On 2025/2/6 19:40, Bruce Richardson wrote:
> On Fri, Jan 24, 2025 at 03:18:11PM +0800, fengchengwen wrote:
>> The new impl don't support re-test, how about add a wrap:
>> 1. rename test_multi_alloc_statistics with do_test_multi_alloc_statistics,
>> and make it take socket as parameter
>> 2. create
The current net CRC API is not thread-safe, this patch
solves this by adding another, thread-safe API functions.
This API is also safe to use across multiple processes,
yet with limitations on max-simd-bitwidth, which will be checked only by
the process that created the CRC context; all other proce
On 2025/1/25 1:34, Stephen Hemminger wrote:
> On Fri, 24 Jan 2025 17:59:57 +0800
> Dengdui Huang wrote:
>
>> diff --git a/lib/mbuf/rte_mbuf.c b/lib/mbuf/rte_mbuf.c
>> index 559d5ad8a7..c828200ea1 100644
>> --- a/lib/mbuf/rte_mbuf.c
>> +++ b/lib/mbuf/rte_mbuf.c
>> @@ -771,7 +771,7 @@ const char
On 2025/1/24 22:34, Morten Brørup wrote:
>> From: Dengdui Huang [mailto:huangdeng...@huawei.com]
>> Sent: Friday, 24 January 2025 11.00
>>
>> After discussion[1], the drivers do not include the CRC in the packet
>> length calculation. This will cause users to be confused about whether
>> the mbuf
The RTL8168 series are Realtek 1G network cards, but the RTL8168KB is
significantly different from other 1G network cards in the Linux kernel
driver, so it is added separately.
Signed-off-by: Howard Wang
---
doc/guides/nics/r8169.rst | 5 +-
drivers/net/r8169/base/rtl8125a.
Howard Wang (2):
net/r8169: replace rte_smp_rmb with atomic read
net/r8169: add support for RTL8168KB
doc/guides/nics/r8169.rst | 5 +-
drivers/net/r8169/base/rtl8125a.c | 4 +-
.../r8169/base/{rtl8125a_mcu.h => rtl8125a.h} | 8 +-
drivers/net/r8169/base/
rte_smp_rmb is deprecated and it is too heavy.
Signed-off-by: Howard Wang
---
drivers/net/r8169/r8169_rxtx.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/r8169/r8169_rxtx.c b/drivers/net/r8169/r8169_rxtx.c
index a3b86300f0..57b97338d4 100644
--- a/drivers
The number of xstats may be large, after the hide zero parameter to
hide zero only non-zero values can be displayed.
So display xstats with hide zero:
dpdk-proc-info --proc-type=secondary -- --xstats
and without hide zero:
dpdk-proc-info --proc-type=secondary -- --xstats=hide_zero
Signed-
> On Feb 6, 2025, at 16:41, Maxime Coquelin wrote:
>
> External email: Use caution opening links or attachments
>
>
> With the recent rework of the FD manager to use epoll,
> an error message is emitted with Vhost-user at FD entry
> removal:
>
> ERR|VHOST_FDMAN: could not remove 102 fd from
> On Dec 20, 2024, at 22:58, Maxime Coquelin wrote:
>
> External email: Use caution opening links or attachments
>
>
> This patch adds missing 'client' devarg documentation and
> improve other devargs.
>
> Bugzilla ID: 1603
>
> Signed-off-by: Maxime Coquelin
> ---
> doc/guides/nics/vhost.r
On Fri, 22 Sep 2023 09:19:07 +0100
Bruce Richardson wrote:
> Following my talk at the recent DPDK Summit [1], here is an RFC patchset
> containing the prototypes I created which led to the talk. This
> patchset is simply to demonstrate:
>
> * what is currently possible with DPDK in terms of zer
On Sat, 23 Apr 2022 09:58:35 +0530
Srikanth Kaka wrote:
> This patchset requires FreeBSD VMBus kernel changes and
> HV_UIO driver. Both are currently under review at
> https://reviews.freebsd.org/D32184
>
> Changelog:
> v5: - renamed dir osi to unix
> - marked a newly added API as experiment
In the function __rte_graph_mcore_dispatch_sched_node_enqueue,
use a slower loop to search for the graph, modify the search logic
to record the result of the first search, and use this record for
subsequent searches to improve search speed.
Signed-off-by: Huichao Cai
---
devtools/libabigail.abig
On Tue, 4 Feb 2025 18:45:08 +0200
Tudor Cornea wrote:
> Currently, if we call rte_eth_dev_stop(), the sockets are closed.
> If we attempt to start the port again, socket related operations
> will not work correctly.
>
> This can be alleviated by closing the socket at the same place in
> which w
On Thu, 6 Feb 2025 02:07:43 -0800
Wei Hu wrote:
> In the 32bit rx path, it rings short doorbell after receiving
> one packet and alocating the new mbuf. This significantly
> impacets the rx performance. Fix this problem by ringing the
> short doorbell in batch.
>
> Fixes: eeb37809601b ("net/man
On Thu, 6 Feb 2025 21:46:45 +0100
Ariel Otilibili wrote:
>
> +static inline struct xdp_desc *
> +reserve_and_fill(struct pkt_tx_queue *txq, struct rte_mbuf *mbuf,
> + struct xsk_umem_info *umem, void **pkt_ptr)
> +{
> + struct xdp_desc *desc = NULL;
> + uint64_t addr, offs
Hi Maxime,
On Wednesday, February 05, 2025 22:18 CET, Maxime Coquelin
wrote:
> Hi Ariel,
>
>
> Not really :)
> Without your patch, ret was assigned by the pthread_mutex_init() return,
> so always 0. With your patch, this assignment is removed so ret will
> always be -1 for VDUSE devices.
>
>
Both legs of the loop share the same logic: the common parts are about
reserving and filling both address and length into the description.
This is moved into reserve_and_fill().
Bugzilla ID: 1440
Suggested-by: Maryam Tahhan
Signed-off-by: Ariel Otilibili
---
drivers/net/af_xdp/rte_eth_af_xdp.c
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, October 9, 2024 3:03 AM
> To: Kusztal, ArkadiuszX ; Marchand, David
>
> Cc: dev@dpdk.org; Ji, Kai ; Dooley, Brian
>
> Subject: Re: [PATCH v2 1/3] net: add thread-safe crc api
>
> On 10/8/2024 9:51 PM, Kusztal, ArkadiuszX wro
Hello,
The series addresses Bugzilla ID 1440 in two steps;
1. Fix use after free.
2. Refactor af_xdp_tx_zc().
Thank you,
---
v8
* fixed seg fault
(https://inbox.dpdk.org/dev/CAFdtZitaNGhC5Q10ATNa7xXX1JbuWob=yzrcwmq8ltz+qji...@mail.gmail.com/)
* addressed feedback from Maryam Tahhan
v7
(https:
tx_bytes is computed after both legs are tested. This might
produce a use after memory free.
The computation is now moved into each leg.
Bugzilla ID: 1440
Fixes: d8a210774e1d ("net/af_xdp: support unaligned umem chunks")
Signed-off-by: Ariel Otilibili
Acked-by: Stephen Hemminger
---
.mailmap
On Thu, Feb 6, 2025 at 2:33 AM Andre Muezerie
wrote:
>
> As per guidance technical board meeting 2024/04/17. This series
> removes the use of VLAs from code built for Windows for all 3
> toolchains. If there are additional opportunities to convert VLAs
> to regular C arrays please provide the deta
> -Original Message-
> From: Stephen Hemminger
> Sent: Monday, December 2, 2024 11:36 PM
> To: Kusztal, ArkadiuszX
> Cc: dev@dpdk.org; ferruh.yi...@amd.com; Ji, Kai ; Dooley,
> Brian
> Subject: Re: [PATCH v2 1/3] net: add thread-safe crc api
>
> On Tue, 1 Oct 2024 19:11:48 +0100
> A
The current net CRC API is not thread-safe, this patch
solves this by adding another, thread-safe API functions.
This API is also safe to use across multiple processes,
yet with limitations on max-simd-bitwidth, which will be checked only by
the process that created the CRC context; all other proce
Recheck-request: iol-intel-Performance
Triggering a retest due to testbed instability yesterday.
Recheck-request: iol-intel-Performance
Triggering a retest due to testbed instability yesterday.
Recheck-request: iol-intel-Performance
Triggering a retest due to testbed instability yesterday.
Recheck-request: iol-intel-Performance
Triggering a retest due to testbed instability yesterday.
On Wed, Feb 5, 2025 at 9:53 PM Huichao Cai wrote:
> In the function __rte_graph_mcore_dispatch_sched_node_enqueue,
> use a slower loop to search for the graph, modify the search logic
> to record th
On Wed, Feb 5, 2025 at 9:20 AM Ajit Khaparde wrote:
>
> Patchset with bug fixes for bnxt PMD.
> Also addresses various Coverity issues reported in the recent
> Coverity scan.
>
> Please apply.
Patchset applied to dpdk-next-net-brcm subtree. Thanks
>
> Ajit Khaparde (4):
> net/bnxt: disable TruF
Hi Maryam,
On Thu, Feb 6, 2025 at 3:09 AM Maryam Tahhan wrote:
>
>
> On Sat 1 Feb 2025, 10:03 Ariel Otilibili,
> wrote:
>
>> diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c
>> b/drivers/net/af_xdp/rte_eth_af_xdp.c
>> index 092bcb73aa0a..840a12dbf508 100644
>> --- a/drivers/net/af_xdp/rte_eth_a
Hi Maryam,
On Thu, Feb 6, 2025 at 2:09 AM Maryam Tahhan wrote:
>
>
> On Sat 1 Feb 2025, 10:03 Ariel Otilibili,
> wrote:
>
>> Both legs of the loop share the same logic: the common parts are about
>> reserving and filling both address and length into the description.
>>
>> This is moved into res
On Thu, Feb 06, 2025 at 04:08:23PM +, Anatoly Burakov wrote:
> This patchset is taken out of recent e1000/igc driver update [1].
>
> [1] https://inbox.dpdk.org/dev/cover.1738681725.git.anatoly.bura...@intel.com/
>
Thanks Anatoly. All the patches for e1000 and igc will be easier to work on
in
The original code had incorrect indentation, and the fix was applied to
follow the indentation, i.e. adding brackets making the indentation valid.
However, the actual issue was incorrect indentation and not missing braces,
so the fix was incorrect.
This fix restores the original logic and corrects
From: Barbara Skobiej
One of the bit shifts in MAC hash calculation triggers a static analysis
warning about a potential overflow. Fix the data type to avoid this.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Barbara Skobiej
Signed-off-by: Anatoly Burakov
--
From: Carolyn Wyborny
On 82575, driver is not supposed to check if managegement control is
enabled, and flush the Rx FIFO unconditionally.
Fixes: 4414059f ("net/e1000/base: remove duplicated codes")
Cc: sta...@dpdk.org
Signed-off-by: Carolyn Wyborny
Signed-off-by: Anatoly Burakov
---
dri
From: Pawel Malinowski
According to datasheet software ownership of SWSM.SWESMBI bit should not
exceed 100ms. Current implementation caused incorrect timeout counter
values, where each iteration equals 50us delay. Because of that driver was
allowed to wait for semaphore even for 1,5s. This might
From: Barbara Skobiej
Fix setting device reset status bit in e1000_reset_hw_82580() function
for 82580 by first reading the register value, and then setting the
device reset bit.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Barbara Skobiej
Signed-off-by: Anat
From: Przemyslaw Ciesielski
There is a static analysis warning due to wrong data types being used for
NVM read data shifts. Fix it via explicit type cast.
Fixes: 38db3f7f50bd ("e1000: update base driver")
Cc: sta...@dpdk.org
Signed-off-by: Przemyslaw Ciesielski
Signed-off-by: Anatoly Burakov
From: Dima Ruinskiy
Static analysis has detected a write that is not checked for errors,
leading to ignored error return value. Add a check.
Fixes: edcdb3c5f71b ("e1000/base: fix link flap on 82579")
Cc: sta...@dpdk.org
Signed-off-by: Dima Ruinskiy
Signed-off-by: Anatoly Burakov
---
drivers/
From: Przemyslaw Ciesielski
There is a static analysis warning due to wrong data types being used for
SW/FW semaphore masking. Fix it via explicit type cast.
Fixes: 5a32a257f957 ("e1000: more NICs in base driver")
Cc: sta...@dpdk.org
Signed-off-by: Przemyslaw Ciesielski
Signed-off-by: Anatoly
From: Jakub Buchocki
Static analysis has detected potential usage of uninitialized values
inside the array. Fix the warning by initializing array.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Jakub Buchocki
Signed-off-by: Anatoly Burakov
---
.mailmap
From: Aleksandr Loktionov
In e1000_hash_mc_addr_generic() the expression:
"mc_addr[4] >> 8 - bit_shift", right shifting "mc_addr[4]"
shift by more than 7 bits always yields zero, so hash becomes not so
different. Add initialization with bit_shift = 1, and add a loop condition
to ensure
From: Amir Avivi
Fix static analysis warning about comparison between types of
incompatible width, which might lead to an infinite loop due to overflow.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Amir Avivi
Signed-off-by: Anatoly Burakov
---
drivers/net/i
From: Przemyslaw Ciesielski
There is a static analysis warning due to wrong data types being used for
NVM read data shifts. Fix it via explicit type cast.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Przemyslaw Ciesielski
Signed-off-by: Anat
From: Pawel Malinowski
According to datasheet software ownership of SWSM.SWESMBI bit should not
exceed 100ms. Current implementation caused incorrect timeout counter
values, where each iteration equals 50us delay. Because of that driver was
allowed to wait for semaphore even for 1,5s. This might
From: Barbara Skobiej
One of the bit shifts in MAC hash calculation triggers a static analysis
warning about a potential overflow. Fix the data type to avoid this.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Barbara Skobiej
Signed-off-by: A
From: Aleksandr Loktionov
In e1000_hash_mc_addr_generic() the expression:
"mc_addr[4] >> 8 - bit_shift", right shifting "mc_addr[4]"
shift by more than 7 bits always yields zero, so hash becomes not so
different. Add initialization with bit_shift = 1, and add a loop condition
to ensure
From: Dima Ruinskiy
Static analysis has reported that when there is no get link status callback
function, the value set in the if condition is not used and gets
overwritten in the "out" section of the code. Fix by not seting the
variable.
Fixes: 8cb7c57d9b3c ("net/igc: support device initializat
On Wed, Feb 5, 2025 at 7:29 PM Bruce Richardson
wrote:
> diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
> index 260e4761bd..9e6a7d553a 100644
> --- a/app/test-pmd/testpmd.h
> +++ b/app/test-pmd/testpmd.h
> @@ -1292,10 +1292,6 @@ RTE_INIT(__##c) \
> testpmd_add_driver_commands
From: Amir Avivi
Fix static analysis warning about comparison between types of
incompatible width, which might lead to an infinite loop due to overflow.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Amir Avivi
Signed-off-by: Anatoly Burakov
From: Dima Ruinskiy
The LTR maximum value was incorrectly written using the scale from the
LTR minimum value. This would cause incorrect values to be sent, in cases
where the initial calculation lead to different min/max scales. Fix the
typo to correctly calculate the LTR maximum value.
Fixes: 8
From: Sasha Neftin
When writing to Shadow RAM, we set rev_val on success, but since the value
is already set to success initially, it is possible for none of the writes
to be successful, yet ret_val will still be set to success. Fix it by
resetting the ret_val to failure before every loop iterati
From: Sasha Neftin
i225 specification recommends minus 1 microsecond from a value
calculated for a LTR. Fix the calculation to match spec.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Sasha Neftin
Signed-off-by: Anatoly Burakov
---
drivers
From: Przemyslaw Ciesielski
Static analysis has found type mismatch between mask and register value.
Fix the bitwise operation type to avoid potential issues.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Przemyslaw Ciesielski
Signed-off-by:
From: Sasha Neftin
PHY specification for i225 requires 300 microsecond delay after power up
sequence, so increase the delay after power up to 300 microseconds.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Sasha Neftin
Signed-off-by: Anatoly
From: Dima Ruinskiy
When the driver fails to acquire HW semaphore, there is nothing that can be
done to address it, so just leave to avoid an infinite loop.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc: sta...@dpdk.org
Signed-off-by: Dima Ruinskiy
Signed-off-by: Anatoly Bu
From: Dima Ruinskiy
Currently, when writing GPY PHY registers, semaphor is acquired before
writing. However, if writing fails, semaphor is not released, causing
a deadlock down the line. Fix the issue by removing premature return.
Fixes: 8cb7c57d9b3c ("net/igc: support device initialization")
Cc
This patchset is taken out of recent e1000/igc driver update [1].
[1] https://inbox.dpdk.org/dev/cover.1738681725.git.anatoly.bura...@intel.com/
Aleksandr Loktionov (2):
net/igc/base: fix MAC addr hash bit shift
net/e1000/base: fix MAC addr hash bit shift
Amir Avivi (2):
net/igc/base: fix
The unit test adapter_pollq_instance_get requires three event queues,
but the test suite was only configuring a single queue. This patch
updates the test suite setup function to configure max available queues.
Fixes: a1793ee8aba0 ("eventdev/eth_rx: add adapter instance get API")
Cc: sta...@dpdk.or
> Add msg chan functions and the use to get
> hardware information or operate hardware.
>
> Signed-off-by: Hanxiao Li
> ---
Before sending the next version, please ensure all patches gets compiled
incrementally.
Please fix compilation.
[1/30] Compiling C object
drivers/libtmp_rte_common_zsda
On Thu, Feb 6, 2025 at 9:42 AM Maxime Coquelin
wrote:
>
> With the recent rework of the FD manager to use epoll,
> an error message is emitted with Vhost-user at FD entry
> removal:
>
> ERR|VHOST_FDMAN: could not remove 102 fd from 101 epfd: No such file or
> directory
>
> It occurs because the r
Reviewed-by: Pravin Pathak
> -Original Message-
> From: Richardson, Bruce
> Sent: Tuesday, January 21, 2025 12:12 PM
> To: dev@dpdk.org
> Cc: Pathak, Pravin ; Richardson, Bruce
> ; sta...@dpdk.org
> Subject: [PATCH] event/dlb2: fix event weight handling in SSE code path
>
> Commit 6e2e9
Hi Maxime,
> On 1/7/25 7:44 PM, Gowrishankar Muthukrishnan wrote:
> > Move vhost-vdpa backend implementation into common folder.
>
> If we decided to have a common base for Virtio devices, which I think is a
> good
> idea to avoid needless duplication, we should do a deeper refactoring by
> shar
On 1/7/25 7:44 PM, Gowrishankar Muthukrishnan wrote:
Add vhost backend to virtio_user crypto.
Signed-off-by: Gowrishankar Muthukrishnan
---
drivers/crypto/virtio/meson.build | 7 +
drivers/crypto/virtio/virtio_cryptodev.c | 57 +-
drivers/crypto/virtio/virtio_cryptode
Hi Brian,
> This patch introduces SM4 GCM algorithm support to the AESNI_MB PMD.
> SM4 GCM is available in the v2.0 release of Intel IPsec MB.
>
> Signed-off-by: Brian Dooley
> ---
> v2:
> Added aad to cpu job params
> Added ipsec mb version checks
> v3:
> Fix naming for patchw
> Subject: [PATCH 1/1] test/crypto: additional RSA tests for CNXK PMD
>
> Include additional RSA tests for CNXK PMD. These tests validates
> RSA operations using private key in exponent form.
>
> Signed-off-by: Gowrishankar Muthukrishnan
Applied to dpdk-next-crypto
Thanks.
> Return relevant error code when crypto session configure
> fails.
>
> Signed-off-by: Rajesh Mudimadugula
Acked-by: Akhil Goyal
Applied to dpdk-next-crypto
Thanks.
> -Original Message-
> From: Akhil Goyal
> Sent: Friday, January 24, 2025 11:53 PM
> To: dev@dpdk.org
> Cc: Akhil Goyal
> Subject: [PATCH] test/security: check MACSEC offload before configuration
>
> rte_ethdev_dev_configure need application to check the
> device info if the offload f
Hi,
From: Maayan Kashani
Sent: Tuesday, January 28, 2025 9:54 AM
To: dev@dpdk.org
Cc: Maayan Kashani; Dariusz Sosnowski; Raslan Darawsheh
Subject: [PATCH 0/3] Non template to HWS fixes
Few fixes for non template mode on top of HWS.
Maayan Kashani (3):
net/mlx5: fix limitation of actions per r
> MSVC issues the warning below:
>
> ../lib/cryptodev/rte_cryptodev.c(623): warning C4334: '<<':
> result of 32-bit shift implicitly converted to 64 bits
> (was 64-bit shift intended?)
>
> The code would be better off by using 64 bit numbers to begin with.
> That eliminates the need for a
On Fri, Jan 24, 2025 at 03:18:11PM +0800, fengchengwen wrote:
> The new impl don't support re-test, how about add a wrap:
> 1. rename test_multi_alloc_statistics with do_test_multi_alloc_statistics,
> and make it take socket as parameter
> 2. create a new function test_multi_alloc_statistics {
>
06/02/2025 01:08, Shani Peretz:
> When registering a new PCI device, the device->name field stored
> the user-provided string from devargs (e.g., "08:00.0" or ":08:00.0").
> This approach led to inconsistencies when registering new devices.
>
> This patch fix this issue by saving the parsed PC
On Wed, Feb 05, 2025 at 11:32:24AM -0800, Andre Muezerie wrote:
> This patch avoids warnings like the ones below emitted by MSVC:
>
> 1)
> ../drivers/net/ice/base/ice_flg_rd.c(71): warning C4334: '<<':
> result of 32-bit shift implicitly converted to 64 bits
> (was 64-bit shift intended?)
Change find_device and rte_cmp_dev_name to accept a struct
with pointer and size instead of a void* pointer.
Signed-off-by: Shani Peretz
---
app/test/test_devargs.c | 23 +++
app/test/test_vdev.c | 23 ++-
drivers/bus/a
Added tests to PCI and vdev bus that compare and find devices
in various forms of names under test_devargs.
The tests check the functionality of the rte_cmp_dev_name function by
calling it with different variations of names, like short and full,
full and full, etc.
Signed-off-by: Shani Peretz
---
DPDK supports multiple formats for specifying buses,
(such as ":08:00.0" and "08:00.0" for PCI).
This flexibility can lead to inconsistencies when using one
format while running testpmd, then attempts to use the other
format in a later command, resulting in a failure.
The issue arises from the
When registering a new PCI device, the device->name field stored
the user-provided string from devargs (e.g., "08:00.0" or ":08:00.0").
This approach led to inconsistencies when registering new devices.
This patch fix this issue by saving the parsed PCI in device->name,
so when a new PCI devic
In the 32bit rx path, it rings short doorbell after receiving
one packet and alocating the new mbuf. This significantly
impacets the rx performance. Fix this problem by ringing the
short doorbell in batch.
Fixes: eeb37809601b ("net/mana: use bulk mbuf allocation for Rx WQEs")
Cc: sta...@dpdk.org
On 2025/2/6 0:54, David Marchand wrote:
>> No, it won't probe twice.
>> I suppose that each PCI device will only be bound to either the VFIO
>> driver or a kernel driver. The drv_flags of the xsc_pmd PCI driver will
>> not preset with RTE_PCI_DRV_NEED_MAPPING. Therefore, in the
>> rte_pci_probe_one
Hi Gowrishankar,
On 1/7/25 7:44 PM, Gowrishankar Muthukrishnan wrote:
Move vhost-vdpa backend implementation into common folder.
If we decided to have a common base for Virtio devices, which I think is
a good idea to avoid needless duplication, we should do a deeper
refactoring by sharing all
Hi,
From: Minggang(Gavin) Li
Sent: Monday, December 23, 2024 12:10 PM
To: Matan Azrad; Slava Ovsiienko; Ori Kam; NBU-Contact-Thomas Monjalon
(EXTERNAL)
Cc: dev@dpdk.org; Raslan Darawsheh
Subject: [PATCH V1 0/7] port probe time optimization
This patch series introduced a feature that the time to
On 1/7/25 7:25 PM, Gowrishankar Muthukrishnan wrote:
Update virtio_crypto_config structure to include AKCIPHER algorithms,
as per VirtIO standard.
Signed-off-by: Gowrishankar Muthukrishnan
Acked-by: Akhil Goyal
---
v3:
- rebased on main.
lib/vhost/virtio_crypto.h | 2 +-
1 file change
With the recent rework of the FD manager to use epoll,
an error message is emitted with Vhost-user at FD entry
removal:
ERR|VHOST_FDMAN: could not remove 102 fd from 101 epfd: No such file or
directory
It occurs because the read callback closes the file
descriptor before it is removed from the F
> On Jan 31, 2025, at 21:09, Maxime Coquelin wrote:
>
> External email: Use caution opening links or attachments
>
>
> This patch fixes a regression in vhost_driver_register()
> causing VDUSE devices registration to fail systematically
> because the return value was initialized to -1 and not
84 matches
Mail list logo
