Update deprecation notice for the new rss_level field of
rte_eth_rss_conf.
Link: http://www.dpdk.org/dev/patchwork/patch/31891
Signed-off-by: Xueming Li
---
doc/guides/rel_notes/deprecation.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/g
Device can only be started if firmware is loaded, as per Skeleton
rawdev driver semantics. This patch fixes original implementation
which attempted to start the device without loading firmware.
Fixes: 55ca1b0f2151 ("raw/skeleton: add test cases")
Cc: shreyansh.j...@nxp.com
Signed-off-by: Shreyans
On 2018年01月29日 22:11, Jens Freimann wrote:
This is a basic implementation of packed virtqueues as specified in the
Virtio 1.1 draft. A compiled version of the current draft is available
at https://github.com/oasis-tcs/virtio-docs.git (or as .pdf at
https://github.com/oasis-tcs/virtio-docs/blob/
On Tue, Feb 06, 2018 at 05:51:29AM +, Herbert Guan wrote:
> Hi Pavan,
>
> > -Original Message-
> > From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> > Sent: Monday, February 5, 2018 17:23
> > To: Herbert Guan ;
> > jerin.ja...@caviumnetworks.com; hemant.agra...@nxp.com;
>
Hi Pavan,
> -Original Message-
> From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Monday, February 5, 2018 17:23
> To: Herbert Guan ;
> jerin.ja...@caviumnetworks.com; hemant.agra...@nxp.com;
> bruce.richard...@intel.com; harry.van.haa...@intel.com
> Cc: dev@dpdk.org
This patch fixes interval error and corrects macros
when enable rx interrupt mode. The patch also fixes
a logical error during support multiple driver.
Fixes: be6c228d4da3 ("i40e: support Rx interrupt")
Fixes: b20aa3aee390 ("net/i40e: fix multiple driver support issue")
Cc: sta...@dpdk.org
Signed
The timestamp flag needs to be set in the offload flags
for the received pkt in case of PTP offload.
Fixes: b11cceb83a34 ("net/bnxt: support timesync")
Cc: somnath.ko...@broadcom.com
Signed-off-by: Somnath Kotur
---
v2->v3: Added the 'fixes commit line'
v1->v2: Trimmed subject line and added co
> -Original Message-
> From: Rybalchenko, Kirill
> Sent: Thursday, February 1, 2018 8:43 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
> -Original Message-
> From: Rybalchenko, Kirill
> Sent: Monday, February 5, 2018 9:59 PM
> To: Xing, Beilei ; dev@dpdk.org
> Cc: sta...@dpdk.org; Chilikin, Andrey ; Wu,
> Jingjing
> Subject: RE: [PATCH v3] net/i40e: fix multiple DDP packages should not be
> allowed
>
> Hi Beilei,
>
>
Since RTE_MAX_NUMA_NODES is configurable, the existing socket number
could greater than RTE_MAX_NUMA_NODES. Optimize test case to cover this
situation.(i.e RTE_MAX_NUMA_NODES=1)
Fixes: 45f1b6e8680a ('app: add new tests on eal flags')
Signed-off-by: Phil Yang
---
test/test/test_eal_flags.c | 7 +
24/01/2018 11:26, Anatoly Burakov:
> lspci reports kernel modules in "Module" string, but devbind
> expects it to be "Module_str". Fix it up similar to how we fix
> up "Driver" to be "Driver_str".
>
> Cc: sta...@dpdk.org
>
> Signed-off-by: Anatoly Burakov
Fixes: c3ce205d5729 ("usertools: optimi
24/01/2018 14:16, Anatoly Burakov:
> Cc: sta...@dpdk.org
Missing commit origin:
Fixes: 629395b063e8 ("igb_uio: remove PCI id table")
> Signed-off-by: Anatoly Burakov
Applied, thanks
05/02/2018 08:43, Nipun Gupta:
> From: Hemant Agrawal
>
> This patch replaces the uses of default mempool ops API
> with newly supported best_mempool_ops API.
>
> Signed-off-by: Hemant Agrawal
Applied, thanks
01/02/2018 11:14, Anatoly Burakov:
> 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
Series applied, thanks
01/02/2018 14:00, Olivier Matz:
> 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
05/02/2018 23:27, Amr Mokhtar:
> This patch fixes shared library compilation due to undefined
> reference to an exported variable 'bbdev_logtype'.
> In this fix, the logtype is converted to static in the bbdev lib
> and in the bbdev null pmd.
>
> Fixes: 7dc2b1589440 ("bb/null: add null base band d
05/02/2018 14:03, Anatoly Burakov:
> Get rid of global static ring variable and don't reuse rings
> between test runs.
>
> Fixes: 4e32101f9b01 ("ring: support freeing")
> Cc: pablo.de.lara.gua...@intel.com
> Cc: sta...@dpdk.org
>
> Signed-off-by: Anatoly Burakov
> Acked-by: Olivier Matz
There
01/02/2018 14:49, Andrew Rybchenko:
> - echo "$SYM is not flagged as experimental"
> - echo "but is listed in version map"
> - echo "Please add __rte_experimental to the definition of $SYM"
> + cat >&2 < +$SYM is not flagged as experimental
> +but is
02/02/2018 19:47, Neil Horman:
> On Fri, Feb 02, 2018 at 03:51:12PM +, Bruce Richardson wrote:
> > On Fri, Feb 02, 2018 at 03:47:43PM +, Bruce Richardson wrote:
> > > On Fri, Feb 02, 2018 at 07:44:39AM -0500, Neil Horman wrote:
> > > > On Fri, Feb 02, 2018 at 12:00:58PM +, Bruce Richard
02/02/2018 14:40, Olivier Matz:
> On Fri, Feb 02, 2018 at 01:33:01PM +0530, Hemant Agrawal wrote:
> > From: Nipun Gupta
> >
> > The existing rte_eal_mbuf_default mempool ops can return the compile time
> > default ops name if the user has not provided command line inputs for
> > mempool ops name.
01/02/2018 15:02, Andrew Rybchenko:
> 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 physic
> > Fixes: 8824b74d8f5f ("bus/fslmc: register platform HW mempool on
> > runtime")
> >
> > Signed-off-by: Nipun Gupta
>
> Acked-by: Shreyansh Jain
Series applied, thanks
This patch fixes shared library compilation due to undefined
reference to an exported variable 'bbdev_logtype'.
In this fix, the logtype is converted to static in the bbdev lib,
in bbdev null pmd and turbo sw pmd.
Fixes: b8cfe2c9aed2 ("bb/turbo_sw: add software turbo driver")
Cc: tho...@monjalon.n
05/02/2018 18:15, Moti Haimovsky:
> This commit modifies vdev_probe to continue probing all the devices
> regardless of device probing failures.
>
> Fixes: 810e5fa3688b ("vdev: move virtual device probing into a bus")
It is not the origin commit.
Anyway it is not really a fix but a better behavio
23/01/2018 17:17, xiangxia.m@gmail.com:
> From: Tonghao Zhang
>
> The kernel uses the '%d' or '%ld' to print irq num.
> But igb_uio may use the '%lx', then the log may confuse
> the user what irq num has been used. The log is show as
> below.
>
> igb_uio :00:03.0: irq 24 for MSI/MSI-X
>
02/02/2018 16:33, Bruce Richardson:
> On Fri, Feb 02, 2018 at 02:51:28PM +, Marko Kovacevic wrote:
> > Error information on current core usage list, mask or map
> > were incomplete. Added states to differentiate core usage
> > and to inform user.
> >
> > Signed-off-by: Marko Kovacevic
> > Rev
05/02/2018 18:39, Burakov, Anatoly:
> On 05-Feb-18 4:37 PM, Anatoly Burakov wrote:
> > During lcore scan, find maximum socket ID and store it.
> >
> > Signed-off-by: Anatoly Burakov
> > ---
> >
> > Notes:
> > v3:
> > - Added ABI backwards compatibility
> >
> > v2:
> > -
05/02/2018 16:45, Marko Kovacevic:
> Code commit for 'make -f' support, breaks the build in cases where
> entries in $(MAKEFILE_LIST) are absolute paths. This commit uses
> notdir and firstword to ensure that only the local filename is used.
>
> Fixes: 3a5c339d51a4 ("mk: support renamed Makefile i
05/02/2018 11:53, Kovacevic, Marko:
> > 05/02/2018 11:22, Marko Kovacevic:
> > > Updated the make build to fix external build issues
> >
> > Please explain what is the issue.
> >
> > > Fixes: 3a5c339d51a4 ("mk: support renamed Makefile in external project")
> > > Cc: sta...@dpdk.org
> >
> > No n
This patch fixes shared library compilation due to undefined
reference to an exported variable 'bbdev_logtype'.
In this fix, the logtype is converted to static in the bbdev lib
and in the bbdev null pmd.
Fixes: 7dc2b1589440 ("bb/null: add null base band device driver")
Cc: tho...@monjalon.net
Sig
Hi Ferruh,
You can drop it then. I encountered the same porting bug in another
project and came across dpdk's code and patchwork comments which helped me
debugging. I just thought I would contribute the fix back. If it's not
functional then just drop it :)
Andy
On Mon, Feb 5, 2018 at 11:05 AM F
On Tue, Jan 23, 2018 at 02:46:19AM +, Yang, Qiming wrote:
> Sorry for reply so late. Answered in line.
Same for me, please see below.
> > > This flag will be configured in dev_configure(), and can be queried by
> > > user
> > through dev->data->dev_conf.rxmode.enable_ptype_direct. In receiv
On 12/18/2017 6:16 AM, Andy Roulin wrote:
> pci_enable_msix_range's return value has a different meaning than what
> was previously returned by pci_enable_msix.
>
> "It returns a negative errno if an error occurs. If it succeeds, it
> returns the actual number of interrupts allocated and indicates
On 2/5/2018 5:19 PM, Pavan Nikhilesh wrote:
> Set allow_experimental_apis to true to allow the use of experimental
> API's.
>
> Signed-off-by: Pavan Nikhilesh
Squashed into relevant commit in next-net, thanks.
On 2/5/2018 11:46 AM, Bruce Richardson wrote:
> On Mon, Feb 05, 2018 at 10:34:00AM +, Ferruh Yigit wrote:
>> On 2/4/2018 3:33 PM, Pavan Nikhilesh wrote:
>>> Register octeontx-fpavf as platform HW mempool when net/octeontx pmd is
>>> used.
>>>
>>> Signed-off-by: Pavan Nikhilesh
>>> ---
>>>
>>>
On 2/3/2018 2:55 PM, David C Harton wrote:
> virtio_dev_free_mbufs was recently modified to free the
> virtqueues but failed to check whether the array was
> allocated. Added a check to ensure vqs was non-null.
>
> Fixes: bdb32afbb610 ("net/virtio: rationalize queue flushing")
> Cc: olivier.m...@
On 2/5/2018 6:11 PM, Ferruh Yigit wrote:
> On 1/23/2018 2:29 PM, Marko Kovacevic wrote:
>> From: Vipin Varghese
>>
>> TUN PMD is not supported, removing the refrences
>> from Network Interface Controller Driver Tun/Tap
>> Poll Mode Driver section
>>
>> Signed-off-by: Vipin Varghese
>
> Reviewed-
On 2/5/2018 3:54 PM, Pascal Mazon wrote:
> From: Vipin Varghese
>
> Allow TAP PMD to pass user desired MAC address as argument.
> The argument value is processed as string, where each 2 bytes
> are converted to HEX MAC address after validation.
>
> Signed-off-by: Vipin Varghese
> Signed-off-by:
Hi Maxime,
Many thanks for the heads up. I'll try out your suggested fix later today and
let you know if it resolves my issue.
Regards
Alan
-Original Message-
From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
Sent: Monday, February 05, 2018 8:42 AM
To: alangordonde...@gmail.co
05/02/2018 11:22, Marko Kovacevic:
> Updated the make build to fix external build issues
>
> Fixes: 3a5c339d51a4 ("mk: support renamed Makefile in external project")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Marko Kovacevic
Applied, thanks
Hi Pascal,
Please find my observation inline
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Varghese, Vipin
> Sent: Monday, February 5, 2018 3:59 PM
> To: Pascal Mazon ; dev@dpdk.org
> Cc: Yigit, Ferruh ; Jain, Deepak K
>
> Subject: Re: [dpdk-dev] [PATCH v2]
On 2/5/2018 2:51 PM, Pascal Mazon wrote:
> On 05/02/2018 15:40, Ophir Munk wrote:
>> The eBPF classifier (section "cls_q" in tap_bpf_program.c) is tracing
>> marked packets in which skb->cb[1] contains an RSS queue number, and
>> redirects those packets to the matched queue.
>> It is expected that
On 1/23/2018 2:29 PM, Marko Kovacevic wrote:
> From: Vipin Varghese
>
> TUN PMD is not supported, removing the refrences
> from Network Interface Controller Driver Tun/Tap
> Poll Mode Driver section
>
> Signed-off-by: Vipin Varghese
Reviewed-by: Ferruh Yigit
On 2/5/2018 2:53 PM, Pascal Mazon wrote:
>
> On 05/02/2018 11:59, Ophir Munk wrote:
>> TAP device is supporting multi segments Tx, however this capability is
>> not reported when querying the TAP device.
>> This commit adds this capability report.
>>
>> Fixes: 818fe14a9891 ("net/tap: use new Tx o
05/02/2018 18:29, Neil Horman:
> Driver information
> +M: Neil Horman
> F: buildtools/pmdinfogen/
> F: usertools/dpdk-pmdinfo.py
> F: doc/guides/tools/pmdinfo.rst
This change deserves a separate patch announcing that you are
volunteer to maintain pmdinfo.
It is really not related to the rest
On 2/5/2018 3:04 PM, 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 v3:
> -
> - Fix 32bits compilation issue in error message
On 2/5/2018 3:31 PM, Adrien Mazarguil wrote:
> On Mon, Feb 05, 2018 at 02:31:11PM +0200, Shahaf Shuler wrote:
>> Signed-off-by: Shahaf Shuler
>
> With one minor nit, rdma-core plug-in compilation hasn't been accepted
> yet. Assuming it will:
>
> Acked-by: Adrien Mazarguil
Series applied to dpd
On 05-Feb-18 4:37 PM, Anatoly Burakov wrote:
During lcore scan, find maximum socket ID and store it.
Signed-off-by: Anatoly Burakov
---
Notes:
v3:
- Added ABI backwards compatibility
v2:
- checkpatch changes
- check socket before deciding if the core is not to b
Added note section to update information for use cases working with
multiple crypto devices.
Signed-off-by: Vipin Varghese
---
V2 changes:
- updated the title from 'info on multi crypto instances' - Pablo
- reframed affirmative word 'should' to 'shall' - pablo
---
doc/guides/sample_app_ug/l2_
Recently, some additional patches were added to allow for programmatic
marking of C symbols as experimental. The addition of these markers is
dependent on the manual addition of exported symbols to the EXPERIMENTAL
section of the corresponding libraries version map file. The consensus
on review i
On 2/5/2018 12:48 PM, Matan Azrad wrote:
> The vdev_netvsc driver does periodic detection of PCI devices matched
> to the netvsc existed interfaces.
>
> When it finds a match, the PCI address is written to the pipe of the
> associated fail-safe PMD instance and a positive value is returned to
> th
On 2/4/2018 6:06 AM, Rahul Lakkireddy wrote:
> From: Kumar Sanghvi
>
> rte_eth_dev_allocate already assigns the eth_dev_data. So,
> don't allocate it separately as part of probe function. And we
> save this eth_dev_data as part of txq structure.
>
> Attach to rte_eth_dev devices allocated by Pri
Set allow_experimental_apis to true to allow the use of experimental
API's.
Signed-off-by: Pavan Nikhilesh
---
v2 Changes:
- Use allow_experimental_apis instead of specifying
'-DALLOW_EXPERIMENTAL_API' through cflags.
drivers/net/octeontx/meson.build | 2 ++
1 file changed, 2 insertions(+)
This commit modifies vdev_probe to continue probing all the devices
regardless of device probing failures.
Fixes: 810e5fa3688b ("vdev: move virtual device probing into a bus")
Cc: sta...@dpdk.org
Signed-off-by: Moti Haimovsky
---
drivers/bus/vdev/vdev.c | 5 +++--
1 file changed, 3 insertions(+
On 2/4/2018 6:06 AM, Rahul Lakkireddy wrote:
> From: Kumar Sanghvi
>
> Add firmware API for updating RSS hash configuration and key. Move
> RSS hash configuration from cxgb4_write_rss() to a separate function
> cxgbe_write_rss_conf().
>
> Also, rename cxgb4_write_rss() to cxgbe_write_rss() for
On 2/4/2018 6:06 AM, Rahul Lakkireddy wrote:
> From: Kumar Sanghvi
>
> Original work by Surendra Mobiya
>
> Fixes: cdac6e2eeafc ("cxgbe: add link related functions")
> Signed-off-by: Kumar Sanghvi
> Signed-off-by: Rahul Lakkireddy
> ---
> drivers/net/cxgbe/cxgbe_ethdev.c | 3 ++-
> 1 file ch
On Mon, Feb 05, 2018 at 04:54:55PM +0100, Adrien Mazarguil wrote:
> On Mon, Feb 05, 2018 at 01:29:42PM -0200, Marcelo Ricardo Leitner wrote:
> > On Mon, Feb 05, 2018 at 03:59:18PM +0100, Adrien Mazarguil wrote:
> > > On Mon, Feb 05, 2018 at 12:37:34PM -0200, Marcelo Ricardo Leitner wrote:
> > > > O
During lcore scan, find maximum socket ID and store it.
Signed-off-by: Anatoly Burakov
---
Notes:
v3:
- Added ABI backwards compatibility
v2:
- checkpatch changes
- check socket before deciding if the core is not to be used
lib/librte_eal/common/eal_common_lcore.c | 3
On 2/3/2018 6:03 AM, Rasesh Mody wrote:
> From: Harish Patil
>
> Few adjustments are required to effectively handle VF vport create/delete
> sequence. The problem is exposed by recent ethdev TX offload changes
> which requires port to be in down state before applying TX offloads.
>
> - Move vpo
Hi Ophir,
On Mon, Feb 05, 2018 at 04:02:06PM +, Ophir Munk wrote:
> Failsafe reported Tx offloads capabilities are the AND result of its
> default capabilities and those of its sub-devices.
> In the corrupted code failsafe default Tx capabilities were set to 0.
> As a result when running testp
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Monday, February 5, 2018 7:41 PM
> To: Shreyansh Jain
> Cc: dev@dpdk.org
> Subject: Re: [PATCH v3] raw/skeleton_rawdev: fix device start test
>
> 05/02/2018 12:31, Shreyansh Jain:
> > Device can only be star
This patch complements the partial cleanup done inside
eth_dev_tap_create when the routine failed.
Such a failure left a non-functional device attached to the system.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: sta...@dpdk.org
Signed-off-by: Moti Haimovsky
---
On 2/5/2018 10:55 AM, Pavan Nikhilesh wrote:
> Register octeontx-fpavf as platform HW mempool when net/octeontx pmd is
> used.
>
> Signed-off-by: Pavan Nikhilesh
> Acked-by: Santosh Shukla
Applied to dpdk-next-net/master, thanks.
On 2/2/2018 2:38 AM, Somnath Kotur wrote:
> The timestamp flag needed to be set in the offload flags
> for the received pkt in case of PTP offload
Hi Somnath,
Can you please add a fixes line?
>
> Signed-off-by: Somnath Kotur
> ---
> v1->v2: Trimmed subject line and added content in commit log
Coverity issue: 260405
Fixes: 2efb58cbab6e ("bond: new link bonding library")
Cc: sta...@dpdk.org
Signed-off-by: Radu Nicolau
---
v2: fixed build issue
drivers/net/bonding/rte_eth_bond_api.c | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bonding/rte_eth
On 2/1/2018 5:21 PM, Radu Nicolau wrote:
> Coverity issue: 260405
> Fixes: 2efb58cbab6e ("bond: new link bonding library")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Radu Nicolau
Applied to dpdk-next-net/master, thanks.
(Missing parenthesis added while applying.)
Failsafe reported Tx offloads capabilities are the AND result of its
default capabilities and those of its sub-devices.
In the corrupted code failsafe default Tx capabilities were set to 0.
As a result when running testpmd with "--tx-offloads=0x8000" parameter
(request for multi segments offload) -
Hi Pascal,
Thanks for the update, I see your point instead of mixing up with int32_t and
uint64_t; converting to ' struct ether_addr' makes sense.
I will check internally and thanks once again for the suggestion.
Thanks
Vipin Varghese
> -Original Message-
> From: Pascal Mazon [mailto:p
Hi Vipin,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vipin Varghese
> Sent: Monday, February 5, 2018 2:32 PM
> To: dev@dpdk.org; Kovacevic, Marko
> Cc: Mcnamara, John ; Varghese, Vipin
>
> Subject: [dpdk-dev] [PATCH] doc: update multiple instance info for
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vipin Varghese
> Sent: Monday, February 5, 2018 2:36 PM
> To: dev@dpdk.org; Kovacevic, Marko
> Cc: Mcnamara, John ; Varghese, Vipin
>
> Subject: [dpdk-dev] [PATCH] doc: update info on multi crypto instances
>
>
On Mon, Feb 05, 2018 at 01:29:42PM -0200, Marcelo Ricardo Leitner wrote:
> On Mon, Feb 05, 2018 at 03:59:18PM +0100, Adrien Mazarguil wrote:
> > On Mon, Feb 05, 2018 at 12:37:34PM -0200, Marcelo Ricardo Leitner wrote:
> > > On Mon, Feb 05, 2018 at 03:16:21PM +0100, Thomas Monjalon wrote:
> > > > 05
From: Vipin Varghese
Allow TAP PMD to pass user desired MAC address as argument.
The argument value is processed as string, where each 2 bytes
are converted to HEX MAC address after validation.
Signed-off-by: Vipin Varghese
Signed-off-by: Pascal Mazon
---
Hi Vipin,
I suggest the following pa
On 2/1/2018 4:52 PM, Michał Krawczyk wrote:
> 2018-02-01 17:49 GMT+01:00 Ferruh Yigit :
>> On 2/1/2018 4:36 PM, Michał Krawczyk wrote:
>>> 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.
>>>
Code commit for 'make -f' support, breaks the build in cases where
entries in $(MAKEFILE_LIST) are absolute paths. This commit uses
notdir and firstword to ensure that only the local filename is used.
Fixes: 3a5c339d51a4 ("mk: support renamed Makefile in external project")
Signed-off-by: Marko Ko
On 2/1/2018 11:06 AM, Radu Nicolau wrote:
> 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
Reviewed-by: Ferruh Yigit
Applied to dpdk-nex
On Mon, Feb 05, 2018 at 02:31:12PM +0200, Shahaf Shuler wrote:
> Signed-off-by: Shahaf Shuler
With one minor nit, title only mentions mlx5 while mlx4 is also affected:
Acked-by: Adrien Mazarguil
> ---
>
> On v3:
> - Highlighted flow counters are supported only in MLNX_OFED.
>
> On v2:
> -
On Mon, Feb 05, 2018 at 02:31:11PM +0200, Shahaf Shuler wrote:
> Signed-off-by: Shahaf Shuler
With one minor nit, rdma-core plug-in compilation hasn't been accepted
yet. Assuming it will:
Acked-by: Adrien Mazarguil
> ---
>
> On v3:
> - No change.
>
> On v2:
> - No change.
>
> ---
> doc/g
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, January 31, 2018 5:24 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Mcnamara, John ; sta...@dpdk.org;
> or...@mellanox.com
> Subject: Re: [dpdk-dev] [PATCH v3] doc: update flow filtering document
>
> On 1/31/2018 2:12 AM, Wei Zhao w
On Mon, Feb 05, 2018 at 03:59:18PM +0100, Adrien Mazarguil wrote:
> On Mon, Feb 05, 2018 at 12:37:34PM -0200, Marcelo Ricardo Leitner wrote:
> > On Mon, Feb 05, 2018 at 03:16:21PM +0100, Thomas Monjalon wrote:
> > > 05/02/2018 14:44, Adrien Mazarguil:
> > > > On Mon, Feb 05, 2018 at 10:58:06AM -020
In case vhost_user_iotlb_miss returns an error, the pending IOTLB
entry has to be removed from the list as no IOTLB update will be
received.
Fixes: fed67a20ac94 ("vhost: introduce guest IOVA to backend VA helper")
Cc: sta...@dpdk.org
Suggested-by: Tiwei Bie
Signed-off-by: Maxime Coquelin
---
l
In the unlikely case the IOTLB memory pool runs out of memory,
an issue may happen if all entries are used by the IOTLB cache,
and an IOTLB miss happen. If the iotlb pending list is empty,
then no memory is freed and allocation fails a second time.
This patch fixes this by doing an IOTLB cache ran
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 v3:
-
- Fix 32bits compilation issue in error message in patch 2 (Ferruh)
Changes since v2:
-
-
On 2/1/2018 10:59 AM, Gaetan Rivet wrote:
> 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
Applied to dpdk-next-n
On 2/5/2018 2:59 PM, Ferruh Yigit wrote:
> On 2/1/2018 10:48 AM, Radu Nicolau wrote:
>> Needed if used with net/bonding
>>
>> Signed-off-by: Radu Nicolau
>
> Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/master, thanks.
On 2/1/2018 10:48 AM, Radu Nicolau wrote:
> Needed if used with net/bonding
>
> Signed-off-by: Radu Nicolau
Reviewed-by: Ferruh Yigit
On Mon, Feb 05, 2018 at 12:37:34PM -0200, Marcelo Ricardo Leitner wrote:
> On Mon, Feb 05, 2018 at 03:16:21PM +0100, Thomas Monjalon wrote:
> > 05/02/2018 14:44, Adrien Mazarguil:
> > > On Mon, Feb 05, 2018 at 10:58:06AM -0200, Marcelo Ricardo Leitner wrote:
> > > > On Mon, Feb 05, 2018 at 12:24:23
Acked-by: Pascal Mazon
On 05/02/2018 11:59, Ophir Munk wrote:
> TAP device is supporting multi segments Tx, however this capability is
> not reported when querying the TAP device.
> This commit adds this capability report.
>
> Fixes: 818fe14a9891 ("net/tap: use new Tx offloads API")
> Cc: sta...@
The mitigation is good enough, random packets are more likely to have
cb[1] == 0 than something above 7cafe800.
Acked-by: Pascal Mazon
On 05/02/2018 15:40, Ophir Munk wrote:
> The eBPF classifier (section "cls_q" in tap_bpf_program.c) is tracing
> marked packets in which skb->cb[1] contains an R
On 2/5/2018 2:40 PM, Ferruh Yigit wrote:
> On 2/1/2018 10:47 AM, Radu Nicolau wrote:
>> Needed if used with net/bonding
>>
>> Signed-off-by: Radu Nicolau
>
> Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/master, thanks.
The eBPF classifier (section "cls_q" in tap_bpf_program.c) is tracing
marked packets in which skb->cb[1] contains an RSS queue number, and
redirects those packets to the matched queue.
It is expected that skb->cb[1] has been previously set with a valid RSS
queue number during an eBPF action (sectio
v2:
* Minor commit message updates
* Update a comment in code
Ophir Munk (1):
net/tap: fix eBPF handling of non-RSS flows
drivers/net/tap/tap_bpf_insns.h | 23 +--
drivers/net/tap/tap_bpf_program.c | 9 ++---
2 files changed, 19 insertions(+), 13 deletions(-)
--
2.
On 2/1/2018 10:47 AM, Radu Nicolau wrote:
> Needed if used with net/bonding
>
> Signed-off-by: Radu Nicolau
Reviewed-by: Ferruh Yigit
On Mon, Feb 05, 2018 at 03:16:21PM +0100, Thomas Monjalon wrote:
> 05/02/2018 14:44, Adrien Mazarguil:
> > On Mon, Feb 05, 2018 at 10:58:06AM -0200, Marcelo Ricardo Leitner wrote:
> > > On Mon, Feb 05, 2018 at 12:24:23PM +, Van Haaren, Harry wrote:
> > > > > From: dev [mailto:dev-boun...@dpdk.o
Added note section to update information for use cases working with
multiple crypto devices.
Signed-off-by: Vipin Varghese
---
doc/guides/sample_app_ug/l2_forward_crypto.rst | 8
1 file changed, 8 insertions(+)
diff --git a/doc/guides/sample_app_ug/l2_forward_crypto.rst
b/doc/guides/s
On Mon, Feb 05, 2018 at 03:16:21PM +0100, Thomas Monjalon wrote:
> 05/02/2018 14:44, Adrien Mazarguil:
> > On Mon, Feb 05, 2018 at 10:58:06AM -0200, Marcelo Ricardo Leitner wrote:
> > > On Mon, Feb 05, 2018 at 12:24:23PM +, Van Haaren, Harry wrote:
> > > > > From: dev [mailto:dev-boun...@dpdk.o
Add foot note & example to inform user how to use multiple instance.
Signed-off-by: Vipin Varghese
---
doc/guides/cryptodevs/null.rst | 20 +---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/doc/guides/cryptodevs/null.rst b/doc/guides/cryptodevs/null.rst
index 03
On 2/1/2018 2:47 PM, Yuanhan Liu wrote:
> 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 e37ff954405addb8ea422426
On 2/1/2018 12:58 PM, Maxime Coquelin wrote:
>
>
> 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_NE
Add note information to intimate about use of option '-d' for shared
library in DPDK application.
Signed-off-by: Vipin Varghese
---
doc/guides/nics/build_and_test.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/nics/build_and_test.rst
b/doc/guides/nics/build_and_test.rst
05/02/2018 14:44, Adrien Mazarguil:
> On Mon, Feb 05, 2018 at 10:58:06AM -0200, Marcelo Ricardo Leitner wrote:
> > On Mon, Feb 05, 2018 at 12:24:23PM +, Van Haaren, Harry wrote:
> > > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Marcelo Ricardo
> > > > Leitner
> > > > Sent: Monday, F
1 - 100 of 194 matches
Mail list logo
