> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Tuesday, April 10, 2018 4:07 PM
> To: Gujjar, Abhinandan S ;
> jerin.ja...@caviumnetworks.com; hemant.agra...@nxp.com; dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Doherty, Declan
> ; Vangati, Narender
> ; Rao, Ni
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Tuesday, April 10, 2018 2:52 PM
> To: Gujjar, Abhinandan S ; De Lara Guarch, Pablo
> ; Doherty, Declan
> ; jerin.ja...@caviumnetworks.com;
> hemant.agra...@nxp.com; dev@dpdk.org
> Cc: Vangati, Narender ; Rao, Ni
Hi Jerin,
Please find some comments inline
> -Original Message-
> From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> Sent: Tuesday, April 10, 2018 11:38 AM
> To: Gujjar, Abhinandan S
> Cc: hemant.agra...@nxp.com; akhil.go...@nxp.com; dev@dpdk.org; De Lara
> Guarch, Pablo ; Doher
On 4/12/2018 4:38 AM, Pablo de Lara wrote:
Signed-off-by: Pablo de Lara
---
.../common/include/rte_pci_dev_feature_defs.h | 58 +-
.../common/include/rte_pci_dev_features.h | 58 +-
2 files changed, 4 insertions(+), 112 deletions(-)
A
Please, could you rebase on HEAD (on top of Anatoly's patches)?
done
Signed-off-by: Hemant Agrawal
---
doc/api/doxy-api-index.md| 3 ++-
doc/api/doxy-api.conf| 1 +
lib/librte_eal/common/include/rte_vfio.h | 5 +
3 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/doc/api/doxy-api-index.md b/doc/api/doxy-api-index.
This patch moves some of the internal vfio functions from
eal_vfio.h to rte_vfio.h for common uses with "rte_" prefix.
This patch also change the FSLMC bus usages from the internal
VFIO functions to external ones with "rte_" prefix
Signed-off-by: Hemant Agrawal
Acked-by: Anatoly Burakov
---
v6:
> On 10-Apr-2018, at 11:43 AM, Yong Wang wrote:
>
> When using 4095, I assume you enabled trunk mode on ESX vswitch. What ESX
> version did you use? Is the vswitch standard switch or DVS? We have tested
> over ESX6.0 and onwards plus DPDK 17.05 and it should work.
Yes, the 4095 enables trun
From: "Chen, Junjie"
When vhost backend works in dequeue zero copy mode, nic locks virtio's
buffer until there is less or equal than tx_free_threshold buffer remain
and then free number of tx burst buffer. This causes packets drop in
virtio side and impacts zero copy performance. So we need to in
Gentle reminder to review the RFC.
Regards
Sunil Kumar
-Original Message-
From: Sunil Kumar Kori [mailto:sunil.k...@nxp.com]
Sent: Monday, March 19, 2018 7:15 PM
To: dev@dpdk.org
Cc: Sunil Kumar Kori ; Hemant Agrawal
Subject: [PATCH] examples/l3fwd: adding event queue support
This pat
From: "Chen, Junjie"
Sometimes gcc does not inline the function despite keyword *inline*,
we obeserve rte_movX is not inline when doing performance profiling,
so use *always_inline* keyword to force gcc to inline the function.
Signed-off-by: Chen, Junjie
---
.../common/include/arch/x86/rte_mem
Hi,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Thursday, April 12, 2018 2:59 AM
> To: Wang, Xiao W
> Cc: maxime.coque...@redhat.com; dev@dpdk.org; Wang, Zhihong
> ; Tan, Jianfeng ; Bie,
> Tiwei ; Liang, Cunming ;
> Daly, Dan ; tho...@monjalon.net;
> gaetan.ri...@6wind.com; Burakov
-Original Message-
> Date: Fri, 30 Mar 2018 15:47:55 +0200
> From: Thomas Monjalon
> To: dev@dpdk.org
> Cc: Ajit Khaparde , Jerin Jacob
> , Shijith Thotton
> , Santosh Shukla
> , Rahul Lakkireddy
> , John Daley , Wenzhuo
> Lu , Konstantin Ananyev
> , Beilei Xing , Qi
> Zhang , Jingj
Hi All
From: Jeff Guo, Friday, April 6, 2018 1:57 PM
> Use testpmd for example, to show how an application smoothly handle
> failure when device be hot removal, and show how to auto bind kernal driver
> to preparing attach device when device being hot insertion.
I saw the kmod of old devices were
On Mon, Feb 5, 2018 at 8:51 AM, wrote:
> From: Tonghao Zhang
>
> The patches in the patchset have no dependency. But all of them is
> about ixgbe or ixgbevf. The patch 1 and 2 add the itr configuration
> for ixgbe and ixgbevf, the user and developer can configure it for
> their platform. Other p
Hi Adrien:
Thank you so much for your careful review and helpful suggestions!
I agree with most of your comments, except couple question about
RTE_FLOW_ITEM_TYPE_TGT_ADDR and RTE_FLOW_ITEM_IPV6_EXT_HDR
Please see my comment inline.
Thanks!
Qi
> -Original Message-
Hello,
I want to use DPDK's rte_hash library to keep track of tcp flows. The
lookups will be done by multiple threads but inserts will be done only
on one thread.
As per the documentation rte_hash library has thread safe lookups. Key
/data inserts should be done on single thread, since those ope
On Wed, Apr 11, 2018 at 8:21 PM, Zhang, Qi Z wrote:
> Hi tonghao:
>
>> -Original Message-
>> From: Tonghao Zhang [mailto:xiangxia.m@gmail.com]
>> Sent: Monday, April 9, 2018 8:53 AM
>> To: Zhang, Qi Z
>> Cc: Xing, Beilei ; Dai, Wei ;
>> Zhang,
>> Helin ; Lu, Wenzhuo ;
>> dev@dpdk.org
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Zhang, Qi Z
> Sent: Wednesday, April 11, 2018 8:37 PM
> To: Zhao1, Wei; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] net/i40e: change warning log to flow error
> set
>
>
>
> > -Or
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Zhang, Qi Z
> Sent: Wednesday, April 11, 2018 8:30 PM
> To: Zhao1, Wei; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] net/i40e: add comment and clean code for
> flow RSS
>
>
>
> >
Signed-off-by: Pablo de Lara
---
.../common/include/rte_pci_dev_feature_defs.h | 58 +-
.../common/include/rte_pci_dev_features.h | 58 +-
2 files changed, 4 insertions(+), 112 deletions(-)
diff --git a/lib/librte_eal/common/include/rte_pci_d
02/04/2018 14:06, Neil Horman:
> https://dpdk.org/tracker/show_bug.cgi?id=18
>
> Indicated that several mmap call sites in the linuxapp eal code used an
> fd that was not -1 in their calls while using MAP_ANONYMOUS. While
> probably not a huge deal, the man page does say the fd should be -1 for
>
09/04/2018 12:22, Hemant Agrawal:
> From: Sunil Kumar Kori
>
> Fixes: 9d32ef0f5d61 ("bus/dpaa: support creating dynamic HW portal")
> Coverity issue: 268332
> Cc: sta...@dpdk.org
>
> Signed-off-by: Sunil Kumar Kori
> Acked-by: Hemant Agrawal
Series applied, thanks
> > The rte_ctrlmbuf structure is not used by any example application
> > in dpdk. Remove it, as announced on the mailing list.
> >
> > Signed-off-by: Olivier Matz
>
> Acked-by: Jerin Jacob
Applied, thanks
On Wed, 11 Apr 2018 22:42:55 +0200
Thomas Monjalon wrote:
> 11/04/2018 19:01, Pavan Nikhilesh:
> > Use __atomic_exchange_n instead of __atomic_exchange_(2/4/8).
> > The error was:
> > include/generic/rte_atomic.h:215:9: error:
> > implicit declaration of function '__atomic_exchang
30/03/2018 12:34, Ferruh Yigit:
> On 3/29/2018 5:37 PM, Ajit Khaparde wrote:
> > From: Darren Edamura
> >
> > Probe function should exit immediately if pcie bridge detected
> >
> > Signed-off-by: Darren Edamura
> > Signed-off-by: Rahul Gupta
> > Signed-off-by: Scott Branden
> > Signed-off-by:
Anyone to review, please?
02/04/2018 20:24, Aaron Conole:
> Rather than attempting to load the contents of the auxv directly,
> prefer to use an exposed API - and if that doesn't exist then attempt
> to load the vector. This is because on some systems, when a user
> is downgraded, the /proc/self/
04/04/2018 09:48, Hemant Agrawal:
> This patch moves some of the internal vfio functions from
> eal_vfio.h to rte_vfio.h for common uses with "rte_" prefix.
>
> This patch also change the FSLMC bus usages from the internal
> VFIO functions to external ones with "rte_" prefix
>
> Signed-off-by: He
11/04/2018 19:01, Pavan Nikhilesh:
> Use __atomic_exchange_n instead of __atomic_exchange_(2/4/8).
> The error was:
> include/generic/rte_atomic.h:215:9: error:
> implicit declaration of function '__atomic_exchange_2'
> is invalid in C99
> include/generic/rte
11/04/2018 21:56, Thomas Monjalon:
> 11/04/2018 21:46, Pavan Nikhilesh:
> > On Wed, Apr 11, 2018 at 09:40:30PM +0200, Thomas Monjalon wrote:
> > > 11/04/2018 21:09, Andrew Rybchenko:
> > > > Hello,
> > > >
> > > > build fails on RHEL 7.4. I've not tried to dig it.
> > >
> > > Thanks for reporting.
11/04/2018 21:46, Pavan Nikhilesh:
> On Wed, Apr 11, 2018 at 09:40:30PM +0200, Thomas Monjalon wrote:
> > 11/04/2018 21:09, Andrew Rybchenko:
> > > Hello,
> > >
> > > build fails on RHEL 7.4. I've not tried to dig it.
> >
> > Thanks for reporting.
> >
> > [...]
> > > ‘FALLOC_FL_PUNCH_HOLE’ undeclar
On Wed, Apr 11, 2018 at 09:40:30PM +0200, Thomas Monjalon wrote:
> 11/04/2018 21:09, Andrew Rybchenko:
> > Hello,
> >
> > build fails on RHEL 7.4. I've not tried to dig it.
>
> Thanks for reporting.
>
> [...]
> > ‘FALLOC_FL_PUNCH_HOLE’ undeclared (first use in this function)
> [...]
> > ‘FALLOC_FL_
11/04/2018 21:09, Andrew Rybchenko:
> Hello,
>
> build fails on RHEL 7.4. I've not tried to dig it.
Thanks for reporting.
[...]
> ‘FALLOC_FL_PUNCH_HOLE’ undeclared (first use in this function)
[...]
> ‘FALLOC_FL_KEEP_SIZE’ undeclared (first use in this function)
These constants were defined in
On 4/11/2018 5:32 PM, Olivier Matz wrote:
> Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a
> return code is added to notify the caller (librte_ether) if an error
> occurred in the PMD.
>
> The new default MAC address is now copied in dev->data->mac_addrs[0]
> only if the o
Hello,
build fails on RHEL 7.4. I've not tried to dig it.
lib/librte_eal/linuxapp/eal/eal_memalloc.c: In function ‘resize_hugefile’:
librte_eal/linuxapp/eal/eal_memalloc.c:343:27: error:
‘FALLOC_FL_PUNCH_HOLE’ undeclared (first use in this function)
int flags = grow ? 0 : FALLOC_FL_PUNCH_
On 4/10/2018 1:20 AM, Ajit Khaparde wrote:
> @@ -158,11 +168,10 @@ The libraries prepended with a plus sign were
> incremented in this version.
> librte_bus_vdev.so.1
> librte_cfgfile.so.2
> librte_cmdline.so.2
> - + librte_common_octeontx.so.1
> librte_cryptodev.so.4
>
On 4/5/2018 7:07 PM, Xiao Wang wrote:
> The IFCVF vDPA (vhost data path acceleration) driver provides support for
> the Intel FPGA 100G VF (IFCVF). IFCVF's datapath is virtio ring compatible,
> it works as a HW vhost backend which can send/receive packets to/from
> virtio directly by DMA.
>
> Diff
On 4/5/2018 7:06 PM, Xiao Wang wrote:
> If we want a virtio device to work in vDPA (vhost data path acceleration)
> mode, we could add a "vdpa=1" devarg for this device to specify the mode.
>
> This patch let virtio pmd skip device probe when detecting this parameter.
>
> Signed-off-by: Xiao Wang
On 4/5/2018 7:06 PM, Xiao Wang wrote:
> This patch set has dependency on http://dpdk.org/dev/patchwork/patch/36772/
> (vhost: support selective datapath).
>
> IFCVF driver
>
> The IFCVF vDPA (vhost data path acceleration) driver provides support for the
> Intel FPGA 100G VF (IFCVF). I
11/04/2018 14:29, Anatoly Burakov:
> This patchset introduces dynamic memory allocation for DPDK (aka memory
> hotplug). Based upon RFC submitted in December [1].
Applied (with some fixes discussed together), thanks for the huge work!
Now waiting adjustments for some devices or platforms.
On 4/5/2018 9:03 PM, Maxime Coquelin wrote:
>
>
> On 04/05/2018 10:08 AM, Tomasz Duszynski wrote:
>> This patch addresses following meson build issues:
>>
>> 1) Since rte_vdpa.h includes rte_pci.h it introduces pci
>> dependency thus deps array should be updated accordingly.
>>
>> 2) Since vh
On 4/11/2018 3:41 PM, Maxime Coquelin wrote:
>
>
> On 04/11/2018 12:09 PM, Fan Zhang wrote:
>> Fixes: cd39f8e4fd2a ("vhost/crypto: add request handler")
>>
>> This patch fixes the descriptor moving for copy mode by adding
>> the missing moving step after destination data parsing.
>>
>> Signed-off
On Wed, Apr 11, 2018 at 05:02:50PM +0300, Andrew Rybchenko wrote:
> On 04/11/2018 02:39 PM, Ananyev, Konstantin wrote:
> > Hi Yongseok,
> >
> > > > > On Mon, Apr 09, 2018 at 06:04:34PM +0200, Olivier Matz wrote:
> > > > > > Hi Yongseok,
> > > > > >
> > > > > > On Tue, Apr 03, 2018 at 05:12:06PM -
On Wed, Apr 11, 2018 at 11:39:47AM +, Ananyev, Konstantin wrote:
>
> Hi Yongseok,
>
> > > >
> > > > On Mon, Apr 09, 2018 at 06:04:34PM +0200, Olivier Matz wrote:
> > > > > Hi Yongseok,
> > > > >
> > > > > On Tue, Apr 03, 2018 at 05:12:06PM -0700, Yongseok Koh wrote:
> > > > > > On Tue, Apr 03
Use __atomic_exchange_n instead of __atomic_exchange_(2/4/8).
The error was:
include/generic/rte_atomic.h:215:9: error:
implicit declaration of function '__atomic_exchange_2'
is invalid in C99
include/generic/rte_atomic.h:494:9: error:
Change the prototype and the behavior of dev_ops->eth_mac_addr_set(): a
return code is added to notify the caller (librte_ether) if an error
occurred in the PMD.
The new default MAC address is now copied in dev->data->mac_addrs[0]
only if the operation is successful.
The patch also updates all th
On Sun, Apr 01, 2018 at 05:19:20PM -0400, Qi Zhang wrote:
> Enhanced the action RTE_FLOW_TYPE_ACTION_COUNT, number of
> milliseconds since last hit can be queried.
>
> Signed-off-by: Qi Zhang
Please confirm whether existing devices have the ability to report time
elapsed since last hit, or if PM
On Sun, Apr 01, 2018 at 05:19:21PM -0400, Qi Zhang wrote:
> Add new protocol header match support as below
>
> RTE_FLOW_ITEM_TYPE_ARP
> - match IPv4 ARP header
> RTE_FLOW_ITEM_TYPE_EXT_HDR_ANY
> - match any IPv6 extension header
While properly defined in the patch, "IPV6" is missing h
On Sun, Apr 01, 2018 at 05:19:19PM -0400, Qi Zhang wrote:
> Add action RTE_FLOW_ACTION_TYPE_PORT, it can be used to redirect
> a packet to a network interface that connect to the same switch
> domain, rte_ethdev's port_id is used as an identification of the
> destination. A typical use case is: wit
Hi
On Fri, Mar 30, 2018 at 3:47 PM, Thomas Monjalon
wrote:
> There are some discussions about a specific part of the offload API:
> "To enable per-port offload, the offload should be set on both
> device configuration and queue setup."
>
> It means the application must repeat the
On 04/11/2018 12:28 AM, Thomas Monjalon wrote:
> Signed-off-by: Thomas Monjalon
> ---
> Patch for the website (to w...@dpdk.org) Cc'ed to dev@dpdk.org
>
> v2:
> - more volunteers
> - propose to do .1 release after -rc1 of next branch.
>
> ---
Acked-by: Kevin Traynor
On 11-Apr-18 3:43 PM, Andrew Rybchenko wrote:
On 04/11/2018 03:29 PM, Anatoly Burakov wrote:
If a user has specified that the zone should have contiguous memory,
use the new _contig allocation API's instead of normal ones.
Just one minor nit..
As I understand _contig above is an artefact of th
On 04/11/2018 04:46 PM, Maxime Coquelin wrote:
On 03/29/2018 06:05 PM, Chas Williams wrote:
From: Robert Shearman
The vid and port of the vq were only set on queues created during initial
device setup.
Fixes: ee584e9710b9 ("vhost: add driver on top of the library")
Cc: sta...@dpdk.org
Si
On 03/29/2018 06:05 PM, Chas Williams wrote:
From: Jan Blunck
This lets the vhost driver handle the VLAN header like the virtio driver
in software.
Signed-off-by: Jan Blunck
---
drivers/net/vhost/rte_eth_vhost.c | 35 ++-
1 file changed, 34 insertions(+),
On 03/29/2018 06:05 PM, Chas Williams wrote:
From: Robert Shearman
The vid and port of the vq were only set on queues created during initial
device setup.
Fixes: ee584e9710b9 ("vhost: add driver on top of the library")
Cc: sta...@dpdk.org
Signed-off-by: Robert Shearman
Signed-off-by: Chas
On Wed, Apr 11, 2018 at 04:07:13PM +0200, Rafal Kozik wrote:
> Support for write combining.
>
> Rafal Kozik (4):
> igb_uio: add wc option
> bus/pci: reference driver structure
> eal: enable WC during resources mapping
> net/ena: enable WC
>
> drivers/bus/pci/linux/pci_uio.c | 39
On 04/11/2018 03:29 PM, Anatoly Burakov wrote:
If a user has specified that the zone should have contiguous memory,
use the new _contig allocation API's instead of normal ones.
Just one minor nit..
As I understand _contig above is an artefact of the previous approach
with dedicated function for
On Fri, Mar 30, 2018 at 03:47:55PM +0200, Thomas Monjalon wrote:
> There are some discussions about a specific part of the offload API:
> "To enable per-port offload, the offload should be set on both
> device configuration and queue setup."
>
> It means the application must repeat the
On 04/11/2018 12:09 PM, Fan Zhang wrote:
Fixes: cd39f8e4fd2a ("vhost/crypto: add request handler")
This patch fixes the descriptor moving for copy mode by adding
the missing moving step after destination data parsing.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 9 +++
On 04/11/2018 12:09 PM, Fan Zhang wrote:
Fixes: cd39f8e4fd2a ("vhost/crypto: add request handler")
This patch fixes the descriptor moving for copy mode by adding
the missing moving step after destination data parsing.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 9 +++
On 04/11/2018 10:59 AM, Maxime Coquelin wrote:
On 04/11/2018 10:47 AM, Maxime Coquelin wrote:
On 04/09/2018 05:34 PM, Fan Zhang wrote:
This patch removes unnecessary packet dump for debugging.
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 36
-
On Wed, Apr 11, 2018 at 01:29:59PM +0100, Anatoly Burakov wrote:
> If a user has specified that the zone should have contiguous memory,
> use the new _contig allocation API's instead of normal ones.
> Otherwise, account for the fact that unless we're in IOVA_AS_VA
> mode, we cannot guarantee that t
On Wed, Apr 11, 2018 at 01:29:59PM +0100, Anatoly Burakov wrote:
> If a user has specified that the zone should have contiguous memory,
> use the new _contig allocation API's instead of normal ones.
> Otherwise, account for the fact that unless we're in IOVA_AS_VA
> mode, we cannot guarantee that t
On 03/29/2018 02:14 PM, Maxime Coquelin wrote:
On 03/14/2018 05:24 PM, Junjie Chen wrote:
In vhost-switch example, when binding nic to vfio-pci with iommu enabled,
dequeue zero copy cannot work in VM2NIC mode due to no iommu dma mapping
is setup for guest memory currently.
Signed-off-by: Ju
Hi Pablo
//snip
>> 1.9.1
>
>As already discussed in separate mails, I will defer these patches to 18.08,
>targetting an earlier merge for that release.
>
Ok. Look forward to review/ack-by for same.
Thanks
Shally
>Thanks,
>Pablo
Unit Testcases are added for power_acpi_cpu_freq,
power_kvm_vm_test to improve coverage
Signed-off-by: Jananee Parthasarathy
Acked-by: David Hunt
---
V3: removed unnecessary extern funtion prototypes.
---
test/test/test_power_acpi_cpufreq.c | 2 +-
test/test/test_power_kvm_vm.c | 60
On Wed, 11 Apr 2018 12:01:09 +
"Weglicki, MichalX" wrote:
> Hello,
>
> I'm trying to test very simple scenario, creating two VFs and testing it with
> test-pmd. Unfortunately I can't make it to work
> DPDK Version: v17.11 (I've checked also 18.02)
> NIC: Niantic 82599ES 10-Gigabit SFI/SFP+
Reference driver structure before calling rte_pci_map_device.
It allow to use driver flags for adjusting configuration.
Signed-off-by: Rafal Kozik
---
drivers/bus/pci/pci_common.c | 13 -
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/bus/pci/pci_common.c b/dri
Write combining (wc) increase NIC performenca by making better
utilization of PCI bus, but cannot be used by all PMD.
It will be enable only if RTE_PCI_DRV_WC_ACTIVATE will be set in
drivers flags. For proper work also igb driver must be loaded with
wc_activate set to 1.
When mapping PCI resource
Write combining (wc) increase NIC performenca by making better
utilization of PCI bus. ENA support this feature.
To enable it load igb driver with wc_activate set to 1.
Signed-off-by: Rafal Kozik
---
drivers/net/ena/ena_ethdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --gi
Support for write combining.
Rafal Kozik (4):
igb_uio: add wc option
bus/pci: reference driver structure
eal: enable WC during resources mapping
net/ena: enable WC
drivers/bus/pci/linux/pci_uio.c | 39 ---
drivers/bus/pci/pci_common.c| 13 -
Write combining (wc) increase NIC performance by making better
utilization of PCI bus, but cannot be use by all PMD.
Parameter wc_activate add possibility to enable it for
those PMD that could support it.
Signed-off-by: Rafal Kozik
---
kernel/linux/igb_uio/igb_uio.c | 17 ++---
1 fi
On 04/11/2018 02:39 PM, Ananyev, Konstantin wrote:
Hi Yongseok,
On Mon, Apr 09, 2018 at 06:04:34PM +0200, Olivier Matz wrote:
Hi Yongseok,
On Tue, Apr 03, 2018 at 05:12:06PM -0700, Yongseok Koh wrote:
On Tue, Apr 03, 2018 at 10:26:15AM +0200, Olivier Matz wrote:
Hi,
On Mon, Apr 02, 2018 at
Thanks for the review.
I have sent an updated patch.
regards,
Shweta
On Wed, Apr 4, 2018 at 3:15 AM, Lu, Wenzhuo wrote:
> Hi Shweta,
>
> > -Original Message-
> > From: Shweta Choudaha [mailto:shweta.choud...@gmail.com]
> > Sent: Thursday, March 22, 2018 1:36 AM
> > To: dev@dpdk.org
> >
From: Shweta Choudaha
Add ixgbe MDIO lock/unlock and access APIs to read and write registers
using specific device address. This provides MDIO access to any devices
that are not associated with the autoprobed PHY.Export these APIs via
the map file
Signed-off-by: Shweta Choudaha
Reviewed-by: Cha
On 04/09/2018 05:42 PM, Adrien Mazarguil wrote:
On Sat, Apr 07, 2018 at 12:05:51PM +0300, Andrew Rybchenko wrote:
On 04/06/2018 04:25 PM, Adrien Mazarguil wrote:
Since its inception, the rte_flow RSS action has been relying in part on
external struct rte_eth_rss_conf for compatibility with the
hained metadata instead of prepend metadata was added in
firmware version 4. However, it could be old firmwares evolving
but not supporting chained metadata.
This patch adds support for an old firmware being updated and
getting a firmware version number higher than 4, but it still not
implementing
On 04/10/2018 07:36 PM, Adrien Mazarguil wrote:
Since its inception, the rte_flow RSS action has been relying in part on
external struct rte_eth_rss_conf for compatibility with the legacy RSS API.
This structure lacks parameters such as the hash algorithm to use, and more
recently, a method to te
On 04/10/2018 07:37 PM, Adrien Mazarguil wrote:
RTE_FLOW_ACTION_TYPE_PORT_ID brings the ability to inject matching traffic
into a different device, as identified by its DPDK port ID.
This is normally only supported when the target port ID has some kind of
relationship with the port ID the flow r
Hi Nelio,
> -Original Message-
> From: Nélio Laranjeiro
> Sent: Wednesday, April 11, 2018 8:37 PM
> To: Xueming(Steven) Li
> Cc: Shahaf Shuler ; dev@dpdk.org
> Subject: Re: [PATCH v2 13/15] net/mlx5: setup RSS flow regardless of queue
> count
>
> On Tue, Apr 10, 2018 at 09:34:13PM +0800
On 04/10/2018 07:37 PM, Adrien Mazarguil wrote:
This patch adds the missing action counterpart to the PHY_PORT pattern
item, that is, the ability to directly inject matching traffic into a
physical port of the underlying device.
It breaks ABI compatibility for the following public functions:
-
On 04/10/2018 07:37 PM, Adrien Mazarguil wrote:
While RTE_FLOW_ITEM_TYPE_PORT refers to physical ports of the underlying
device using specific identifiers, these are often confused with DPDK port
IDs exposed to applications in the global name space.
Since this pattern item is seldom used, rename
On 04/10/2018 07:36 PM, Adrien Mazarguil wrote:
VLAN TCI is a 16-bit field broken down as PCP (3b), DEI (1b) and VID (12b).
The default mask used by PMDs for the VLAN pattern when one isn't provided
by the application comprises the entire TCI, which is problematic because
most devices only suppo
Hi Fiona,
> -Original Message-
> From: Trahe, Fiona
> Sent: Friday, April 6, 2018 7:52 PM
> To: dev@dpdk.org; De Lara Guarch, Pablo
> Cc: Trahe, Fiona ; Jozwiak, TomaszX
>
> Subject: [PATCH 00/30] crypto/qat: refactor to support multiple service
>
> The QAT crypto PMD was peppered with
On 04/10/2018 07:36 PM, Adrien Mazarguil wrote:
TPID handling in rte_flow VLAN and E_TAG pattern item definitions is not
consistent with the normal stacking order of pattern items, which is
confusing to applications.
Problem is that when followed by one of these layers, the EtherType field
of th
11/04/2018 14:32, Nélio Laranjeiro:
> On Tue, Apr 10, 2018 at 09:34:12PM +0800, Xueming Li wrote:
> > -- Inner RSS for VXLAN frames is not supported yet.
> > -- Hardware checksum RX offloads for VXLAN inner header are not supported
> > yet.
> > - For secondary process:
>
> Inner RSS may deserve
> -Original Message-
> From: Zhao1, Wei
> Sent: Monday, April 9, 2018 10:27 AM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Zhang, Qi Z ; Zhao1, Wei
>
> Subject: [PATCH v2] net/i40e: change warning log to flow error set
>
> There is a specific error set function for flow error configuratio
On 04/10/2018 07:36 PM, Adrien Mazarguil wrote:
By definition, RSS involves some kind of hash algorithm, usually Toeplitz.
Until now it could not be modified on a flow rule basis and PMDs had to
always assume RTE_ETH_HASH_FUNCTION_DEFAULT, which remains the default
behavior when unspecified (0).
Hi Shally,
> -Original Message-
> From: Shally Verma [mailto:shally.ve...@caviumnetworks.com]
> Sent: Thursday, April 5, 2018 12:25 PM
> To: De Lara Guarch, Pablo
> Cc: Doherty, Declan ; Trahe, Fiona
> ; pathr...@caviumnetworks.com;
> ss...@caviumnetworks.com; agu...@caviumnetworks.com; d
On Tue, Apr 10, 2018 at 09:34:13PM +0800, Xueming Li wrote:
> In some environments it is desirable to have the NIC perform RSS
> normally on the packet regardless of the number of queues configured.
> The RSS hash result that is stored in the mbuf can then be used by
> the application to make decis
On Tue, Apr 10, 2018 at 09:34:12PM +0800, Xueming Li wrote:
> Remove tunnel limitations, add new hardware tunnel offload features.
>
> Signed-off-by: Xueming Li
> ---
> doc/guides/nics/mlx5.rst | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/doc/guides/nics/mlx5.rst
>From 3293d014123150bcd0650ce1d09b19bbb9eae9c4 Mon Sep 17 00:00:00 2001
From: zhouyangchao
Date: Tue, 10 Apr 2018 18:26:35 +0800
Subject: [PATCH] kni: fix possible rx_q mbuf leak and speed up alloc_q release
rx_q fifo can only be released by kernel thread. There may be
mbuf leaks in rx_q because
fslmc bus needs to map all allocated memory for VFIO before
device probe. This bus doesn't support hotplug, so at the time
of this call, all possible device that could be present, are
present. This will also be the place where we install VFIO
callback, although this change will come in the next pat
Callbacks will be triggered just after allocation and just
before deallocation, to ensure that memory address space
referenced in the callback is always valid by the time
callback is called.
Signed-off-by: Anatoly Burakov
Tested-by: Santosh Shukla
Tested-by: Hemant Agrawal
Tested-by: Gowrishank
Before, we were aggregating multiple pages into one memseg, so the
number of memsegs was small. Now, each page gets its own memseg,
so the list of memsegs is huge. To accommodate the new memseg list
size and to keep the under-the-hood workings sane, the memseg list
is now not just a single list, bu
VFIO needs to map and unmap segments for DMA whenever they
become available or unavailable, so register a callback for
memory events, and provide map/unmap functions.
Remove unneeded check for number of segments, as in non-legacy
mode this now becomes a valid scenario.
Signed-off-by: Shreyansh Ja
Now that every other piece of the puzzle is in place, enable non-legacy
init mode.
Signed-off-by: Anatoly Burakov
Tested-by: Santosh Shukla
Tested-by: Hemant Agrawal
Tested-by: Gowrishankar Muthukrishnan
---
lib/librte_eal/linuxapp/eal/eal.c | 2 --
1 file changed, 2 deletions(-)
diff --git
It is common sense to expect for DPDK process to not deallocate any
pages that were preallocated by "-m" or "--socket-mem" flags - yet,
currently, DPDK memory subsystem will do exactly that once it finds
that the pages are unused.
Fix this by marking pages as unfreebale, and preventing malloc from
It's there, so we might as well use it. Some operations will be
sped up by that.
Since we have to allocate an fbarray for memzones, we have to do
it before we initialize memory subsystem, because that, in
secondary processes, will (later) allocate more fbarrays than the
primary process, which will
This set of changes enables rte_malloc to allocate and free memory
as needed. Currently, it is disabled because legacy mem mode is
enabled unconditionally.
The way it works is, first malloc checks if there is enough memory
already allocated to satisfy user's request. If there isn't, we try
and all
1 - 100 of 223 matches
Mail list logo
