From: Beilei Xing
Move avx512 vector path for single queue to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_rxtx.h| 20 +
.../idpf/idpf_common_rxtx_avx512.c} | 4 +--
drivers/common/idpf/meson.build | 30 +
From: Beilei Xing
Move vector queue setup for single queue model to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_rxtx.c | 57 ++
drivers/common/idpf/idpf_common_rxtx.h | 2 +
drivers/common/idpf/version.map| 1 +
drivers/net/id
From: Beilei Xing
Add timestamp filed to idpf_adapter structure.
Add scalar data path for single queue model and split queue model.
Signed-off-by: Mingxia Liu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.h | 5 +
drivers/common/idpf/idpf_common_logs.h | 24 +
dri
From: Beilei Xing
Add timestamp filed to idpf_adapter structure.
Move scalar Rx/Tx data path for both single queue and split queue
to common module.
Signed-off-by: Mingxia Liu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.h | 5 +
drivers/common/idpf/idpf_common_logs
From: Beilei Xing
Refine rxq setup and txq setup.
Move some help functions of queue setup and queue release
to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_rxtx.c | 414 +
drivers/common/idpf/idpf_common_rxtx.h | 57 ++
drivers/common/idpf/meson.bu
From: Beilei Xing
Add idpf_rxq and idpf_txq structure in common module.
Move idpf_vc_config_rxq and idpf_vc_config_txq functions
to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.h | 2 +
drivers/common/idpf/idpf_common_rxtx.h | 112 +
From: Beilei Xing
Move vector flags from idpf_adapter_ext structure to
idpf_vport structure.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.h | 5 +
drivers/net/idpf/idpf_ethdev.h | 5 -
drivers/net/idpf/idpf_rxtx.c | 22 ++
From: Beilei Xing
Initialize create vport info in common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 35 +
drivers/common/idpf/idpf_common_device.h | 11 ++
drivers/common/idpf/version.map | 1 +
drivers/net/idpf/idpf_ethdev.c
From: Beilei Xing
Move queue module fields from idpf_adapter_ext structure to
idpf_adapter structure.
Refine some parameter and function name, and move function
idpf_create_vport_info_init to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 35 ++
From: Beilei Xing
Move ptype_tbl field to idpf_adapter structure.
Move get_pkt_type to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 216 +
drivers/common/idpf/idpf_common_device.h | 7 +
drivers/common/idpf/idpf_common_virtc
From: Beilei Xing
Move ptype_tbl field to idpf_adapter structure.
Move get_pkt_type to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 216 +
drivers/common/idpf/idpf_common_device.h | 7 +
drivers/common/idpf/idpf_common_virtc
From: Beilei Xing
Introduce idpf_config_irq_map/idpf_config_irq_unmap functions
in common module, and refine config rxq irqs function.
Refine device start function with some irq error handling. Besides,
vport->stopped should be initialized at the end of the function.
Signed-off-by: Jingjing Wu
From: Beilei Xing
Move configure RSS to common module.
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 25 +++
drivers/common/idpf/idpf_common_device.h | 2 ++
drivers/common/idpf/version.map | 1 +
drivers/net/idpf/idpf_ethdev.c
From: Beilei Xing
Introduce idpf_vport_init and idpf_vport_deinit functions
in common module.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 115 +
drivers/common/idpf/idpf_common_device.h | 13 +-
drivers/common/idpf/id
From: Beilei Xing
Introduce idpf_adapter_init and idpf_adapter_deinit
functions in common module.
And also introduce idpf_adapter_ext_init and
idpf_adapter_ext_deinit functions.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.c | 153
From: Beilei Xing
Move most of virtual channel functions to idpf common module.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/base/meson.build | 2 +-
drivers/common/idpf/idpf_common_device.c | 8 +
drivers/common/idpf/idpf_common_device.h | 61 ++
From: Beilei Xing
Move most of the virtual channel functions to idpf common module.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/base/meson.build | 2 +-
drivers/common/idpf/idpf_common_device.c | 8 +
drivers/common/idpf/idpf_common_device.h | 61
From: Beilei Xing
Move idpf_vport structure to common module, remove ethdev dependency.
Also remove unused functions.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_common_device.h | 59 ++
drivers/net/idpf/idpf_ethdev.c | 10 +-
drivers/net/i
From: Beilei Xing
Add structure idpf_adapter in common module, the structure includes
some basic fields.
Introduce structure idpf_adapter_ext in PMD, this structure includes
extra fileds except idpf_adapter.
Signed-off-by: Wenjun Wu
Signed-off-by: Beilei Xing
---
drivers/common/idpf/idpf_comm
From: Beilei Xing
Refactor idpf pmd by introducing idpf common module, which will be also
consumed by a new PMD - CPFL (Control Plane Function Library) PMD.
v2 changes:
- Refine irq map/unmap functions.
- Fix cross compile issue.
v3 changes:
- Embed vport_info field into the vport structure.
On Sat, Jan 14, 2023 at 12:22 AM Tyler Retzlaff
wrote:
>
> Remove the rte_thread_getname API. The API is __rte_experimental and
> requires no deprecation notice.
>
> Fold the platform specific variants into the one place it is used as a
> special case to retain the functionality for linux only.
>
Hi Qi,
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, January 17, 2023 10:25 AM
> To: Su, Simei ; Guo, Junfeng
> Cc: dev@dpdk.org; Wu, Wenjun1
> Subject: RE: [PATCH 1/3] net/igc: code refactoring
>
>
>
> > -Original Message-
> > From: Su, Simei
> > Sent: Tuesday,
HI Ori:
Those three matching items are redundant. Has been removed already.
Do I need to send RFC v2?
BR
Rongwei
> -Original Message-
> From: Ori Kam
> Sent: Tuesday, January 17, 2023 00:15
> To: Rongwei Liu ; Matan Azrad ;
> Slava Ovsiienko ; NBU-Contact-Thomas Monjalon
There are many high-performance DMA devices supported in DPDK now, and
these DMA devices can also be integrated into other modules of DPDK as
accelerators, such as Vhost. Before integrating DMA into applications,
developers need to know the performance of these DMA devices in various
scenarios and
> -Original Message-
> From: Su, Simei
> Sent: Tuesday, December 20, 2022 11:41 AM
> To: Zhang, Qi Z ; Guo, Junfeng
>
> Cc: dev@dpdk.org; Wu, Wenjun1 ; Su, Simei
>
> Subject: [PATCH 1/3] net/igc: code refactoring
>
> Move related structures for Rx/Tx queue from igc_txrx.c to igc_txrx
> -Original Message-
> From: Zhichao Zeng
> Sent: Thursday, January 12, 2023 5:32 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Zhou, YidingX ; Zeng,
> ZhichaoX ; Wu, Jingjing ;
> Xing, Beilei ; Doherty, Declan
> ; Sinha, Abhijit ;
> Nicolau, Radu
> Subject: [PATCH] net/iavf: fix buildi
> -Original Message-
> From: David Marchand
> Sent: Thursday, January 5, 2023 9:58 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Wu, Jingjing ; Xing, Beilei
> ; Zhang, Qi Z ; Yang, Qiming
>
> Subject: [PATCH] net/iavf: protect insertion in flow list
>
> Add missing lock acquire.
>
> F
> -Original Message-
> From: Vipin P R
> Sent: Friday, January 13, 2023 9:19 PM
> To: Wu, Jingjing ; Xing, Beilei
> Cc: dev@dpdk.org; Vipin P R ; sta...@dpdk.org
> Subject: [PATCH] Intel iavf: Return in the case of ADD/DEL ETH address
>
> In case of i40vf, VIRTCHNL_OP_DEL_ETH_ADDR and
Hi ferruh,
Our application use rte_eth_dev_socket_id to query the socket that a NIC port
connected, then allocate lcore/memory according to this affinity.
The remote memory access is really slow compared to local.
Thanks,
Frank
-Original Message-
From: Ferruh Yigit,
Sent: Monday, Jan
> -Original Message-
> From: Yang, SteveX
> Sent: Monday, December 26, 2022 8:37 AM
> To: dev@dpdk.org
> Cc: Zhang, Yuying ; Xing, Beilei
> ; Yang, Qiming ; Zhang, Qi
> Z ; Yang, SteveX
> Subject: [PATCH v1 2/2] net/ice: fix unsupported flow rule transfer attribute
>
> ice doesn't sup
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, January 17, 2023 9:27 AM
> To: 'Yang, SteveX' ; dev@dpdk.org
> Cc: Zhang, Yuying ; Xing, Beilei
> ; Yang, Qiming
> Subject: RE: [PATCH v1 1/2] net/i40e: fix unsupported flow rule transfer
> attribute
>
>
>
> > -Original Me
> -Original Message-
> From: Yang, SteveX
> Sent: Monday, December 26, 2022 8:37 AM
> To: dev@dpdk.org
> Cc: Zhang, Yuying ; Xing, Beilei
> ; Yang, Qiming ; Zhang, Qi
> Z ; Yang, SteveX
> Subject: [PATCH v1 1/2] net/i40e: fix unsupported flow rule transfer attribute
>
> i40e doesn't s
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, January 17, 2023 8:15 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Su, Simei
> ; Wu, Wenjun1 ; Burakov,
> Anatoly
> Subject: [PATCH v3 3/7] net/e1000: fix whitespace
>
> The style standard is to use blank after keywords
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, January 17, 2023 8:15 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Su, Simei
> ; Wu, Wenjun1 ; Burakov,
> Anatoly
> Subject: [PATCH v3 3/7] net/e1000: fix whitespace
>
> The style standard is to use blank after keyword
> -Original Message-
> From: Mike Pattrick
> Sent: Thursday, December 29, 2022 7:00 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; tho...@monjalon.net;
> david.march...@redhat.com; Zhou, YidingX ;
> ktray...@redhat.com; Mike Pattrick ; sta...@dpdk.org
> Subject: [PATCH v4] net/iavf: add lock
> -Original Message-
> From: Xing, Beilei
> Sent: Friday, January 6, 2023 5:16 PM
> To: Wu, Jingjing
> Cc: dev@dpdk.org; Zhang, Qi Z ; Xing, Beilei
>
> Subject: [PATCH v2 07/15] common/idpf: add irq map/unmap
>
> From: Beilei Xing
>
> Add irq map/unmap functions in common module.
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, January 17, 2023 8:15 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Zhang, Yuying
> ; Xing, Beilei
> Subject: [PATCH v3 4/7] i40e: fix whitespace
>
> The style standard is to use blank after keywords.
> I.e "if (" not "
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/ip_frag/rte_ipv4_reassembly.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/ip_frag/rte_ipv4_reassembly.c
b/lib/ip_frag/rte_ipv4_reassembly.c
index 4a89a5f5
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/cmdline/cmdline_rdline.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/lib/cmdline/cmdline_rdline.c b/lib/cmdline/cmdline_rdline.c
index 5cf723a0126
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
examples/ip_reassembly/main.c | 2 +-
examples/l3fwd-power/main.c| 9 +
examples/l3fwd/main.c | 9 +
examples/multi_proce
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/i40e/i40e_pf.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/i40e/i40e_pf.c b/drivers/net/i40e/i40e_pf.c
index 15d9ff868f3a..7050e005
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/em_ethdev.c | 2 +-
drivers/net/e1000/igb_ethdev.c | 16
drivers/net/e1000/igb_pf.c | 2 +-
drivers/net/e1000/igb_rxtx.c | 6 +++---
4 files c
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test-pmd/cmdline.c| 33 +
app/test-pmd/parameters.c | 12 +++-
app/test-pmd/testpmd.c| 2 +-
3 files changed, 25 insertions(+), 22 del
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test/test_cmdline_cirbuf.c | 4 ++--
app/test/test_debug.c | 6 +++---
app/test/test_hash.c | 10 +-
app/test/test_lpm6_perf.c | 2 +-
app/test/test
These are the results of a script replacing 'if(' with 'if ('
in various places.
v3 - more checkpatch fallout
also fix places where 'for(' is used.
Stephen Hemminger (7):
test: fix whitespace
testpmd: fix whitespace
net/e1000: fix whitespace
i40e: fix whitespace
examples: fix white
Acked-by: Kai Ji
> -Original Message-
> From: Stephen Hemminger
> Sent: Friday, January 13, 2023 6:44 PM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Ji, Kai
> ; De Lara Guarch, Pablo ;
> Power, Ciara
> Subject: [PATCH] ipsec: remove unneccessary null check
>
> The function rte_ring_fr
On Wed, Jan 11, 2023 at 5:11 AM John Levon wrote:
> On Sun, Jan 08, 2023 at 06:52:39PM -0700, Ashish Sadanandan wrote:
>
> > The code added for allowing --huge-dir to specify hugetlbfs
> > sub-directories has a bug where it incorrectly matches mounts that
> > contain a prefix of the specified --h
On Fri, 13 Jan 2023 13:19:23 +
Vipin P R wrote:
> In case of i40vf, VIRTCHNL_OP_DEL_ETH_ADDR and VIRTCHNL_OP_ADD_ETH_ADDR are
> unsupported.
> i40evf_execute_vf_cmd is invoked with these operations as part of
> i40evf_set_mc_addr_list()
>
> The cases are not handled in i40evf_execute_vf_cm
On Fri, 13 Jan 2023 13:12:47 +
Vipin P R wrote:
> add test case coverage to cover the ms_idx jump
>
> Cc: sta...@dpdk.org
>
> Signed-off-by: Vipin P R
> Acked-by: Kumara Parameshwaran
> ---
> Depends-on: 0001-Memory-Allocation-Fixes-ms_idx-jump-lookahead-during.patch
> Depends-on: 0002-Me
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/ip_frag/rte_ipv4_reassembly.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/ip_frag/rte_ipv4_reassembly.c
b/lib/ip_frag/rte_ipv4_reassembly.c
index 4a89a5f5
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/cmdline/cmdline_rdline.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/lib/cmdline/cmdline_rdline.c b/lib/cmdline/cmdline_rdline.c
index 5cf723a0126
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/i40e/i40e_pf.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/i40e/i40e_pf.c b/drivers/net/i40e/i40e_pf.c
index 15d9ff868f3a..7050e005
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
examples/ip_reassembly/main.c | 2 +-
examples/l3fwd-power/main.c| 7 ---
examples/l3fwd/main.c | 7 ---
examples/multi_process/s
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/em_ethdev.c | 2 +-
drivers/net/e1000/igb_ethdev.c | 16
drivers/net/e1000/igb_pf.c | 2 +-
drivers/net/e1000/igb_rxtx.c | 6 +++---
4 files c
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test-pmd/cmdline.c| 33 +
app/test-pmd/parameters.c | 11 ++-
app/test-pmd/testpmd.c| 2 +-
3 files changed, 24 insertions(+), 22 dele
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test/test_cmdline_cirbuf.c | 4 ++--
app/test/test_debug.c | 6 +++---
app/test/test_hash.c | 10 +-
app/test/test_lpm6_perf.c | 2 +-
app/test/test
These are the results of a script replacing 'if(' with 'if ('
in various places.
v2 - fix related style changes on same lines reported
by checkpatch
Stephen Hemminger (7):
test: fix whitespace
testpmd: fix whitespace
net/e1000: fix whitespace
i40e: fix whitespace
examples: fix whitespac
Validate device operation when a device is stopped or restarted.
The only complication - and gap in the dmadev ABI specification - is
what happens to the job ids on restart. Some drivers reset them to 0,
while others continue where things left off. Take account of both
possibilities in the test ca
The copy tests for dmadev had separate blocks in the test function for
single copy and burst copies. Separate out the single-copy block to its
own function so that it can be re-used if necessary.
Signed-off-by: Bruce Richardson
---
app/test/test_dmadev.c | 120 ++-
The DMA device stop API can return an error value so check that return
value when running dmadev unit tests.
Signed-off-by: Bruce Richardson
---
app/test/test_dmadev.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/app/test/test_dmadev.c b/app/test/test_dmadev.c
index f
When the DMA device was stopped and restarted by the driver, the control
register specifying the behaviour on error was not getting correctly
reset. This caused unit tests to fail as explicitly introduced errors
were got getting reported back.
Fix by moving the setting of the register to the start
As part of the process of restarting a dma instance, the IOAT driver
will reset the HW addresses and state values. The read and write
indexes for SW use need to be similarly reset to keep HW and SW in
sync.
Fixes: 583f046dd404 ("dma/ioat: add start and stop")
Cc: conor.wa...@intel.com
Cc: sta...@d
The HW DMA devices supported by IOAT driver do not transition to
the "active" state until the first operation is started by the HW.
Therefore, if the user calls "rte_dma_stop()" on a device without
triggering any operations, the sequence of commands to be sent to
the HW is different, as is the fina
This patchset fixes a couple of problems with stopping and restarting an
ioat DMA device. Following the three fixes, a series of improvements are
made to the dmadev unit tests to properly validate that dmadevs work
correctly as they are started and stopped, and ensure that no other or
future driver
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/ip_frag/rte_ipv4_reassembly.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/ip_frag/rte_ipv4_reassembly.c
b/lib/ip_frag/rte_ipv4_reassembly.c
index 4a89a5f5
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
examples/ip_reassembly/main.c | 2 +-
examples/l3fwd-power/main.c| 4 ++--
examples/l3fwd/main.c | 4 ++--
examples/multi_process/symmetr
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
lib/cmdline/cmdline_rdline.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/lib/cmdline/cmdline_rdline.c b/lib/cmdline/cmdline_rdline.c
index 5cf723a0126a..28fc
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/em_ethdev.c | 2 +-
drivers/net/e1000/igb_ethdev.c | 8
drivers/net/e1000/igb_pf.c | 2 +-
drivers/net/e1000/igb_rxtx.c | 6 +++---
4 files changed, 9 in
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
drivers/net/i40e/i40e_pf.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/i40e/i40e_pf.c b/drivers/net/i40e/i40e_pf.c
index 15d9ff868f3a..7050e005
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test-pmd/cmdline.c| 30 +++---
app/test-pmd/parameters.c | 8
app/test-pmd/testpmd.c| 2 +-
3 files changed, 20 insertions(+), 20 deletions(
The style standard is to use blank after keywords.
I.e "if (" not "if("
Signed-off-by: Stephen Hemminger
---
app/test/test_debug.c| 4 ++--
app/test/test_hash.c | 6 +++---
app/test/test_malloc.c | 10 +-
app/test/test_mbuf.c | 12 ++--
app/test/test_spinlock.c |
These are the results of a script replacing 'if(' with 'if ('
in various places.
Stephen Hemminger (7):
test: fix whitespace
testpmd: fix whitespace
net/e1000: fix whitespace
i40e: fix whitespace
examples: fix whitespace
cmdline: fix whitespace
ip_frag: fix whitespace
app/test-pmd/
On 1/16/2023 1:07 PM, Morten Brørup wrote:
> Add nonnull function attribute to help the compiler detect a NULL
> pointer being passed to a function not accepting NULL pointers as an
> argument at build time.
>
> Add access function attributes to tell the compiler how a function
> accesses memory p
On Mon, Jan 16, 2023 at 04:09:19PM +, Walsh, Conor wrote:
> Hi Bruce,
>
> This patchset breaks the dmadev autotest for IOAT on IceLake.
>
> Trace below:
>
> ### Test dmadev instance 0 [:00:01.0] IOAT.status: ACTIVE
> [0x100242880] DMA Dev 0: Running copy Tests Ops submitted: 85120Ops
Hi Rongwei,
> -Original Message-
> From: Rongwei Liu
> Sent: Wednesday, 21 December 2022 10:43
>
> Add IPv6 protocol modify field definition.
>
> Signed-off-by: Rongwei Liu
> ---
> lib/ethdev/rte_flow.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/lib/ethdev/rte_flow.h b/
Hi Rongwei,
> -Original Message-
> From: Rongwei Liu
> Sent: Wednesday, 21 December 2022 10:43
>
> Add IPv6 routing extension header definition and no
> TLV support for now.
> At rte_flow layer, there are new items defined for matching
> type/nexthdr/segment_left field.
>
> Signed-off-
Hi Bruce,
This patchset breaks the dmadev autotest for IOAT on IceLake.
Trace below:
### Test dmadev instance 0 [:00:01.0]
IOAT.status: ACTIVE [0x100242880]
DMA Dev 0: Running copy Tests
Ops submitted: 85120Ops completed: 85120Errors: 0
DMA Dev 0: Running stop-start Tests
IOAT.status
Members Attending: 6
* Aaron Conole (chair)
* Hement Agarwal
* Maxime Coquelin
* Nathan Southern
* Stephen Hemminger
* Thomas Monjalon
NOTE: The Technical Board meetings take place every second Wednesday on
https://meet.jit.si/DPDK at 3 pm UTC.
Meetings are public, and DPDK community members are
Validate device operation when a device is stopped or restarted.
The only complication - and gap in the dmadev ABI specification - is
what happens to the job ids on restart. Some drivers reset them to 0,
while others continue where things left off. Take account of both
posibilities in the test cas
The copy tests for dmadev had separate blocks in the test function for
single copy and burst copies. Separate out the single-copy block to its
own function so that it can be re-used if necessary.
Signed-off-by: Bruce Richardson
---
app/test/test_dmadev.c | 120 ++-
The DMA device stop API can return an error value so check that return
value when running dmadev unit tests.
Signed-off-by: Bruce Richardson
---
app/test/test_dmadev.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/app/test/test_dmadev.c b/app/test/test_dmadev.c
index f
As part of the process of restarting a dma instance, the IOAT driver
will reset the HW addresses and state values. The read and write
indexes for SW use need to be similarly reset to keep HW and SW in
sync.
Fixes: 583f046dd404 ("dma/ioat: add start and stop")
Cc: conor.wa...@intel.com
Cc: sta...@d
The HW DMA devices supported by IOAT driver do not transition to
the "active" state until the first operation is started by the HW.
Therefore, if the user calls "rte_dma_stop()" on a device without
triggering any operations, the sequence of commands to be sent to
the HW is different, as is the fina
This patchset fixes a couple of problems with stopping and restarting an
ioat DMA device. Following the two fixes, a series of improvements are
made to the dmadev unit tests to properly validate that dmadevs work
correctly as they are started and stopped, and ensure that no other or
future drivers
Minutes of Technical Board Meeting, 2022-Nov-16
Members Attending
-
∘ Maxime Coquelin
∘ Thomas Monjalon
∘ Kevin Traynor
∘ Hemant Agrawal
∘ Bruce Richardson
∘ Konstantin Ananyev
∘ Jerin Jacob
∘ Honnappa Nagarahalli
∘ Aaron Conole
NOTE: The technical board meetings every second Wed
Thanks Jasvinder. I guess we are on the same page. With the design that you
mention we run short by 1 level of hierarchy -- which is why I was
originally asking for the difficulty of adding a layer. I think I
understand your assessment in that regard i.e. it is easier to add a shaped
dequeue at the
> -Original Message-
> From: Stephen Hemminger
> Sent: Thursday, January 12, 2023 11:32 PM
> To: Zhang, Ke1X
> Cc: Zhang, Qi Z ; Zhang, Yuying
> ; dev@dpdk.org
> Subject: Re: [PATCH v3] net/ice: add devargs for disabling default mac
>
> On Thu, 12 Jan 2023 15:55:38 +0800
> Ke Zhang w
On 12/12/2022 12:48 AM, Frank Du wrote:
> Get from /sys/class/net/{if}/device/numa_node.
>
> Signed-off-by: Frank Du
> ---
> drivers/net/af_xdp/rte_eth_af_xdp.c | 17 ++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c
> b/d
Add nonnull function attribute to help the compiler detect a NULL
pointer being passed to a function not accepting NULL pointers as an
argument at build time.
Add access function attributes to tell the compiler how a function
accesses memory pointed to by its pointer arguments.
Add these attribut
Use RTE_PTR_ADD where copying to the offset of a field in a structure
holding multiple fields, to avoid compiler warnings with decorated
rte_memcpy.
Fixes: 16a7dbc4f69006cc1c96ca2a2c6d3e3c51a2ff50 ("net/mlx5: make flow modify
action list thread safe")
Cc: xuemi...@nvidia.com
Cc: ma...@nvidia.com
Bugfix: The vlan in the bulletin does not contain a VLAN header, only the
VLAN ID, so only copy 2 byte, not 4. The target structure has padding
after the field, so copying 2 byte too many is effectively harmless.
There is no need to backport this patch.
Use RTE_PTR_ADD where copying arrays to the
Copying with the same src and dst address has no effect; removed to
avoid compiler warning with decorated rte_memcpy.
Fixes: e7c9971a857a ("event/dlb2: add probe-time hardware init")
Cc: timothy.mcdan...@intel.com
Signed-off-by: Morten Brørup
Acked-by: Stephen Hemminger
---
v7:
* No changes.
v6
> From: Morten Brørup
> Sent: Monday, 9 January 2023 13.28
>
> > From: David Marchand [mailto:david.march...@redhat.com]
> > Sent: Monday, 9 January 2023 12.22
> > attributes
> >
> > On Wed, Dec 28, 2022 at 4:10 PM Morten Brørup
> > wrote:
> > >
> > > Add "nonnull" function attribute to help the
Add nonnull function attribute to help the compiler detect a NULL
pointer being passed to a function not accepting NULL pointers as an
argument at build time.
Add access function attributes to tell the compiler how a function
accesses memory pointed to by its pointer arguments.
Add these attribut
Use RTE_PTR_ADD where copying to the offset of a field in a structure
holding multiple fields, to avoid compiler warnings with decorated
rte_memcpy.
Fixes: 16a7dbc4f69006cc1c96ca2a2c6d3e3c51a2ff50 ("net/mlx5: make flow modify
action list thread safe")
Cc: xuemi...@nvidia.com
Cc: ma...@nvidia.com
Bugfix: The vlan in the bulletin does not contain a VLAN header, only the
VLAN ID, so only copy 2 byte, not 4. The target structure has padding
after the field, so copying 2 byte too many is effectively harmless.
There is no need to backport this patch.
Use RTE_PTR_ADD where copying arrays to the
Copying with the same src and dst address has no effect; removed to
avoid compiler warning with decorated rte_memcpy.
Fixes: e7c9971a857a ("event/dlb2: add probe-time hardware init")
Cc: timothy.mcdan...@intel.com
Signed-off-by: Morten Brørup
Acked-by: Stephen Hemminger
---
v6:
* Add Fixes to p
On 12/15/2022 10:56 AM, lihuisong (C) wrote:
>
> 在 2022/12/14 17:55, humin (Q) 写道:
>>
>> 在 2022/12/14 14:13, Chengwen Feng 写道:
>>> This patchset adds device private dump for bonding PMD, and use
>>> rte_eth_dev_priv_dump API to implement testpmd show bonding command.
>>>
>>> Chengwen Feng (3):
>
Hi David,
> -Original Message-
> From: David Marchand
> Sent: Monday, January 16, 2023 7:19 PM
> To: Su, Simei
> Cc: Xing, Beilei ; Zhang, Yuying
> ; dev@dpdk.org; Zhang, Qi Z
> ; Yang, Qiming ;
> sta...@dpdk.org; Zhang, Helin
> Subject: Re: [PATCH] net/i40e: rework maximum frame size c
Hi Ferruh and Andrew,
This patch series optimizes some codes and bug.
Can you take a look at this patch series?
If there are no other questions, can it be merged?
Best,
Huisong
在 2022/12/19 15:06, Huisong Li 写道:
Some lib telemetry interfaces add the 'u32' and 'u64' data by the
rte_tel_data_add
1 - 100 of 120 matches
Mail list logo
