On Thu, Jan 04, 2018 at 07:59:37AM -0800, Xiao Wang wrote:
[...]
> +void
> +virtio_inject_pkts(struct rte_eth_dev *dev, struct virtnet_tx *txvq,
> + struct rte_mbuf **buf, int count)
> +{
> + struct virtio_hw *hw = dev->data->dev_private;
> +
> + hw->special_buf = buf;
I think
Rte_flow actually defined to include RSS,
but till now, RSS is out of rte_flow.
This patch is to move igb existing RSS to rte_flow.
The old RSS configuration is still reserved.
Signed-off-by: Wei Zhao
---
doc/guides/rel_notes/release_18_02.rst | 6 ++
drivers/net/e1000/e1000_ethdev.h |
Rte_flow actually defined to include RSS,
but till now, RSS is out of rte_flow.
This patch is to move ixgbe existing RSS to rte_flow.
The old RSS configuration is still reserved.
Signed-off-by: Wei Zhao
---
doc/guides/rel_notes/release_18_02.rst | 6 +-
drivers/net/ixgbe/ixgbe_ethdev.c |
The patches mainly finish following functions:
1) igb move RSS to flow API
2) ixgbe move RSS to flow API
v2:
-fix bug for RSS flush code.
-fix patch check warning.
v3:
-fix bug for ixgbe rss restore.
v4:
-fix build warning and add release notes comment.
Wei Zhao (2):
net/e1000: move RSS to fl
On Wed, Jan 03, 2018 at 07:23:30AM -0800, Stephen Hemminger wrote:
> On Wed, 3 Jan 2018 08:52:01 +0100
> Nelio Laranjeiro wrote:
>
> > Hi Stephen,
> >
> > Seems you missed an important point, MLNX_OFED is still supported with
> > this driver allowing it to work on stable releases like strict deb
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Wednesday, January 3, 2018 9:34 PM
> To: dev@dpdk.org; Wu, Jingjing ; Xing, Beilei
>
> Cc: sta...@dpdk.org
> Subject: [PATCH v2] net/i40e: fix setting of MAC address on i40evf
>
> When setting the MAC addre
Hi Shachar,
On Wed, Jan 03, 2018 at 03:00:46PM +, Shachar Beiser wrote:
> > > --- a/config/common_base
> > > +++ b/config/common_base
> > > @@ -236,6 +236,7 @@ CONFIG_RTE_LIBRTE_MLX4_TX_MP_CACHE=8
> > > # Compile burst-oriented Mellanox ConnectX-4 & ConnectX-5 (MLX5) PMD
> > > # CONFIG_RTE_
v4:
- Move spinlock lock/unlock into dev_pause/resume.
- Separate out a patch for packet injection.
v3:
- Remove Tx function code duplication, use a special pointer for rarp
injection.
- Rename function generate_rarp to virtio_notify_peers, replace
'virtnet_' with 'virtio_'.
- Add comment for
This patch adds dev_pause, dev_resume and inject_pkts api to allow
driver to pause the worker thread and inject special packets into
Tx queue. The next patch will be based on this.
Signed-off-by: Xiao Wang
---
drivers/net/virtio/virtio_ethdev.c | 44 +
driver
When live migration is done, for the backup VM, either the virtio
frontend or the vhost backend needs to send out gratuitous RARP packet
to announce its new network location.
This patch enables VIRTIO_NET_F_GUEST_ANNOUNCE feature to support live
migration scenario where the vhost backend doesn't h
The virtio_send_command function may be called from app's configuration
routine, but also from an interrupt handler called when live migration is
done on the backup side. So this patch makes control queue thread-safe
first.
Signed-off-by: Xiao Wang
---
drivers/net/virtio/virtio_ethdev.c | 7
Hi Tiwei,
> -Original Message-
> From: Bie, Tiwei
> Sent: Thursday, January 4, 2018 10:51 AM
> To: Wang, Xiao W
> Cc: dev@dpdk.org; y...@fridaylinux.org; step...@networkplumber.org
> Subject: Re: [PATCH v3 2/2] net/virtio: support GUEST ANNOUNCE
>
> Hi Xiao,
>
> On Wed, Jan 03, 2018 at
Hi Beilei
> -Original Message-
> From: Xing, Beilei
> Sent: Friday, December 8, 2017 3:52 PM
> To: Wu, Jingjing ; Lu, Wenzhuo
> ; Zhang, Qi Z
> Cc: dev@dpdk.org; Chilikin, Andrey
> Subject: [PATCH v6 2/2] app/testpmd: add configuration for input set
>
> This patch adds command to config
When binding X710 NIC (i40e driver) to DPDK, vhost sample startups
failure.
The sample requires that MAX_QUEUES should be defined no less than 320.
So, the patch redefines MAX_QUEUES 320 to fix the issue.
Cc: sta...@dpdk.org
Signed-off-by: Zhiyong Yang
---
examples/vhost/main.c | 2 +-
1 file ch
https://dpdk.org/tracker/show_bug.cgi?id=6
Bug ID: 6
Summary: dpdk-pdump leads to ovs-vswitchd crash
Product: DPDK
Version: 17.11
Hardware: All
OS: All
Status: CONFIRMED
Severity: critical
Priori
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Wednesday, January 3, 2018 10:29 PM
> To: dev@dpdk.org; Wu, Jingjing ; Xing, Beilei
>
> Cc: sta...@dpdk.org; Laurent Hardy
> Subject: [PATCH] net/i40e: fix VSI MAC filter on primary address change
>
> Whe
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 1 +
doc/guides/nics/features/avf_vec.ini | 1 +
drivers/net/avf/avf_ethdev.c | 204 ---
3 files changed, 170 insertions(+), 36 deletions(-)
diff --git a/doc/guid
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/intel_vf.rst | 16 ++--
doc/guides/rel_notes/release_18_02.rst | 16
2 files changed, 30 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rs
Signed-off-by: Wenzhuo Lu
---
drivers/net/avf/avf.h| 1 +
drivers/net/avf/avf_ethdev.c | 1 +
drivers/net/avf/avf_rxtx.c | 300 +++
drivers/net/avf/avf_rxtx.h | 6 +
4 files changed, 308 insertions(+)
diff --git a/drivers/net/avf/avf.h b/
From: Jingjing Wu
Enable Virtchnl offload Caps negotiation and RSS_PF offload
to support AVF basic interface.
Signed-off-by: Jingjing Wu
---
drivers/net/i40e/i40e_ethdev.c | 69
drivers/net/i40e/i40e_ethdev.h | 5 ++
drivers/net/i40e/i40e_pf.c | 140
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
config/common_base| 1 +
doc/guides/nics/features/avf_vec.ini | 36 ++
drivers/net/avf/Makefile | 1 +
drivers/net/avf/avf.h | 4 +
drivers/net/avf/avf_ethdev.c | 11 +
drivers/ne
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 1 +
drivers/net/avf/avf_ethdev.c | 30 ++
2 files changed, 31 insertions(+)
diff --git a/doc/guides/nics/features/avf.ini b/doc/guides/nics/features/avf.ini
index 61527d7..cf1b
From: Jingjing Wu
- rxq_info_get
- txq_info_get
- rx_queue_count
- rx_descriptor_status
- tx_descriptor_status
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 2 +
drivers/net/avf/avf_ethdev.c | 5 ++
drivers/net/avf/avf_rxtx.c | 120 +++
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 2 +
drivers/net/avf/avf_ethdev.c | 142 +++
2 files changed, 144 insertions(+)
diff --git a/doc/guides/nics/features/avf.ini b/doc/guides/nics/features/avf.ini
index 1
From: Jingjing Wu
- promiscuous_enable
- promiscuous_disable
- allmulticast_enable
- allmulticast_disable
- mac_addr_add
- mac_addr_remove
- mac_addr_set
- vlan_filter_set
- vlan_offload_set
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 5 +
drivers/net/avf/avf.h
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 1 +
drivers/net/avf/avf.h| 2 ++
drivers/net/avf/avf_ethdev.c | 27 +++
drivers/net/avf/avf_vchnl.c | 27 +++
4 files changed, 57 insertion
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
doc/guides/nics/features/avf.ini | 3 +++
drivers/net/avf/avf.h| 2 ++
drivers/net/avf/avf_ethdev.c | 51 +++-
drivers/net/avf/avf_vchnl.c | 38 +-
4 files cha
From: Jingjing Wu
enable device and queue setup ops like:
- dev_configure
- dev_start
- dev_stop
- dev_close
- dev_infos_get
- rx_queue_start
- rx_queue_stop
- tx_queue_start
- tx_queue_stop
- rx_queue_setup
- rx_queue_release
- tx_queue_setup
- tx_queue_release
Signed-off-by: Jing
Signed-off-by: Wenzhuo Lu
---
MAINTAINERS | 1 +
config/common_base | 6 +-
doc/guides/nics/features/avf.ini | 22 ++
drivers/net/avf/Makefile | 3 +
drivers/net/avf/avf_ethdev.c | 36 +-
drivers/net/avf/avf_log.h| 21 ++
drivers/net
From: Jingjing Wu
Signed-off-by: Jingjing Wu
---
config/common_base | 5 +
drivers/net/Makefile| 1 +
drivers/net/avf/Makefile| 31 +++
drivers/net/avf/avf.h | 187 ++
drivers/net/avf/avf_ethdev.c
Adaptive Virtual Function (AVF) Driver is VF driver which
supports for all future Intel devices without requiring a
VM update.
It promises the basic high speed connectivity. And since
this happens to be an adaptive VF driver, every new drop
of the VF driver would add more and more advanced features
Hi Xiao,
On Wed, Jan 03, 2018 at 11:41:40PM -0800, Xiao Wang wrote:
[...]
> +static int
> +virtio_dev_pause(struct rte_eth_dev *dev)
> +{
> + struct virtio_hw *hw = dev->data->dev_private;
> +
> + if (hw->started == 0)
> + return -1;
> + hw->started = 0;
> + /*
> +
When live migration is done, for the backup VM, either the virtio
frontend or the vhost backend needs to send out gratuitous RARP packet
to announce its new network location.
This patch enables VIRTIO_NET_F_GUEST_ANNOUNCE feature to support live
migration scenario where the vhost backend doesn't h
The virtio_send_command function may be called from app's configuration
routine, but also from an interrupt handler called when live migration is
done on the backup side. So this patch makes control queue thread-safe
first.
Signed-off-by: Xiao Wang
---
v2:
- Use spaces instead of tabs between the
When live migration is finished, the backup VM needs to proactively announce
its new location. DPDK vhost has implemented VHOST_USER_PROTOCOL_F_RARP to
generate a RARP packet to switch in dequeue path. Another method is to let
the guest proactively send out RARP packet using VIRTIO_NET_F_GUEST_ANNO
This patch updates the rte_lcore_has_role() function so that it returns
true/false instead of success/failure, which seems more intuitive given the
function name.
There is currently one call site for rte_lcore_has_role() and the caller uses
it (incorrectly) as though it returns true/false. The ca
Update rte_lcore_has_role() so that it returns true/false instead of
success/failure.
Fixes: 78666372fa2b ("eal: add function to check lcore role")
Signed-off-by: Erik Gabriel Carrillo
---
lib/librte_eal/common/eal_common_thread.c | 5 +
lib/librte_eal/common/include/rte_lcore.h | 2 +-
2 f
In short, same comments as the TX patch, more below.
On Wed, Jan 03, 2018 at 09:16:17AM +0200, Shahaf Shuler wrote:
> Ethdev Rx offloads API has changed since:
>
> commit ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
>
> This commit support the new Rx offloads API.
>
> Signed-off-by:
Hi Shahaf,
Some relatively minor nits mostly unrelated to functionality, please see
below.
On Wed, Jan 03, 2018 at 09:16:16AM +0200, Shahaf Shuler wrote:
> Ethdev Tx offloads API has changed since:
>
> commit cba7f53b717d ("ethdev: introduce Tx queue offloads API")
>
> This commit support the n
> > > +int
> > > +rte_red_set_scaling(uint16_t max_red_queue_length);
> > > +
> > > +/**
> > > + * @brief Reset the RED scaling factor - only for use by RED
> > > +unit-tests
> > > + *
> > > + * @return Operation status
> > > + */
> > > +void
> > > +rte_red_reset_scaling(void);
> >
> > As stated ab
On Wed, 3 Jan 2018 08:52:01 +0100
Nelio Laranjeiro wrote:
> Hi Stephen,
>
> Seems you missed an important point, MLNX_OFED is still supported with
> this driver allowing it to work on stable releases like strict debian 9
> i.e. without updating the Linux kernel.
So the documentation should refl
On Wed, 3 Jan 2018 08:35:23 +0100
Nelio Laranjeiro wrote:
> Hi Stephen,
>
> On Tue, Jan 02, 2018 at 12:53:09PM -0800, Stephen Hemminger wrote:
> > Since wait_to_complete is unused, don't pass it to helper functions.
> > Use the standard RTE macro to indicate this is an unused parameter.
>
> I
On Wed, 3 Jan 2018 11:25:53 +0100
Nelio Laranjeiro wrote:
> On Tue, Jan 02, 2018 at 12:53:08PM -0800, Stephen Hemminger wrote:
> > Trying to eliminate all runtime calls to look at kernel version
> > to determine API because they are source of portablity problems
> > in distributions.
> >
> > Ste
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shahaf Shuler
> Sent: Tuesday, December 26, 2017 9:24 AM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH v3 33/39] examples/flow_classify: convert to new
> ethdev offloads API
>
> Ethdev offloads API has changed si
> -Original Message-
> From: Nelio Laranjeiro [mailto:nelio.laranje...@6wind.com]
> Sent: Tuesday, January 2, 2018 4:07 PM
> To: Shachar Beiser
> Cc: dev@dpdk.org; Adrien Mazarguil
> Subject: Re: [PATCH v4] net/mlx5: load libmlx5 and libibverbs in run-time
>
> Hi Shachar,
>
> Please s
When primary address mac is changed, the mac filters were not updated in
the VSI with the new mac addr and incoming packets with this destination
address are dropped by the hardware filters.
This patch removes the VSI mac filter for the previous mac address and
adds a new one for new mac address.
On Fri, Dec 29, 2017 at 09:09:25AM -0800, Stephen Hemminger wrote:
> On Tue, 21 Nov 2017 01:42:41 +
> Ferruh Yigit wrote:
>
> > To track modification:
> > 380a7aab1ae2 ("mbuf: rename deprecated VLAN flags")
> >
> > Proposed deadline for PMDs is v18.02
> >
> > Signed-off-by: Ferruh Yigit
>
On 01/03/2018 04:54 PM, Olivier Matz wrote:
On Wed, Jan 03, 2018 at 02:43:59PM +0100, Olivier Matz wrote:
I've walked through the PMDs as suggested by Andrew, and there was
indeed some conflicts with the initial patch. I've just submitted the
patch for vmxnet3 [1] and bnxt [2].
But there is sti
Hi,
On Fri, Dec 29, 2017 at 09:07:49AM -0800, Stephen Hemminger wrote:
> On Tue, 21 Nov 2017 01:42:37 +
> Ferruh Yigit wrote:
>
> > To track modification:
> > 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool")
> >
> > Proposed deadline for PMDs is v18.02
> >
> > Signed-off-by: Ferruh Yig
On Wed, Jan 03, 2018 at 02:43:59PM +0100, Olivier Matz wrote:
> I've walked through the PMDs as suggested by Andrew, and there was
> indeed some conflicts with the initial patch. I've just submitted the
> patch for vmxnet3 [1] and bnxt [2].
>
> But there is still an issue with the qede driver, tha
Hi,
On Wed, Dec 20, 2017 at 01:00:01PM +0300, Andrew Rybchenko wrote:
> On 12/19/2017 12:47 PM, Andrew Rybchenko wrote:
> > On 12/19/2017 12:29 PM, Olivier MATZ wrote:
> > > Hi,
> > >
> > > On Mon, Dec 18, 2017 at 02:38:55PM +0300, Andrew Rybchenko wrote:
> > > > On 12/18/2017 01:53 PM, Igor Ryzh
-Original Message-
> Date: Thu, 21 Dec 2017 13:33:47 +0800
> From: Herbert Guan
> To: dev@dpdk.org, jerin.ja...@caviumnetworks.com
> CC: Herbert Guan
> Subject: [PATCH v4] arch/arm: optimization for memcpy on AArch64
> X-Mailer: git-send-email 1.8.3.1
>
> This patch provides an option to
When setting the MAC address, the ethdev layer copies the new mac
address in dev->data->mac_addrs[0] before calling the dev_ops.
Therefore, "is_same_ether_addr(mac_addr, dev->data->mac_addrs)" was
always true, and the MAC was never set. Remove this test to fix the
issue.
Fixes: 943c2d899a0c ("net
This operation is already done by the ethdev layer, it should not
be done by the driver.
Signed-off-by: Olivier Matz
---
drivers/net/bnxt/bnxt_ethdev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index 6f8a6335b..9d1ddae38 10
This operation is already done by the ethdev layer, it should not
be done by the driver.
Signed-off-by: Olivier Matz
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c
b/drivers/net/vmxnet3/vmxnet3_ethdev.c
index 82d5
From: Maciej Czekaj
This patch removes all references to old-style offload API
replacing them with new offload flags.
Signed-off-by: Maciej Czekaj
---
drivers/net/thunderx/nicvf_ethdev.c | 143 +++-
drivers/net/thunderx/nicvf_ethdev.h | 14
drivers/net/thu
Hi Neil,
On 22/12/2017 16:37, Neil Horman wrote:
On Fri, Dec 22, 2017 at 02:41:16PM +, Remy Horton wrote:
Port Representors provide a logical presentation in DPDK of VF (virtual
function) ports for the purposes of control and monitoring. Each port
representor device represents a single VF
Hi Neil,
On 26/12/2017 13:54, Neil Horman wrote:
On Fri, Dec 22, 2017 at 02:52:16PM +, Remy Horton wrote:
Port Representors provide a logical presentation in DPDK of VF (virtual
function) ports for the purposes of control and monitoring. Each port
representor device represents a single VF
s///g effects ;)
Thank you!
Reviewed-by: Radoslaw Biernacki
On 21 December 2017 at 19:19, Anatoly Burakov
wrote:
> Fixes: 71330483a193 ("test/memzone: fix memory leak")
> Cc: radoslaw.bierna...@linaro.org
> Cc: sta...@dpdk.org
> Signed-off-by: Anatoly Burakov
> ---
> test/test/test_memzone.c
Hi Zhike,
On Wed, Jan 03, 2018 at 08:21:26AM +, 王志克 wrote:
> Hi Tiwei,
>
> Thanks for your help and info.
>
> I have another question about your previous fix below.
> You mentioned that " Otherwise it will lead to incorrect packet collection
> for port state." Do you mean port statistics? O
On Wed, Dec 20, 2017 at 04:22:43PM +0800, Beilei Xing wrote:
> Add support of PPPoE and L2TP packet types.
>
> Signed-off-by: Beilei Xing
Acked-by: Olivier Matz
Hi Tomasz,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Tomasz Duszynski
> Sent: Friday, December 22, 2017 4:33 PM
> To: dev@dpdk.org
> Cc: Tomasz Duszynski ; Dumitrescu, Cristian
>
> Subject: [dpdk-dev] [PATCH] app/testpmd: set metering algorithm to the
> c
When allocating a new mbuf for Rx, the value of m->data_off should not
be reset to its default value (RTE_PKTMBUF_HEADROOM), instead of reusing
the previous undefined value, which could cause the packet to have a too
small or too high headroom.
Fixes: 2eb53b134aae ("net/bnxt: add initial Rx code")
Replace internal functions to get dma address them with their generic iova
version. Also rename the 'data' variable to 'mbuf' for more readability.
Signed-off-by: Olivier Matz
Acked-by: Ajit Khaparde
---
v1 -> v2:
- invert patches 1/2 and 2/2, and update commit log consequently
drivers/net/bn
In the info get API we were returning number of event
ports as MAX number of LCORE's. After this change actual
number of event ports (i.e. number of DPIO's) is provided
in the info get API.
Signed-off-by: Nipun Gupta
---
This patch is dependent on https://dpdk.org/dev/patchwork/patch/32834/
as it
On Tue, Jan 02, 2018 at 12:53:08PM -0800, Stephen Hemminger wrote:
> Trying to eliminate all runtime calls to look at kernel version
> to determine API because they are source of portablity problems
> in distributions.
>
> Stephen Hemminger (2):
> mlx5: don't pass unused argument to sub-function
> -Original Message-
> From: Yuanhan Liu [mailto:y...@fridaylinux.org]
> Sent: Wednesday, December 27, 2017 10:29 PM
> To: Yang, Zhiyong
> Cc: dev@dpdk.org; maxime.coque...@redhat.com
> Subject: Re: [PATCH] lib/librte_vhost: remove redundant logic judgement
>
> On Mon, Dec 25, 2017 at 0
I don't believe that it would work since you cannot assume that mmap
addresses will just increase. Especially with ASLR anything can
happen. I don't understand why you want to get rid of --base-virtaddr
I think it is a valid solution for the problem.
On Wed, 3 Jan 2018 09:37:00 +
"Xuemin
So the idea of item 3 might sound and lead to seldom usage of
'--base-virtaddress'.
Reserve an address hole big enough before hugepage almost cost nothing.
> -Original Message-
> From: Jonas Pfefferle [mailto:peppe...@japf.ch]
> Sent: Wednesday, January 3, 2018 5:22 PM
> To: Xueming(Steve
Changing the EQCR stashing threshold boosts the performance
of l3fwd application on LS2088 by more than 20% as it helps
in burst packet processing at the Tx side. CPU is immediately
informed about the empty EQCR entries once consumed by the
hardware.
Signed-off-by: Nipun Gupta
---
drivers/bus/fs
Hi Xueming,
Correct --base-virtaddr was introduced for that purpose. There are
multiple reasons why the address layout of the secondary process might
look different: reasons you mentioned in 2), ASLR etc. I believe there
is no way to avoid this in real world use cases. The reason for this
par
MLX5 NIC does not support all hash fields, this patch limit by refusing
impossible RSS combination to avoid errors.
Fixes: 2f97422e7759 ("mlx5: support RSS hash update and get")
Cc: sta...@dpdk.org
Signed-off-by: Nelio Laranjeiro
Acked-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_defs.h | 5 +++
> -Original Message-
> From: Wang, Xiao W
> Sent: Wednesday, January 3, 2018 9:37 AM
> To: Bie, Tiwei
> Cc: y...@fridaylinux.org; dev@dpdk.org; step...@networkplumber.org
> Subject: RE: [PATCH v2 2/2] net/virtio: support GUEST ANNOUNCE
>
> Hi,
>
> > -Original Message-
> > From:
On Wed, Jan 03, 2018 at 12:06:22AM -0800, Yongseok Koh wrote:
> Checking HW checksum offload flag for outer IP is missing. If flag is set
> for only outer IP, this can't be set properly.
>
> Fixes: f5fde5205101 ("net/mlx5: add hardware checksum offload for tunnel
> packets")
> Cc: sta...@dpdk.org
Hi Tiwei,
Thanks for your help and info.
I have another question about your previous fix below.
You mentioned that " Otherwise it will lead to incorrect packet collection for
port state." Do you mean port statistics? Or such packets may leads to issue,
like more TCP restransmission? Thanks.
c
This patch add inforation about i40e queue region
realted to release notes, it has been missed before
in v17.11 release notes. This feature has been
implemented in v17.11.
Signed-off-by: Wei Zhao
---
v2:
-change this information to v18.02 release notes.
---
doc/guides/rel_notes/release_18_02.r
> -Original Message-
> From: Zhao1, Wei
> Sent: Wednesday, January 3, 2018 3:17 PM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Zhao1, Wei
> Subject: [PATCH v3] net/i40e: fix port segmentation fault when restart
>
> This patch will clear all queue region related configuration when dev stop
>
On 01/02/2018 07:11 PM, Stefan Hajnoczi wrote:
On Tue, Jan 02, 2018 at 11:27:02AM +0100, Maxime Coquelin wrote:
Hi Stefan,
On 01/02/2018 10:31 AM, Stefan Hajnoczi wrote:
v2:
* Add internal vhost_vring_call() helper function [Maxime]
These patches eliminate code duplication for vhost_virt
02/01/2018 13:21, Neil Horman:
> On Tue, Jan 02, 2018 at 11:35:02AM +, Iremonger, Bernard wrote:
> > > int _rte_eth_dev_callback_process(struct rte_eth_dev *dev,
> > > - enum rte_eth_event_type event, void *cb_arg, void *ret_param);
> > > + enum rte_eth_event_type event, void *
02/01/2018 17:34, Stephen Hemminger:
> On Sat, 30 Dec 2017 23:47:23 +0100
> Thomas Monjalon wrote:
>
> > The CPUID instruction is catched by hypervisor which can return
> > a flag indicating one is running, and its name.
> >
> > Suggested-by: Stephen Hemminger
> > Signed-off-by: Thomas Monjalon
Checking HW checksum offload flag for outer IP is missing. If flag is set
for only outer IP, this can't be set properly.
Fixes: f5fde5205101 ("net/mlx5: add hardware checksum offload for tunnel
packets")
Cc: sta...@dpdk.org
Signed-off-by: Yongseok Koh
Acked-by: Shahaf Shuler
---
drivers/net/m
03/01/2018 02:16, Tan, Jianfeng:
>
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> >
> > The scan callback allows to spawn a vdev automatically
> > given some custom scan rules.
> > It is especially useful to create a TAP device automatically
> > connected to a netdevice as remote.
> >
>
82 matches
Mail list logo
