match GRE key and present bits")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow_dv.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
index a04a3c2bb8..feeeaf6a1d 100644
--- a/driver
This patch set fixs several problems of MPLS RSS:
- removed MPLSoIP(HW doesn't support) related code
- support MPLSoUDP, MPLSoGRE RSS expansion
- reduced number of expanded sub-flows for inner MPLS
Xiaoyu Min (3):
net/mlx5: fix MPLS over IP
net/mlx5: fix MPLS RSS expansion
net/mlx5:
HW doesn't support match MPLS over IP traffic.
Remove related code.
Fixes: d1abe664ddde ("net/mlx5: add MPLS to Direct Verbs flow engine")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c| 5 ++---
drivers/net/mlx5/mlx5_flow_dv.c | 3 ---
2 f
SoGRE.
In addition to above, support for eth over MPLS expansion is
added too.
Fixes: a4a5cd21d20a ("net/mlx5: add flow MPLS item")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 19 ---
1 file changed, 12 insertions(+), 7 deletions(-
/ mpls / eth / ipv6 / tcp
[4]:
pattern eth / ipv4 / udp / mpls / eth / end actions rss type tcp udp ip
level 2 / end
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
This patch set fixs the missing items in RSS expansion.
Xiaoyu Min (2):
net/mlx5: fix missing RSS expandable items
net/mlx5: fix missing RSS expansion of IPv6 frag
drivers/net/mlx5/mlx5_flow.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
--
2.32.0
Some RSS expandable items are missing which leads to the expanded
rte flow rules with wrong patterns.
Fix by adding missed items.
Fixes: d91093b9a2af ("net/mlx5: fix RSS pattern expansion")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
1 fi
ons rss level 2 types ip end / end
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 1b682ac8ed..90b8cf6692 100644
--- a/drivers/net/mlx5/mlx5_flow.
thdev: add VLAN attributes to ethernet and
VLAN items")
[2]:
commit 86b59a1af671 ("net/mlx5: support VLAN matching fields")
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 16
1 file changed, 16 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_flow.c
Currently root table as destination is not supported.
The jump action which finally be translated to underlying root table in
rdma-core should be rejected.
Fixes: f78f747f41d0 ("net/mlx5: allow jump to group lower than current")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
Acked-by:
which queues have aged out flows instead of
passing queue id via *ret_param* in event.
- Use bit flags instead of enum
- Fix typo and wording
Xiaoyu Min (2):
ethdev: port flags for pre-configuration flow hints
ethdev: queue-based flow aged report
lib/ethdev/rte_flow.h
resource could be
isolated and access based on queue, without lock, for example.
This patch add flag about above situation and could be extended to cover
more situations.
Signed-off-by: Xiaoyu Min
---
lib/ethdev/rte_flow.h | 11 +++
1 file changed, 11 insertions(+)
diff --git a/lib/ethdev
above change, another new API is added which help the
application get information about which queues have aged out flows after
RTE_ETH_EVENT_FLOW_AGED event received. The queried queue id can be
used in the above queue based query aged flows API.
Signed-off-by: Xiaoyu Min
---
lib/ethdev/rte_f
with VLAN")
Cc: sta...@dpdk.org
[1]:
commit c0d239263156 ("net/mlx4: support flow w/o ETH spec and with VLAN")
Signed-off-by: Xiaoyu Min
Acked-by: Matan Azrad
---
drivers/net/mlx4/mlx4_flow.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mlx4/mlx4_flo
This series of patchs fix two problems of shared RSS action:
1. inner RSS (level > 1) doesn't work
2. missed RSS types support (i.e L3-src-only)
Xiaoyu Min (2):
net/mlx5: fix shared inner RSS
net/mlx5: fix missing shared RSS hash types
drivers/net/mlx5/mlx5_flow.h| 22 +++-
dri
ed RSS action there is only one set of TIRs -
outer or inner could be so the unnecessary set of TIRs are removed
in order to reduce resource.
Fixes: d2046c09aa64 ("net/mlx5: support shared action for RSS")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.h
only one TIR will be created.
Fixes: d2046c09aa64 ("net/mlx5: support shared action for RSS")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.h| 20 +
drivers/net/mlx5/mlx5_flow_dv.c | 128
2 files changed, 148
operations of the
same flow happens in sequence.
The current flow aged report API hasn't queue parameter as same as other
queue-based flow management API.
This RFC propose to add new flow aged report API with queue parameter.
Keep the old one for compatibility.
Xiaoyu Min (2):
ethdev: port
ource could be
isolated and access based on queue, without lock for example.
This patch add flag about above situation and could be extanded to cover
more situations.
Signed-off-by: Xiaoyu Min
---
lib/ethdev/rte_flow.h | 16
1 file changed, 16 insertions(+)
diff --git a/lib/e
isolated by queue and needn't synchronize.
If application do use queue-based flow management but configure port
without RTE_FLOW_PORT_FLAG_STRICT_QUEUE, which means application operate
the same flow on different queues, the queue id parameter will
be ignored.
Signed-off-by: Xiaoyu Min
---
doc/g
On 18-09-29 07:03:33, Yongseok Koh wrote:
> On Tue, Sep 25, 2018 at 07:51:06PM +0800, Xiaoyu Min wrote:
> > Offload the following rte_flow actions by inserting accordingly
> > E-Switch rules via TC Flower driver
> >
> > - RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC
> > -
On 18-10-05 13:52:03, Ferruh Yigit wrote:
> On 9/25/2018 3:37 PM, Xiaoyu Min wrote:
> > This patch series is for RFC[1]
> >
> > Patch 1 adds generic TTL rewrite actions to flow API
> > Patch 2 adds corresponding testpmd commands
> > Patch 3 implements the offl
On 18-10-05 13:54:38, Ferruh Yigit wrote:
> On 9/25/2018 4:03 PM, Xiaoyu Min wrote:
> > This series is for RFC[1]
> >
> > Patch 1 adds generic MAC address rewrite actions to flow API
> > Patch 2 adds testpmd commands for that
> > Patch 3 offloads these actions o
On 18-10-04 04:07:02, Yongseok Koh wrote:
> On Tue, Sep 25, 2018 at 09:47:18PM +0800, Xiaoyu Min wrote:
> > Offload following modify TTL actions to E-Swtich via
> > TC-Flower driver
> >
> > - RTE_FLOW_ACTION_TYPE_SET_TTL
> > - RTE_FLOW_ACTION_TYPE_DEC_TTL
>
On 18-10-02 04:19:00, Yongseok Koh wrote:
> On Sun, Sep 30, 2018 at 03:21:04PM +0800, Xiaoyu Min wrote:
> > On 18-09-29 07:03:33, Yongseok Koh wrote:
> > > On Tue, Sep 25, 2018 at 07:51:06PM +0800, Xiaoyu Min wrote:
> > > > Offload the following rte_flow actions by i
it is EINVAL as expected
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_rxq.c | 20 +++-
1 file changed, 15 insertions(+), 5 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index 1f7bfd4..e7056e8 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/dr
There is a need to offload rewrite outermost MAC address for both
destination and source from the matched flow
The proposed actions could make above easily achieved
Signed-off-by: Xiaoyu Min
---
v2:
- Updated description about the MAC address is the outermost one
lib/librte_ethdev/rte_flow.h
There is a need to offload rewrite outermost MAC address for both
destination and source from the matched flow
The proposed actions could make above easily achieved
Signed-off-by: Xiaoyu Min
---
v2:
- Updated description about the MAC address is the outermost one
lib/librte_ethdev/rte_flow.h
>
> static int
> diff --git a/lib/librte_ethdev/rte_flow.h b/lib/librte_ethdev/rte_flow.h
> index f8ba71cdb..48c3c606e 100644
> --- a/lib/librte_ethdev/rte_flow.h
> +++ b/lib/librte_ethdev/rte_flow.h
> @@ -1505,6 +1505,34 @@ enum rte_flow_action_type {
>* error.
>*/
> RTE_F
>
> diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> index 638331c17..f60be0862 100644
> --- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> +++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> @@ -3713,6 +3713,14 @@ This section lists suppo
IPV6_SRC,
> +
> + /**
> + * Modify IPv6 destination address in the outermost IPv6 header.
> + *
> + * If flow pattern does not define a valid RTE_FLOW_ITEM_TYPE_IPV6,
> + * then the PMD should return a RTE_FLOW_ERROR_TYPE_ACTION error.
> + *
> + * See struct rte_flow_action_set_ipv6.
> + */
> + RTE_FLOW_ACTION_TYPE_SET_IPV6_DST,
> };
>
> /**
> @@ -1868,6 +1908,36 @@ struct rte_flow_action_nvgre_encap {
> struct rte_flow_item *definition;
> };
>
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this structure may change without prior notice
> + *
> + * RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC
> + * RTE_FLOW_ACTION_TYPE_SET_IPV4_DST
> + *
> + * Allows modification of IPv4 source (RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC)
> + * and destination address (RTE_FLOW_ACTION_TYPE_SET_IPV4_DST) in the
> + * specified outermost IPv4 header.
> + */
> +struct rte_flow_action_set_ipv4 {
> + uint32_t ipv4_addr;
> +};
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this structure may change without prior notice
> + *
> + * RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC
> + * RTE_FLOW_ACTION_TYPE_SET_IPV6_DST
> + *
> + * Allows modification of IPv6 source (RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC)
> + * and destination address (RTE_FLOW_ACTION_TYPE_SET_IPV6_DST) in the
> + * specified outermost IPv6 header.
> + */
> +struct rte_flow_action_set_ipv6 {
> + uint8_t ipv6_addr[16];
> +};
> +
> /*
> * Definition of a single action.
> *
> --
> 2.18.0
>
Acked-by: Xiaoyu Min
Thanks
* Modify destination port number in the outermost TCP/UDP header.
> + *
> + * If flow pattern does not define a valid RTE_FLOW_ITEM_TYPE_TCP
> + * or RTE_FLOW_ITEM_TYPE_UDP, then the PMD should return a
> + * RTE_FLOW_ERROR_TYPE_ACTION error.
> + *
> + * See struct rte_flow_action_set_tp.
> + */
> + RTE_FLOW_ACTION_TYPE_SET_TP_DST,
> };
>
> /**
> @@ -1938,6 +1960,21 @@ struct rte_flow_action_set_ipv6 {
> uint8_t ipv6_addr[16];
> };
>
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this structure may change without prior notice
> + *
> + * RTE_FLOW_ACTION_TYPE_SET_TP_SRC
> + * RTE_FLOW_ACTION_TYPE_SET_TP_DST
> + *
> + * Allows modification of source (RTE_FLOW_ACTION_TYPE_SET_TP_SRC)
> + * and destination (RTE_FLOW_ACTION_TYPE_SET_TP_DST) port numbers
> + * in the specified outermost TCP/UDP header.
> + */
> +struct rte_flow_action_set_tp {
> + uint16_t port;
> +};
> +
> /*
> * Definition of a single action.
> *
> --
> 2.18.0
>
Acked-by: Xiaoyu Min
Thanks
- RTE_FLOW_ACTION_TYPE_SET_TP_DST
Signed-off-by: Xiaoyu Min
---
This patch bases on Rahul Lakkireddy's patchs[1][2] and
Yongseok Koh's patchset [3]
[1] https://patches.dpdk.org/patch/45191/
[2] https://patches.dpdk.org/patch/45192/
[3] https://patches.dpdk.org/project/dpdk/list/?series=1474
d
This patch series is for RFC[1]
Patch 1 adds generic TTL rewrite actions to flow API
Patch 2 adds corresponding testpmd commands
Patch 3 implements the offloading logic of E-Switch rules on Mellanox MLX5
[1]: https://patches.dpdk.org/patch/43617/
Xiaoyu Min (3):
ethdev: add generic TTL
rewrite TTL by decrease or just set it directly
it's not necessary to check if the final result
is zero or not
This is slightly different from the one defined
by openflow and more generic
Signed-off-by: Xiaoyu Min
---
doc/guides/prog_guide/rte_flow.rst | 30 +
Offload following modify TTL actions to E-Swtich via
TC-Flower driver
- RTE_FLOW_ACTION_TYPE_SET_TTL
- RTE_FLOW_ACTION_TYPE_DEC_TTL
The corresponding IP protocol rte_flow_item_ipv[4|6]
must be present in rte_flow pattern otherwith PMD
return error
Signed-off-by: Xiaoyu Min
---
drivers/net
add commands which supports following TTL actions:
- RTE_FLOW_ACTION_TYPE_DEC_TTL
- RTE_FLOW_ACTION_TYPE_SET_TTL
Signed-off-by: Xiaoyu Min
---
app/test-pmd/cmdline_flow.c | 34 +
app/test-pmd/config.c | 3 ++
doc/guides/testpmd_app_ug
checkpatch
Xiaoyu Min (3):
ethdev: add generic TTL rewrite actions
app/testpmd: add commands of modify TTL
net/mlx5: eswitch-modify TTL actions
app/test-pmd/cmdline_flow.c | 34 ++
app/test-pmd/config.c | 3 +
doc/guides/prog_guide/rte_flow.rst
rewrite TTL by decrease or just set it directly
it's not necessary to check if the final result
is zero or not
This is slightly different from the one defined
by openflow and more generic
Signed-off-by: Xiaoyu Min
---
doc/guides/prog_guide/rte_flow.rst | 30 +
add commands which supports following TTL actions:
- RTE_FLOW_ACTION_TYPE_DEC_TTL
- RTE_FLOW_ACTION_TYPE_SET_TTL
Signed-off-by: Xiaoyu Min
---
app/test-pmd/cmdline_flow.c | 34 +
app/test-pmd/config.c | 3 ++
doc/guides/testpmd_app_ug
Offload following modify TTL actions to E-Switch via
TC-Flower driver
- RTE_FLOW_ACTION_TYPE_SET_TTL
- RTE_FLOW_ACTION_TYPE_DEC_TTL
The corresponding IP protocol rte_flow_item_ipv[4|6]
must be present in rte_flow pattern otherwith PMD
return error
Signed-off-by: Xiaoyu Min
---
drivers/net
This series is for RFC[1]
Patch 1 adds generic MAC address rewrite actions to flow API
Patch 2 adds testpmd commands for that
Patch 3 offloads these actions on Mellanox MLX5 by using E-Switch rule
[1]: https://patches.dpdk.org/patch/44005/
Xiaoyu Min (3):
ethdev: add generic MAC address
add commands to support following actions:
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
Signed-off-by: Xiaoyu Min
---
app/test-pmd/cmdline_flow.c | 50 +
app/test-pmd/config.c | 4 ++
doc/guides/testpmd_app_ug
rte_flow actions:
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
added in order to offload to NIC
The rte_flow_itme_eth must be present in rte_flow pattern
Signed-off-by: Xiaoyu Min
---
doc/guides/prog_guide/rte_flow.rst | 30 ++
lib
Offload following modify MAC address actions to E-Switch
via TC-Flower driver
- RTE_FLOW_ACTION_TYPE_SET_MAC_SRC
- RTE_FLOW_ACTION_TYPE_SET_MAC_DST
The corresponding rte_flow_item_eth must be present in
rte_flow pattern
Only support modify outer layer MAC address
Signed-off-by: Xiaoyu Min
pointer point to (sh->flow_tbls) is
overwritten by the later created hast list.
To fix this, just don't create hash list if it is already created.
Fixes: 54534725d2f3 ("net/mlx5: fix flow table hash list conversion")
Cc: sta...@dpdk.org
Reported-by: Zhike Wang
Signed-
From: Xueming Li
Add pmd unix socket server to enable external tool applications to
trigger flow dump.
Socket path:
/var/tmp/dpdk_mlx5_
Socket format:
io_raw: port_id of uint16
file: file descriptor of int
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
From: Xueming Li
Dump fdb/nic_rx/nic_tx raw flow data into specified file.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/Makefile | 11 ++-
drivers/net/mlx5/meson.build | 4 +++
drivers/net/mlx5/mlx5.h | 2
This RFC intends to provide a way to dump all the offloaded rte flows
in HW. This is very helpful for user and developer to debug flow offloading
stuff, i.e, to check whether PMD offloads the rte flow in a correct way
from HW perspective.
A private PMD API is provided as well as a socket server fo
From: Xueming Li
Guide of mlx5 is updated on how to dump HW flows.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
doc/guides/nics/mlx5.rst | 28
1 file changed, 28 insertions(+)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index
From: Xueming Li
New flow dump CLI to dump MLX5 PMD specific flows into screen.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
app/test-pmd/Makefile | 4 ++
app/test-pmd/cmdline_flow.c | 91 +
app/test-pmd/config.c | 33
in a correct way
from HW perspective.
The output file is in vendor specific format. An external vendor
provided tool may be needed in order to get human readable info.
[1]: https://patches.dpdk.org/cover/64597/
Xiaoyu Min (2):
ethdev: add API to dump device internal flow info
net/mlx5: support
Dump fdb/nic_rx/nic_tx raw flow data into specified file.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/Makefile | 7 ++-
drivers/net/mlx5/meson.build | 2 ++
drivers/net/mlx5/mlx5.h | 4
drivers/net/mlx5/mlx5_devx_cmds.c | 35
Introduce an API which dump the device's internal representation
information of rte flows in hardware.
Signed-off-by: Xiaoyu Min
---
lib/librte_ethdev/rte_ethdev_version.map | 3 +++
lib/librte_ethdev/rte_flow.c | 16
lib/librte_ethdev/rte_flow.h
From: Xueming Li
New flow dump CLI to dump device internal representation information
of flows into screen.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
app/test-pmd/cmdline_flow.c | 91 +
app/test-pmd/config.c | 27 +++
app/test
From: Xueming Li
Add pmd unix socket server to enable external tool applications to
trigger flow dump.
Socket path:
/var/tmp/dpdk_mlx5_
Socket format:
io_raw: port_id of uint16
file: file descriptor of int
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
From: Xueming Li
Guide of mlx5 is updated on how to dump HW flows.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
doc/guides/nics/mlx5.rst | 28
1 file changed, 28 insertions(+)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index
improvement per review comments
Xiaoyu Min (2):
ethdev: add API to dump device internal flow info
net/mlx5: support flow dump API
Xueming Li (3):
app/testpmd: new flow dump CLI
net/mlx5: add socket server for external tools
doc: update mlx5 document for flow dump feature
app/test-pmd
Dump fdb/nic_rx/nic_tx raw flow data into specified file.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/Makefile | 7 ++-
drivers/net/mlx5/meson.build | 4 +++-
drivers/net/mlx5/mlx5.h | 4
drivers
Introduce an API which dump the device's internal representation
information of rte flows in hardware.
Signed-off-by: Xiaoyu Min
Acked-by: Ori Kam
---
lib/librte_ethdev/rte_ethdev_version.map | 3 +++
lib/librte_ethdev/rte_flow.c | 16
lib/librte_ethdev/rte_f
From: Xueming Li
Guide of mlx5 is updated on how to dump HW flows.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
---
doc/guides/nics/mlx5.rst | 28
1 file changed, 28 insertions(+)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index
From: Xueming Li
Add pmd unix socket server to enable external tool applications to
trigger flow dump.
Socket path:
/var/tmp/dpdk_mlx5_
Socket format:
io_raw: port_id of uint16
file: file descriptor of int
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
Acked-by
From: Xueming Li
New flow dump CLI to dump device internal representation information
of flows into screen.
Signed-off-by: Xueming Li
Signed-off-by: Xiaoyu Min
Acked-by: Ori Kam
---
app/test-pmd/cmdline_flow.c | 91 +
app/test-pmd/config.c | 27
Explanation of flow dump command is added into testpmd functions.
Signed-off-by: Xiaoyu Min
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 20
1 file changed, 20 insertions(+)
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
b/doc/guides/testpmd_app_ug
according to the user inputs.
This will be very helpful for developer/tester in some test scenarios.
For example, connection tracking functinality in OVS, which needs to
swap UDP ports in addition to L2/L3 addresses in order to complete one
connection.
Signed-off-by: Xiaoyu Min
---
app/test-pmd
bject: [dpdk-dev] [PATCH 1/5] app/test-flow-perf: add flow performance
> >skeleton
> >
> >Add flow performance application skeleton.
> >
> >Signed-off-by: Wisam Jaddo
Reviewed-by: Xiaoyu Min
rent flow each time, and all other items will
> have open masks.
>
> The current design have single core insertion rate.
> In the future we may have a multi core insertion
> rate measurement support in the app.
>
> Signed-off-by: Wisam Jaddo
Reviewed-by: Xiaoyu Min
ion rate scenario alone"
>
> 2- Check that no memory leackage after doing insertion then
> deletion.
>
> Signed-off-by: Suanming Mou
> Signed-off-by: Wisam Jaddo
Reviewed-by: Xiaoyu Min
ff-by: Wisam Jaddo
Reviewed-by: Xiaoyu Min
.
>
> The support has single and multi performance measurements.
>
> Signed-off-by: Wisam Jaddo
Reviewed-by: Xiaoyu Min
On Tue, 20-04-21, 15:47, Iremonger, Bernard wrote:
> Hi Xiaoyu,
Hey Bernard,
>
> > -Original Message-
> > From: Xiaoyu Min
> > Sent: Wednesday, April 15, 2020 2:49 PM
> > To: tho...@monjalon.net; as...@mellanox.com; Lu, Wenzhuo
> > ; Wu, Jingjing
On Tue, 20-04-21, 21:56, Ferruh Yigit wrote:
> On 4/15/2020 2:48 PM, Xiaoyu Min wrote:
> > This RFC propose a generic `swap` forwarding engine, which could be seen
> > as an extension of existing `macswap` but provide more flexibility.
> >
> > With this generic `swap
On Wed, 20-04-22, 10:26, Kevin Traynor wrote:
> On 15/04/2020 14:48, Xiaoyu Min wrote:
> > This RFC propose a generic `swap` forwarding engine, which could be seen
> > as an extension of existing `macswap` but provide more flexibility.
> >
> > With this generic `swap
with ETH_MQ_RX_RSS_FLAG
set, then RSS is needed for default rules.
Fixes: c64ccc0eca2f ("mlx5: fix overwritten RSS configuration")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.
tested easily.
Signed-off-by: Xiaoyu Min
---
app/test-pmd/parameters.c | 12
app/test-pmd/testpmd.c| 17 ++---
app/test-pmd/testpmd.h| 3 +++
doc/guides/testpmd_app_ug/run_app.rst | 7 +++
4 files changed, 36 insertions
On Thu, 20-04-30, 10:33, Wisam Jaddo wrote:
> Add flow performance application skeleton.
>
> Signed-off-by: Wisam Jaddo
Acked-by: Xiaoyu Min
rent flow each time, and all other items will
> have open masks.
>
> The current design have single core insertion rate.
> In the future we may have a multi core insertion
> rate measurement support in the app.
>
> Signed-off-by: Wisam Jaddo
Acked-by: Xiaoyu Min
On Thu, 20-04-30, 10:33, Wisam Jaddo wrote:
> Add the ability to test deletion rate for flow performance
> application.
>
> This feature is disabled by default, and can be enabled by
> add "--deletion-rate" in the application command line options.
>
> Signed-off-by
ion rate scenario alone"
>
> 2- Check that no memory leackage after doing insertion then
> deletion.
>
> Signed-off-by: Suanming Mou
> Signed-off-by: Wisam Jaddo
Acked-by: Xiaoyu Min
.
>
> The support has single and multi core performance measurements.
>
> Signed-off-by: Wisam Jaddo
Acked-by: Xiaoyu Min
On Thu, 20-04-30, 09:16, Iremonger, Bernard wrote:
> Hi Xiaoyu,
Hey Bernard,
>
> > -Original Message-
> > From: Xiaoyu Min
> > Sent: Wednesday, April 29, 2020 2:04 PM
> > To: Lu, Wenzhuo ; Wu, Jingjing
> > ; Iremonger, Bernard
> > ; Mcnamara, Jo
tested easily.
Signed-off-by: Xiaoyu Min
---
app/test-pmd/parameters.c | 12
app/test-pmd/testpmd.c | 17 ++---
app/test-pmd/testpmd.h | 3 +++
doc/guides/rel_notes/release_20_05.rst | 4
doc/guides/testpmd_app_ug
On Tue, 20-05-05, 17:06, Ferruh Yigit wrote:
> On 4/30/2020 2:07 PM, Xiaoyu Min wrote:
> > One new cmdline option `--rx-mq-mode` is added in order to have the
> > possibility to check whether PMD handle the mq mode correctly or not.
> >
> > The reason is some NICs ne
On Wed, 20-05-06, 10:36, Ferruh Yigit wrote:
> On 5/6/2020 3:52 AM, Xiaoyu Min wrote:
> > On Tue, 20-05-05, 17:06, Ferruh Yigit wrote:
> >> On 4/30/2020 2:07 PM, Xiaoyu Min wrote:
> >>> One new cmdline option `--rx-mq-mode` is added in order to have the
> >
tested easily.
Signed-off-by: Xiaoyu Min
---
app/test-pmd/parameters.c | 15 +++
app/test-pmd/testpmd.c | 17 ++---
app/test-pmd/testpmd.h | 2 ++
doc/guides/rel_notes/release_20_05.rst | 4
doc/guides/testpmd_app_ug
fix set VLAN ID/PCP in new header")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
Reviewed-by: Dekel Peled
---
drivers/net/mlx5/mlx5_flow_dv.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
ind
nsfer group 0 priority 3 pattern
eth / vlan vid spec 2859 vid prefix 4 / ipv4 / end
actcions of_push_vlan ethertype 0x88A8 /
of_set_vlan_pcp vlan_pcp 6 / port_id id 0 / end
Signed-off-by: Xiaoyu Min
Reviewed-by: Dekel Peled
---
drivers/net/mlx5/mlx5_f
fix set VLAN ID/PCP in new header")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyu Min
Reviewed-by: Dekel Peled
Acked-by: Viacheslav Ovsiienko
---
v2:
- rebased
- added Acked-by tag
drivers/net/mlx5/mlx5_flow_dv.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/dri
nsfer group 0 priority 3 pattern
eth / vlan vid spec 2859 vid prefix 4 / ipv4 / end
actcions of_push_vlan ethertype 0x88A8 /
of_set_vlan_pcp vlan_pcp 6 / port_id id 0 / end
Signed-off-by: Xiaoyu Min
Reviewed-by: Dekel Peled
Acked-by: Viacheslav Ovsi
5: optimize tag traversal with hash list")
> Fixes: 6801116688fe ("net/mlx5: fix multiple flow table hash list")
> Cc: sta...@dpdk.org
>
> Signed-off-by: David Marchand
Acked-by: Xiaoyu Min
> ---
> drivers/net/mlx5/mlx5.c | 6 +++---
> drivers/net/m
The layer bits should be unique otherwise layer info will be
interpreted wrongly.
Fixes: 70d84dc797b7 ("net/mlx5: add internal tag item and action")
Cc: or...@mellanox.com
Fixes: 55deee1715f0 ("net/mlx5: extend flow mark support")
Cc: viachesl...@mellanox.com
Signe
DR engine support matching on GRE protocol field without MPLS supports.
So bypassing the MPLS check when DR is enabled.
Signed-off-by: Xiaoyu Min
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.c b
support matching on the present bits (C,K,S)
as well as the optional key field.
If the rte_flow_item_gre_key is specified in pattern,
it will set K present match automatically.
Signed-off-by: Xiaoyu Min
Acked-by: Viacheslav Ovsiienko
---
doc/guides/rel_notes/release_19_08.rst | 5 ++
drivers
d one bug
v4:
* resend patchs in thread mode
v5:
* report error when K is off but gre_key item present
* removed ITEM_CRKSV, added c_bit, k_bit, s_bit in testpmd
* document updated
v6:
* one fix in pmd
v7:
* addressed comments in TestPMD
v8:
* rebased PMD patchs on v19.08-rc1
---
Xiaoy
DR engine support matching on GRE protocol field without MPLS supports.
So bypassing the MPLS check when DR is enabled.
Signed-off-by: Xiaoyu Min
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.c b
* fix release note
---
Xiaoyu Min (2):
net/mlx5: support match GRE protocol on DR engine
net/mlx5: match GRE's key and present bits
doc/guides/rel_notes/release_19_08.rst | 1 +
drivers/net/mlx5/mlx5_flow.c | 63 ++-
drivers/net/mlx5/mlx5_flow.h | 5 ++
d
support matching on the present bits (C,K,S)
as well as the optional key field.
If the rte_flow_item_gre_key is specified in pattern,
it will set K present match automatically.
Signed-off-by: Xiaoyu Min
Acked-by: Viacheslav Ovsiienko
---
doc/guides/rel_notes/release_19_08.rst | 1 +
drivers
FLEX_PARSER_PROFILE_ENABLE=0
Signed-off-by: Xiaoyu Min
---
v2:
* updated release note
v3:
* rebased on 19.08-rc1
---
doc/guides/nics/mlx5.rst | 15 ++-
doc/guides/rel_notes/release_19_08.rst | 1 +
drivers/net/mlx5/mlx5_flow.c | 35
1] http://mails.dpdk.org/archives/dev/2018-October/116092.html
Signed-off-by: Xiaoyu Min
---
app/test-pmd/cmdline.c | 7 +
app/test-pmd/cmdline_flow.c | 535 +++-
app/test-pmd/testpmd.h | 2 +
doc/guides/testpmd_app_ug/testp
rect data.
[1] https://patches.dpdk.org/patch/53456/
---
v2:
* add gre key support
v3:
* removed help string from help filters
* rebased on 19.08-rc1
---
Xiaoyu Min (3):
app/testpmd: support raw encap/decap actions
app/testpmd: support MPLS's TC and S bits
app/testpmd: add GRE key
1 - 100 of 185 matches
Mail list logo
