Enable Tx checksum offload for tunneling packets by
configuring tunneling parameters in Tx descriptors,
including outer L3/L4 checksum offload.
Signed-off-by: Beilei Xing
---
drivers/net/ice/ice_ethdev.c | 3 +-
drivers/net/ice/ice_rxtx.c | 73 +---
2 f
When arguments delimited with RTE_KVARGS_PAIRS_DELIM happen to have
spaces before and after the delimiter, the rte_kvargs_process() can not
match them to the intended key. For example, the first argument below
triggers the support-multi-driver handler as expected, but the second
one silently fails
When i40e_rx_vec_dev_conf_condition_check_default() determines whether
vector receive functions would be allowed during initialization phase,
it should honor previously recorded disallowance during configuration
phase, and not override simply because it is for the first queue.
Signed-off-by: Mesut
Applications using DPDK, including but not limited to OVS DPDK,
utilize rte_flow to benefit from hardware flow offloads. Three
patches in this set improves i40e offload capabilities by
(*) Enhancing Flow Director to support MARK + RSS action combination
(*) Giving applications ability to disable v
Currently, i40e Flow Director action parser only allows following nine
action combinations: (QUEUE, PASSTHRU, DROP, QUEUE + MARK, PASSTHRU +
MARK, DROP + MARK, QUEUE + FLAG, PASSTHRU + FLAG, DROP + FLAG)
Using the existing Cloud Filter profile on the NIC, it is possible to
add support for two more
Vector RX functions are not at feature parity with non-vector ones and
currently the vector RX path is enabled by default. Hence, the only
option to force selection of non-vector variants and be able to retain
functionality is to disable vector PMD globally at compile time via the
config file optio
The failsafe driver device info had several issues in the
info it reported in dev_info_get:
- it cleared dev_info->device set in rte_eth_dev_info_get
- many fields (for example max_rx_queue) should be the minimum
of all sub devices
- it reported tx capa for the active transmit device, but
This patch intend to support
action_raw_encap/decap [1] in a generic and convenient way.
Two new commands - set raw_encap, set raw_decap are introduced just
like the other commands for encap/decap, i.e. set vxlan.
These two commands have corresponding global buffers
which can be used by PMD as th
Each hash entry has a pointer to one uint32 memory location.
However, all the readers increment the same location causing
race conditions. Allocate memory for each thread so that each
thread will increment its own memory location.
Fixes: b87089b0bb19 ("test/rcu: add API and functional tests")
Rep
Using bit operations like or and xor is faster than a loop
on all architectures. Really just explicit unrolling.
Similar cast to uint16 unaligned is already done in
other functions here.
Signed-off-by: Stephen Hemminger
---
lib/librte_net/rte_ether.h | 17 +++--
1 file changed, 7 in
Make a function that coresponds with eth_aton_r which can
be used to convert string to ether_addr.
This also allows rte_ethdev to no longer depend on the
cmdline library.
Signed-off-by: Stephen Hemminger
---
lib/librte_net/rte_ether.c | 12
lib/librte_net/rte_ether.h
Use eth_unformat_addr, so that ethdev can be built and work
without the cmdline library. The dependency on cmdline was
an arrangement of convenience anyway.
Signed-off-by: Stephen Hemminger
---
lib/librte_ethdev/rte_class_eth.c | 9 +
1 file changed, 1 insertion(+), 8 deletions(-)
diff
A bunch of little changes to net/ether
Stephen Hemminger (4):
net/ether: deinline non-critical functions
net/ether: add eth_unformat_addr
ethdev: use eth_unformat_addr
net/ether: use bitops to speedup comparison
lib/librte_ethdev/rte_class_eth.c | 9 +
lib/librte_net/Makefile
Formatting ethernet address and getting a random value are
not in critical path so they should not be inlined.
Signed-off-by: Stephen Hemminger
---
lib/librte_net/Makefile| 1 +
lib/librte_net/rte_ether.c | 29 +
lib/librte_net/rte_ether.h
Each hash entry has a pointer to one uint32 memory location.
However, all the readers increment the same location causing
race conditions. Allocate memory for each thread so that each
thread will increment its own memory location.
Reported-by: David Marchand
Signed-off-by: Honnappa Nagarahalli
R
The libbpf requires linking elf library. Fix it by
adding -lelf.
Fixes: f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")
Signed-off-by: William Tu
---
mk/rte.app.mk | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 7c9b4b538e52..e5d15218618a
>
> Prefer the existing apis rather than direct access lcore_config that is going
> to
> disappear.
>
> Fixes: b87089b0bb19 ("test/rcu: add API and functional tests")
>
> Signed-off-by: David Marchand
> ---
> app/test/test_rcu_qsbr.c | 22 ++
> app/test/test_rcu_qsbr_
The driver currently uses rte_pktmbuf_free() to free each mbuf
after transmit completion. This is optimized to free multiple
mbufs using rte_mempool_put_bulk().
Signed-off-by: Ajit Khaparde
Signed-off-by: Sriharsha Basavapatna
---
drivers/net/bnxt/bnxt_txq.c | 11
drivers/net/bnxt/bnxt
From: Sriharsha Basavapatna
This patch adds a few optimizations to Tx batching. Instead of
specifying 'cmpl_next' to bnxt_start_xmit() as a hint to enable
completion for a given packet, request for completion on the last
successfully enqueued TxBD. This takes care of both success and
error cases.
The HW can have limits on the minimum packet size it can support,
or the maximum number of segments it can support. Check for such
possibilities. Also check if we are going to have a 0 length buffer.
Fixes: 6eb3cc2294fd ("net/bnxt: add initial Tx code")
Signed-off-by: Ajit Khaparde
Reviewed-by: S
We wrongly update lflags in the Tx descriptor; avoid it. Also, instead of
calculating the last producer index to see if mbuf segments are chained,
check if the pointer is NULL to iterate through the segment list.
Fixes: 6eb3cc2294fd ("net/bnxt: add initial Tx code")
Signed-off-by: Ajit Khaparde
R
Add support to update ipid during TSO.
Signed-off-by: Ajit Khaparde
Reviewed-by: Somnath Kotur
Signed-off-by: Sriharsha Basavapatna
---
drivers/net/bnxt/bnxt_txr.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
in
This patchset brings in few fixes and some changes tuning
the Tx datapath performance in bnxt PMD.
Please apply.
Ajit Khaparde (4):
net/bnxt: fix an issue seen with TSO
net/bnxt: add support to update ipid
net/bnxt: check for some error conditions in Tx path
net/bnxt: support bulk free of
From: Sriharsha Basavapatna
This patch addresses the following issues with Tx batching:
1. Tx stall observed in some conditions:
The batching code doesn't request for a completion when only a partial
chain of packets is transmitted due to mbuf allocation errors. Because
of this, Tx consumer ind
On 2019-05-14 15:37, Bruce Richardson wrote:
The meson build never checked for the presence of rdrand and rdseed
instructions, while make build never checked for rdseed. Ensure builds
always have the appropriate checks - and therefore defines - for these
instructions. For runtime, we also add in
Hi Akhil, etc,
Is a deprecation notice necessary for this patch?
If this patch is accepted I will send a follow-up patchset zeroing the xforms
in crypto apps.
Fiona
> -Original Message-
> From: Trahe, Fiona
> Sent: Wednesday, May 15, 2019 5:37 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; ak
Signed-off-by: Fiona Trahe
---
doc/guides/prog_guide/cryptodev_lib.rst | 10 --
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/doc/guides/prog_guide/cryptodev_lib.rst
b/doc/guides/prog_guide/cryptodev_lib.rst
index 23fa5bc..cc53b25 100644
--- a/doc/guides/prog_guide/cry
This patch tries to fix the coverity issue of unchecked
return value. Since the function that causes the problem
is unused, it is removed completely.
Coverity issue: 336816
Fixes: f5188211c721 ("examples/vhost_crypto: add sample application")
Cc: sta...@dpdk.org
Signed-off-by: Fan Zhang
---
exa
This patch fixes a few same class bugs that causes the
logically dead code in vhost_crypto.
Coverity issue: 277236
Coverity issue: 277233
Coverity issue: 277220
Coverity issue: 277214
Fixes: 3bb595ecd682 ("vhost/crypto: add request handler")
Cc: sta...@dpdk.org
Signed-off-by: Fan Zhang
---
lib
This patch fixes the inferred misuse of enum of crypto
algorithms.
Coverity issue: 325879
Fixes: e80a98708166 ("vhost/crypto: add session message handler")
Cc: sta...@dpdk.org
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 93 ++---
1 file cha
Use of weak symbols can hide makefile errors especially when
custom makefiles are used. Removing the use of weak symbols
to avoid a stub function being linked in production code.
Signed-off-by: David Harton
---
v2 - added CC_AVX2_SUPPORT check to code enabling avx2 vectors
drivers/net/i40e/Ma
Coverity issue: 336866
Coverity issue: 336841
Coverity issue: 336838
Fixes: 41d561cbdd24 ("examples/fips_validation: add power on self test")
Signed-off-by: Fan Zhang
---
examples/fips_validation/fips_dev_self_test.c | 15 ---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --
This patch fixes the out-of-bounds coverity issue by adding
missed algorithms to the array.
Coverity issue: 337683
Fixes: c68d7aa354f6 ("crypto/aesni_mb: use architecture independent macros")
Signed-off-by: Fan Zhang
---
drivers/crypto/aesni_mb/rte_aesni_mb_pmd_private.h | 8 +++-
1 file c
On Wed, 2019-05-15 at 12:38 +0100, Bruce Richardson wrote:
> To improve code quality we want to turn on as many warnings as we can
> in
> the DPDK code, so turn on the "unused-parameter" warning in meson
> builds to
> match that of the make builds. To ensure correct compilation, disable
> the
> war
When a new pipeline is added to a thread, the "time_next_min" value may
need update, otherwise this pipeline won't get served timely.
Fixes: 70709c78fda6 ("net/softnic: add command to enable/disable pipeline")
Cc: sta...@dpdk.org
Signed-off-by: Xiao Wang
---
drivers/net/softnic/rte_eth_softnic_
On Wed, May 15, 2019 at 09:05:12AM -0400, David Harton wrote:
> Use of weak symbols can hide makefile errors especially when
> custom makefiles are used. Removing the use of weak symbols
> to avoid a stub function being linked in production code.
>
> Signed-off-by: David Harton
> ---
Looks reaso
Add new rte_flow_item_gre_key in order to match the optional key field.
Signed-off-by: Xiaoyu Min
---
v2:
* new rte_flow_item_gre_key added instead of expanding existing
rte_flow_item_gre.
* updated document.
doc/guides/prog_guide/rte_flow.rst | 9 +
lib/librte_ethdev/rte_flow.c
Use of weak symbols can hide makefile errors especially when
custom makefiles are used. Removing the use of weak symbols
to avoid a stub function being linked in production code.
Signed-off-by: David Harton
---
drivers/net/i40e/Makefile| 1 +
drivers/net/i40e/i40e_rxtx.c | 52 +
Hello,
On Thu, Apr 11, 2019 at 9:45 AM David Marchand
wrote:
> Hello,
>
> On Tue, Apr 9, 2019 at 9:06 PM Vivian Kong wrote:
>
>> To build and run DPDK on Linux on IBM Z (s390x), big endian support
>> is added and s390x vector intrinics are used in the implementation
>>
>
> intrinsics*
>
> of DP
On 5/15/19 9:57 AM, David Marchand wrote:
Prefer the existing apis rather than direct access lcore_config that is
going to disappear.
Fixes: b87089b0bb19 ("test/rcu: add API and functional tests")
Signed-off-by: David Marchand
---
app/test/test_rcu_qsbr.c | 22 ++
On 5/15/19 9:56 AM, David Marchand wrote:
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency")
Fixes: 3f9aab961ed3 ("test/hash: check lock-free extendable bucket")
Cc:sta...@dpdk.org
Signed-off-by: Da
> -Original Message-
> From: Fiona Trahe
> Sent: Wednesday, May 15, 2019 4:46 PM
> To: dev@dpdk.org
> Cc: fiona.tr...@intel.com; Shally Verma ; Sunila Sahu
> ; lee.d...@intel.com; Ashish Gupta
> ; akhil.go...@nxp.com; tomaszx.jozw...@intel.com;
> sta...@dpdk.org
> Subject: [PATCH v3] do
> -Original Message-
> From: Trahe, Fiona
> Sent: Wednesday, May 15, 2019 1:16 PM
> To: dev@dpdk.org
> Cc: Trahe, Fiona ; shal...@marvell.com;
> ss...@marvell.com; Daly, Lee ; ashi...@marvell.com;
> akhil.go...@nxp.com; Jozwiak, TomaszX ;
> sta...@dpdk.org
> Subject: [PATCH v3] doc/compr
To improve code quality we want to turn on as many warnings as we can in
the DPDK code, so turn on the "unused-parameter" warning in meson builds to
match that of the make builds. To ensure correct compilation, disable the
warning selectively for driver base code that otherwise would have issues.
Fixed some typos and clarified how errors on ops which
fail to get submitted on the enqueue API should be handled.
Fixes: a584d3bea902 ("doc: add compressdev library guide")
cc: sta...@dpdk.org
Signed-off-by: Fiona Trahe
---
v3 changes:
- change proposal so appl must check status of op_enqueued
Hi Arek,
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Wednesday, May 15, 2019 1:51 AM
> To: Trahe, Fiona ; Doherty, Declan
> ; De Lara Guarch,
> Pablo ; akhil.go...@nxp.com;
> ravi1.ku...@amd.com; Jerin Jacob
> Kollanukkaran ; Anoob Joseph ; Zhang,
> Roy Fan
> ; t...@semihal
Patch [1] added, among other definitions, the macro MLX5_ST_SZ_DB.
Patch [2] added later the macro MLX5_ST_SZ_BYTES, which is exactly
the same macro with a different name.
Each of these macros was used in very few places.
This patch removes the definition of MLX5_ST_SZ_DB, and replaces it
with MLX
Previous patch added handling of metadata for multi-segment packet.
Function txq_scatter_v in file mlx5_rxtx_vec_neon.h was updated
incorrectly, items were inserted into WQE in wrong order.
This patch fixes the issue, inserting items into WQE correctly.
Fixes: 7f4019d370f6 ("net/mlx5: fix Tx meta
On 5/15/19 9:54 AM, David Marchand wrote:
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: de3cfa2c9823 ("sched: initial import")
Cc:sta...@dpdk.org
Signed-off-by: David Marchand
---
examples/qos_sched/args.c | 7 +++
1 file changed, 3 insertions(
On 5/15/19 9:54 AM, David Marchand wrote:
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
examples/multi_process/symmetric_mp/main.c | 2 +-
1 file changed,
On 5/15/19 9:54 AM, David Marchand wrote:
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: a958a5c07f4b ("net/softnic: support service cores")
Cc:sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/softnic/rte_eth_softnic_thread.c | 13 --
On 5/15/19 9:54 AM, David Marchand wrote:
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: 92c8a63223e5 ("cxgbe: add device configuration and Rx support")
Cc:sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/cxgbe/cxgbe_main.c | 5 ++---
1
On Tue, 19-05-14, 08:25, Stephen Hemminger wrote:
> On Tue, 14 May 2019 10:18:29 +0300
> Xiaoyu Min wrote:
>
> > Add GRE's checksum, key, and sequence field to the
> > struct rte_flow_item_gre in order to match.
> >
> > Signed-off-by: Xiaoyu Min
> > ---
> > lib/librte_ethdev/rte_flow.h | 4 +++
On Tue, 19-05-14, 11:00, Adrien Mazarguil wrote:
> On Tue, May 14, 2019 at 10:34:22AM +0300, Andrew Rybchenko wrote:
> > On 5/14/19 10:18 AM, Xiaoyu Min wrote:
> > > Add GRE's checksum, key, and sequence field to the
> > > struct rte_flow_item_gre in order to match.
> > >
> > > Signed-off-by: Xiao
This patch enables busy-poll support for AF_XDP pmd. With busy-poll, the
kernel driver is executed in process context by calling the poll() syscall.
The main advantage of busy-poll feature is that all processing occurs on a
single core. This eliminates the core-to-core cache transfers that occur
b
Implement zero copy of af_xdp pmd through mbuf's external memory
mechanism to achieve high performance.
This patch also provides a new parameter "pmd_zero_copy" for user, so they
can choose to enable zero copy of af_xdp pmd or not.
To be clear, "zero copy" here is different from the "zero copy mo
This patch adds two parameters `start_queue` and `queue_count` to
specify the range of netdev queues used by AF_XDP pmd.
Signed-off-by: Xiaolong Ye
---
doc/guides/nics/af_xdp.rst | 3 +-
drivers/net/af_xdp/rte_eth_af_xdp.c | 88 +++--
2 files changed, 49 inserti
Hi,
This patch series mainly includes 3 new features for AF_XDP pmd. They
are separated independent features, the reason I take them in one
patchset is that they have code dependency.
1. zero copy
This patch enables `zero copy` between af_xdp umem and mbuf by using
external mbuf mechanism.
2. m
libnuma.so is needed to augment the cross toolchain with NUMA support.
This fixed meson cross compiling issue.
Command used:
meson arm64-build --cross-file config/arm/arm64_armv8_linux_gcc
ninja -C arm64-build
Compiling error:
.../aarch64-linux-gnu/bin/ld: lib/librte_eal.so.10.1: version node
not
14/05/2019 21:45, Nicolas Chautru:
> +Installation
> +--
> +
> +Section 3 of the DPDK manual provides instuctions on installing and
> compiling DPDK. The
> +default set of bbdev compile flags may be found in config/common_base, where
> for example
> +the flag to build the FPGA LTE FEC
Meeting notes for the DPDK technical board meeting held on 2019-05-08
Attendees: 5/9
- Bruce Richardson
- Ferruh Yigit
- Hemant Agrawal
- Jerin Jacob
- Thomas Monjalon
We did not have the quorum to take any decision.
1) Honnappa prepared a report of the p
Prefer the existing apis rather than direct access lcore_config that is
going to disappear.
Fixes: b87089b0bb19 ("test/rcu: add API and functional tests")
Signed-off-by: David Marchand
---
app/test/test_rcu_qsbr.c | 22 ++
app/test/test_rcu_qsbr_perf.c | 12
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency")
Fixes: 3f9aab961ed3 ("test/hash: check lock-free extendable bucket")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
app/test/test_hash_readwrit
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
examples/multi_process/symmetric_mp/main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/examp
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: 92c8a63223e5 ("cxgbe: add device configuration and Rx support")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/cxgbe/cxgbe_main.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: de3cfa2c9823 ("sched: initial import")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
examples/qos_sched/args.c | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/examples/qos_s
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: a958a5c07f4b ("net/softnic: support service cores")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/softnic/rte_eth_softnic_thread.c | 13 -
1 file changed, 4 insertions(+), 9 de
On Wed, May 15, 2019 at 7:34 AM Stephen Hemminger <
step...@networkplumber.org> wrote:
> On Tue, 14 May 2019 23:00:17 +0200
> Thomas Monjalon wrote:
>
> > 14/05/2019 18:32, David Marchand:
> > > On Tue, May 14, 2019 at 6:08 PM Thomas Monjalon
> wrote:
> > >
> > > > Start a new release cycle with
15/05/2019 07:34, Stephen Hemminger:
> On Tue, 14 May 2019 23:00:17 +0200
> Thomas Monjalon wrote:
>
> > 14/05/2019 18:32, David Marchand:
> > > On Tue, May 14, 2019 at 6:08 PM Thomas Monjalon
> > > wrote:
> > >
> > > > Start a new release cycle with empty release notes.
> > > >
> > > > Sign
15/05/2019 08:52, Nithin Dabilpuram:
> Hi Thomas,
> On Tue, May 14, 2019 at 05:39:30PM +0200, Thomas Monjalon wrote:
> > Hi,
> >
> > 13/05/2019 13:21, Nithin Dabilpuram:
> > > With the latest published interface of
> > > rte_eal_hotplug_[add,remove](), and rte_eth_dev_close(),
> > > rte_eth_dev_cl
> -Original Message-
> From: Xing, Beilei
> Sent: Wednesday, May 15, 2019 2:36 PM
> To: Zhang, Qi Z ; Lu, Wenzhuo
> ; Yang, Qiming ; Ananyev,
> Konstantin
> Cc: dev@dpdk.org
> Subject: RE: [PATCH 0/3] fix invalid Tx threshhold setup
>
>
>
> > -Original Message-
> > From: Zhan
71 matches
Mail list logo
