From: HongBo Zheng
In function 'stats_mem_init', pointer 'stats' should
be confirmed not null before memset it.
Fixes: af1ae8b6a32c ("graph: implement stats")
Cc: sta...@dpdk.org
Signed-off-by: HongBo Zheng
Signed-off-by: Min Hu (Connor)
---
lib/graph/graph_stats.c | 2 +-
1 file changed, 1
From: HongBo Zheng
Fix function 'stats_mem_populate' return without
free dynamic memory referenced by 'stats'.
Fixes: af1ae8b6a32c ("graph: implement stats")
Cc: sta...@dpdk.org
Signed-off-by: HongBo Zheng
Signed-off-by: Min Hu (Connor)
---
lib/graph/graph_stats.c | 5 -
1 file changed,
This patchset contains two bugfixes for graph.
HongBo Zheng (2):
graph: fix memory leak
graph: fix dereferencing null pointer
lib/graph/graph_stats.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
---
v2:
* fix double free.
--
2.7.4
在 2021/5/4 22:15, David Marchand 写道:
On Thu, Apr 22, 2021 at 1:52 PM Min Hu (Connor) wrote:
From: HongBo Zheng
Fix function 'stats_mem_populate' return without
free dynamic memory referenced by 'stats'.
Fixes: af1ae8b6a32c ("graph: implement stats")
Cc: sta...@dpdk.org
Signed-off-by: Ho
> Subject: [PATCH v13 00/10] app/testpmd: enable testpmd on Windows
>
> External email: Use caution opening links or attachments
>
>
> This patchset is to enable testpmd on windows. It mainly includes:
> - Enable building libraries on Windows that testpmd depends on
> - Add necessary macros requ
On Wed, May 5, 2021 at 11:52 PM Thomas Monjalon wrote:
>
> 05/05/2021 23:31, Owen Hilyard:
> > The Intel 10G and Intel 40G systems at the community lab had test jobs
> > begin to crash a few hours ago. This was the result of DTS crashing
> > severely enough that the job was unable to continue. A b
Hello Ferruh,
[:snip:]
> > btw, I can see 'MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL' still checked if it in
> > the first location of the items (items[0].type), in
> > 'flow_dv_validate()', 'mlx5_flow_dv.c'
> >
> https://git.dpdk.org/dpdk/tree/drivers/net/mlx5/mlx5_flow_dv.c?h=v21.0
> > 5-rc1#n6298
> > Can
Hi Juraj,
Thanks a lot for your kindly help :)
The reason why I failed to build KNI module from DPDK caused by the
cross-compiler which Linux kernel used.
After I changed to use generic Linaro cross-compiler, instead of our internal
ones, to build Linux kernel, then KNI module can pass build.
Hareware: CX5/CX6 DX + Intel(R) Xeon(R) Platinum 9242 CPU @
2.30GHz DPDK version: 19.11.8/20.11/21.05-rc1&2
testpmd with case:
testpmd> flow create 0 ingress pattern eth / ipv4 / udp dst is 53 / end
actions count / drop / end
testpmd> flow create 0 ingress pattern eth / ipv4 / udp src is 53 /
06/05/2021 04:06, Chengchang Tang:
>
> On 2021/5/6 5:37, Thomas Monjalon wrote:
> > 15/04/2021 09:12, Min Hu (Connor):
> >> From: Chengchang Tang
> >>
> >> Timer sample example assumes that the frequency of the timer is about
> >> 2Ghz to control the period of calling rte_timer_manage(). But this
On 2021/5/6 16:08, Thomas Monjalon wrote:
> 06/05/2021 04:06, Chengchang Tang:
>>
>> On 2021/5/6 5:37, Thomas Monjalon wrote:
>>> 15/04/2021 09:12, Min Hu (Connor):
From: Chengchang Tang
Timer sample example assumes that the frequency of the timer is about
2Ghz to control th
This code is not performance sensitive and can be switched to dynamic
allocations.
Signed-off-by: David Marchand
---
lib/telemetry/rte_telemetry.h | 2 +-
lib/telemetry/telemetry.c | 15 +--
2 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/lib/telemetry/rte_teleme
Fixes: ce9efbf5bb09 ("bus/fslmc: support dynamic logging")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/bus/fslmc/fslmc_logs.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/bus/fslmc/fslmc_logs.h b/drivers/bus/fslmc/fslmc_logs.h
index dd74cb7dcf..a1e14dd84e 100644
Fixes: 653242c3375a ("event/dpaa2: add self test")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/event/dpaa2/dpaa2_eventdev_logs.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/event/dpaa2/dpaa2_eventdev_logs.h
b/drivers/event/dpaa2/dpaa2_eventdev_logs.h
index 5da
On Thu, May 6, 2021 at 12:46 PM Min Hu (Connor) wrote:
>
> From: HongBo Zheng
>
> In function 'stats_mem_init', pointer 'stats' should
> be confirmed not null before memset it.
>
> Fixes: af1ae8b6a32c ("graph: implement stats")
> Cc: sta...@dpdk.org
>
> Signed-off-by: HongBo Zheng
> Signed-off-b
>From the documentation:
"The SoC configuration is a combination of implementer and CPU part number
configuration and SoC-specific configuration."
Align Qualcomm SoC configuration with the configuration of other server
SoCs (eMAG, Kunpeng 9x0): add a soc configuration to the existing
implementer
From: Chengchang Tang
Timer sample example assumes that the frequency of the timer is about
2Ghz to control the period of calling rte_timer_manage(). But this
assumption is easy to fail. For example. the frequency of tsc on ARM64
is much less than 2Ghz.
This patch uses the frequency of the curre
On 05/05/2021 15:30, David Marchand wrote:
> Hook check-symbol-maps.sh in the symbol check when in developer mode to
> help developers catch issues before submitting their changes.
>
> Signed-off-by: David Marchand
> ---
> Changes since v1:
> - now that we have the developer mode, added this c
From: Kamil Vojanec
> This patch fixes a bug where firmware version was not copied from
> ibv_device_attr structure into mlx5_dev_attr structure, resulting in inability
> to read firmware version.
>
> Signed-off-by: Kamil Vojanec
Acked-by: Matan Azrad
> ---
> drivers/net/mlx5/linux/mlx5_o
After looking at the control thread API use in recent changes, I noticed
that some thread resources are not properly released.
This series fixes two net drivers.
Additional notes:
- I noticed that event/dlb2 never kills/terminates its service thread.
It means unplug of this device (if supported)
A terminated pthread should be joined or detached so that its associated
resources are released.
The "ark-delay-pg" thread is just used to delay some task but it is never
joined by the thread that created it.
The easiest solution is to detach the new thread.
Fixes: 727b3fe292bc ("net/ark: integra
A terminated pthread should be joined or detached so that its associated
resources are released.
The "ice-reset-" threads are used to service some reset task in the
background, but they are never joined by the thread that created them.
The easiest solution is to detach new threads.
Fixes: 3b3757b
Tunnel offload API requires application to query PMD for specific flow
items and actions. Application uses these PMD specific elements to
build flow rules according to the tunnel offload model.
The model does not restrict private elements location in a flow rule,
but the current MLX5 PMD implementa
This is reported by our internal covscan:
1. dpdk-20.11/lib/librte_eal/common/eal_common_options.c:508: alloc_fn:
Storage is returned from allocation function "dlopen".
6. dpdk-20.11/lib/librte_eal/common/eal_common_options.c:508:
leaked_storage: Failing to save or free storage allocated by
"dlope
This is reported by our internal covscan:
1. dpdk-20.11/drivers/net/ice/base/ice_switch.c:4214: sign_extension:
Suspicious implicit sign extension: "s_rule_size" with type "u16" (16
bits, unsigned) is promoted in "num_unicast * s_rule_size" to type "int"
(32 bits, signed), then sign-extended to ty
> -Original Message-
> From: David Marchand
> Sent: Thursday, May 6, 2021 17:45
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Yang, Qiming ; Zhang, Qi Z
> ; Wang,
> Haiyue
> Subject: [PATCH 2/2] net/ice: fix leak on thread termination
>
> A terminated pthread should be joined or detached so
On Thu, May 06, 2021 at 12:06:37PM +0200, David Marchand wrote:
> This is reported by our internal covscan:
>
> 1. dpdk-20.11/lib/librte_eal/common/eal_common_options.c:508: alloc_fn:
> Storage is returned from allocation function "dlopen".
> 6. dpdk-20.11/lib/librte_eal/common/eal_common_options.
Hi, Kang
There are have some questions to clarify:
- what Is packet packet rate (in packet-per-second)?
* what Is packet size?
* do you use the switchdev configuration (E-Switch)?
* could you try create all flows in group 1 (and have the first flow in
group 0 forwarding all the traf
Hi David,
>-Original Message-
>From: David Marchand
>Sent: Thursday 6 May 2021 09:28
>To: dev@dpdk.org
>Cc: Power, Ciara
>Subject: [PATCH] telemetry: remove static limit on callbacks count
>
>This code is not performance sensitive and can be switched to dynamic
>allocations.
>
>Signed-of
> From: dev On Behalf Of Ferruh Yigit
> Sent: Wednesday, May 5, 2021 8:09 PM
>
> On 5/5/2021 1:21 PM, Michał Krawczyk wrote:
> > śr., 5 maj 2021 o 13:45 Ferruh Yigit napisał(a):
> >>
> >> On 4/1/2021 3:30 PM, Ferruh Yigit wrote:
> >>> On 3/31/2021 10:52 AM, Qi Zhang wrote:
> PMDs use RTE_LI
When reading the /dev directory as part of the bus scan for DSA devices,
the directory handle from opendir was not freed on function return,
leading to a resource leak.
Coverity issue: 370588
Fixes: b7aaf417f936 ("raw/ioat: add bus driver for device scanning
automatically")
Signed-off-by: Bruce
Hi, Feifei
Sorry, I do not follow why we should get rid of the last (after dev_gen update)
wmb.
We've rebuilt the global cache, we should notify other agents it's happened and
they should flush local caches. So, dev_gen change should be made visible
to other agents to trigger this activity and th
Hi, Xuemig
This patch looks like a fix - could you, please add the "Fixes:" tag and modify
the headline?
With best regards,
Slava
> -Original Message-
> From: Xueming Li
> Sent: Thursday, April 22, 2021 10:25
> Cc: dev@dpdk.org; Xueming(Steven) Li ; Matan
> Azrad ; Shahaf Shuler ; Slav
https://bugs.dpdk.org/show_bug.cgi?id=697
Bug ID: 697
Summary: build failure in event/cnxk when cross-compiling with
gcc 7.1.1
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNC
rte_thash_adjust_tuple() uses random to generate a new subtuple if
fn() callback reports about collision. In some cases random changes
the subtuple in a way that after complementary bits are applied the
original tuple is obtained. This patch replaces random with subtuple
increment.
Fixes: 28ebff11
Release status meeting minutes {Date}
=
:Date: 6 May 2021
:toc:
.Agenda:
* Release Dates
* -rc2 status
* Subtrees
* LTS
* Defects
* Opens
.Participants:
* Arm
* Broadcom
* Debian/Microsoft
* Intel
* Marvell
* Nvidia
* Red Hat
Release Dates
-
* `v
>On Wed, May 5, 2021 at 6:30 PM Tyler Retzlaff
> wrote:
>>
>> On Fri, Mar 12, 2021 at 09:07:22AM +0100, David Marchand wrote:
>> > On Thu, Mar 11, 2021 at 10:08 PM Tyler Retzlaff
>> > wrote:
>> > >
>> > > Avoid expanding v and mul parameters multiple times in the
>macro. based
>> > > on usage of t
Acked-by: Hemant Agrawal
Acked-by: Hemant Agrawal
This patch adds more description for hns3 PMD document, that is:
'Sample Application Notes', 'Statistics','Performance tuning'.
Signed-off-by: Min Hu (Connor)
---
doc/guides/nics/hns3.rst | 144 +--
1 file changed, 140 insertions(+), 4 deletions(-)
di
> >>> 21/04/2021 11:11, Conor Walsh:
> + The following will include a snippet from the skeleton sample
> app::
> +
> + .. literalinclude:: ../../../examples/skeleton/basicfwd.c
> +:language: c
> +:start-after: Display the port
Hi,
this version updates the driver to version 2.3.0, which fixes multiple
bugs, contains part of the work on making the ENA PMD fully MP aware, and
also updates HAL to the latest version.
More detailed list of changes:
* memcpy mapping to the dpdk-optimized version.
* ena_com (HAL) update to
From: Igor Chauskin
memcpy is now mapped to rte_memcpy macro on x86 architectures.
Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
Cc: sta...@dpdk.org
Signed-off-by: Igor Chauskin
Reviewed-by: Michal Krawczyk
Reviewed-by: Artur Rojek
---
v2:
* Fix nested declaration of the rte_
Instead of using 'queue' for struct ena_com_admin_queue and 'dev' for
struct ena_com_dev variables, use more descriptive 'admin_queue' and
'ena_dev'.
This also unifies the names of variables of the type struct ena_com_dev
in the driver.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Some platforms may make use of the device argument to make the logs more
verbose and specific for the appropriate device.
As it's not used by the ENA DPDK PMD for the logging, the type is just
defined, but never used.
It may be reconsidered to change this in the future by adding port ID
to the me
List of changes:
* Comment style was adjusted for the functions
* The keys_num at "struct ena_admin_feature_rss_flow_hash_control" was
renamed to the key_parts to better describe it's meaning
* The RSS indirection table was called "REDIRECTION" -> changed to
INDIRECTION
* Change AEN
To silence error messages from the static code analysis, make the type
conversions explicit where they're intended.
Also fix the type for the DMA width value.
Fixes: 99ecfbf845b3 ("ena: import communication layer")
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzal
Although the ENA DPDK PMD doesn't have to perform any actions for
destroying the wait event, some other platforms have to.
The macro "ENA_WAIT_EVENT_DESTROY" was renamed to
"ENA_WAIT_EVENTS_DESTROY" and also whole implementation responsible for
that was moved to a separate function for better read
The RSS indirection table shouldn't be included as a part of the
device features context.
If the driver has to acquire it, it can be done using the separate API
whenever the RSS configuration is needed.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Amit Bernstein
---
This feature wasn't used by any of the drivers. Because of that, it was
removed.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Shay Agroskin
---
drivers/net/ena/base/ena_defs/ena_admin_defs.h | 13 +
1 file changed, 1 insertion(+), 12 deletions(-)
diff --g
The current ena_com version was generated on 18.09.2020.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Amit Bernstein
---
drivers/net/ena/base/ena_defs/ena_gen_info.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ena/base/ena_defs/
As in the v20.11 rte_prefetch0_write API was added, it should be used
in the platform file for the definition of the macro prefetchw, instead
of using simply prefetch0.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Amit Bernstein
---
drivers/net/ena/base/ena_plat_dpdk.
From: Amit Bernstein
1. As memzone uses unique names, changed alloc coherent macro to use
64 bit size atomic variable to increase the memzone name space
2. "handle" param name change to be consistent with other macros
3. Variable definition displacement
4. Backslash alignment to column 80
Sig
From: Igor Chauskin
The code incorrectly checked the return value of comparison when parsing
the argument key name. The return value of strcmp should be compared
to 0 to identify a match.
Fixes: 8a7a73f26cc9 ("net/ena: support large LLQ headers")
Cc: sta...@dpdk.org
Signed-off-by: Igor Chauskin
As the documentation of rte_kvargs_parse() states, the valid_keys
argument must be NULL terminated. Lack of this feature may cause
segmentation fault if the passed devarg will be different then the
supported value.
Fixes: 8a7a73f26cc9 ("net/ena: support large LLQ headers")
Cc: sta...@dpdk.org
Sig
To make it possible to the app to determine if the hash was calculated
for the packet or not, the PKT_RX_RSS_HASH should be set in the mbuf's
ol_flags.
As the PMD wasn't setting that, the application couldn't check if there
is a hash in a proper way.
The hash is valid only if it's UDP or TCP and
From: Stanislaw Kardach
swap*_*_le() functions are not used anywhere and besides there are rte
alternatives already present.
Fixes: 1173fca25af9 ("ena: add polling-mode driver")
Signed-off-by: Stanislaw Kardach
Reviewed-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Shay Agroski
From: Stanislaw Kardach
pthread_cond_timedwait() may spuriously wakeup according to POSIX.
Therefore it is required to check whether predicate is actually true
before finishing the waiting loop.
Signed-off-by: Stanislaw Kardach
Reviewed-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-
From: Stanislaw Kardach
Introduce a memory area for ENA driver shared between all the processes
of a same prefix (memzone backed).
Move the memzone allocation counter for ENA_MEM_ALLOC_COHERENT there so
that all processes may utilize it.
Signed-off-by: Stanislaw Kardach
Reviewed-by: Michal Kraw
From: Stanislaw Kardach
For dev_ops not supported in SMP, either return -EPERM or return without
doing anything. In both cases log a warning.
Signed-off-by: Stanislaw Kardach
Reviewed-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Shay Agroskin
---
drivers/net/ena/ena_ethdev.c
From: Stanislaw Kardach
rte_pci_device and rte_eth_dev are process-local structures. Therefore
ena_adapter::pdev and ena_adapter::rte_dev cannot be used universally.
Switch this to extracting those structures via rte_eth_devices indexing
and remove pdev since it's not used outside of init.
Signe
This version update contains:
* memcpy mapping to the dpdk-optimized version.
* ena_com (HAL) update to the latest version.
* Bug fixes for the large LLQ headers and devargs parsing.
* Mbuf RSS hash presence indication.
* Bug fix for the default ring size.
* Various fixes for SMP mode (
From: Stanislaw Kardach
Make sure the same random generated RSS key is available to all ENA PMD
instances in all processes.
Signed-off-by: Stanislaw Kardach
Reviewed-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Shay Agroskin
---
drivers/net/ena/ena_ethdev.c | 16 +
From: Stanislaw Kardach
Remove invalid ring size alignment logic and add default rx and tx port
ring sizes to the device info spec.
The logic in lines 1297 and 1371 is invalid. The
RTE_ETH_DEV_FALLBACK_RX_RINGSIZE (and the TX counterpart) is a value
that rte_eth_rx_queue_setup() will set if
dev_
If after a bus scan, there are no devices using a particular bus, then
that bus should not be taken into account when deciding whether DPDK
should be run in VA or PA addressing mode. This becomes an issue when
the DSA bus driver code is used on a system without an IOMMU. The PCI
bus correctly repor
Testing OVS build against 21.05-rc2 revealed some issues.
Bits were also missing on OVS side, so for people interested, a
rebased dpdk-latest OVS branch is available at:
https://github.com/david-marchand/ovs/commits/dpdk-latest
--
David Marchand
David Marchand (2):
net: add endianness annotat
Spotted by sparse in OVS build:
/home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_flow.h:789:27:
error: incorrect type in initializer (different base types)
/home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_flow.h:789:27:
expected unsigned short [usertype] ether_type
/home/runner/work/ovs/ov
Spotted by sparse in OVS build:
../../lib/netdev-dpdk.c: note: in included file (through
/home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_ip.h,
/home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_flow.h, ...):
../../include/sparse/arpa/inet.h:22:2: error: "Must include
before for FreeBSD sup
On 06-May-21 4:09 PM, Bruce Richardson wrote:
If after a bus scan, there are no devices using a particular bus, then
that bus should not be taken into account when deciding whether DPDK
should be run in VA or PA addressing mode. This becomes an issue when
the DSA bus driver code is used on a syst
On 06-May-21 4:09 PM, Bruce Richardson wrote:
If after a bus scan, there are no devices using a particular bus, then
that bus should not be taken into account when deciding whether DPDK
should be run in VA or PA addressing mode. This becomes an issue when
the DSA bus driver code is used on a syst
> -Original Message-
> From: Burakov, Anatoly
> Sent: Thursday, May 6, 2021 4:17 PM
> To: Richardson, Bruce ; dev@dpdk.org
> Cc: Van Haaren, Harry
> Subject: Re: [PATCH] raw/ioat: fix bus requiring virtual addressing when no
> devs
>
> On 06-May-21 4:09 PM, Bruce Richardson wrote:
> > I
On Thu, May 06, 2021 at 04:27:03PM +0100, Burakov, Anatoly wrote:
> On 06-May-21 4:09 PM, Bruce Richardson wrote:
> > If after a bus scan, there are no devices using a particular bus, then
> > that bus should not be taken into account when deciding whether DPDK
> > should be run in VA or PA address
Minutes of Technical Board Meeting, 2021-04-07
Members Attending
-
-Bruce
-Ferruh
-Hemant
-Honnappa
-Jerin
-Konstantin
-Maxime
-Olivier
-Stephen
-Thomas
NOTE: The technical board meetings every second Wednesday at
https://meet.jit.si/DPDK at 3 pm UTC.
Meetings are public, and DP
Hi all,
dpdk-next-qos and dpdk-next-pipeline remotes have been removed.
dpdk-next-virtio and dpdk-next-crypto remotes have been switched to
track main and for-main branches respectively.
Thanks,
Brandon
On Thu, May 6, 2021 at 3:32 AM David Marchand wrote:
>
> On Wed, May 5, 2021 at 11:52 PM Tho
Currently the documentation describes how to add code snippets to the
docs using code blocks. This can be problematic as the code snippets
in the docs may fall out of sync with the actual code it is referencing
within DPDK. This patch adds instructions to the contribution guide
about how to include
From: Pavan Nikhilesh
The last lcore declared in the list is also a valid lcore in the list.
Fixes: 32d7dbf269be ("app/eventdev: fix overflow in lcore list parsing")
Cc: sta...@dpdk.org
Signed-off-by: Pavan Nikhilesh
---
app/test-eventdev/parser.c | 2 +-
1 file changed, 1 insertion(+), 1 del
2021-05-06 17:14 (UTC+0200), David Marchand:
> Spotted by sparse in OVS build:
> ../../lib/netdev-dpdk.c: note: in included file (through
> /home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_ip.h,
> /home/runner/work/ovs/ovs/dpdk-dir/build/include/rte_flow.h, ...):
> ../../include/sparse/arpa/ine
> -Original Message-
> From: Anatoly Burakov
> Sent: Friday, April 23, 2021 7:03 PM
> To: dev@dpdk.org
> Cc: step...@networkplumber.org; Richael Zhuang
> ; reshma.pat...@intel.com;
> david.h...@intel.com
> Subject: [21.08 PATCH v4 2/2] power: refactor pstate and acpi code
>
> Currently
Hi, Slava
Thanks very much for your reply.
> -邮件原件-
> 发件人: Slava Ovsiienko
> 发送时间: 2021年5月6日 19:22
> 收件人: Feifei Wang ; Matan Azrad
> ; Shahaf Shuler
> 抄送: dev@dpdk.org; nd ; sta...@dpdk.org; Ruifeng Wang
> ; nd
> 主题: RE: [PATCH v1 3/4] net/mlx5: fix rebuild bug for Memory Region cache
79 matches
Mail list logo