I do see current cryptodev unit testcase (inside \test dir) uses
info.sym.max_nb_sessions param for session mempool_create. So, such testcases
change are also in proposal?
Another point, we recently submitted an RFC patch on lib/cryptodev with
asymmetric crypto support (https://dpdk.org/dev/pat
Customized info is updated without checking package
operation - ADD or DEL, it only covers ADD operation
currently. This patch adds process for DEL operation.
Fixes: e163c18a15b0 ("net/i40e: update ptype and pctype info")
Cc: sta...@dpdk.org
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_
This patch will update example application of flow_filting document.
It add Tx queues configuration related comment.
Signed-off-by: Wei Zhao
---
v2:
-change code indentation style.
---
doc/guides/sample_app_ug/flow_filtering.rst | 108 ++--
1 file changed, 72 insertions
This patch will update example application of flow_filting document.
It add Tx queues configuration related comment.
Signed-off-by: Wei Zhao
---
doc/guides/sample_app_ug/flow_filtering.rst | 112 ++--
1 file changed, 74 insertions(+), 38 deletions(-)
diff --git a/doc/gui
Private shaper profiles are attached to nodes defined
in traffic manager hierarchy.
Since not every node must have a configured shaper
testpmd should allow setting shaper profile id to
invalid (RTE_TM_SHAPER_PROFILE_ID_NONE) easily.
This patch follows same approach as in case of setting
parent id
From: Gowrishankar Muthukrishnan
This patch defines __NR_bpf for powerpc architecture and hence,
fixes compiling tap driver for this architecture.
Fixes: b02d85e1 ("net/tap: add eBPF API")
Signed-off-by: Gowrishankar Muthukrishnan
---
drivers/net/tap/tap_bpf.h | 2 ++
1 file changed, 2 insert
We need the synchronous way for multi-process communication,
i.e., blockingly waiting for reply message when we send a request
to the peer process.
We add two APIs rte_eal_mp_request() and rte_eal_mp_reply() for
such use case. By invoking rte_eal_mp_request(), a request message
is sent out, and th
v6->v7:
- Add __rte_experimental tag for new APIs.
- Rebased on master.
v5->v6:
- Correct the API name issue in rte_eal_version.map.
v3->v5:
- Drop the patch 3 on vfio communication (postponed).
- Change names from rte_eal_mp_* -> rte_mp_* as suggested by Thomas.
- Add nb_sent and nb_
Previouly, there are three channels for multi-process
(i.e., primary/secondary) communication.
1. Config-file based channel, in which, the primary process writes
info into a pre-defined config file, and the secondary process
reads the info out.
2. vfio submodule has its own channel ba
On Thursday 25 January 2018 03:23 PM, Hemant Agrawal wrote:
fman/netcfg_layer.c:80:1: error: unused function 'get_num_netcfg_interfaces
' [-Werror,-Wunused-function] get_num_netcfg_interfaces(char *str)
Fixes: 919eeaccb2ba ("bus/dpaa: introduce NXP DPAA bus driver skeleton")
Cc: sta...@dpdk.org
On Thursday 25 January 2018 03:23 PM, Hemant Agrawal wrote:
fman.c:570:15: error: format specifies type 'unsigned short' but the
argument has type 'int' [-Werror,-Wformat] __FILE__, __LINE__, __func__,
fman/netcfg_layer.c:80:1: error: unused function 'get_num_netcfg_interfaces
' [-Werror,-Wunus
On 01/29/2018 08:13 PM, Olivier Matz wrote:
Announce internal PMD API change in the function to set the default MAC
address. The objective is to be able to notify errors occurring in the
PMD.
Link: https://dpdk.org/dev/patchwork/patch/32284/
Signed-off-by: Olivier Matz
---
doc/guides/rel_not
This patch fixes the coverity CHECKED_RETURN issue.
Coverity issue: 257045
Fixes: 48de41ca11f0 ("net/avf: enable link status update")
Reported-by: John McNamara
Signed-off-by: Jingjing Wu
---
drivers/net/avf/avf_ethdev.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Lu, Wenzhuo
> Sent: Tuesday, January 30, 2018 10:25 AM
> To: Zhao1, Wei; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/ixgbe: fix hardware reset issue in VF
>
> Hi,
>
> > -Original
This patch fixes the coverity CHECKED_RETURN issue.
Coverity issue: 257045
Fixes: 48de41ca11f0 ("net/avf: enable link status update")
Reported-by: John McNamara
Signed-off-by: Jingjing Wu
---
drivers/net/avf/avf_ethdev.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git
This patch fixes the coverity UNINIT issue.
Coverity issue: 257016, 257036
Fixes: 69dd4c3d0898 ("net/avf: enable queue and device")
Reported-by: John McNamara
Signed-off-by: Jingjing Wu
---
v2 change:
- add fix for 257016
drivers/net/avf/avf_ethdev.c | 8
1 file changed, 4 insertio
This patch fixes the coverity UNINIT issue.
Coverity issue: 257036
Fixes: 69dd4c3d0898 ("net/avf: enable queue and device")
Reported-by: John McNamara
Signed-off-by: Jingjing Wu
---
drivers/net/avf/avf_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/avf
Hi Konstantin,
> -Original Message-
> From: Ananyev, Konstantin [mailto:konstantin.anan...@intel.com]
> Sent: Tuesday, January 30, 2018 12:49 AM
> To: Xueming(Steven) Li ; Olivier MATZ
>
> Cc: dev@dpdk.org; Wu, Jingjing ; Shahaf Shuler
> ; Yongseok Koh ; Thomas Monjalon
> ; Yigit, Ferruh
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wei Zhao
> Sent: Friday, January 26, 2018 4:47 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z; Zhao1, Wei
> Subject: [dpdk-dev] [PATCH v3] net/i40e: fix issue for RSS flow API
>
> This patch fix issue check from DPDK co
Ok.
> -Original Message-
> From: Lu, Wenzhuo
> Sent: Tuesday, January 30, 2018 10:25 AM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: RE: [PATCH] net/ixgbe: fix hardware reset issue in VF
>
> Hi,
>
> > -Original Message-
> > From: Zhao1, Wei
> > Sent: Monday, J
Hi,
> -Original Message-
> From: Zhao1, Wei
> Sent: Monday, January 29, 2018 4:07 PM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo ; Zhao1, Wei
>
> Subject: [PATCH] net/ixgbe: fix hardware reset issue in VF
>
> There is no specific handling when there is error happened of hardware
> reset process
Hi folks
It is a bit too late for 18.02, and I'd prefer to defer it to 18.05 after being
well
reviewed and tested. Thanks!
/Helin
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Beilei Xing
> Sent: Monday, January 29, 2018 5:54 PM
> To: Zhang, Qi Z; Wu, Jingj
detail as below, bug is happened on bond of enp1s16 and enp1s16f1
[huanghuai-test@yf-mos-test-net14 ~]$ sudo
/usr/local/share/openvswitch/scripts/dpdk_nic_bind --status
Network devices using DPDK-compatible driver
:01:00.0 'Ethernet Controller 10-G
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Martin Weiser
> Sent: Friday, January 26, 2018 5:30 PM
> To: Lu, Wenzhuo; Ananyev, Konstantin
> Cc: dev@dpdk.org; Martin Weiser
> Subject: [dpdk-dev] [PATCH] net/ixgbe: allow for setting 2.5G and 5G speeds on
> X5
I found a bug about ixgbevf kernel module in centos-3.10.0-229.20.1.el7.
And this bug is also in 3.10.0-514.10.2.el7.
How to produce this bug: use SRIOV first, then add lots of network traffic
on vf port, and then ifdow/ifup vf port, after many times, this bug happens.
BUG:
[308026.586026] ixgbe
Hi Fan,
On 2018/1/30 1:19, Zhang, Roy Fan wrote:
Hi Jay,
A few more comments inline.
-Original Message-
From: Jay Zhou [mailto:jianjay.z...@huawei.com]
Sent: Friday, November 17, 2017 5:10 PM
To: dev@dpdk.org
Cc: y...@fridaylinux.org; maxime.coque...@redhat.com;
arei.gong...@huawei.co
27/01/2018 04:48, Guo, Jia:
> On 1/27/2018 12:53 AM, Bruce Richardson wrote:
> > On Fri, Jan 26, 2018 at 11:49:35AM +0800, Jeff Guo wrote:
> >> + ret = rte_service_lcore_add(slcore);
> >> + if (ret) {
> >> + RTE_LOG(ERR, EAL, "dev event monitor lcore add fail");
> >> + return re
26/01/2018 04:41, Jianfeng Tan:
> v5->v6:
> - Correct the API name issue in rte_eal_version.map.
>
> v3->v5:
> - Drop the patch 3 on vfio communication (postponed).
> - Change names from rte_eal_mp_* -> rte_mp_* as suggested by Thomas.
> - Add nb_sent and nb_received in struct rte_mp_reply
25/01/2018 23:21, Thomas Monjalon:
> 23/01/2018 14:59, Shreyansh Jain:
> > Defining a very generic super-set of device type and its device operations
> > that
> > can be exposed such that any new/upcoming/experimental device can be layered
> > over it. 'rawdevice' semantic in this patchset represe
> > Crypto API
> > +M: Pablo de Lara
> > M: Declan Doherty
> > T: git://dpdk.org/next/dpdk-next-crypto
> > F: lib/librte_cryptodev/
> >
> Acked-by: Declan Doherty
Acked-by: Thomas Monjalon
Applied, thanks for your work Pablo
29/01/2018 22:55, Thomas Monjalon:
> Fixes: 8a61c83af2fa ("crypto/mrvl: add mrvl crypto driver")
>
> Signed-off-by: Thomas Monjalon
Applied
29/01/2018 20:30, Pablo de Lara:
> http://dpdk.org/git/next/dpdk-next-crypto
Pulled, thanks
29/01/2018 23:36, Thomas Monjalon:
> Seen with GCC 7.2.0, a switch fall through is detected and
> cannot be fixed with a fall-through comment or attribute:
>
> drivers/crypto/dpaa2_sec/hw/rta/operation_cmd.h:89:6: error:
> this statement may fall through [-Werror=implicit-fallthrough=]
>if (rt
Seen with GCC 7.2.0, a switch fall through is detected and
cannot be fixed with a fall-through comment or attribute:
drivers/crypto/dpaa2_sec/hw/rta/operation_cmd.h:89:6: error:
this statement may fall through [-Werror=implicit-fallthrough=]
if (rta_sec_era < RTA_SEC_ERA_2)
^
The check i
Hi Burakov,
When using vfio-pci on host both VF and PF interfaces works fine with dpdk
i.e. I don't see DMAR fault messages anymore. However, when I attach a VF
interface to a VM and start DPDK with vfio-pci inside VM I still see DMAR
fault messages on host. Both host and VM are booted with 'intel
Fixes: 8a61c83af2fa ("crypto/mrvl: add mrvl crypto driver")
Signed-off-by: Thomas Monjalon
---
drivers/crypto/mrvl/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/mrvl/Makefile b/drivers/crypto/mrvl/Makefile
index 5515b4079..bc5c22700 100644
--- a/driv
22/01/2018 02:48, Neil Horman:
> v5 Changes
> * Clean ups suggested by Thomas
There were a lot of new functions to tag when rebasing this v5.
Rebased and applied, thanks.
23/01/2018 11:35, Mcnamara, John:
>
> > -Original Message-
> > From: Neil Horman [mailto:nhor...@tuxdriver.com]
> > Sent: Monday, January 22, 2018 1:48 AM
> > To: dev@dpdk.org
> > Cc: Neil Horman ; Thomas Monjalon
> > ; Mcnamara, John ;
> > Richardson, Bruce
> > Subject: [[PATCH v5] 5/5]
25/01/2018 22:30, Neil Horman:
> On Thu, Jan 25, 2018 at 11:12:25AM +, Bruce Richardson wrote:
> > Rather than having to work off files all the time, allow stdin and stdout
> > to be used as the source and destination for pmdinfogen. This will allow
> > other possible usages from scripts, e.g.
The following changes since commit 1dd133ae073d9e2bcf6f471f3b831385aa0051c4:
service: restrict finalize to internal usage (2018-01-29 19:24:45 +0100)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-crypto
for you to fetch changes up to 8bf542fda490ed5059d8149e5c7
> -Original Message-
> From: Trahe, Fiona
> Sent: Monday, January 29, 2018 6:34 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Trahe, Fiona
> ; sta...@dpdk.org
> Subject: [PATCH] crypto/qat: fix truncated response ring value
>
> Issue detected by coverity. Could never actually cause
Issue detected by coverity. Could never actually cause a
problem as truncated value (0x7f7f7f7f->0x7f) is what's needed.
But fix in code for correctness.
Fixes: 571365dd4c5e ("crypto/qat: enable Rx head writes coalescing")
Cc: sta...@dpdk.org
Signed-off-by: Fiona Trahe
---
drivers/crypto/qat/qa
On Mon, Jan 29, 2018 at 1:05 PM, Ananyev, Konstantin <
konstantin.anan...@intel.com> wrote:
>
>
> > -Original Message-
> > From: Ananyev, Konstantin
> > Sent: Monday, January 29, 2018 5:51 PM
> > To: Ananyev, Konstantin
> > Subject: [PATCH] net/ixgbe: fix reconfiguration of rx queues
> >
29/01/2018 17:37, Harry van Haaren:
> This commit moves the rte_service_finalize() function
> to be in the component header, and marks it as @internal.
> The function is only called internally by rte_eal_finalize().
>
> Signed-off-by: Harry van Haaren
> Acked-by: Vipin Varghese
Series applied w
29/01/2018 17:37, Harry van Haaren:
> @@ -79,6 +80,10 @@ rte_exit(int exit_code, const char *format, ...)
> va_end(ap);
>
> #ifndef RTE_EAL_ALWAYS_PANIC_ON_ERROR
> + int ret = rte_eal_cleanup();
You should not declare a variable in the middle of the function.
Will fix on apply.
> +
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, January 29, 2018 5:51 PM
> To: Ananyev, Konstantin
> Subject: [PATCH] net/ixgbe: fix reconfiguration of rx queues
>
>
>
> From: Chas Williams [mailto:3ch...@gmail.com]
> Sent: Monday, January 29, 2018 4:49 PM
> To: Anany
29/01/2018 09:10, Hemant Agrawal:
> Hemant Agrawal (6):
> eal: prefix mbuf pool ops name with user defined
> mbuf: maintain user and compile time mempool ops name
> mbuf: add pool ops name selection API helpers
> mbuf: pktmbuf pool create helper for specific mempool ops
> dpaa: register d
Hi Radu,
On 01/29/2018 03:31 PM, Nicolau, Radu wrote:
-Original Message-
From: Anoob Joseph [mailto:anoob.jos...@caviumnetworks.com]
Sent: Monday, January 29, 2018 8:04 AM
To: Akhil Goyal ; Nicolau, Radu
Cc: anoob.jos...@caviumnetworks.com; Doherty, Declan
; Gonzalez Monroy, Sergio
;
On Mon, Jan 29, 2018 at 09:29:52AM +, Ananyev, Konstantin wrote:
> Hi Michael,
>
> >
> > On Mon, Jan 15, 2018 at 04:15:00PM +0100, Maxime Coquelin wrote:
> > > Hi Michael,
> > >
> > > FYI:
> > >
> > > Forwarded Message
> > > Subject: [dpdk-dev] [PATCH v3 2/2] eal/x86: Use lo
Hi Jay,
> > + switch (cmd_id) {
> > + case VIRTIO_CRYPTO_CMD_CIPHER_HASH:
> > + case VIRTIO_CRYPTO_CMD_HASH_CIPHER:
> > + ctrl->u.sym_create_session.op_type
> > + = VIRTIO_CRYPTO_SYM_OP_ALGORITHM_CHAINING;
>
> The above line is clearly a bug.
My bad, it isn't a
When mlx5 is not compiled directly as an independent shared object (e.g.
CONFIG_RTE_BUILD_SHARED_LIB not enabled for performance reasons), DPDK
applications inherit its dependencies on libibverbs and libmlx5 through
rte.app.mk.
This is an issue both when DPDK is delivered as a binary package (Linu
From: Nelio Laranjeiro
This lays the groundwork for externalizing rdma-core as an optional
run-time dependency instead of a mandatory one.
No functional change.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/Makefile | 1 +
drivers/net/mlx5/mlx5.c
When mlx4 is not compiled directly as an independent shared object (e.g.
CONFIG_RTE_BUILD_SHARED_LIB not enabled for performance reasons), DPDK
applications inherit its dependencies on libibverbs and libmlx4 through
rte.app.mk.
This is an issue both when DPDK is delivered as a binary package (Linu
This lays the groundwork for externalizing rdma-core as an optional
run-time dependency instead of a mandatory one.
No functional change.
Signed-off-by: Adrien Mazarguil
Acked-by: Nelio Laranjeiro
---
drivers/net/mlx4/Makefile | 1 +
drivers/net/mlx4/mlx4.c| 35 ++---
drivers/n
A problem encountered with Mellanox PMDs and frequently reported by DPDK
application developers and Linux distribution package maintainers is their
dependency on rdma-core components, namely libibverbs, libmlx4, and libmlx5.
For best performance in applications, DPDK is normally built as a collect
Hi Jay,
A few more comments inline.
> -Original Message-
> From: Jay Zhou [mailto:jianjay.z...@huawei.com]
> Sent: Friday, November 17, 2017 5:10 PM
> To: dev@dpdk.org
> Cc: y...@fridaylinux.org; maxime.coque...@redhat.com;
> arei.gong...@huawei.com; Zhang, Roy Fan ; Zeng,
> Xin ; weidon
On 1/29/2018 7:26 AM, Verma, Shally wrote:
> Hi
>
>> -Original Message-
>> From: Trahe, Fiona [mailto:fiona.tr...@intel.com]
>> Sent: 26 January 2018 00:13
>> To: Verma, Shally ; Ahmed Mansour
>> ; dev@dpdk.org; Akhil Goyal
>>
>> Cc: Challa, Mahipal ; Athreya, Narayana
>> Prasad ; De Lara
Announce internal PMD API change in the function to set the default MAC
address. The objective is to be able to notify errors occurring in the
PMD.
Link: https://dpdk.org/dev/patchwork/patch/32284/
Signed-off-by: Olivier Matz
---
doc/guides/rel_notes/deprecation.rst | 8
1 file changed
Hi Xueming,
>
> This patch introduce new TX offloads flag for devices that support
> tunnel agnostic checksum and TSO offloads.
>
> The support from the device is for inner and outer checksums on
> IPV4/TCP/UDP and TSO for *any packet with the following format*:
>
> < some headers > / [optional
On Mon, Jan 29, 2018 at 11:25 AM, Ananyev, Konstantin <
konstantin.anan...@intel.com> wrote:
>
> > -Original Message-
> > From: Chas Williams [mailto:3ch...@gmail.com]
> > Sent: Monday, January 29, 2018 3:21 PM
> > To: dev@dpdk.org
> > Cc: Lu, Wenzhuo ; Ananyev, Konstantin <
> konstantin.a
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Monday, January 29, 2018 1:12 PM
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; Thomas Monjalon
> ; Richardson, Bruce ;
> Hemant Agrawal ; Lu, Wenzhuo ;
> Ananyev, Konstantin
>
> Subject: [PATCH 16/17] net/ixgb
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Monday, January 29, 2018 1:11 PM
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; Thomas Monjalon
> ; Richardson, Bruce ;
> Hemant Agrawal ; Ananyev, Konstantin
>
> Subject: [PATCH 06/17] eal: use SPDX tags on 6W
This patch adds a call to the newly introduced cleanup()
function just before quitting the app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause hugepag
This patch adds a call to the newly introduced cleanup()
function just before quitting the pdump app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause h
This commit adds a new function rte_eal_cleanup().
The function serves as a hook to allow DPDK to release
internal resources (e.g.: hugepage allocations).
This function allows DPDK to become more like an ordinary
library, where the library context itself can be initialized
and cleaned up by the ap
This commit moves the rte_service_finalize() function
to be in the component header, and marks it as @internal.
The function is only called internally by rte_eal_finalize().
Signed-off-by: Harry van Haaren
Acked-by: Vipin Varghese
---
v4:
- Include Ack
Cc: tho...@monjalon.net
Cc: vipin.vargh.
On 01/29/2018 04:13 PM, Maxime Coquelin wrote:
@@ -52,8 +54,13 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct
vhost_virtqueue *vq,
*/
vhost_user_iotlb_rd_unlock(vq);
- vhost_user_iotlb_pending_insert(vq, iova + tmp_size, perm);
- vhost
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 v2:
-
- patch 2: Fix error message with correct IOVA
Changes since v1:
-
- Make log levels cons
> -Original Message-
> From: Chas Williams [mailto:3ch...@gmail.com]
> Sent: Monday, January 29, 2018 3:21 PM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; Charles (Chas) Williams
>
> Subject: [PATCH] net/ixgbe: fix reconfiguration of rx queues
>
> From: "Charles (Chas)
On Tue, Jan 16, 2018 at 02:13:19PM +0100, Adrien Mazarguil wrote:
> Hi Kevin,
>
> On Fri, Jan 12, 2018 at 10:48:43AM +, Kevin Laatz wrote:
> > Increasing the RX/TX default ring size to 1024/1024 to accommodate for
> > faster NICs. With the increase of number of PPS, a larger RX buffer is
> > r
29/01/2018 10:36, Olivier Matz:
> Fix inconsistency between mbuf structure documentation and flags
> documentation.
>
> Fixes: 380a7aab1ae2 ("mbuf: rename deprecated VLAN flags")
> Cc: sta...@dpdk.org
>
> Reported-by: Morten Brørup
> Signed-off-by: Olivier Matz
Applied, thanks
> -Original Message-
> From: Kovacevic, Marko
> Sent: Monday, January 22, 2018 4:29 PM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; Varghese, Vipin ;
> Kovacevic, Marko ; sta...@dpdk.org
> Subject: [PATCH v1] mk: support building with renamed makefile
>
> The build system made a recursi
29/01/2018 10:37, Olivier Matz:
> For consistency with the Rx flags, the flags PKT_TX_VLAN_PKT and
> PKT_TX_QINQ_PKT are respectively renamed as PKT_TX_VLAN and
> PKT_TX_QINQ. The old defines are deprecated but will stay for some time
> for compatibility.
>
> Reported-by: Morten Brørup
> Signed-o
Hi All,
I see few patches in the DPDK regarding "Implement device reset
on VF" and also "support reset of VF link" but I am not sure which version of
DPDK is having the changes. Are they at all upstreamed or they are still under
discussion. I am currently using DPDK 16.11, and faci
This patch adds a call to the newly introduced cleanup()
function just before quitting the app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause hugepag
This commit adds a new function rte_eal_cleanup().
The function serves as a hook to allow DPDK to release
internal resources (e.g.: hugepage allocations).
This function allows DPDK to become more like an ordinary
library, where the library context itself can be initialized
and cleaned up by the ap
This patch adds a call to the newly introduced cleanup()
function just before quitting the pdump app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause h
This commit moves the rte_service_finalize() function
to be in the component header, and marks it as @internal.
The function is only called internally by rte_eal_finalize().
Signed-off-by: Harry van Haaren
Acked-by: Vipin Varghese
---
v4:
- Include Ack
Cc: tho...@monjalon.net
Cc: vipin.vargh.
29/01/2018 10:39, Olivier Matz:
> Do not panic when calling rte_pktmbuf_free(NULL) with mbuf debug
> enabled, it is a valid operation.
>
> Fixes: af75078fece3 ("first public release")
> Cc: sta...@dpdk.org
>
> Reported-by: Keith Wiles
> Signed-off-by: Olivier Matz
Applied, thanks
> -Original Message-
> From: stable [mailto:stable-boun...@dpdk.org] On Behalf Of De Lara
> Guarch, Pablo
> Sent: Monday, January 29, 2018 11:53 AM
> To: Trahe, Fiona ; dev@dpdk.org
> Cc: Nicolau, Radu ; sta...@dpdk.org
> Subject: Re: [dpdk-stable] [PATCH 2/2] test: improve test validatio
> -Original Message-
> From: Nicolau, Radu
> Sent: Thursday, January 25, 2018 5:37 PM
> To: Trahe, Fiona ; dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: RE: [PATCH 1/2] crypto/qat: fix null auth algo issue
>
>
> > -Original Message-
> > From: Trahe, Fiona
> > Sent: Thursd
15/01/2018 16:09, Konstantin Ananyev:
> On x86 it is possible to use lock-prefixed instructions to get
> the similar effect as mfence.
> As pointed by Java guys, on most modern HW that gives a better
> performance than using mfence:
> https://shipilev.net/blog/2014/on-the-fence-with-dependencies/
From: "Charles (Chas) Williams"
.dev_configure() may be called again after RX queues have been setup.
This has the effect of clearing whatever setting the RX queues made for
rx_bulk_alloc_allowed or rx_vec_allowed. Only reset this configuration
is there aren't any currently allocated queues.
Fi
03/12/2017 13:37, Jerin Jacob:
> On thunderx and octeontx, ring_perf_autotest and
> ring_pmd_perf_autotest test shows better performance
> when disabling CONFIG_RTE_RING_USE_C11_MEM_MODEL.
> On the other hand, Enabling CONFIG_RTE_RING_USE_C11_MEM_MODEL
> shows better performance on thunderx2.
> Sin
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 v1:
-
- Make log levels consistent (Tiwei)
- Remove pending IOTLB entry of miss request seding failed (Tiwei)
M
22/01/2018 05:41, Jia He:
> There are 2 model barrier options in librte_ring suggested by Jerin:
> 1. use rte_smp_rmb
> 2. use load_acquire/store_release
>
> CONFIG_RTE_RING_USE_C11_MEM_MODEL is provided for supporting C11 memory
> model barrier in librte_ring. By default it is "y" on arm64, "n" o
This patch introduce new TX offloads flag for devices that support
tunnel agnostic checksum and TSO offloads.
The support from the device is for inner and outer checksums on
IPV4/TCP/UDP and TSO for *any packet with the following format*:
< some headers > / [optional IPv4/IPv6] / [optional TCP/UD
"show port cap" and "csum parse tunnel" command support TX generic
tunnel offloads
Signed-off-by: Xueming Li
---
app/test-pmd/cmdline.c | 9 +++--
app/test-pmd/config.c | 9 +
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdli
This commit adds support for generic tunnel TSO and checksum offload.
PMD will compute the inner/outer headers offset according to the
mbuf fields. Hardware will do calculation based on offsets and types.
Signed-off-by: Xueming Li
---
doc/guides/nics/mlx5.rst | 8 +++
drivers/net/
Change max inline header length to 192B to allow IPv6 VXLAN TSO headers
and header with options that more than 128B.
Signed-off-by: Xueming Li
---
drivers/net/mlx5/mlx5_defs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_defs.h b/drivers/net/mlx5/mlx5
Separate TSO function to make logic of mlx5_tx_burst clear.
Signed-off-by: Xueming Li
---
drivers/net/mlx5/mlx5_rxtx.c | 112 ++-
1 file changed, 67 insertions(+), 45 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
in
> -Original Message-
> From: Van Haaren, Harry
> Sent: Monday, January 29, 2018 5:38 PM
> To: dev@dpdk.org
> Cc: Van Haaren, Harry ; tho...@monjalon.net;
> Varghese, Vipin
> Subject: [PATCH v3 4/4] app/proc_info: call eal cleanup before exit
>
> This patch adds a call to the newly intro
> -Original Message-
> From: Van Haaren, Harry
> Sent: Monday, January 29, 2018 5:38 PM
> To: dev@dpdk.org
> Cc: Van Haaren, Harry ; tho...@monjalon.net;
> Varghese, Vipin
> Subject: [PATCH v3 3/4] app/pdump: call eal cleanup before exit
>
> This patch adds a call to the newly introduce
> -Original Message-
> From: Van Haaren, Harry
> Sent: Monday, January 29, 2018 5:38 PM
> To: dev@dpdk.org
> Cc: Van Haaren, Harry ; tho...@monjalon.net;
> Varghese, Vipin
> Subject: [PATCH v3 2/4] eal: add function to release internal resources
>
> This commit adds a new function rte_e
Moving the function as internal is ok with me.
Acked-by: Vipin Varghese
> -Original Message-
> From: Van Haaren, Harry
> Sent: Monday, January 29, 2018 5:38 PM
> To: dev@dpdk.org
> Cc: Van Haaren, Harry ; tho...@monjalon.net;
> Varghese, Vipin
> Subject: [PATCH v3 1/4] service: move fin
Fixes: 09150784a776 ("net/bonding: burst mode hash calculation")
Cc: sta...@dpdk.org
Wrong function was used for l23 and l34 hashing
slave index was incremented twice.
Signed-off-by: Radu Nicolau
---
drivers/net/bonding/rte_eth_bond_api.c | 3 +++
drivers/net/bonding/rte_eth_bond_pmd.c | 8
1 - 100 of 199 matches
Mail list logo
