On Wed, Aug 7, 2019 at 4:58 PM Aaron Conole wrote:
>
> It's possible that the mcsunlock occurs before the test_mcslock_try has
> a chance to execute, which will result in the trylock being successful,
> making the test case fail. Fix this by waiting until all lcores have
> completed their test be
You seem to be having an older version of firmware on the card.
I will have someone contact you for the newer firmware.
Thanks
Ajit
On Wed, Aug 7, 2019 at 10:19 PM vikram T wrote:
> Hi,
> I am trying to run the sample program "hello_world" using the DPDK - 18.11
> version on Braodcom BNXT drive
Hi,
I am trying to run the sample program "hello_world" using the DPDK - 18.11
version on Braodcom BNXT driver the crash is seen:
[root@localhost build]# ./helloworld
EAL: Detected 48 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Probing VFIO suppor
On Wed, Aug 07, 2019 at 05:09:17PM +0200, Thierry Herbelot wrote:
> From: Thibaut Collet
>
> With vectorized functions, only the rx stats for number of packets is
> incremented.
> Update also the other statistics.
> Performance impact is about 2%
Could you share some details about your performan
> -Original Message-
> From: Aaron Conole
> Sent: Wednesday, August 7, 2019 10:59 PM
> To: dev@dpdk.org
> Cc: Phil Yang (Arm Technology China) ; Gavin Hu (Arm
> Technology China) ; Honnappa Nagarahalli
>
> Subject: [PATCH] test/mcslock: wait for lcore completion
>
> It's possible that th
On 08/08, Congwen Zhang wrote:
>In function ixgbe_parse_rss_filter, memset(rss_conf, 0,
>sizeof(struct rte_eth_rss_conf)) is using
>memset(aaa, 0, sizeof(struct bbb)) format,
>maybe it's better to make it consistent with others.
Er...These comments are just for the style of memset, putting them in
In function ixgbe_parse_rss_filter, memset(rss_conf, 0,
sizeof(struct rte_eth_rss_conf)) is using
memset(aaa, 0, sizeof(struct bbb)) format,
maybe it's better to make it consistent with others.
Fixes: 518cc3927b13 ("net/ixgbe: move RSS to flow API")
Cc: sta...@dpdk.org
Signed-off-by: Congwen Zhan
The "and" condition offset == 0 && offset == NVM_INVALID_PTR
can never be true.
Fixes: cf3af5aa56c9 ("net/ixgbe/base: add functions to get version info")
Cc: sta...@dpdk.org
Signed-off-by: Congwen Zhang
Acked-by: Xiaolong Ye
---
drivers/net/ixgbe/base/ixgbe_common.c | 2 +-
1 file changed, 1
+ dev@dpdk.org
From: 王志克
Sent: Monday, August 05, 2019 6:23 PM
To: 'us...@dpdk.org'
Subject: Why non LTM releases do not have pkg/dpdk.spec
Hi,
I checked the dpdk release, and found ususally LTM (eg 18.11) have
pkg/dpdk.spec. For other release (eg 19.05), there is no such file.
So if I want t
On 8/7/19 7:09 PM, pbhagavat...@marvell.com wrote:
From: Pavan Nikhilesh
Add new offload flags ``DEV_RX_OFFLOAD_PTYPE``, ``DEV_RX_OFFLOAD_RSS``
and ``DEV_RX_OFFLOAD_FLOW_MARK``.
Signed-off-by: Pavan Nikhilesh
---
doc/guides/rel_notes/deprecation.rst | 9 +
1 file changed, 9 inserti
From: Pavan Nikhilesh
Add new offload flags ``DEV_RX_OFFLOAD_PTYPE``, ``DEV_RX_OFFLOAD_RSS``
and ``DEV_RX_OFFLOAD_FLOW_MARK``.
Signed-off-by: Pavan Nikhilesh
---
doc/guides/rel_notes/deprecation.rst | 9 +
1 file changed, 9 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.r
On 8/7/19 9:56 AM, Agalya Babu RadhaKrishnan wrote:
From: Hari Kumar Vemula
Add a programmer's guide section for meson ut
Signed-off-by: Hari Kumar Vemula
Acked-by: Bruce Richardson
---
v7: Updated v6 patch comments
v6: Updated comments
v5: Modified
v4: Typos corrected
v3: Modified
v2: Remov
On 8/7/19 6:22 PM, Stephen Hemminger wrote:
On Wed, 7 Aug 2019 11:32:35 +0300
Andrew Rybchenko wrote:
On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
-Original Message-
From: Stephen Hemminger
Sent: Wednesday, August 7, 2019 4:45 AM
To: Andrew Rybchenko
Cc: Pavan Nikhilesh Bhaga
On Wed, 7 Aug 2019 15:42:04 +0530
Gagandeep Singh wrote:
> DPDK currently is supporting maximum 3 hugepage,
> sizes whereas system can support more than this e.g.
> 64K, 2M, 32M and 1G.
>
> Having these four hugepage sizes available to use by DPDK,
> which is valid in case of '--in-memory' EAL
On Wed, 7 Aug 2019 11:32:35 +0300
Andrew Rybchenko wrote:
> On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
> >> -Original Message-
> >> From: Stephen Hemminger
> >> Sent: Wednesday, August 7, 2019 4:45 AM
> >> To: Andrew Rybchenko
> >> Cc: Pavan Nikhilesh Bhagavatula ; Hemant
> >>
On 7/19/19 4:38 PM, Olivier Matz wrote:
In rte_mempool_populate_default(), we determine the page size,
which is needed for calc_size and allocation of memory.
Move this in a function and export it, it will be used in next
commit.
The major change here is taking page sizes into account even in
On 7/19/19 4:38 PM, Olivier Matz wrote:
When using iova contiguous memory and objets smaller than page size,
ensure that objects are not located across several pages.
It looks like as an attempt to make exception a generic rule and
I think it is not a good idea.
mempool has a notion of IOVA co
On 7/19/19 4:38 PM, Olivier Matz wrote:
The size returned by rte_mempool_op_calc_mem_size_default() is aligned
to the specified page size. This means that with big pages, the returned
amount is more that what we really need to populate the mempool.
This problem is tempered by the allocation meth
On 7/19/19 4:38 PM, Olivier Matz wrote:
When IOVA mode is VA, a mempool can be created with objects that
are not physically contiguous, which breaks KNI.
To solve this, this patchset changes the default behavior of mempool
populate function, to prevent objects from being located across pages.
On Wed, 7 Aug 2019 07:02:02 +
Matan Azrad wrote:
> From: Stephen Hemminger
> > On Wed, 7 Aug 2019 05:38:42 +
> > Matan Azrad wrote:
> >
> > > From: Stephen Hemminger
> > > > Sent: Wednesday, August 7, 2019 2:09 AM
> > > > To: Matan Azrad
> > > > Cc: dev@dpdk.org; Stephen Hemminger
Like for Ethernet ports, the OcteonTx crypto engines must first be unbound
from their kernel module, then rebound to vfio-pci, before being usable
in DPDK.
As this capability is detected at runtime by dpdk-pmdinfo, add the info
in the PMD registering directives.
Then an external script can be use
dpaa_sec needs translations between physical and virtual addresses.
V to P translation is relatively fast, as memory is managed in
contiguous segments.
The result of each V to P translation is used to update the DPAA iova
table, which should be updated by a Mem event callback, but is not.
Then the
From: Laurent Hardy
During PF/VF link update, a default speed value of 100M will be set
if get_link_info has failed or speed is unknown.
Consequently if PF is put in no-carrier state, VFs will switch to
"in carrier" state due to a link up + a link speed set to 100M
(default value if no speed det
From: Thibaut Collet
With vectorized functions, only the rx stats for number of packets is
incremented.
Update also the other statistics.
Performance impact is about 2%
Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: sta...@dpdk.org
Signed-off-by: Thibaut Collet
---
drivers/net/virtio/virti
Session contexts are used for temporary storage when processing a
packet.
If packets for the same session are to be processed simultaneously on
multiple cores, separate contexts must be used.
Note: with openssl 1.1.1 EVP_CIPHER_CTX can no longer be defined as a
variable on the stack: it must be al
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Thibaut Collet
The loop to read packets does not take all packets as the number of
available packets (nb_used) is decremented in the loop.
Take all available packets provides a performance improvement of 3%.
Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: sta...@dpdk.org
Signed-off-by:
From: Olivier Matz
The API comment of rte_eth_tx_descriptor_status() was incorrect. The
reference descriptor (when offset = 0) is not where the next packet
will be sent, but where the latest packet has been enqueued.
Fixes: 52f5cdd2e897 ("ethdev: add descriptor status API")
Cc: sta...@dpdk.org
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
This series of patches includes fixes for issues seen with
6WIND fast path, built on DPDK.
The patches are in 6WIND version of DPDK, and should have been
upstreamed a long time ago.
V2 changes:
fix checkpatch issues
Guo Fengtian (1):
net/ixgbevf: fix stats update after a PF reset
Laurent Hardy
From: Guo Fengtian
When PF is set down, in VF, the value of stats register is zero.
So only increase stats when it's non zero.
Fixes: af75078fece3 ('first public release')
Cc: sta...@dpdk.org
Signed-off-by: Guo Fengtian
---
drivers/net/ixgbe/ixgbe_ethdev.c | 6 --
1 file changed, 4 insert
It's possible that the mcsunlock occurs before the test_mcslock_try has
a chance to execute, which will result in the trylock being successful,
making the test case fail. Fix this by waiting until all lcores have
completed their test before unlocking the master lock.
Fixes: 32dcb9fd2a22 ("test/mc
Like for Ethernet ports, the OcteonTx crypto engines must first be unbound
from their kernel module, then rebound to vfio-pci, before being usable
in DPDK.
As this capability is detected at runtime by dpdk-pmdinfo, add the info
in the PMD registering directives.
Then an external script can be use
dpaa_sec needs translations between physical and virtual addresses. V to P
translation is relatively fast, as memory is managed in contiguous segments.
The result of each V to P translation is used to update the DPAA iova table,
which should be updated by a Mem event callback, but is not.
Then the
From: Laurent Hardy
During PF/VF link update, a default speed value of 100M will be set
if get_link_info has failed or speed is unknown.
Consequently if PF is put in no-carrier state, VFs will switch to
"in carrier" state due to a link up + a link speed set to 100M
(default value if no speed det
From: Thibaut Collet
With vectorized functions, only the rx stats for number of packets is
incremented.
Update also the other statistics.
Performance impact is about 2%
Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: stable at dpdk.org
Signed-off-by: Thibaut Collet
---
drivers/net/virtio/vi
From: Thibaut Collet
The loop to read packets does not take all packets as the number of
available packets (nb_used) is decremented in the loop.
Take all available packets provides a performance improvement of 3%.
Fixes: fc3d66212fed ("virtio: add vector Rx")
Cc: stable at dpdk.org
Signed-off-b
Session contexts are used for temporary storage when processing a
packet.
If packets for the same session are to be processed simultaneously on
multiple cores, separate contexts must be used.
Note: with openssl 1.1.1 EVP_CIPHER_CTX can no longer be defined as a
variable on the stack: it must be al
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The Tx descriptor status api was not behaving as expected. This API is
used to inspect the content of the descriptors in the Tx ring to
determine the length of the Tx queue.
Since the software advances the tail pointer and the hardware advances
the head pointer, the Tx queue i
From: Olivier Matz
The API comment of rte_eth_tx_descriptor_status() was incorrect. The reference
descriptor (when offset = 0) is not where the next packet will be sent, but
where the latest packet has been enqueued.
Fixes: 52f5cdd2e897 ("ethdev: add descriptor status API")
Cc: stable at dpdk.or
From: Guo Fengtian
When PF is set down, in VF, the value of stats register is zero.
So only increase stats when it's non zero.
Fixes: af75078fece3 ('first public release')
Cc: stable at dpdk.org
Signed-off-by: Guo Fengtian
---
drivers/net/ixgbe/ixgbe_ethdev.c | 6 --
1 file changed, 4 ins
This series of patches includes fixes for issues seen with
6WIND fast path, built on DPDK.
The patches are in 6WIND version of DPDK, and should have been
upstreamed a long time ago.
Guo Fengtian (1):
net/ixgbevf: fix stats update after a PF reset
Laurent Hardy (1):
net/i40e: set speed to unde
>
> Hi Konstantin
>
> From: Ananyev, Konstantin
> > Sent: Wednesday, August 7, 2019 1:18 PM
> > To: Matan Azrad ; dev@dpdk.org
> > Cc: Thomas Monjalon ; Yigit, Ferruh
> > ; Andrew Rybchenko
> > ; Olivier Matz
> > Subject: RE: [PATCH 2/2] doc: announce new mbuf field for LRO
> >
> > Hi Matan,
> -Original Message-
> From: dev On Behalf Of Agalya Babu
> RadhaKrishnan
> Sent: Wednesday, August 7, 2019 7:26 PM
> To: dev@dpdk.org
> Cc: reshma.pat...@intel.com; john.mcnam...@intel.com;
> marko.kovace...@intel.com; bruce.richard...@intel.com;
> jananeex.m.parthasara...@intel.com; Hari
> Hi Thomas,
>
> > 07/08/2019 14:00, David Marchand:
> > > On Wed, Aug 7, 2019 at 12:26 PM Gagandeep Singh
> > wrote:
> > > >
> > > > DPDK currently is supporting maximum 3 hugepage, sizes whereas
> > > > system can support more than this e.g.
> > > > 64K, 2M, 32M and 1G.
> > >
> > > You can m
On Mon, Aug 5, 2019 at 2:27 AM David Marchand wrote:
>
> On Sat, Aug 3, 2019 at 12:00 AM Thomas Monjalon wrote:
> >
> > 02/08/2019 23:25, Aaron Conole:
> > > This series turns the fast unit tests on for a limited set of
> > > builds under the travis build system. An example run is available
> >
From: Hari Kumar Vemula
Add a programmer's guide section for meson ut
Signed-off-by: Hari Kumar Vemula
Acked-by: Bruce Richardson
---
v7: Updated v6 patch comments
v6: Updated comments
v5: Modified
v4: Typos corrected
v3: Modified
v2: Removed enhancement details
---
.../prog_guide/build-sdk-m
>
> Check the return value of the rte_eth_dev_rss_hash_conf_get function.
>
> Coverity issue: 344970
> Fixes: 3a690d5a65e2 ("examples/ipsec-secgw: fix first packet with inline
> crypto")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Bernard Iremonger
> ---
Acked-by: Akhil Goyal
Thomas,
Could y
Hi,
> -Original Message-
> From: dev On Behalf Of Viacheslav Ovsiienko
> Sent: Wednesday, August 7, 2019 3:58 PM
> To: dev@dpdk.org
> Cc: Yongseok Koh ; Shahaf Shuler
>
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix completion request for multi-
> segment packets
>
> The copying of sent mb
Hi,
> -Original Message-
> From: dev On Behalf Of Viacheslav Ovsiienko
> Sent: Wednesday, August 7, 2019 3:58 PM
> To: dev@dpdk.org
> Cc: Yongseok Koh ; Shahaf Shuler
>
> Subject: [dpdk-dev] [PATCH] doc: update inline settings in mlx5 guide
>
> This patch updates mlx5 documentation in p
HI Thomas,
> > > DPDK currently is supporting maximum 3 hugepage, sizes whereas
> > > system can support more than this e.g.
> > > 64K, 2M, 32M and 1G.
> >
> > You can mention ARM platform here, and that this issue starts with
> > kernel 5.2 (and I would try to mention this in the title as well).
From: Amit Gupta
On receiving signal, testpmd showing warning as
"LATENCY_STATS: failed to remove Rx/Tx callback"
because rte_latencystats_uninit is called without
checking if latencystats is enabled or not.
After this fix, rte_latencystats_uninit will be
called onlyif latencystats is enabled.
The ast.literal_eval() was used incorrectly and wouldn't properly
retrieve the user option. Was causing the options to keep being listed
in a loop. Removed and replaced with raw_input() being cast to an int.
Works as expected now.
Fixes: 53f293c9a783 ("usertools: replace unsafe input function")
Cc
The copying of sent mbufs pointers might be deferred to the end of
tx_burst() routine to be copied in one call of rte_memcpy.
For the multi segment packets this optimization is not applicable,
because number of packets does not match with number of mbufs and
we do not have linear array of pointers
This patch updates mlx5 documentation in parts:
- txq_inline_min parameter is described in more details,
values are fixed
- maximal amount of segments in multi-segment packets.
Signed-off-by: Viacheslav Ovsiienko
---
doc/guides/nics/mlx5.rst | 31 +++
1 file
Hi Thomas,
> 07/08/2019 14:00, David Marchand:
> > On Wed, Aug 7, 2019 at 12:26 PM Gagandeep Singh
> wrote:
> > >
> > > DPDK currently is supporting maximum 3 hugepage,
> > > sizes whereas system can support more than this e.g.
> > > 64K, 2M, 32M and 1G.
> >
> > You can mention ARM platform here,
>
> On Wed, Aug 7, 2019 at 12:26 PM Gagandeep Singh wrote:
> >
> > DPDK currently is supporting maximum 3 hugepage,
> > sizes whereas system can support more than this e.g.
> > 64K, 2M, 32M and 1G.
>
> You can mention ARM platform here, and that this issue starts with
> kernel 5.2 (and I would
Hi Konstantin
From: Ananyev, Konstantin
> Sent: Wednesday, August 7, 2019 1:18 PM
> To: Matan Azrad ; dev@dpdk.org
> Cc: Thomas Monjalon ; Yigit, Ferruh
> ; Andrew Rybchenko
> ; Olivier Matz
> Subject: RE: [PATCH 2/2] doc: announce new mbuf field for LRO
>
> Hi Matan,
>
> > > >
> > > > The AP
Check the return value of the rte_eth_dev_rss_hash_conf_get function.
Coverity issue: 344970
Fixes: 3a690d5a65e2 ("examples/ipsec-secgw: fix first packet with inline
crypto")
Cc: sta...@dpdk.org
Signed-off-by: Bernard Iremonger
---
examples/ipsec-secgw/ipsec.c | 9 -
1 file changed, 8
07/08/2019 14:00, David Marchand:
> On Wed, Aug 7, 2019 at 12:26 PM Gagandeep Singh wrote:
> >
> > DPDK currently is supporting maximum 3 hugepage,
> > sizes whereas system can support more than this e.g.
> > 64K, 2M, 32M and 1G.
>
> You can mention ARM platform here, and that this issue starts w
On Wed, Aug 7, 2019 at 12:26 PM Gagandeep Singh wrote:
>
> DPDK currently is supporting maximum 3 hugepage,
> sizes whereas system can support more than this e.g.
> 64K, 2M, 32M and 1G.
You can mention ARM platform here, and that this issue starts with
kernel 5.2 (and I would try to mention this
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Andrius Sirvys
>
> The ast.literal_eval() was used incorrectly and wouldn't properly retrieve the
> user option. Was causing the options to keep being listed in a loop. Removed
> and replaced with raw_input() being cast to an int.
> Works as e
The ast.literal_eval() was used incorrectly and wouldn't properly
retrieve the user option. Was causing the options to keep being listed
in a loop. Removed and replaced with raw_input() being cast to an int.
Works as expected now.
Fixes: 53f293c9a783 ("usertools: replace unsafe input function")
Cc
Hello,
We are trying to build an application over DPDK, but we are getting this
warning when we call
rte_eal_init().
EAL: Detected 24 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: No available hugepages reported in hugepages-1048576kB
EAL: Probi
DPDK currently is supporting maximum 3 hugepage,
sizes whereas system can support more than this e.g.
64K, 2M, 32M and 1G.
Having these four hugepage sizes available to use by DPDK,
which is valid in case of '--in-memory' EAL option or
using 4 separate mount points for each hugepage size;
hugepage
Hi Matan,
> > >
> > > The API breakage is because the ``tso_segsz`` field was documented for
> > > LRO.
> > >
> > > The ``tso_segsz`` field in mbuf indicates the size of each segment in
> > > the LRO packet in Rx path and should be provided by the LRO packet
> > > port.
> > >
> > > While the gener
On Wed, Aug 7, 2019 at 11:42 AM Congwen Zhang wrote:
>
> The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
> not struct rte_eth_rss_conf *.
>
> Fixes: 518cc3927b13 ("net/ixgbe: move RSS to flow API")
Cc: sta...@dpdk.org must be part of the commitlog.
This commitlog does not describe the
The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
not struct rte_eth_rss_conf *.
Fixes: 518cc3927b13 ("net/ixgbe: move RSS to flow API")
Signed-off-by: Congwen Zhang
---
drivers/net/ixgbe/ixgbe_flow.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe
The "and" condition offset == 0 && offset == NVM_INVALID_PTR
can never be true.
Fixes: cf3af5aa56c9 ("net/ixgbe/base: add functions to get version info")
Signed-off-by: Congwen Zhang
Acked-by: Xiaolong Ye
---
drivers/net/ixgbe/base/ixgbe_common.c | 2 +-
1 file changed, 1 insertion(+), 1 dele
The type of rss_conf is struct igb_rte_flow_rss_conf *,
not struct rte_eth_rss_conf *.
Fixes: 424ae915baf0 ("net/e1000: move RSS to flow API")
Signed-off-by: Congwen Zhang
---
drivers/net/e1000/igb_flow.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/e1000/igb
On Wed, Aug 7, 2019 at 10:57 AM Ye Xiaolong wrote:
>
> On 08/07, David Marchand wrote:
> >On Wed, Aug 7, 2019 at 10:28 AM Congwen Zhang
> >wrote:
> >>
> >> The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
> >> not struct rte_eth_rss_conf *.
> >
> >What is the actual issue?
> >Does it d
On 08/07, David Marchand wrote:
>On Wed, Aug 7, 2019 at 10:28 AM Congwen Zhang wrote:
>>
>> The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
>> not struct rte_eth_rss_conf *.
>
>What is the actual issue?
>Does it deserve a Fixes: tag?
>
>>
>> Signed-off-by: Congwen Zhang
>> ---
>> driv
The type of rss_conf is struct igb_rte_flow_rss_conf *,
not struct rte_eth_rss_conf *.
Signed-off-by: Congwen Zhang
---
drivers/net/e1000/igb_flow.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index 4e0b38f..0d2
On 08/07, Congwen Zhang wrote:
>The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
> not struct rte_eth_rss_conf *.
Please add the fix tag and cc sta...@dpdk.org.
>
>Signed-off-by: Congwen Zhang
>---
> drivers/net/ixgbe/ixgbe_flow.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
On Wed, Aug 7, 2019 at 10:28 AM Congwen Zhang wrote:
>
> The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
> not struct rte_eth_rss_conf *.
What is the actual issue?
Does it deserve a Fixes: tag?
>
> Signed-off-by: Congwen Zhang
> ---
> drivers/net/ixgbe/ixgbe_flow.c | 2 +-
> 1 file
Primary process is responsible to initialize the data struct of each
crypto devices.
Secondary process should not override this data during the
initialization.
Fixes: d11b0f30df88 ("cryptodev: introduce API and framework for crypto
devices")
Cc: sta...@dpdk.org
Signed-off-by: Julien Meunier
--
Each cryptodev are indexed with its dev_id in the global
rte_crypto_devices variable. nb_devs is incremented / decremented each
time a cryptodev is created / deleted. The goal of nb_devs is to prevent
the user to get an invalid dev_id.
Let's imagine DPDK has configured N cryptodevs. If the cryptod
Hi,
On 08/07, Congwen Zhang wrote:
>The "and" condition offset == 0 && offset == NVM_INVALID_PTR
> can never be true.
A fix tag is missing here, you can refer to other fix commits in git log
history.
and also cc sta...@dpdk.org.
>
>Signed-off-by: Congwen Zhang
>---
> drivers/net/ixgbe/base/ixg
On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
-Original Message-
From: Stephen Hemminger
Sent: Wednesday, August 7, 2019 4:45 AM
To: Andrew Rybchenko
Cc: Pavan Nikhilesh Bhagavatula ; Hemant
Agrawal ; Jerin Jacob Kollanukkaran
; dev@dpdk.org
Subject: [EXT] Re: [dpdk-dev] [RFC 0/3]
07/08/2019 05:11, jer...@marvell.com:
> From: Jerin Jacob
>
> gcc-9 stricter on NULL arguments for printf.
> Fix the following build error by avoiding NULL argument to printf.
>
> In file included from drivers/net/memif/memif_socket.c:26:
> In function 'memif_socket_create',
> inlined from 'memi
The type of rss_conf is struct ixgbe_rte_flow_rss_conf *,
not struct rte_eth_rss_conf *.
Signed-off-by: Congwen Zhang
---
drivers/net/ixgbe/ixgbe_flow.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/ixgbe_flow.c b/drivers/net/ixgbe/ixgbe_flow.c
index 9237
The ops pointers in fm10k_stats_get() are set up from primary
process, when secondary process call these ops pointers,
a segment fault will happen.
Fixes: 7223d200c227 ("fm10k: add base driver")
Cc: jeffrey.b.s...@intel.com
Signed-off-by: Lu Qiuwen
Acked-by: Xiao Wang
---
V5 - fix grammar probl
On 19-08-05 17:09, David Marchand wrote:
> External Email
>
> --
> On Mon, Aug 5, 2019 at 4:46 PM wrote:
> >
> > From: Krzysztof Kanas
> >
> > Bonding selection logic uses agg_bandwidth, agg_count indexed by port_id
> > but thos
Hi Qiuwen,
> -Original Message-
> From: Lu Qiuwen [mailto:luqiu...@iie.ac.cn]
> Sent: Wednesday, August 7, 2019 3:21 PM
> To: dev@dpdk.org
> Cc: Shaw, Jeffrey B ; Wang, Xiao W
>
> Subject: [PATCH v4] net/fm10k: fix fm10k stats crash in multi-process
>
> The ops pointers in fm10k_stats_ge
The "and" condition offset == 0 && offset == NVM_INVALID_PTR
can never be true.
Signed-off-by: Congwen Zhang
---
drivers/net/ixgbe/base/ixgbe_common.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/base/ixgbe_common.c
b/drivers/net/ixgbe/base/ixgbe_common
The ops pointers in fm10k_stats_get() is setup from primary process,
when secondary process call these function pointers, a segment fault
will happened.
v2 - delete some empty lines after the function declaration.
v3 - add patch version, fixes and make title shorter.
v4 - fix the misspelled word i
The ops pointers in fm10k_stats_get() is setup from primary process,
when secondary process call these function pointers, a segment fault
will happend.
v2 - delete some empty lines after the function declaration.
v3 - add patch version, fixes and make title shorter.
Fixes: 7223d200c227 ("fm10k: a
From: Stephen Hemminger
> On Wed, 7 Aug 2019 05:38:42 +
> Matan Azrad wrote:
>
> > From: Stephen Hemminger
> > > Sent: Wednesday, August 7, 2019 2:09 AM
> > > To: Matan Azrad
> > > Cc: dev@dpdk.org; Stephen Hemminger
> > > Subject: Re: [dpdk-dev] [PATCH v5 1/4]
> > > examples/multi_proce
94 matches
Mail list logo
