crypto drivers
> through a dedicated channel.
>
> Signed-off-by: David Marchand
> Signed-off-by: Shreyansh Jain
> ---
> lib/librte_cryptodev/rte_cryptodev.c |
On Wed, Jun 22, 2016 at 02:36:29PM +0530, Shreyansh Jain wrote:
> Now that all pdev are pci drivers, we don't need to register ethdev drivers
> through a dedicated channel.
>
> Signed-off-by: David Marchand
> Signed-off-by: Shreyansh Jain
> ---
> lib/librte_ether/rte_ethdev.c | 22
2016-06-22 14:27, Thomas F Herbert:
> Program received signal SIGSEGV, Segmentation fault.
> 0x00616172 in vtpci_init (dev=0xbfb0f0, hw=0x7fffd57d0700,
> dev_flags=0x7fffdf9c)
> at /home/heat-admin/dpdk/drivers/net/virtio/virtio_pci.c:722
> 722dev->devargs->typ
On Wednesday 22 June 2016 06:57 PM, Neil Horman wrote:
> On Wed, Jun 22, 2016 at 02:36:28PM +0530, Shreyansh Jain wrote:
>> Now that all pdev are pci drivers, we don't need to register crypto drivers
>> through a dedicated channel.
>>
>> Signed-off-by: David Marchand
>> Signed-off-by: Shreyansh Ja
On Wednesday 22 June 2016 06:58 PM, Neil Horman wrote:
> On Wed, Jun 22, 2016 at 02:36:29PM +0530, Shreyansh Jain wrote:
>> Now that all pdev are pci drivers, we don't need to register ethdev drivers
>> through a dedicated channel.
>>
>> Signed-off-by: David Marchand
>> Signed-off-by: Shreyansh Ja
2016-06-22 09:27, Neil Horman:
> > +++ b/lib/librte_cryptodev/rte_cryptodev_version.map
> > - rte_cryptodev_pmd_driver_register;
> NAK, you can't just remove exported symbols without going through the
> deprecation process. Better still would be to only expose it for DPDK_16.04
> and
> hide it
1 - 100 of 116 matches
Mail list logo
