On 12/17/2024 9:59 AM, David Marchand wrote:
Add an assert to double check the passed handle is not NULL, as it
points at an initialisation/allocation issue prior to accessing this
lcore variable.
Signed-off-by: David Marchand
---
lib/eal/include/rte_lcore_var.h | 2 ++
1 file changed, 2 ins
On 12/17/2024 9:59 AM, David Marchand wrote:
The lcore variable in this code unit is only used through
rte_power_monitor*() public symbols.
Defer the unconditional lcore variable allocation in those symbols.
Fixes: 18b5049ab4fe ("eal/x86: keep power intrinsics state in lcore variable")
Cc: sta.
On 12/17/2024 9:59 AM, David Marchand wrote:
The lcore variable in this code unit is only used through
rte_power_ethdev_pmgmt_queue_*() public symbols.
Defer the unconditional lcore variable allocation in those symbols.
Fixes: 130643319579 ("power: keep per-lcore state in lcore variable")
Cc: s
On 12/17/2024 9:59 AM, David Marchand wrote:
Now that the per-lcore state was moved into a lcore variable,
there is no reason to align a per-lcore state on a cache line to avoid
false sharing.
Remove this alignment and save a few bytes.
Fixes: 130643319579 ("power: keep per-lcore state in lcore
On 12/10/2024 10:41 AM, Mattias Rönnblom wrote:
Maybe the DAG is available on the build (meson) level, and thus the code
can be generated out of that?
There is in fact a patchset that produces just that kind of graph:
https://patches.dpdk.org/project/dpdk/list/?series=34055
It's currentl
On 12/5/2024 6:57 PM, David Marchand wrote:
As I had reported in rc2, the lcore variables allocation have a
noticeable impact on applications consuming DPDK, even when such
applications does not use DPDK, or use features associated to
some lcore variables.
While the amount has been reduced in a
On 12/5/2024 6:57 PM, David Marchand wrote:
The RNG is documented as being seeded as part of EAL init.
/**
* Seed the pseudo-random generator.
*
* The generator is automatically seeded by the EAL init with a timer
* value. It may need to be re-seeded by the user with a real random
* va
On 12/12/2024 7:02 PM, Stephen Hemminger wrote:
On Thu, 12 Dec 2024 16:19:03 +
Anatoly Burakov wrote:
Currently, the architecture of the base driver is such that it uses
function pointers internally. These are not guaranteed to be valid in
secondary processes, which can lead to crashes. Th
On 12/2/2024 10:35 AM, Anatoly Burakov wrote:
Support for `--noiommu-mode` flag was added, but documentation for it was
not. Add documentation for the flag.
Signed-off-by: Anatoly Burakov
---
This update is also included in my devbind rewrite:
https://patches.dpdk.org/project/dpdk/list/?seri
On 12/2/2024 10:31 AM, Anatoly Burakov wrote:
Currently, when binding a device to VFIO, the UID/GID for the device will
always stay as system default (`root`). Yet, when running DPDK as non-root
user, one has to change the UID/GID of the device to match the user's
UID/GID to use the device.
This
On 12/4/2024 10:45 AM, Anatoly Burakov wrote:
It has been suggested [1] that a major cleanup/rewrite of devbind would be
beneficial in terms of long term maintainability of the code. I was in a
coding mood over the weekend, and so I've went ahead and rewritten devbind.
Note that this is one gian
On 12/3/2024 11:16 PM, Stephen Hemminger wrote:
On Tue, 3 Dec 2024 11:25:00 +
Anatoly Burakov wrote:
Devbind is one of the oldest tools in DPDK, and is written in a way that
uses a lot of string matching, no type safety, lots of global variables,
and has a few inconsistencies in the way i
On 12/3/2024 6:07 PM, Stephen Hemminger wrote:
On Tue, 3 Dec 2024 11:25:00 +
Anatoly Burakov wrote:
+
+def check_installed(program: str, package: str) -> None:
+"""Check if a program is installed."""
+if subprocess.call(
+["which", program], stdout=subprocess.DEVNULL,
std
On 12/2/2024 6:01 PM, Stephen Hemminger wrote:
On Mon, 2 Dec 2024 15:09:34 +
Anatoly Burakov wrote:
+# For kernels < 3.15 when binding devices to a generic driver (i.e. one
that doesn't have a PCI
+# ID table) using new_id, some devices that are not bound to any other
driver cou
On 12/2/2024 5:14 PM, Bruce Richardson wrote:
On Mon, Dec 02, 2024 at 03:09:33PM +, Anatoly Burakov wrote:
It has been suggested [1] that a major cleanup/rewrite of devbind would be
beneficial in terms of long term maintainability of the code. I was in a
coding mood over the weekend, and so
On 12/2/2024 10:31 AM, Anatoly Burakov wrote:
Currently, when binding a device to VFIO, the UID/GID for the device will
always stay as system default (`root`). Yet, when running DPDK as non-root
user, one has to change the UID/GID of the device to match the user's
UID/GID to use the device.
This
On 11/29/2024 10:12 AM, Burakov, Anatoly wrote:
On 11/28/2024 6:20 PM, Stephen Hemminger wrote:
On Thu, 28 Nov 2024 16:08:55 +
Anatoly Burakov wrote:
+ # occasionally, system may report NUMA support but lspci will
not, so we
+ # want to go through all devices and see if any of them
On 11/28/2024 6:20 PM, Stephen Hemminger wrote:
On Thu, 28 Nov 2024 16:08:55 +
Anatoly Burakov wrote:
+# occasionally, system may report NUMA support but lspci will not, so we
+# want to go through all devices and see if any of them do not have
NUMANode
+# property - this will
On 11/27/2024 3:56 PM, Anatoly Burakov wrote:
From: Bruce Richardson
Remove any unnecessary dependencies from the driver dependency lists.
This will give each driver a near-minimum set of required dependencies.
Signed-off-by: Bruce Richardson
Reviewed-by: Rosen Xu
---
diff --git a/driver
On 11/26/2024 5:15 PM, Robin Jarry wrote:
Hi Anatoly,
Anatoly Burakov, Nov 26, 2024 at 16:02:
Currently, when binding a device to VFIO, the UID/GID for the device will
always stay as system default (`root`). Yet, when running DPDK as non-
root
user, one has to change the UID/GID of the device
On 11/26/2024 3:39 PM, Anatoly Burakov wrote:
As part of the meson build, we can record the dependencies for each
component as we process it, logging them to a file. This file can be
used as input to a number of other scripts and tools, for example, to
graph the dependencies, or to allow higher-l
On 09/11/2024 02:48, Andre Muezerie wrote:
From: Konstantin Ananyev
1) ../drivers/net/ixgbe/ixgbe_ethdev.c:3556:46: warning:
variable length array used [-Wvla]
2) ../drivers/net/ixgbe/ixgbe_ethdev.c:3739:23: warning:
variable length array used [-Wvla]
3) ../drivers/net/ixgbe/ixgbe_rxt
On 09/11/2024 02:48, Andre Muezerie wrote:
From: Konstantin Ananyev
../drivers/net/ice/ice_rxtx.c:1871:29: warning:
variable length array used [-Wvla]
Here VLA is used as a temp array for mbufs that will be used as a split
RX data buffers.
As at any given time only one thread can do RX fr
On 10/1/2024 5:25 PM, Stephen Hemminger wrote:
On Tue, 1 Oct 2024 14:25:46 +0200
David Marchand wrote:
On Tue, Oct 1, 2024 at 2:21 PM Burakov, Anatoly
wrote:
+
+/**
+ * Frees the memory space pointed to by the provided pointer.
+ *
+ * This pointer must have been returned by a previous call
On 9/30/2024 8:43 PM, Stephen Hemminger wrote:
Using the freed value for tracing is not a good idea.
Although it is harmless for tracing, it will cause analyzers to flag
this as unsafe.
Signed-off-by: Stephen Hemminger
Acked-by: Chengwen Feng
---
lib/eal/common/eal_common_memzone.c | 3 ++-
On 9/30/2024 8:44 PM, Stephen Hemminger wrote:
The allocation functions take a alignment argument that
can be useful to hint the compiler optimizer.
This is supported by Gcc and Clang but only useful with
Gcc because Clang gives warning if alignment is 0.
Recent versions of GCC have a malloc at
On 9/12/2024 1:50 PM, Varghese, Vipin wrote:
[Public]
Snipped
Based on the discussions we agreed on sharing version-2 FRC for
extending API as `rte_get_next_lcore_extnd` with extra argument as
`flags`.
As per my ideation, for the API ` rte_get_next_sibling_core`, the above
On 9/9/2024 10:36 AM, Anatoly Burakov wrote:
When last driver update was performed, README was not updated with data on
latest shared code package generation date. Update README to reflect the
date of last shared code package generation.
Signed-off-by: Anatoly Burakov
---
drivers/net/ixgbe/ba
On 9/6/2024 4:51 PM, Bruce Richardson wrote:
On Wed, Sep 04, 2024 at 04:08:29PM +0100, Anatoly Burakov wrote:
Allow specifying dependencies as either mandatory or optional. This does
not change anything about the build, but it is useful for tooling to know
if a dependency is required or not.
On 9/6/2024 3:07 PM, Bruce Richardson wrote:
On Fri, Sep 06, 2024 at 03:02:53PM +0200, Morten Brørup wrote:
From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
Sent: Friday, 6 September 2024 14.46
On 9/6/2024 2:37 PM, Morten Brørup wrote:
From: Anatoly Burakov [mailto:anatoly.bura
On 9/6/2024 2:37 PM, Morten Brørup wrote:
From: Anatoly Burakov [mailto:anatoly.bura...@intel.com]
Sent: Friday, 6 September 2024 13.47
To: dev@dpdk.org
Subject: [RFC PATCH v1 0/5] Adjust wording for NUMA vs. socket ID in DPDK
While initially, DPDK has used the term "socket ID" to refer to physi
On 9/6/2024 10:28 AM, Morten Brørup wrote:
From: fengchengwen [mailto:fengcheng...@huawei.com]
Sent: Friday, 6 September 2024 09.41
On 2024/9/5 15:29, David Marchand wrote:
On Wed, Sep 4, 2024 at 5:17 PM Anatoly Burakov
wrote:
Enter this script. It relies on Meson's introspection capabilitie
Yes, this does help clarify things a lot as to why current NUMA support
would be insufficient to express what you are describing.
However, in that case I would echo sentiment others have expressed
already as this kind of deep sysfs parsing doesn't seem like it would be
in scope for EAL, it sou
On 9/5/2024 3:05 PM, Ferruh Yigit wrote:
On 9/3/2024 9:50 AM, Burakov, Anatoly wrote:
On 9/2/2024 5:33 PM, Varghese, Vipin wrote:
Hi Ferruh,
I feel like there's a disconnect between my understanding of the problem
space, and yours, so I'm going to ask a very basic question:
On 9/5/2024 9:29 AM, David Marchand wrote:
On Wed, Sep 4, 2024 at 5:17 PM Anatoly Burakov
wrote:
Currently, the only way to set up a build directory for DPDK development
is through running Meson directly. This has a number of drawbacks.
For one, the default configuration is very "fat", meanin
On 9/2/2024 3:57 PM, Anatoly Burakov wrote:
Currently, when binding a device to VFIO, the UID/GID for the device will
always stay as system default (`root`). Yet, when running DPDK as non-root
user, one has to change the UID/GID of the device to match the user's
UID/GID to use the device.
This p
On 9/2/2024 5:33 PM, Varghese, Vipin wrote:
I recently looked into how Intel's Sub-NUMA Clustering would work
within
DPDK, and found that I actually didn't have to do anything, because the
SNC "clusters" present themselves as NUMA nodes, which DPDK already
supports natively.
yes, this is c
On 8/2/2024 2:44 PM, Bruce Richardson wrote:
As meson processes our DPDK source tree it manages dependencies
specified by each individual driver. To enable future analysis of the
dependency links between components, log the dependencies of each DPDK
component as it gets processed. This could pote
On 9/2/2024 3:08 AM, Varghese, Vipin wrote:
Thank you Antaloy for the response. Let me try to share my understanding.
I recently looked into how Intel's Sub-NUMA Clustering would work within
DPDK, and found that I actually didn't have to do anything, because the
SNC "clusters" present themsel
On 8/27/2024 5:10 PM, Vipin Varghese wrote:
As core density continues to increase, chiplet-based
core packing has become a key trend. In AMD SoC EPYC
architectures, core complexes within the same chiplet
share a Last-Level Cache (LLC). By packing logical cores
within the same LLC, we can enhance
On 8/21/2024 11:26 AM, Robin Jarry wrote:
Anatoly Burakov, Aug 21, 2024 at 11:22:
Update coding style:
- Make the code PEP-484 compliant
- Add more comments, improve readability, use f-strings everywhere
- Address all Python static analysis (e.g. mypy, pylint) warnings
- Format code with Ruff
-
On 8/21/2024 11:06 AM, Burakov, Anatoly wrote:
On 8/21/2024 10:52 AM, Burakov, Anatoly wrote:
On 8/20/2024 5:57 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 20, 2024 at 17:35:
Update coding style:
- Make the code PEP-484 compliant
- Add more comments, improve readability, use f-strings
On 8/21/2024 10:52 AM, Burakov, Anatoly wrote:
On 8/20/2024 5:57 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 20, 2024 at 17:35:
Update coding style:
- Make the code PEP-484 compliant
- Add more comments, improve readability, use f-strings everywhere
- Use quotes consistently
- Address all
On 8/20/2024 5:52 PM, Stephen Hemminger wrote:
On Tue, 20 Aug 2024 16:35:16 +0100
Anatoly Burakov wrote:
Update coding style:
- Make the code PEP-484 compliant
- Add more comments, improve readability, use f-strings everywhere
- Use quotes consistently
- Address all Python static analysis (e.
On 8/20/2024 5:57 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 20, 2024 at 17:35:
Update coding style:
- Make the code PEP-484 compliant
- Add more comments, improve readability, use f-strings everywhere
- Use quotes consistently
- Address all Python static analysis (e.g. mypy, pylint) warnings
On 8/20/2024 9:22 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 20, 2024 at 17:35:
In traditional NUMA case, NUMA nodes and physical sockets were used
interchangeably, but there are cases where there can be multiple NUMA
nodes per socket, as well as all CPU's being assigned NUMA node 0 even in
cas
On 8/20/2024 5:59 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 20, 2024 at 17:35:
Update coding style:
- make it PEP-484 compliant
- address all flake8, mypy etc. warnings
- use f-strings in place of old-style string interpolation
- refactor printing to make the code more readable
- read valid C
On 8/20/2024 11:45 AM, Robin Jarry wrote:
Burakov, Anatoly, Aug 20, 2024 at 11:31:
> I checked and unless I missed something, dpdk-pmdinfo.py uses the >
symbols from the typing module for annotations. Not builtin container
> types.
It does both. Check e.g. line 147:
def scrub_pci
On 8/20/2024 11:49 AM, Robin Jarry wrote:
Burakov, Anatoly, Aug 20, 2024 at 11:40:
I have heard about driverctl for a long time in context of devbind,
and I quickly tried it out just now, and IMO while the *functionality*
is there, the usability of devbind is IMO far more friendly:
- it
On 8/20/2024 11:28 AM, Robin Jarry wrote:
Burakov, Anatoly, Aug 20, 2024 at 11:08:
Rewriting this one would take a bit more time because unlike working
with hugepages or sysfs CPU layouts, I'm not familiar enough with all
of the specifics this script does, so I'd have to learn it m
On 8/20/2024 11:20 AM, Robin Jarry wrote:
Burakov, Anatoly, Aug 20, 2024 at 11:12:
> FYI: if we change the minimum supported python version to 3.9, we
could > even get rid of this import completely as builtin types `set`,
`list`, > `tuple` and `dict` have become subscriptable.
>
On 8/19/2024 1:11 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 16, 2024 at 14:16:
Update coding style:
- make it PEP-484 compliant
- address all flake8, mypy etc. warnings
- use f-strings in place of old-style string interpolation
- refactor printing to make the code more readable
Signed-off-by
On 8/19/2024 1:34 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 16, 2024 at 14:16:
Currently, devbind does not print out any NUMA information, which makes
figuring out which NUMA node device belongs to not trivial. Add printouts
for NUMA information if NUMA support is enabled on the system.
Signe
On 8/19/2024 1:32 PM, Robin Jarry wrote:
Anatoly Burakov, Aug 16, 2024 at 14:16:
Currently, the list of per-NUMA node hugepages is displayed in glob
order,
which can be arbitrary. Fix it to sort the glob order.
Signed-off-by: Anatoly Burakov
Hey Anatoly,
I mean no offense to anyone but dpd
On 8/19/2024 11:26 AM, Robin Jarry wrote:
Anatoly Burakov, Aug 14, 2024 at 13:19:
Update coding style:
- make it PEP-484 compliant
- address all flake8, mypy etc. warnings
- use f-strings in place of old-style string interpolation
- refactor printing to make the code more readable
Signed-off-b
On 8/16/2024 2:16 PM, Anatoly Burakov wrote:
Currently, the list of per-NUMA node hugepages is displayed in glob order,
which can be arbitrary. Fix it to sort the glob order.
Signed-off-by: Anatoly Burakov
---
usertools/dpdk-hugepages.py | 40 ++---
1 file cha
On 7/30/2024 5:01 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 02:05:51PM +0100, Anatoly Burakov wrote:
Lots of developers (myself included) uses Visual Studio Code as their primary
IDE for DPDK development. I have been successfully using various incarnations of
this script internally to
On 7/30/2024 12:31 PM, Bruce Richardson wrote:
On Tue, Jul 30, 2024 at 11:21:25AM +0200, Burakov, Anatoly wrote:
On 7/29/2024 6:41 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 06:16:48PM +0200, Burakov, Anatoly wrote:
On 7/29/2024 4:30 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024
On 7/29/2024 6:41 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 06:16:48PM +0200, Burakov, Anatoly wrote:
On 7/29/2024 4:30 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 02:05:52PM +0100, Anatoly Burakov wrote:
A lot of developers use Visual Studio Code as their primary IDE. This
On 7/29/2024 4:30 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 02:05:52PM +0100, Anatoly Burakov wrote:
A lot of developers use Visual Studio Code as their primary IDE. This
script generates a configuration file for VSCode that sets up basic build
tasks, launch tasks, as well as C/C++ cod
On 7/29/2024 3:14 PM, Bruce Richardson wrote:
On Mon, Jul 29, 2024 at 02:05:52PM +0100, Anatoly Burakov wrote:
A lot of developers use Visual Studio Code as their primary IDE. This
script generates a configuration file for VSCode that sets up basic build
tasks, launch tasks, as well as C/C++ cod
On 7/26/2024 5:36 PM, Stephen Hemminger wrote:
On Fri, 26 Jul 2024 13:42:56 +0100
Anatoly Burakov wrote:
A lot of developers use Visual Studio Code as their primary IDE. This
script generates a configuration file for VSCode that sets up basic build
tasks, launch tasks, as well as C/C++ code an
On 7/16/2024 11:53 AM, Mingjin Ye wrote:
In secondary processes, insert_vdev() may be called multiple times on the
same device due to multi-process hot-plugging of the vdev bus and EAL
parameters to add the same vdev.
In this case, when rte_devargs_insert() is called, the devargs->name
reference
On 7/12/2024 4:18 AM, Ye, MingjinX wrote:
-Original Message-
From: Burakov, Anatoly
Sent: Friday, July 12, 2024 12:10 AM
To: Ye, MingjinX ; dev@dpdk.org
Cc: sta...@dpdk.org
Subject: Re: [PATCH 3/3] net/vdev: fix insert vdev core dump
On 3/14/2024 10:36 AM, Mingjin Ye wrote
On 3/14/2024 10:36 AM, Mingjin Ye wrote:
Inserting a vdev device when the device arguments are already stored
in devargs_list, the rte_devargs_insert function replaces the supplied
new devargs with the found devargs and frees the new devargs. As a
result, the use of free devargs results in a core
On 3/14/2024 10:36 AM, Mingjin Ye wrote:
The asan tool detected a memory leak in the vdev driver alloc_devargs.
The previous commit does not insert device arguments into devargs_list
when attaching a device during a bus scan of a secondary process.
This resulted in an existing memory leak when re
On 6/26/2024 1:42 PM, Anatoly Burakov wrote:
The Tx and Rx calibration and timestamp generation blocks are independent. It is
not required to wait for both to complete before programming the offsets.
Instead, we can program the offset for each independently as soon as they are
ready.
Modify the
On 6/26/2024 1:42 PM, Anatoly Burakov wrote:
Adds the Set/Get Port Options commands (0x06EA/0x06EB), also include
additional status and ID bits to improve the Link topology configuration
as well as ability to change port option from pre-boot environment via
the UEFI driver.
Signed-off-by: Anatol
On 6/26/2024 1:42 PM, Anatoly Burakov wrote:
The driver checks the netlist for nodes indicating hardware support using
functions named "ice_is__present" sometimes with an additional _e810t
postfix. These functions check the contents of the netlist, and don't make any
direct device ID check.
When
On 6/13/2024 8:17 AM, Przemek Kitszel wrote:
On 6/12/24 17:00, Anatoly Burakov wrote:
From: Ian Stokes
Refactor __ice_aq_get_set_rss_lut():
get:
- make use params->lut_size only as a size of params->lut;
- return LUT size via params->lut_size;
set:
- remove option to set RSS LUT smaller
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
These patches integrate the latest changes in MEV TS IDPF Base driver.
---
v3:
- Removed additional whitespace changes
- Fixed warnings of CI
- Updated documentation relating to MEV TS FW release
---
Off list,
I don't know anything about idpf drive
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
Instead of using 'divide by 0' to check the struct length,
use the static_assert macro
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/virtchnl2.h | 13 +
1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/driver
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
'u32' data type is used for the struct members in
'virtchnl2_version_info' which should be '__le32'.
Make the change accordingly.
It is not stated why the data type "should" be __le32. Can the commit
message be clarified to explain why this should b
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
Based on the upstream feedback, driver should not use any
defensive programming strategy by checking for NULL pointers
and other conditional checks unnecessarily in the code flow
to fall back, instead fail and fix the bug in a proper way.
Some of the
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
Update IDPF VF device id to 145C.
Also added device ID for S-IOV device.
Signed-off-by: Soumyadeep Hore
---
drivers/common/idpf/base/idpf_devids.h | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/common/idpf/base
On 6/12/2024 5:52 AM, Soumyadeep Hore wrote:
Removes NVME dependency on memory allocations and
uses a prepared buffer instead.
The changes do not affect other components.
Signed-off-by: Soumyadeep Hore
---
return status;
}
@@ -232,8 +244,13 @@ void idpf_ctlq_remove(struct idpf_h
> >> This is a patchset loosely based on internal development tree which
> >> tracked ICE driver development over a period of time since last
> >> snapshot update.
> >>
> >> RFC -> v1:
> >> - From one, many
> >>
> > Apologies, this was meant to be a v1 but it was sent as a v2 due to my
> > patch su
On 6/12/2024 4:59 PM, Anatoly Burakov wrote:
This is a patchset loosely based on internal development tree which
tracked ICE driver development over a period of time since last
snapshot update.
RFC -> v1:
- From one, many
Apologies, this was meant to be a v1 but it was sent as a v2 due to my
p
On 4/18/2024 3:53 PM, edwin.brosse...@6wind.com wrote:
From: Edwin Brossette
Since link state may need some time to stabilize after a link state
change, we cannot update the link state right after one occurs. So link
state change interrupts (lsc) are handled after a delay. To do this, an
alarm
On 1/29/2024 10:22 AM, Chaoyong He wrote:
From: Zerun Fu
In the previous logic the 'fd' was only saved in the primary process,
but for some devices this value is also used in the secondary logic.
For example, the call of 'rte_pci_find_ext_capability()' will fail in
the secondary process.
Fix
On 1/29/2024 10:22 AM, Chaoyong He wrote:
From: Zerun Fu
For the primary process, the logic loops all BARs and will skip
the map of BAR with an invalid physical address (0), also will
assign 'uio_res->nb_maps' with the real mapped BARs number. But
for the secondary process, instead of loops all
On 3/7/2024 8:01 AM, Artemy Kovalyov wrote:
The initialization of the Memzone file-backed array ensures its
uniqueness by employing an exclusive lock. This is crucial because only
one primary process can exist per specific shm_id, which is further
protected by the exclusive EAL runtime configurat
On 3/7/2024 8:01 AM, Artemy Kovalyov wrote:
If the configuration file is absent, the autodetection function should
generate and secure it. Otherwise, multiple simultaneous openings could
erroneously identify themselves as primary instances.
Fixes: af75078fece3 ("first public release")
Cc: sta...
On 3/7/2024 8:01 AM, Artemy Kovalyov wrote:
This commit addresses an issue related to the cleanup of the
multiprocess channel. Previously, when closing the channel, there was a
risk of losing trailing messages. This issue was particularly noticeable
when broadcast message from primary to secondar
On 3/7/2024 8:01 AM, Artemy Kovalyov wrote:
There exists a time gap between the creation of the multiprocess channel
and the registration of request action handlers. Within this window, a
secondary process that receives an eal_dev_mp_request broadcast
notification might respond with ENOTSUP. This
On 3/7/2024 8:01 AM, Artemy Kovalyov wrote:
This commit adds a test scenario that initiates multiple processes
concurrently. These processes attach to the same shared heap, with an
automatic detection mechanism to identify the primary process.
Signed-off-by: Artemy Kovalyov
---
Acked-by: Anato
On 1/23/2024 12:40 PM, Bruce Richardson wrote:
Inside the AVX2 code paths, there was special case code for loading two
16-byte descriptors simultaneously, if that build-time feature was
enabled. As well as not being enabled by default, these code blocks also
were incorrect as there is no guarante
On 1/10/2024 3:25 AM, Mingjin Ye wrote:
Implemented a Tx wrapper to perform a thorough check on mbufs,
categorizing and counting invalid cases by types for diagnostic
purposes. The count of invalid cases is accessible through xstats_get.
Also, the devarg option "mbuf_check" was introduced to con
On 1/10/2024 3:25 AM, Mingjin Ye wrote:
Implemented a Tx wrapper to perform a thorough check on mbufs,
categorizing and counting invalid cases by types for diagnostic
purposes. The count of invalid cases is accessible through xstats_get.
Also, the devarg option "mbuf_check" was introduced to con
On 1/24/2024 3:05 AM, Mingjin Ye wrote:
The "vsi" may be null, so it needs to be used after checking.
Fixes: ab28aad9c24f ("net/iavf: fix Rx Tx burst in multi-process")
Cc: sta...@dpdk.org
Signed-off-by: Mingjin Ye
---
Acked-by: Anatoly Burakov
--
Thanks,
Anatoly
On 9/1/2023 9:24 AM, Mingjin Ye wrote:
When a device is created by a secondary process, an empty devargs is
temporarily generated and bound to it. This causes the device to not
be associated with the correct devargs, and the empty devargs are not
released when the resource is freed.
This patch f
On 11/14/2023 11:48 AM, Mingjin Ye wrote:
This patch adds an API to support getting device information.
The driver can use the "rte_vfio_get_device_info" helper to get
device information from EAL.
Cc: sta...@dpdk.org
Signed-off-by: Mingjin Ye
---
lib/eal/include/rte_vfio.h | 26
On 10/2/2023 9:25 AM, David Marchand wrote:
Hello guys,
On Mon, Aug 28, 2023 at 2:07 PM Anatoly Burakov
wrote:
Currently, the rte_rand() state is initialized with seed, and each
rand state is initialized up until RTE_MAX_LCORE'th rand state. However,
rand state also has one extra rand state r
On 8/14/2023 5:39 AM, Jerin Jacob wrote:
On Fri, Aug 11, 2023 at 9:45 PM Anatoly Burakov
wrote:
This commit implements functions necessary to use inter-domain
operations with idxd driver.
The process is as follows:
1. Process A that wishes to share its memory with others, shall call
`rte
On 7/28/2023 11:15 AM, Bruce Richardson wrote:
From: Stephen Hemminger
Function was added by commit 067855e651d6 ("cmdline: add polling mode")
but never tested or used by DPDK applications. Mark it for
future removal.
Signed-off-by: Stephen Hemminger
Signed-off-by: Bruce Richardson
---
v2:
On 7/10/2023 7:49 AM, Chengwen Feng wrote:
This patch supports rte_memarea_dump() API test.
Signed-off-by: Chengwen Feng
Reviewed-by: Dongdong Liu
Acked-by: Morten Brørup
---
app/test/test_memarea.c | 40
1 file changed, 40 insertions(+)
diff --git
On 7/10/2023 7:49 AM, Chengwen Feng wrote:
This patch supports rte_memarea_alloc() and rte_memarea_free() API
test.
Signed-off-by: Chengwen Feng
Reviewed-by: Dongdong Liu
Acked-by: Morten Brørup
---
+static int
+test_memarea_free_fail(void)
+{
+ struct rte_memarea_param init;
+
On 7/10/2023 7:49 AM, Chengwen Feng wrote:
This patch supports rte_memarea_alloc() and rte_memarea_free() API.
Signed-off-by: Chengwen Feng
Reviewed-by: Dongdong Liu
Acked-by: Morten Brørup
---
Hi,
Kind of a general question: the allocation code doesn't seem to take
into account that sinc
On 7/10/2023 7:49 AM, Chengwen Feng wrote:
This patch supports memarea test of rte_memarea_create() and
rte_memarea_destroy() API.
Signed-off-by: Chengwen Feng
Reviewed-by: Dongdong Liu
Acked-by: Morten Brørup
---
Hi,
+ /* test for create with LIBC */
+ test_memarea_init_param
On 7/10/2023 7:49 AM, Chengwen Feng wrote:
The memarea library is an allocator of variable-size object which based
on a memory region.
This patch provides rte_memarea_create() and rte_memarea_destroy() API.
Signed-off-by: Chengwen Feng
Reviewed-by: Dongdong Liu
Acked-by: Morten Brørup
---
1 - 100 of 1027 matches
Mail list logo
