Signed-off-by: Marvin Liu
diff --git a/doc/guides/rel_notes/known_issues.rst
b/doc/guides/rel_notes/known_issues.rst
index 95e4ce693..617255cd7 100644
--- a/doc/guides/rel_notes/known_issues.rst
+++ b/doc/guides/rel_notes/known_issues.rst
@@ -759,3 +759,21 @@ Netvsc driver and application restar
This series adds support of encap and decap actions in DV format.
L2 tunnel support for VXLAN and NVGRE, and L2/L3 tunnel support using raw data
buffer.
It is using the generic encapsulation framework from [1].
[1] "ethdev: add generic L2/L3 tunnel encapsulation actions"
http://mails.dpdk.org
This patch adds glue functions for operations:
- Create packet reformat (encap/decap) flow action.
- Destroy flow action.
The new operations depend on HAVE_IBV_FLOW_DV_SUPPORT.
Signed-off-by: Dekel Peled
Acked-by: Yongseok Koh
Acked-by: Shahaf Shuler
---
drivers/net/mlx5/Makefile| 2 +-
This patch implements the VXLAN encap action in DV flow for MLX5 PMD.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow.h| 3 +
drivers/net/mlx5/mlx5_flow_dv.c | 347 +++-
2 files changed, 345 insertions(+), 5 deletions(-)
diff --git a/drivers/n
This patch implements the VXLAN decap action in DV flow for MLX5 PMD.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow.h| 1 +
drivers/net/mlx5/mlx5_flow_dv.c | 93 +++--
2 files changed, 90 insertions(+), 4 deletions(-)
diff --git a/drivers/net
This patch implements the NVGRE decap action in DV flow for MLX5 PMD.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow.h| 4
drivers/net/mlx5/mlx5_flow_dv.c | 19 +--
2 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_flow.h b
This patch implements the nvgre encap action in DV flow for MLX5 PMD.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow.h| 4
drivers/net/mlx5/mlx5_flow_dv.c | 37 -
2 files changed, 36 insertions(+), 5 deletions(-)
diff --git a/drivers/net/
Make flow encap and decap Verbs actions cacheable resources.
Reuse 17.11 PR 876.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_flow.h| 18 ++-
drivers/net/mlx5/mlx5_flow_dv.c | 265 ++--
3 files changed, 193
This patch implements the encap and decap actions, using raw data,
in DV flow for MLX5 PMD.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow.h| 12 +-
drivers/net/mlx5/mlx5_flow_dv.c | 246 +---
2 files changed, 241 insertions(+), 17 deletions(-)
Hi,
I have a very basic question about jumbo frame support for ixgbe.
I understand that some drivers support jumbo frame and
if it receive jumbo packet (greater than 1500 byte), it creates
mbuf chains and pass it to DPDK application through
e.g. rte_eth_rx_burst.
However it looks that ixgbe d
Hi,
PSB
> -Original Message-
> From: Yongseok Koh
> Sent: Monday, October 29, 2018 8:04 PM
> To: Ori Kam
> Cc: Shahaf Shuler ; dev@dpdk.org
> Subject: Re: [PATCH] net/mlx5: fix Direct Verbs getting item and action flags
>
> > On Oct 28, 2018, at 11:03 PM, Ori Kam wrote:
> >
> > Why shou
Hi Shahaf,
I don't see how rte_eth_rx_descriptor_status can actually give me the number of
packets in the RX queue? It will tell me the status of a packet at a given
offset, right?
About the goal: we have a full view of a network (switches and servers), and we
want to know where the queueing i
On Wed, Oct 31, 2018 at 12:12:27AM +0100, Thomas Monjalon wrote:
> 30/10/2018 19:09, Cody Doucette:
> > OK, I will send three separate patches plus a cover letter.
> >
> > I seem to be having trouble with checkpatch complaining that new symbols
> > are not inserted into the EXPERIMENTAL section of
31/10/2018 04:35, Gavin Hu:
> --- a/doc/guides/rel_notes/release_18_11.rst
> +++ b/doc/guides/rel_notes/release_18_11.rst
> +* **Updated rte ring C11 driver.**
> +
> + Updated the rte ring C11 driver including the following changes:
It is not a driver, it is the ring library with C11 memory model
Hi Reshma,
30/10/2018 15:22, Reshma Pattan:
> From: Reshma Pattan
>
> Use strlcpy instead of strcpy to avoid buffer overrun.
>
> Coverity issue: 323514
>
> Fixes: b767f8efc8 ("net/softnic: replace pointers with arrays")
> CC: cristian.dumitre...@intel.com
> CC: jasvinder.si...@intel.com
>
> S
Use strlcpy instead of strcpy to avoid buffer overrun.
Coverity issues: 323475,323478,323514,323515
Fixes: b767f8efc8 ("net/softnic: replace pointers with arrays")
Fixes: c169b6a588 ("net/softnic: map flow attribute to pipeline table")
CC: cristian.dumitre...@intel.com
CC: jasvinder.si...@intel.c
https://bugs.dpdk.org/show_bug.cgi?id=102
Bug ID: 102
Summary: IOVA mode causes deadlock
Product: DPDK
Version: 18.11
Hardware: x86
OS: Linux
Status: CONFIRMED
Severity: normal
Priority: Normal
> -Original Message-
> From: Trahe, Fiona
> Sent: Wednesday, October 31, 2018 12:42 AM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; akhil.go...@nxp.com; Jozwiak, TomaszX
> ; Daly, Lee ; Trahe, Fiona
>
> Subject: [PATCH] test/compress: improve trace
>
> Make clear which engine is compr
v2->v3
1) reword the change and relocate it in the release note.
v1->v2
1) Add the changes to the 18.11 release note.
V1:
Updated the ring library with C11 memory model including the following changes
1) Synchronize the load and store of the tail to ensure the enqueue/dequeue
operations are re
Synchronize the load-acquire of the tail and the store-release
within update_tail, the store release ensures all the ring operations,
enqueue or dequeue, are seen by the observers on the other side as soon
as they see the updated tail. The load-acquire is needed here as the
data dependency is not a
In __rte_ring_move_prod_head, move the __atomic_load_n up and out of
the do {} while loop as upon failure the old_head will be updated,
another load is costly and not necessary.
This helps a little on the latency,about 1~5%.
Test result with the patch(two cores):
SP/SC bulk enq/dequeue (size: 8
For packed ring layout, we need save avail index and its wrap
counter value. At restore time, the used index and its wrap counter
are set to available's ones, as the ring procressing is stopped
at vring base get time.
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost_user.c | 40
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index b4abad30c..760f42192 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -275,7 +275,8 @@
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, October 31, 2018 5:37 PM
> To: Gavin Hu (Arm Technology China)
> Cc: dev@dpdk.org; olivier.m...@6wind.com; chao...@linux.vnet.ibm.com;
> bruce.richard...@intel.com; konstantin.anan...@intel.com;
> jerin.ja...@caviumnetwork
In this v4, it restores back to only save last avail index and
its wrap counter value at get time, and restore both used
and avail indexes to avail values at set time.
The change compared to v1 is that wrap counter value is
saved into bit 15, so that it is consistent with the event
suppression stru
12/10/2018 19:05, Luca Boccassi:
> A Kbuild is also included to allow users to use DKMS natively without
> additional code.
>
> Signed-off-by: Luca Boccassi
> Tested-by: Bruce Richardson
> Acked-by: Bruce Richardson
Was applied in 18.11-rc1.
Thanks Ferruh for catching the miss of notification
Including svg files with the svg extension is a common mistake:
.. figure:: example.svg
must be
.. figure:: example.*
So it will work also when building pdf doc with figures converted
to png files.
A check is added in checkpatches.sh.
Signed-off-by: Thomas Monjalon
PS: it seems
29/10/2018 21:34, Dan Gora:
> Don't use .svg extension on ..figure references. PDF versions of
> the documents use .png images generated from the .svg images.
>
> Fixes: 0ba610ca1d17 ("net/mvpp2: document MTR and TM usage")
> Cc: nsams...@marvell.com
>
> Signed-off-by: Dan Gora
Applied, thanks
Fix mixing enum types enum rte_table_action_policer
and enum rte_mtr_policer_action for dereference of
policer action.
Coverity issue 323483, 323511
Fixes: 7e30e444c3e4 ("net/softnic: support flow meter action")
Fixes: 8a917ef88db7 ("net/softnic: update policer actions")
Signed-off-by: Jasvinder
The vm_power_manager app was not respecting the POWER_MGR_MAX_CPUS
during initialisation, so if there were more CPUs than this value (64),
it would lead to buffer overruns of there were more then 64 cores in
the system.
Added in a check during init and un-init to only initialise up to
lcore_id 63.
Fix mixing enum types enum rte_table_action_policer
and enum rte_mtr_policer_action for dereference of
policer action.
Coverity issue 323483, 323511
Fixes: 7e30e444c3e4 ("net/softnic: support flow meter action")
Fixes: 8a917ef88db7 ("net/softnic: update policer actions")
Signed-off-by: Jasvinder
Enable NIC loopback mode based on rte_eth_conf.lpbk_mode
configuration.
Signed-off-by: Dekel Peled
---
drivers/net/mlx5/mlx5_rxq.c | 27 +--
drivers/net/mlx5/mlx5_rxtx.h | 2 +-
2 files changed, 22 insertions(+), 7 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxq.c
On Fri, Oct 26, 2018 at 01:43:45PM +0800, Tiwei Bie wrote:
On Thu, Oct 25, 2018 at 03:54:16PM +0200, Jens Freimann wrote:
On Thu, Oct 25, 2018 at 05:39:09PM +0800, Tiwei Bie wrote:
> On Wed, Oct 24, 2018 at 04:32:34PM +0200, Jens Freimann wrote:
> > Implement the receive part.
> >
> > Signed-off
Fixes: 244d5130719c ("eal: enable hotplug on multi-process")
Cc: qi.z.zh...@intel.com
Cc: anatoly.bura...@intel.com
Signed-off-by: Darek Stojaczyk
---
lib/librte_eal/common/hotplug_mp.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/lib/librte_eal/common/hotplug_mp.c
b/l
> -Original Message-
> From: Stojaczyk, Dariusz
> Sent: Wednesday, October 31, 2018 8:17 AM
> To: dev@dpdk.org
> Cc: Stojaczyk, Dariusz ; Zhang, Qi Z
> ; Burakov, Anatoly
> Subject: [PATCH] eal: fix memleak on device hotplug rollback
>
> Fixes: 244d5130719c ("eal: enable hotplug on mul
After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
from probe() segfaults; there is no need to call the function, just set
the mode directly.
Fixes: 391797f04208 ("drivers/bus: move driver assignment to end of probing")
Signed-off-by: Radu Nicolau
---
drivers/net/bonding/rt
Thanks for the suggestion. It looks like
49bcce138374458d1edd1c50d8e5726959108ef4 is already in my tree. I tried
applying and checking again anyway and it seems that the error is still
present.
On Wed, Oct 31, 2018 at 5:28 AM Neil Horman wrote:
> On Wed, Oct 31, 2018 at 12:12:27AM +0100, Thomas
Reduced test time for efd_autotest.
Key length is updated, invoke times of random function is reduced.
Signed-off-by: Jananee Parthasarathy
---
v2: value updated for each hash key
---
test/test/test_efd.c | 17 -
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/test/
The new API introduced in 18.11 is suggesting, that the driver should
release all it's resources at the dev_close routine.
All resources previously released in uninit routine during PCI removal,
are now being released at the dev_close and the PMD is indicating that
it is supporting API changes by
On Wed, Oct 31, 2018 at 10:20:46AM -0400, Cody Doucette wrote:
> Thanks for the suggestion. It looks like
> 49bcce138374458d1edd1c50d8e5726959108ef4 is already in my tree. I tried
> applying and checking again anyway and it seems that the error is still
> present.
>
Thats not a commit in the upstr
31/10/2018 14:59, Radu Nicolau:
> After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
> from probe() segfaults; there is no need to call the function, just set
> the mode directly.
>
> Fixes: 391797f04208 ("drivers/bus: move driver assignment to end of probing")
It would not s
31/10/2018 16:03, Neil Horman:
> On Wed, Oct 31, 2018 at 10:20:46AM -0400, Cody Doucette wrote:
> > Thanks for the suggestion. It looks like
> > 49bcce138374458d1edd1c50d8e5726959108ef4 is already in my tree. I tried
> > applying and checking again anyway and it seems that the error is still
> > pr
Hi Dekel,
Wednesday, October 31, 2018 9:11 AM, Dekel Peled:
> Subject: [PATCH v7 0/7] add encap and decap actions to Direct Verbs flow in
> MLX5 PMD
>
> This series adds support of encap and decap actions in DV format.
> L2 tunnel support for VXLAN and NVGRE, and L2/L3 tunnel support using raw
>
Wednesday, October 31, 2018 9:11 AM, Dekel Peled:
> Subject: [dpdk-dev] [PATCH v7 4/7] net/mlx5: add NVGRE encap action to
> Direct Verbs
>
> This patch implements the nvgre encap action in DV flow for MLX5 PMD.
>
> Signed-off-by: Dekel Peled
> ---
> drivers/net/mlx5/mlx5_flow.h| 4
>
Wednesday, October 31, 2018 9:11 AM, Dekel Peled:
> Subject: [PATCH v7 2/7] net/mlx5: add VXLAN encap action to Direct Verbs
>
> This patch implements the VXLAN encap action in DV flow for MLX5 PMD.
>
> Signed-off-by: Dekel Peled
> ---
> drivers/net/mlx5/mlx5_flow.h| 3 +
> drivers/net/ml
Wednesday, October 31, 2018 9:11 AM, Dekel Peled:
> Subject: [dpdk-dev] [PATCH v7 7/7] net/mlx5: add caching of encap decap
> actions
>
> Make flow encap and decap Verbs actions cacheable resources.
> Reuse 17.11 PR 876.
No one knows what is PR 876 in the mailing list, also this code is not in 17
On 10/31/2018 3:06 PM, Thomas Monjalon wrote:
31/10/2018 14:59, Radu Nicolau:
After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
from probe() segfaults; there is no need to call the function, just set
the mode directly.
Fixes: 391797f04208 ("drivers/bus: move driver assi
On 10/31/2018 11:06 AM, Thomas Monjalon wrote:
31/10/2018 14:59, Radu Nicolau:
After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
from probe() segfaults; there is no need to call the function, just set
the mode directly.
Fixes: 391797f04208 ("drivers/bus: move driver ass
31/10/2018 16:37, Chas Williams:
>
> On 10/31/2018 11:06 AM, Thomas Monjalon wrote:
> > 31/10/2018 14:59, Radu Nicolau:
> >> After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
> >> from probe() segfaults; there is no need to call the function, just set
> >> the mode directly.
Hi Thomas
Glad the function gets to be reused :)
Now that it has more than one consumer apparently the function
check_forbidden_additions() cannot be fed by stdin.
I got it working with 3 changes:
1. call the awk script with $tmpinput as a parameter instead of stdin. This
aligns with Neils change
On Wed, 31 Oct 2018 17:22:02 +0900
Hideyuki Yamashita wrote:
> Hi,
>
> I have a very basic question about jumbo frame support for ixgbe.
>
> I understand that some drivers support jumbo frame and
> if it receive jumbo packet (greater than 1500 byte), it creates
> mbuf chains and pass it to DP
Hi Arnon,
31/10/2018 16:46, Arnon Warshavsky:
> Hi Thomas
>
> Glad the function gets to be reused :)
> Now that it has more than one consumer apparently the function
> check_forbidden_additions() cannot be fed by stdin.
> I got it working with 3 changes:
Thanks for the help
> 1. call the awk sc
> > and added an extra backslash
>
> Are you sure we need an extra backslash?
> Note that I am using single quotes.
> I thought we need only 2 backslashes in this case.
>
You are right.
Its only required with double quotes
After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
from probe() segfaults; there is no need to call the function, just set
the mode directly.
Also, reverted 1620175b400e.
Fixes: 391797f04208 ("drivers/bus: move driver assignment to end of probing")
Fixes: 1620175b400e ("net/bo
31/10/2018 16:50, Radu Nicolau:
> After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
> from probe() segfaults; there is no need to call the function, just set
> the mode directly.
> Also, reverted 1620175b400e.
>
> Fixes: 391797f04208 ("drivers/bus: move driver assignment to e
Hi,
-Original Message-
From: Parthasarathy, JananeeX M
Sent: Wednesday, October 31, 2018 2:30 PM
To: dev@dpdk.org
Cc: Marohn, Byron ; De Lara Guarch, Pablo
; Pattan, Reshma ;
Parthasarathy, JananeeX M
Subject: [PATCH v2] test: reduce test duration for efd autotest
Reduced test time fo
On 10/31/2018 11:50 AM, Radu Nicolau wrote:
After the patch below the call to rte_eth_bond_8023ad_agg_selection_set
from probe() segfaults; there is no need to call the function, just set
the mode directly.
Also, reverted 1620175b400e.
Fixes: 391797f04208 ("drivers/bus: move driver assignment
rte_strerror uses strerror_r(), and strerror_r() has two version of it.
- XSI-compliant version, (_POSIX_C_SOURCE >= 200112L) && ! _GNU_SOURCE
- GNU-specific version
Those two has different return types, so the exiting return type check
is not correct for GNU-specific version.
And this is causin
Including svg files with the svg extension is a common mistake:
.. figure:: example.svg
must be
.. figure:: example.*
So it will work also when building pdf doc with figures converted
to png files.
A check is added in checkpatches.sh.
Signed-off-by: Thomas Monjalon
Signed-off-by:
Last call for review.
Qian, it probably makes to have a validation test of this patchset.
31/10/2018 11:26, Gavin Hu:
> v2->v3
> 1) reword the change and relocate it in the release note.
>
> v1->v2
> 1) Add the changes to the 18.11 release note.
>
> V1:
> Updated the ring library with C11 memo
31/10/2018 03:17, Cody Doucette:
> Compilation flag D_XOPEN_SOURCE is causing failsafe to fail to
> build when changing some DPDK libraries. The flag is not needed
> and therefore is removed.
>
> Signed-off-by: Cody Doucette
Gaetan, please approve that the flag is not needed.
31/10/2018 03:17, Cody Doucette:
> Add a common IPv6 extension header and an inline function
> for determining whether a next header field represents
> an IPv6 extension header.
>
> Signed-off-by: Cody Doucette
Olivier, is this patch OK?
31/10/2018 03:17, Cody Doucette:
> Add the ability to parse IPv6 extenders to find the
> IPv6 fragment header, and update callers.
>
> According to RFC 8200, there is no guarantee that the IPv6
> Fragment extension header will come before any other extension
> header, even though it is recommended
31/10/2018 18:19, Ferruh Yigit:
> rte_strerror uses strerror_r(), and strerror_r() has two version of it.
> - XSI-compliant version, (_POSIX_C_SOURCE >= 200112L) && ! _GNU_SOURCE
> - GNU-specific version
>
> Those two has different return types, so the exiting return type check
> is not correct f
30/10/2018 11:15, Burakov, Anatoly:
> On 29-Oct-18 11:47 AM, Darek Stojaczyk wrote:
> > rte_mp_request_sync() says that the caller is responsible
> > for freeing one of its parameters afterwards. EAL didn't
> > do that, causing a memory leak.
> >
> > Fixes: 244d5130719c ("eal: enable hotplug on mu
Any update or question for this patch?
If no update, it will miss 18.11.
27/10/2018 17:09, Thomas Monjalon:
> 19/09/2018 17:47, Chas Williams:
> > On Wed, Sep 19, 2018 at 8:58 AM Luca Boccassi wrote:
> > >
> > > The vmxnet3 driver can't call back into dev_close(), and possibly
> > > dev_stop(),
On 10/28/18 2:08 AM, Ferruh Yigit wrote:
Fixes: d7280c9fffcb ("vhost: support selective datapath")
Cc: sta...@dpdk.org
Signed-off-by: Ferruh Yigit
---
lib/librte_vhost/vdpa.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/librte_vhost/vdpa.c b/lib/librte_vhost/vdpa.c
index c2c
Current name rte_eal_check_dma_mask does not follow the naming
used in the rest of the file.
Signed-off-by: Alejandro Lucero
---
doc/guides/rel_notes/release_18_11.rst | 2 +-
drivers/bus/pci/linux/pci.c| 2 +-
drivers/net/nfp/nfp_net.c | 2 +-
lib/librte_eal
The param needs to be the maskbits and not the mask.
Fixes: 223b7f1d5ef6 ("mem: add function for checking memseg IOVA")
Signed-off-by: Alejandro Lucero
---
lib/librte_eal/common/malloc_heap.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/lib/librte_eal/common/malloc_heap
A patchset sent introducing DMA mask checks has several critical
issues precluding apps to execute. The patchset was reviewed and
finally accepted after three versions. Obviously it did not go
through the proper testing what can be explained, at least from my
side, due to the big changes to the me
Calling rte_mem_check_dma_mask when memory has not been initialized
yet is wrong. This patch use rte_mem_set_dma_mask instead.
Once memory initialization is done, the dma mask set will be used
for checking memory mapped is within the specified mask.
Fixes: fe822eb8c565 ("bus/pci: use IOVA DMA mas
This patch adds the possibility of setting a dma mask to be used
once the memory initialization is done.
This is currently needed when IOVA mode is set by PCI related
code and an x86 IOMMU hardware unit is present. Current code calls
rte_mem_check_dma_mask but it is wrong to do so at that point
be
If a device reports addressing limitations through a dma mask,
the IOVAs for mapped memory needs to be checked out for ensuring
correct functionality.
Previous patches introduced this DMA check for main memory code
currently being used but other options like legacy memory and the
no hugepages one
During memory initialization calling rte_mem_check_dma_mask
leads to a deadlock because memory_hotplug_lock is locked by a
writer, the current code in execution, and rte_memseg_walk
tries to lock as a reader.
This patch adds safe and unsafe versions for invoking the final
function specifying if th
If DMA mask checks shows mapped memory out of the supported range
specified by the DMA mask, nothing can be done but return an error
an report the error. This can imply the app not being executed at
all or precluding dynamic memory allocation once the app is running.
In any case, we can advice the
Sorry, been otherwise busy - I can do what you and Chas have asked, but
the problem is that v1 already did that and the VMWare maintainers
asked to change it back. So can I assume that the v1 way is the way to
go?
On Wed, 2018-10-31 at 18:27 +0100, Thomas Monjalon wrote:
> Any update or question f
On Wed, Oct 31, 2018 at 5:29 PM Alejandro Lucero <
alejandro.luc...@netronome.com> wrote:
> A patchset sent introducing DMA mask checks has several critical
> issues precluding apps to execute. The patchset was reviewed and
> finally accepted after three versions. Obviously it did not go
> through
31/10/2018 18:46, Luca Boccassi:
> Sorry, been otherwise busy - I can do what you and Chas have asked, but
> the problem is that v1 already did that and the VMWare maintainers
> asked to change it back. So can I assume that the v1 way is the way to
> go?
I am expecting an answer from the vmxnet3 m
30/10/2018 16:19, Zhang, Qi Z:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 27/10/2018 05:20, Qi Zhang:
> > > When scanning an already plugged device, the virtual address of mapped
> > > PCI resource in rte_pci_device will be overridden with 0, that may
> > > cause driver does not work
On 10/31/2018 5:16 PM, Thomas Monjalon wrote:
> 31/10/2018 18:19, Ferruh Yigit:
>> rte_strerror uses strerror_r(), and strerror_r() has two version of it.
>> - XSI-compliant version, (_POSIX_C_SOURCE >= 200112L) && ! _GNU_SOURCE
>> - GNU-specific version
>>
>> Those two has different return types,
On 10/31/2018 6:26 PM, Ferruh Yigit wrote:
> On 10/31/2018 5:16 PM, Thomas Monjalon wrote:
>> 31/10/2018 18:19, Ferruh Yigit:
>>> rte_strerror uses strerror_r(), and strerror_r() has two version of it.
>>> - XSI-compliant version, (_POSIX_C_SOURCE >= 200112L) && ! _GNU_SOURCE
>>> - GNU-specific ve
Hi Qi,
30/10/2018 16:27, Qi Zhang:
> When scanning an already plugged device, the virtual address
> of mapped PCI resource in rte_pci_device will be overridden
> with 0, that may cause driver does not work correctly.
> The fix is not to update any rte_pci_device's field if the being
> scanned devi
Register and unregister the virtio interrupt handler when the device is
started and stopped. This allows a virtio device to be hotplugged or
unplugged.
Fixes: c1f86306a026 ("virtio: add new driver")
Cc: sta...@dpdk.org
Signed-off-by: Brian Russell
Signed-off-by: Luca Boccassi
Reviewed-by: Maxim
If a device is unplugged while an interrupt is pending, the
read call to the uio device to remove it from the poll wait list
can fail resulting in it being continually polled forever. This
change checks for the read failing and if so, unregisters the device
as an interrupt source and causes the wai
The vmxnet3 driver can't call back into dev_close(), and possibly
dev_stop(), in dev_uninit(). When dev_uninit() is called, anything
that those routines would want to clean up has already been released.
Further, for complete cleanup, it is necessary to release any of the
queue resources during dev
I am not able to figure out any problem with my code, I am using testpmd in
txonly mode (./x86_64-native-linuxapp-gcc/app/testpmd --
--forward-mode=txonly) as a transmitter on one machine and this code as a
receiver on another machine.
-- Forwarded message -
From: Avinash Chauras
31/10/2018 19:26, Ferruh Yigit:
> On 10/31/2018 6:26 PM, Ferruh Yigit wrote:
> > On 10/31/2018 5:16 PM, Thomas Monjalon wrote:
> >> 31/10/2018 18:19, Ferruh Yigit:
> >>> rte_strerror uses strerror_r(), and strerror_r() has two version of it.
> >>> - XSI-compliant version, (_POSIX_C_SOURCE >= 200112
Hey I'm taking paternity leave now so late on response.
The v1 was different from what Thomas asked for and (hw->adapter_stopped == 0)
was ignored (see cited below). So we felt uncomfortable about that as there is
no guarantee that the device has been closed before calling uninit. Now that
you
Hi Cody,
>
> Add the ability to parse IPv6 extenders to find the
> IPv6 fragment header, and update callers.
>
> According to RFC 8200, there is no guarantee that the IPv6
> Fragment extension header will come before any other extension
> header, even though it is recommended.
>
> Signed-off-by
On Wed, Oct 31, 2018 at 06:02:29PM +0100, Thomas Monjalon wrote:
> 31/10/2018 03:17, Cody Doucette:
> > Compilation flag D_XOPEN_SOURCE is causing failsafe to fail to
> > build when changing some DPDK libraries. The flag is not needed
> > and therefore is removed.
> >
> > Signed-off-by: Cody Douce
Display trace if error returned from firmware is likely due
to intermediate buffers being too small for the compressed
output. Update documentation to explain this error case
and to clarify intermediate buffer memory usage.
Signed-off-by: Fiona Trahe
---
v2 changes:
- improved some text in qat.r
On Wed, 31 Oct 2018 18:26:26 +0800
Gavin Hu wrote:
> - /*
> - * The subtraction is done between two unsigned 32bits value
> + /* load-acquire synchronize with store-release of ht->tail
> + * in update_tail.
> + */
> + con
> On Oct 31, 2018, at 1:25 AM, Ori Kam wrote:
>
> Hi,
> PSB
>
>> -Original Message-
>> From: Yongseok Koh
>> Sent: Monday, October 29, 2018 8:04 PM
>> To: Ori Kam
>> Cc: Shahaf Shuler ; dev@dpdk.org
>> Subject: Re: [PATCH] net/mlx5: fix Direct Verbs getting item and action flags
>>
>
Hi Burakov,
I'm sorry for the late response.
Thanks a lot for your comments. Please find my response below (marked with
"Tone:"). 😊
Br,
Tone
-Original Message-
From: Burakov, Anatoly
Sent: Wednesday, October 24, 2018 5:09 PM
To: Tone Zhang (Arm Technology China) ; dev@dpdk.org
Cc: n
Add Stephen Hemminger for discussion.
> -Original Message-
> From: Zhao1, Wei
> Sent: Thursday, November 1, 2018 11:10 AM
> To: 'Hideyuki Yamashita' ;
> dev@dpdk.org
> Subject: RE: [dpdk-dev] Question about jumbo frame support on ixgbe
>
> Hi, Hideyuki Yamashita
>
>
> > -Original
Hi, Hideyuki Yamashita
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Hideyuki Yamashita
> Sent: Wednesday, October 31, 2018 4:22 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] Question about jumbo frame support on ixgbe
>
> Hi,
>
> I have a very basic questio
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen
> Hemminger
> Sent: Wednesday, October 31, 2018 11:49 PM
> To: Hideyuki Yamashita
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] Question about jumbo frame support on ixgbe
>
> On Wed, 31 Oct 2018 17:22:0
Hi,
We are using Dpdk 17.11.4 and facing issue in bringing setup with bonding
although without bonding it is working fine.
Your help is much appreciated!
*Command used *
--vdev eth_bond0,mode=1,slave=:37:00.0,slave=:37:00.1
Error Logs
=
Oct 31 13:13:07 - INFO - net_mlx5: c
Various configuration flags in rte_hash library result in increase of
number of test cases. Configuration flags for enabling transactional
memory use and read/write concurrency are not required. These features
should be supported by default. Please refer to [1] for more context.
This patch marks t
RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY and
RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT configuration flags are
deprecated. Reader/Writer concurrency is provided by default.
Transactional memory will be used if the platform supports it.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Dharmik Thakkar
Rev
1 - 100 of 107 matches
Mail list logo