Hi, wei
Is it a fix patch?
Thanks,
Xiaolong
On 08/02, Wei Zhao wrote:
>a new mail box version of ixgbe_mbox_api_13 need to enable for pf
>host, in order that it can communicate with vf for queue number.
>
>Signed-off-by: Wei Zhao
>---
> drivers/net/ixgbe/ixgbe_pf.c | 1 +
> 1 file changed, 1 ins
On 08/07, Lu Qiuwen wrote:
>The ops pointers in fm10k_stats_get() are set up from primary
>process, when secondary process call these ops pointers,
>a segment fault will happen.
>
>Fixes: 7223d200c227 ("fm10k: add base driver")
>Cc: jeffrey.b.s...@intel.com
>
>Signed-off-by: Lu Qiuwen
>Acked-by: X
On 08/09, Andy Pei wrote:
>set up mtu to the minimun in tx mtu, rx mtu and IPN3KE_MAC_FRAME_SIZE_MAX.
>
>Signed-off-by: Andy Pei
>---
>v2:
>* modify low bound and upper bound.
>
> drivers/net/ipn3ke/ipn3ke_ethdev.c | 97 ++
> drivers/net/ipn3ke/ipn3ke_ethdev.h |
Hello Thomas M,
Can you please review this path "http://patches.dpdk.org/patch/57593/";? I see
this has been assigned to you. Kindly provide your feedback.
Regards,
Nilanjan
Disclaimer:
This communication (including any attachments) is intended for the use of the
intended recipient(s) only and
Hi Jerin,
Thursday, August 15, 2019 2:34 PM, Thomas Monjalon:
> Subject: Re: [dpdk-dev] [RFC PATCH v1] regexdev: introduce regexdev
> subsystem
>
> +Cc more
>
>
>
> From: Jerin Jacob
>
> Even though there are some vendors which offer Regex HW offload, due to
> lack of standard AP
On Tue, Aug 20, 2019 at 02:37:28AM -0700, Jim Harris wrote:
> This function is listed under EXPERIMENTAL in the
> rte_vhost_version.map, so it needs to be marked
> with __rte_experimental in the header file as well.
>
> Found by check-experimental-syms.sh when trying to compile
> DPDK with -finstr
MTU change is currently only allowed when device is stopped.
Current code in master branch already sets MTU in shared data correctly when
starting the device:
static int
vmxnet3_setup_driver_shared(struct rte_eth_dev *dev)
{
struct rte_eth_conf port_conf = dev->data->dev_conf;
st
On Wed, 21 Aug 2019 02:16:58 +
"Myers, Charles" wrote:
>
> static int
> +vmxnet3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
> +{
> + if (dev->data->dev_started) {
> + PMD_DRV_LOG(ERR, "Port %d must be stopped to configure MTU",
> + dev->data-
From: Charles Myers
When the mtu_set() function is not implemented, rte_eth_dev_set_mtu()
fails with -ENOTSUP and mtu is not stored in the mtu field in the
rte_eth_dev_data. This causes the mtu in Vmxnet3_MiscConf which is
shared with hypervisor to always be set to 1500.
This may cause issues r
The function rte_eal_init_alert ends up printing the same message
twice. Once via RTE_LOG and once to stderr. Remove the fprintf
to stderr since it is redundant.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/linux/eal/eal.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/librte_eal/
EAL should always use rte_log instead of putting errors to
stderr (which maybe redirected to /dev/null in a daemon).
Also checks for null before rte_free are unnecessary.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/rte_service.c | 23 +++
1 file changed, 11 in
Fix some mistakes in Tx bursts in regard to TSO flag check.
Fixes: 18a1c20044c0 ("net/mlx5: implement Tx burst template")
Cc: viachesl...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_rxtx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff
This function is listed under EXPERIMENTAL in the
rte_vhost_version.map, so it needs to be marked
with __rte_experimental in the header file as well.
Found by check-experimental-syms.sh when trying to compile
DPDK with -finstrument-functions. This script didn't
catch this in the normal case, sinc
From: Michael Shamis
Added error handler for offload mode.
Signed-off-by: Michael Shamis
---
examples/ipsec-secgw/ipsec.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/examples/ipsec-secgw/ipsec.c b/examples/ipsec-secgw/ipsec.c
index dc85adfe5..583c91658 100644
--- a/examples/ipsec
> On Aug 20, 2019, at 7:35 AM, cha...@m.scnu.edu.cn wrote:
>
> Hello DPDK,
>I am a postgraduate student from South China Normal University, Guangzhou,
> China.
>I found that the IOAT driver was released in DPDK 19.08 for the first
> time. At the same time, I noticed that the code of
On Tue, 20 Aug 2019 04:06:53 +
"Myers, Charles" wrote:
> static int
> +vmxnet3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
> +{
> + if (mtu < VMXNET3_MIN_MTU || mtu > VMXNET3_MAX_MTU) {
> + PMD_DRV_LOG(ERR, "MTU should be between %d and %d",
> +
Acked-by: Michel Machado
[ ]'s
Michel Machado
On 8/16/19 8:53 AM, Konstantin Ananyev wrote:
Right now inclusion of rte_mbuf.h header can cause inclusion of
some arch/os specific headers.
That prevents it to be included directly by some
non-DPDK (but related) entities: KNI, BPF programs, etc.
T
Acked-by: Michel Machado
[ ]'s
Michel Machado
On 8/16/19 8:53 AM, Konstantin Ananyev wrote:
Right now RTE_CACHE_ and IOVA definitions are located inside rte_memory.h
That might cause an unwanted inclusions of arch/os specific header files.
See [1] for particular problem example.
Probably the s
Since rte_mbuf_core.h requires generic/rte_atomic.h, shouldn't
rte_mbuf_core.h include generic/rte_atomic.h instead of forcing users of
rte_mbuf_core.h be aware of this dependency?
[ ]'s
Michel Machado
On 8/16/19 8:53 AM, Konstantin Ananyev wrote:
Get rid of duplicate definitions for rte_mbuf
Hi All,
VirtIO-1.1 seems to have VIRTIO_F_IN_ORDER support for Split Virtqueues.
In this regards, does DPDK Virtio and Vhost drivers support VIRTIO_F_IN_ORDER
on Split Virtqueues - which allows single used-ring entry to notify a batch of
buffers to driver ?
Also, is this feature applicable for
From: Alvin Zhang
If VF driver in VM continuous sending invalid messages by mailbox,
it will waste CPU cycles on PF driver and impact other VF drivers
configuration. New feature can count the numbers of invalid and
unsupported messages from VFs, when the statistics from a VF
exceed maximum limit,
Hello DPDK,
I am a postgraduate student from South China Normal University, Guangzhou,
China.
I found that the IOAT driver was released in DPDK 19.08 for the first time.
At the same time, I noticed that the code of DPDK IOAT driver was similar to
SPDK one. So there are some questions I
spi should be set with network endian values.
While 0x == htonl(0x), this missing annotation is caught
by sparse when compiling ovs (dpdk-latest branch).
Fixes: d4b684f7197a ("net: add ESP header to generic flow steering")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
li
On 20-Aug-19 2:16 PM, Harris, James R wrote:
On Aug 20, 2019, at 6:13 AM, Burakov, Anatoly wrote:
On 16-Aug-19 1:13 PM, Jim Harris wrote:
The code checks both rte_mp_request_sync() return
code and that the number of messages in the reply
equals 1. If rte_mp_request_sync() succeeds but
ther
> On Aug 20, 2019, at 6:13 AM, Burakov, Anatoly
> wrote:
>
>> On 16-Aug-19 1:13 PM, Jim Harris wrote:
>> The code checks both rte_mp_request_sync() return
>> code and that the number of messages in the reply
>> equals 1. If rte_mp_request_sync() succeeds but
>> there was more than one messag
This patch fixes the return value of the test_deflate_comp_decomp
function on capabilities retrieval error to be -ENOTSUP.
It also fixes passing of the test_deflate_comp_decomp function's
return value to the upper level (as the test suite function return
value).
Signed-off-by: Adam Dybkowski
---
On 16-Aug-19 1:13 PM, Jim Harris wrote:
The code checks both rte_mp_request_sync() return
code and that the number of messages in the reply
equals 1. If rte_mp_request_sync() succeeds but
there was more than one message, those messages
would get leaked.
Found via code review by Anatoly Burakov
On Tue, Aug 20, 2019 at 7:16 AM Tiwei Bie wrote:
>
> On Mon, Aug 19, 2019 at 05:58:08AM -0700, Jim Harris wrote:
> > This function is declared __rte_always_inline so it
> > seems unnecessary to include it in the map file. In
> > addition, it was included in the EXPERIMENTAL section
> > even thoug
For the rte_flow_action_raw_encap, the header defination for
encapsulation must be available, otherwise it will lead to crash on some
OFED versions and logically it should be rejected.
Fixes: 8ba9eee4ce32 ("net/mlx5: add raw data encap/decap to Direct Verbs")
Cc: dek...@mellanox.com
Signed-off-by
patch 1/2: Add GTP extension header to flow API.
patch 2/2: Add PPPoE to flow API.
---
v3: Split original patch, one for GTP and the other for PPPoE.
Add RTE_FLOW_ITEM_TYPE_PPPOE_PROTO_ID for PPPoE session packets.
v2: Remove Gerrit Change-Id's.
---
Wang Ying A (2):
ethdev: add GTP extensi
- RTE_FLOW_ITEM_TYPE_PPPOES: matches a PPPoE session header.
- RTE_FLOW_ITEM_TYPE_PPPOED: matches a PPPoE discovery header.
- RTE_FLOW_ITEM_TYPE_PPPOE_PROTO_ID: matches a PPPoE session
protocol identifier.
Signed-off-by: Wang Ying A
---
app/test-pmd/cmdline_flow.c | 51 ++
- RTE_FLOW_ITEM_TYPE_GTP_PSC: matches a GTP
PDU extension header (PDU session container).
Signed-off-by: Wang Ying A
---
app/test-pmd/cmdline_flow.c | 36 +
doc/guides/prog_guide/rte_flow.rst | 9
doc/guides/testpmd_app_ug/testpmd_
32 matches
Mail list logo
