Hi Lei,
It's on my todo list, I'll check this as soon as possible.
Olivier
On Thu, Feb 01, 2018 at 03:14:15AM +, Yao, Lei A wrote:
> Hi, Olivier
>
> This is Lei from DPDK validation team in Intel. During our DPDK 18.02-rc1
> test,
> I find the following patch will cause one serious issue
Wednesday, January 31, 2018 5:33 PM, Adrien Mazarguil:
> Resources allocated for drop flow rules are not freed properly. This causes a
> memory leak and triggers an assertion failure on a reference counter when
> compiled in debug mode.
>
> This issue can be reproduced with testpmd by entering the
On 01/31/2018 07:45 PM, Olivier Matz wrote:
On Tue, Jan 23, 2018 at 01:15:59PM +, Andrew Rybchenko wrote:
The callback allows to customize how objects are stored in the
memory chunk. Default implementation of the callback which simply
puts objects one by one is available.
Suggested-by: Oliv
On 01/31/2018 07:45 PM, Olivier Matz wrote:
On Tue, Jan 23, 2018 at 01:16:06PM +, Andrew Rybchenko wrote:
From: "Artem V. Andreev"
Callback to calculate required memory area size may require mempool
driver data to be already allocated and initialized.
Signed-off-by: Artem V. Andreev
Sign
On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
> On 02/01/2018 08:05 AM, santosh wrote:
>> On Wednesday 31 January 2018 10:15 PM, Olivier Matz wrote:
>>> On Tue, Jan 23, 2018 at 01:15:56PM +, Andrew Rybchenko wrote:
There is not specified dependency between rte_mempool_pop
> -Original Message-
> From: Zhao1, Wei
> Sent: Wednesday, January 31, 2018 8:47 AM
> To: dev@dpdk.org
> Cc: Mcnamara, John ; Lu, Wenzhuo
> ; Zhao1, Wei
> Subject: [PATCH v2] doc: add a user guidance document for igb
>
> This patch add a user guidance document specific for igb nic.
> By
Hi Jens,
On 01/29/2018 03:11 PM, Jens Freimann wrote:
From: Yuanhan Liu
Add code to set up packed queues when enabled.
Signed-off-by: Yuanhan Liu
Signed-off-by: Jens Freimann
---
lib/librte_vhost/vhost.c | 4
lib/librte_vhost/vhost.h | 1 +
lib/librte_vhost/vhost_user.c
On 02/01/2018 12:09 PM, santosh wrote:
On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
On 02/01/2018 08:05 AM, santosh wrote:
On Wednesday 31 January 2018 10:15 PM, Olivier Matz wrote:
On Tue, Jan 23, 2018 at 01:15:56PM +, Andrew Rybchenko wrote:
There is not specified depe
On 01/29/2018 03:11 PM, Jens Freimann wrote:
Add some helper functions to set/check descriptor flags
and toggle the used wrap counter.
Signed-off-by: Jens Freimann
---
lib/librte_vhost/virtio-1.1.h | 43 +++
1 file changed, 43 insertions(+)
diff --gi
> -Original Message-
> From: stable [mailto:stable-boun...@dpdk.org] On Behalf Of Kirill
> Rybalchenko
> Sent: Wednesday, January 31, 2018 11:15 AM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Rybalchenko, Kirill ;
> Chilikin, Andrey ; Xing, Beilei
> ; Wu, Jingjing
> Subject: [dpdk-stable]
On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
> On 02/01/2018 12:09 PM, santosh wrote:
>> On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
>>> On 02/01/2018 08:05 AM, santosh wrote:
On Wednesday 31 January 2018 10:15 PM, Olivier Matz wrote:
> On Tue, Jan 23,
The application may want to store private data along with the
rte_security that is transparent to the rte_security layer.
For e.g., If an eventdev based application is submitting a
rte_security_session operation and wants to indicate event information
required to construct a new event that will be
The application may want to store private data along with the
rte_crypto_op that is transparent to the rte_cryptodev layer.
For e.g., If an eventdev based application is submitting a
crypto session-less operation and wants to indicate event
information required to construct a new event that will be
The application may want to store private data along with the
rte_cryptodev that is transparent to the rte_cryptodev layer.
For e.g., If an eventdev based application is submitting a
rte_cryptodev_sym_session operation and wants to indicate event
information required to construct a new event that w
On 01/29/2018 03:11 PM, Jens Freimann wrote:
Implement code to dequeue and process descriptors from
the vring if VIRTIO_F_PACKED is enabled.
Check if descriptor was made available by driver by looking at
VIRTIO_F_DESC_AVAIL flag in descriptor. If so dequeue and set
the used flag VIRTIO_F_DESC_
Traffic manager provides an API for resuming
an arbitrary node in a hierarchy.
This commit adds support for calling this API
from testpmd.
Signed-off-by: Tomasz Duszynski
---
app/test-pmd/cmdline.c | 4 ++
app/test-pmd/cmdline_tm.c | 70 ++
Add new testpmd commands for invoking traffic manager suspend/resume API.
Tomasz Duszynski (2):
app/testpmd: add command to suspend a TM node
app/testpmd: add command to resume a TM node
app/test-pmd/cmdline.c | 8 ++
app/test-pmd/cmdline_tm.c | 140 +
Traffic manager provides an API for suspending
an arbitrary node in a hierarchy.
This commit adds support for calling this API from testpmd.
Signed-off-by: Tomasz Duszynski
---
app/test-pmd/cmdline.c | 4 ++
app/test-pmd/cmdline_tm.c | 70
On Thu, Feb 01, 2018 at 09:18:22AM +0800, Changpeng Liu wrote:
> For PCI prefetchable resources, Linux will create a
> write combined file as well, the library will try
> to map resourceX_wc file first, if the file does
> not exist, then it will map resourceX as usual.
>
> Signed-off-by: Changpeng
On 02/01/2018 12:30 PM, santosh wrote:
On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
On 02/01/2018 12:09 PM, santosh wrote:
On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
On 02/01/2018 08:05 AM, santosh wrote:
On Wednesday 31 January 2018 10:15 PM, Olivier Mat
Hi Andrew,
On Thursday 01 February 2018 11:48 AM, Jacob, Jerin wrote:
> The driver requires one and only one physically contiguous
> memory chunk for all objects.
>
> Signed-off-by: Andrew Rybchenko
> ---
> drivers/mempool/octeontx/rte_mempool_octeontx.c | 25
> +
> 1
Ensure that memzone count in eal mem config is incremented and
decremented whenever memzones are allocated and freed.
Signed-off-by: Anatoly Burakov
---
test/test/test_memzone.c | 20
1 file changed, 20 insertions(+)
diff --git a/test/test/test_memzone.c b/test/test/test_me
Currently, memzone autotest expects there to be no memzones
present by the time the test is run. Some hardware drivers
will allocate memzones for internal use during initialization,
resulting in tests failing due to unexpected memzones being
allocated before the test was run.
Fix this by making su
01/02/2018 05:43, Zhiyong Yang:
> The following error is reported when compiling 18.02-rc2 usng ICC,
> "transfer of control bypasses initialization of".
> The patch fixes the issue.
>
> Fixes: 1911c5edc6cd ("net/tap: fix eBPF RSS map key handling")
> Cc: sta...@dpdk.org
stable is not needed here
Fixes: a9bb0c44c775 ("doc: add rawdev library guide and doxygen page")
Cc: shreyansh.j...@nxp.com
'+' sign was missing from librawdev library which is added
in this release.
Signed-off-by: Shreyansh Jain
---
doc/guides/rel_notes/release_18_02.rst | 2 +-
1 file changed, 1 insertion(+), 1 deleti
On 01-Feb-18 12:12 AM, Thomas Monjalon wrote:
31/01/2018 16:29, Anatoly Burakov:
Ensure that memzone count in eal mem config is incremented and
decremented whenever memzones are allocated and freed.
Signed-off-by: Anatoly Burakov
Please report acks from previous version.
OK, will submit a
On 02/01/2018 12:59 PM, Bruce Richardson wrote:
On Thu, Feb 01, 2018 at 09:18:22AM +0800, Changpeng Liu wrote:
For PCI prefetchable resources, Linux will create a
write combined file as well, the library will try
to map resourceX_wc file first, if the file does
not exist, then it will map resour
On 31-Jan-18 9:51 PM, Ravi Kerur wrote:
Hi Anatoly,
Thanks. I am following wiki link below which uses vIOMMU with DPDK as a
use-case and instantiate VM as specified with Q35 chipset in Qemu.
https://wiki.qemu.org/Features/VT-d
Qemu-version is 2.11
Host kernel 4.9
Guest kernel 4.4
I can onl
On Thu, Feb 01, 2018 at 01:00:12PM +0300, Andrew Rybchenko wrote:
> On 02/01/2018 12:30 PM, santosh wrote:
> > On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
> > > On 02/01/2018 12:09 PM, santosh wrote:
> > > > On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
> > > > >
Ensure that memzone count in eal mem config is incremented and
decremented whenever memzones are allocated and freed.
Reviewed-by: Radoslaw Biernacki
Signed-off-by: Anatoly Burakov
---
Notes:
v4: added missing reviewed-by tag
test/test/test_memzone.c | 20
1 file cha
Currently, memzone autotest expects there to be no memzones
present by the time the test is run. Some hardware drivers
will allocate memzones for internal use during initialization,
resulting in tests failing due to unexpected memzones being
allocated before the test was run.
Fix this by making su
On Thursday 01 February 2018 03:30 PM, Andrew Rybchenko wrote:
> On 02/01/2018 12:30 PM, santosh wrote:
>> On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
>>> On 02/01/2018 12:09 PM, santosh wrote:
On Thursday 01 February 2018 12:24 PM, Andrew Rybchenko wrote:
> On 02/01/20
Ownership API returns a negative value, strerror expects a valid errno
value, thus positive.
CID 260401: Error handling issues (NEGATIVE_RETURNS)
"ret" is passed to a parameter that cannot be negative.
Fixes: dcd0c9c32b8d ("net/failsafe: use ownership mechanism for slaves")
Signed-off-by: Gaet
On Thu, Feb 01, 2018 at 10:35:18AM +0100, Maxime Coquelin wrote:
On 01/29/2018 03:11 PM, Jens Freimann wrote:
Implement code to dequeue and process descriptors from
the vring if VIRTIO_F_PACKED is enabled.
Check if descriptor was made available by driver by looking at
VIRTIO_F_DESC_AVAIL flag
On Thursday 01 February 2018 03:44 PM, Olivier Matz wrote:
> On Thu, Feb 01, 2018 at 01:00:12PM +0300, Andrew Rybchenko wrote:
>> On 02/01/2018 12:30 PM, santosh wrote:
>>> On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
On 02/01/2018 12:09 PM, santosh wrote:
> On Thursday
Needed if used with net/bonding
Signed-off-by: Radu Nicolau
---
v2: remove redundant memcpy
drivers/net/null/rte_eth_null.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/net/null/rte_eth_null.c
index 9385ffd..d003b28 100644
--- a/drivers/ne
Needed if used with net/bonding
Signed-off-by: Radu Nicolau
---
v2: remove redundant memcpy
drivers/net/null/rte_eth_null.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/net/null/rte_eth_null.c
index 9385ffd..d003b28 100644
--- a/drivers/ne
Needed if used with net/bonding
Signed-off-by: Radu Nicolau
---
v2: remove redundant memcpy
drivers/net/null/rte_eth_null.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/net/null/rte_eth_null.c
index 9385ffd..d003b28 100644
--- a/drivers/ne
Needed if used with net/bonding
Signed-off-by: Radu Nicolau
---
v2: remove redundant memcpy
test/test/virtual_pmd.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/test/test/virtual_pmd.c b/test/test/virtual_pmd.c
index 7a7adbb..2f5b31d 100644
--- a/test/test/virtual_p
Prevent failure in rte_eth_dev_default_mac_addr_set() that
resunts in bonding add slave failure.
Signed-off-by: Radu Nicolau
---
v2: update commit message
test/test/test_link_bonding_rssconf.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/test/test/test_link_bonding_rssconf.c
b/test
Ownership API returns a negative value, strerror expects a valid errno
value, thus positive.
Coverity issue: 260401
Fixes: dcd0c9c32b8d ("net/failsafe: use ownership mechanism for slaves")
Signed-off-by: Gaetan Rivet
---
v2: Fix coverity reference syntax in commit log.
drivers/net/failsafe/fa
Added hash support in lib compressdev. It's an incremental patch to
compression lib RFC v3 https://dpdk.org/dev/patchwork/patch/32331/
Changes from RFC v3:
- Added hash algo enumeration and associated capability stucture
and params in xform and rte_comp_op
- Rearranged rte_compresdev_capability
Prevent failure in rte_eth_dev_default_mac_addr_set() that
resunts in bonding add slave failure.
Fixes: aa7791ba8de0 ("net/bonding: fix setting slave MAC addresses")
Signed-off-by: Radu Nicolau
---
v3: update commit message
test/test/test_link_bonding_rssconf.c | 5 +
1 file changed, 5 ins
Hi Pablo/Fiona
Could you please provide your input on this RFC. Your feedback is awaited.
Thanks
Shally
-Original Message-
From: Verma, Shally
Sent: 23 January 2018 15:24
To: declan.dohe...@intel.com
Cc: dev@dpdk.org; Athreya, Narayana Prasad ;
Murthy, Nidadavolu ; Sahu, Sunila
; Gupt
Indeed, rx_offload_capa or tx_offload_capa in struct rte_eth_dev_info
includes not only per port offloading features but also per queue ones.
This patch make its meaning much clearer.
Fixes: ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes: cba7f53b717d ("ethdev: introduce Tx queue
Signed-off-by: Shahaf Shuler
---
doc/guides/rel_notes/release_18_02.rst | 27 +++
1 file changed, 27 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_02.rst
b/doc/guides/rel_notes/release_18_02.rst
index 689080bed..714a24388 100644
--- a/doc/guides/rel_notes/re
Signed-off-by: Shahaf Shuler
---
doc/guides/nics/mlx5.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index a9e4bf51a..b2376363b 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -131,7 +131,7 @@
DPDK i40e PMD will modify some global registers during initialization
and post initialization, there'll be impact during use of 700 series
Ethernet Adapter with both Linux kernel and DPDK PMD.
This patchset adds log for global configuration and adds device args
to disable global configuration.
v3
Add warnings when writing global registers.
Signed-off-by: Beilei Xing
---
doc/guides/nics/i40e.rst | 12
drivers/net/i40e/i40e_ethdev.c | 25
drivers/net/i40e/i40e_ethdev.h | 43 ++
drivers/net/i40e/i40e_fdir.c
This patch provides the option to disable writing some global registers
in PMD, in order to avoid affecting other drivers, when multiple drivers
run on the same NIC and control different physical ports. Because there
are few global resources shared among different physical ports.
Fixes: ec246eeb5d
Add debug logs when writing global registers.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 153 ++---
drivers/net/i40e/i40e_ethdev.h | 11 +++
2 files changed, 123 insertions(+), 41 deletions(-)
diff --git a/drivers/net/i40e/i40e_ethdev.c
On Wed, Jan 31, 2018 at 05:09:05PM +, Bruce Richardson wrote:
> The AVX2 code path includes files from the ethdev, hash and kvargs libs.
> These are not listed as dependencies in the case where AVX2 is not in
> the default instruction set for the build e.g. machine=nehalem. This
> leads to comp
> >[Fiona] I propose if BFINAL bit is detected before end of input
> >the decompression should stop. In this case consumed will be < src.length.
> >produced will be < dst buffer size. Do we need an extra STATUS response?
> >STATUS_BFINAL_DETECTED ?
> [Shally] @fiona, I assume you mean here decomp
Add debug logs when writing global registers.
Signed-off-by: Beilei Xing
Cc: sta...@dpdk.org
---
drivers/net/i40e/i40e_ethdev.c | 131 ++---
drivers/net/i40e/i40e_ethdev.h | 9 +++
2 files changed, 92 insertions(+), 48 deletions(-)
diff --git a/drivers/net/
DPDK i40e PMD will modify some global registers during initialization
and post initialization, there'll be impact during use of 700 series
Ethernet Adapter with both Linux kernel and DPDK PMD.
This patchset adds logs for global configuration and adds device args
to disable global configuration.
Th
Add warnings when writing global registers.
Signed-off-by: Beilei Xing
Cc: sta...@dpdk.org
---
doc/guides/nics/i40e.rst | 12
drivers/net/i40e/i40e_ethdev.c | 15 +++
drivers/net/i40e/i40e_ethdev.h | 43 ++
3 files changed, 7
This patch provides the option to disable writing some global registers
in PMD, in order to avoid affecting other drivers, when multiple drivers
run on the same NIC and control different physical ports. Because there
are few global resources shared among different physical ports.
Fixes: ec246eeb5d
Received a note the other day from the Linux Foundation governance board
for DPDK indicating that several files I have copyright on need to be
relicensed to be compliant with the DPDK licensing guidelines. I have
some concerns with some parts of the request, but am not opposed to
other parts. So,
rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
is smaller than requested, application can consider it end of packet
stream. Some hardware can only support smaller burst sizes which need
to be advertised. Similar is the case for Tx burst.
This patch adds deprecation notice
Update f_post_init for pipeline frontend.
Move f_track from pipeline backend to pipeline frontend.
Signed-off-by: longtb5
---
doc/guides/sample_app_ug/ip_pipeline.rst | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/doc/guides/sample_app_ug/ip_pipeline.rst
b/doc/guides/
rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
is smaller than requested, application can consider it end of packet
stream. Some hardware can only support smaller burst sizes which need
to be advertised. Similar is the case for Tx burst.
This patch adds deprecation notice
Should be not possible to load conflicting DDP profiles.
Only DDP profiles of the same group (not 0) can be loaded
together;
If DDP profile group is 0, it is exclusive, i.e. it cannot
be loaded with any other DDP profile;
If DDP profile groups are different - these profiles cannot
be loaded togethe
On 2/1/2018 5:49 PM, Neil Horman wrote:
Received a note the other day from the Linux Foundation governance board
for DPDK indicating that several files I have copyright on need to be
relicensed to be compliant with the DPDK licensing guidelines. I have
some concerns with some parts of the reques
On 02/01/2018 11:24 AM, Stefan Hajnoczi wrote:
On Wed, Jan 31, 2018 at 07:07:50PM +0100, Maxime Coquelin wrote:
Hi Stefan,
On 01/31/2018 06:46 PM, Stefan Hajnoczi wrote:
Commit e29109323595beb3884da58126ebb3b878cb66f5 ("vhost: destroy unused
virtqueues when multiqueue not negotiated") broke
Tuesday, January 30, 2018 3:37 PM, Nelio Laranjeiro:
> priv_flow_stop() may be called several times, in such situation flows are
> already removed from the NIC and thus all associated objects are no present
> in the flow object (ibv_flow, indirections tables, ).
s/indirections/ indirection
>
On 2/1/2018 6:18 PM, Shreyansh Jain wrote:
rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
is smaller than requested, application can consider it end of packet
stream. Some hardware can only support smaller burst sizes which need
to be advertised. Similar is the case for T
Thursday, February 1, 2018 3:42 AM, Yongseok Koh:
> > On Jan 31, 2018, at 8:13 AM, Nelio Laranjeiro
> wrote:
> >
> > A single queue should have the same verbs priority as an RSS one.
> >
> > Fixes: 8086cf08b2f0 ("net/mlx5: handle RSS hash configuration in RSS flow")
> > Cc: sta...@dpdk.org
> >
> >
On 02/01/2018 03:48 PM, Shreyansh Jain wrote:
rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
is smaller than requested, application can consider it end of packet
stream. Some hardware can only support smaller burst sizes which need
to be advertised. Similar is the case fo
On 2/1/2018 12:10 PM, Jerin Jacob wrote:
-Original Message-
Date: Wed, 31 Jan 2018 17:46:51 +0100
From: Olivier Matz
To: Andrew Rybchenko
CC: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] doc: announce API/ABI changes for mempool
User-Agent: NeoMutt/20170113 (1.7.2)
On Tue, Jan 23, 201
On 01/31/2018 06:46 PM, Stefan Hajnoczi wrote:
These patches fix a recent regression in librte_vhost that breaks the
vhost_scsi example application. vhost_user.c assumes all devices are vhost net
backends when handling the VIRTIO_NET_F_MQ feature bit. The code is triggered
by vhost scsi devic
On Wed, Jan 31, 2018 at 02:17:32PM +, Anatoly Burakov wrote:
> Function reentrancy test limits maximum number of iterations based
> on the number of memzones and cores, however it doesn't free the
> memzones after the fact, so on a machine with big amount of cores
> the tests will fail due to r
ENA device supports Rx jumbo frames and such information needs to
be provided in the offloads flags.
Fixes: 7369f88f88c0 ("net/ena: convert to new Rx offloads API")
Signed-off-by: Rafal Kozik
---
drivers/net/ena/ena_ethdev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ena
> -Original Message-
> From: Rybalchenko, Kirill
> Sent: Thursday, February 1, 2018 12:43 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Rybalchenko, Kirill ;
> Chilikin, Andrey ; Xing, Beilei
> ; Wu, Jingjing
> Subject: [PATCH v3] net/i40e: fix multiple DDP packages should not be
> allowed
On Thu, Feb 01, 2018 at 06:18:23PM +0530, Shreyansh Jain wrote:
> rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
> is smaller than requested, application can consider it end of packet
> stream. Some hardware can only support smaller burst sizes which need
> to be advertised
Hi all,
I wonder if there is any means in DPDK to perform link discovery.
I know that DPDK is all about packet I/O, but maybe there is some library
with useful functions that an application could use for link discovery
(e.g., using LLDP).
Any suggestions are much appreciated.
Thanks,
--
Georgios
On Thursday 01 February 2018 03:31 PM, santosh wrote:
> Hi Andrew,
>
>
> On Thursday 01 February 2018 11:48 AM, Jacob, Jerin wrote:
>> The driver requires one and only one physically contiguous
>> memory chunk for all objects.
>>
>> Signed-off-by: Andrew Rybchenko
>> ---
>> drivers/mempool/octe
If build fails because of failed experimental check and stdout is
redirected to /dev/null, it is absolutely unclear why build fails.
Fixes: a4bcd61de82d ("buildtools: add script to check experimental API exports")
Signed-off-by: Andrew Rybchenko
---
buildtools/check-experimental-syms.sh | 8 +++
There is not specified dependency between rte_mempool_populate_default()
and rte_mempool_populate_iova(). So, the second should not rely on the
fact that the first adds capability flags to the mempool flags.
Fixes: 65cf769f5e6a ("mempool: detect physical contiguous objects")
Cc: sta...@dpdk.org
S
On 02/01/2018 01:33 PM, santosh wrote:
On Thursday 01 February 2018 03:44 PM, Olivier Matz wrote:
On Thu, Feb 01, 2018 at 01:00:12PM +0300, Andrew Rybchenko wrote:
On 02/01/2018 12:30 PM, santosh wrote:
On Thursday 01 February 2018 02:48 PM, Andrew Rybchenko wrote:
On 02/01/2018 12:09 PM, san
A per port offloading feature should be enabled or
disabled at same time in both rte_eth_dev_configure( )
and rte_eth_rx_queue_setup( )/rte_eth_tx_queue_setup( ).
This patch check if a per port offloading flag has
same configuration in rte_eth_dev_configure( ) and
rte_eth_rx_queue_setup( )/rte_eth_
On Thursday 01 February 2018 06:57 PM, Bruce Richardson wrote:
On Thu, Feb 01, 2018 at 06:18:23PM +0530, Shreyansh Jain wrote:
rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
is smaller than requested, application can consider it end of packet
stream. Some hardware can on
On Thu, Feb 01, 2018 at 07:58:32PM +0530, Shreyansh Jain wrote:
> On Thursday 01 February 2018 06:57 PM, Bruce Richardson wrote:
> > On Thu, Feb 01, 2018 at 06:18:23PM +0530, Shreyansh Jain wrote:
> > > rte_eth_rx_burst(..,nb_pkts) function has semantic that if return value
> > > is smaller than re
There are a few issues with building DPDK for FreeBSD using the
meson build system, specifically:
* the kernel modules aren't compiling due to an incorrect VPATH
* a number of unit tests depend on libraries not supported on BSD
* applications and examples need to be linked with execinfo library.
-
The kernel module source file directory passed via VPATH was wrong,
which caused the source files to be not found via make. Rather than
explicitly passing VPATH, make use of the fact that the full path
to the source files is passed by meson, so split that into directory
part - to be used as VPATH -
The binaries and apps in DPDK all need to be linked against the
execinfo library on FreeBSD so add this as a dependency in cases
where it is found. It's available by default on BSD, but not
at all on Linux
Fixes: 16ade738fd0d ("app/testpmd: build with meson")
Fixes: 89f0711f9ddf ("examples: build
The power management and KNI libraries are not compiled on a FreeBSD
platform, which means that the tests can't run. Add in stub code for
these cases, allowing the tests to still be compiled, but to report
as skipped in those cases.
Signed-off-by: Bruce Richardson
CC: Ferruh Yigit
CC: David Hunt
The power library is not built on FreeBSD, so it needs to be an
optional rather than a mandatory dependency for building the autotest
binary.
Fixes: b5dc795a8a55 ("test: build app with meson as dpdk-test")
Signed-off-by: Bruce Richardson
---
test/test/meson.build | 4 +++-
1 file changed, 3 ins
The KNI library is not built on FreeBSD, so it needs to be an
optional rather than a mandatory dependency for building the autotest
binary.
Fixes: b5dc795a8a55 ("test: build app with meson as dpdk-test")
Signed-off-by: Bruce Richardson
---
test/test/meson.build | 3 +++
1 file changed, 3 insert
On Wed, Jan 31, 2018 at 03:39:19PM +0800, Herbert Guan wrote:
> 1) Add native PN option '-march=native' to allow automatic detection.
>Set 'arm_force_native_march' to 'true' in config/arm/meson.build
>to use native PN option.
> 2) Add implementer_pn option for part num selection in cross co
Hi Stefan,
On Wed, Jan 31, 2018 at 05:46:50PM +, Stefan Hajnoczi wrote:
> The librte_vhost API is used in two ways:
> 1. As a vhost net device backend via rte_vhost_enqueue/dequeue_burst().
This is how DPDK vhost-user firstly implemented.
> 2. As a library for implementing vhost device backe
On Wed, Jan 31, 2018 at 05:46:49PM +, Stefan Hajnoczi wrote:
> These patches fix a recent regression in librte_vhost that breaks the
> vhost_scsi example application. vhost_user.c assumes all devices are vhost
> net
> backends when handling the VIRTIO_NET_F_MQ feature bit. The code is trigge
On Wed, Jan 31, 2018 at 05:48:28PM +, Stefan Hajnoczi wrote:
> The vhost_scsi example application negotiates the
> VIRTIO_RING_F_EVENT_IDX feature bit but does not honor it when accessing
> vrings.
>
> In particular, commit e37ff954405addb8ea422426a2d162d00dcad196 ("vhost:
> support virtqueue
On Wed, Jan 31, 2018 at 04:46:46PM +, Marko Kovacevic wrote:
> Added examples in lcore index for better
> explanation on various examples,
> Sited examples for lcore id.
>
> Signed-off-by: Marko Kovacevic
> ---
> lib/librte_eal/common/include/rte_lcore.h | 17 +++--
> 1 file chan
On 2/1/2018 5:09 AM, Somnath Kotur wrote:
Hi Somnath,
Can you please keep patch title brief (around 50 characters) and put more
content in commit log?
> Signed-off-by: Somnath Kotur
> ---
> drivers/net/bnxt/bnxt_rxr.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/dr
On Mon, Jan 29, 2018 at 05:30:38PM +0100, Maxime Coquelin wrote:
> First patch of the series fixes OOM handling from the IOTLB
> mempool, the second one removes pending IOTLB entry when the
> IOTLB miss request sending failed.
>
> Changes since v2:
> -
> - patch 2: Fix error messag
Error information on the current core
usage list,mask and map were incomplete.
Added states to differentiate core usage
and to inform user.
Signed-off-by: Marko Kovacevic
---
doc/guides/testpmd_app_ug/run_app.rst | 4
lib/librte_eal/common/eal_common_options.c | 33 +++
Sure , will do a response
Thanks
Som
On Feb 1, 2018 8:54 PM, "Ferruh Yigit" wrote:
> On 2/1/2018 5:09 AM, Somnath Kotur wrote:
>
> Hi Somnath,
>
> Can you please keep patch title brief (around 50 characters) and put more
> content in commit log?
>
> > Signed-off-by: Somnath Kotur
> > ---
> >
Hi Bruce,
On 31/1/2018 5:42 PM, Bruce Richardson wrote:
The power management and KNI libraries are not compiled on a FreeBSD
platform, which means that the tests can't run. Add in stub code for
these cases, allowing the tests to still be compiled, but to report
as skipped in those cases.
Signed
2018-02-01 14:06 GMT+01:00 Rafal Kozik :
>
> ENA device supports Rx jumbo frames and such information needs to
> be provided in the offloads flags.
>
> Fixes: 7369f88f88c0 ("net/ena: convert to new Rx offloads API")
>
> Signed-off-by: Rafal Kozik
Signed-off-by: Michal Krawczyk
>
> ---
> drivers
On 01-Feb-18 3:39 PM, Marko Kovacevic wrote:
Error information on the current core
usage list,mask and map were incomplete.
Added states to differentiate core usage
and to inform user.
Nitpicking, but line width on commit message is a little on the short
side...
Signed-off-by: Marko Kovace
1 - 100 of 134 matches
Mail list logo
