Are there any comments on this series?
Thanks.
Xavier
On 2020/2/25 17:29, Wei Hu (Xavier) wrote:
This series include two fixes patches for bonding PMD driver.
Wei Hu (Xavier) (2):
net/bonding: fix MAC address when switching active port
net/bonding: fix MAC address when one port resets
27/03/2020 16:53, Tom Barbette:
> Le 27/03/2020 à 16:06, Thomas Monjalon a écrit :
> > 27/03/2020 15:24, Tom Barbette:
> >> Le 27/03/2020 à 14:55, Thomas Monjalon a écrit :
> >>> 27/03/2020 13:35, Tom Barbette:
> Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
> > 27/03/2020 10:14, Tom Ba
>> fail:
>> return rc;
>
>Pavan - sorry for being so ... finicky :)
>I've said 'replace all "goto fail" with "return rc"' and I meant that.
>So not only the "goto fail" in you changes but all "goto fail" in that
>function.
Ah, sure I will send a v5.
>
>Apart from that:
>Reviewed-by: Andrze
On 3/26/20 6:15 PM, Thomas Monjalon wrote:
The directories ppc_64 are renamed as ppc in
- config/
- lib/librte_eal/common/arch/
- lib/librte_eal/common/include/arch/
The EAL directories are not really renamed, but symbolically linked,
because they will be moved with th
On 3/26/20 6:15 PM, Thomas Monjalon wrote:
The arch-specific directories arm, ppc and x86 in common/include/arch/
are moved as include/ sub-directories of respective arch directories:
- arm/include/
- ppc/include/
- x86/include/
Signed-off-by: Thomas Monjalon
Review
On 3/26/20 6:15 PM, Thomas Monjalon wrote:
The arch-specific directories arm, ppc and x86 in common/arch/
are moved at the same level as the OS-specific directories.
It makes more clear that EAL is covering a matrix combining OS and arch.
Signed-off-by: Thomas Monjalon
Reviewed-by: David C
mlx5 PMD refuses to update link state if link speed is defined but
status is down or if link speed is undefined but status is up, even if
the ioctl() succeeded.
This prevents application to detect link up/down event, especially when
the link speed is not correctly detected.
As link speed is nice to
On Fri, Mar 27, 2020 at 4:16 PM David Marchand
wrote:
>
> On Fri, Mar 27, 2020 at 9:10 AM Olivier Matz wrote:
> >
> > This patchset fixes a buffer overflow in kvargs when parsing an invalid
> > string, and fixes the kvargs unit tests.
> >
> > Olivier Matz (2):
> > tests/kvargs: fix to consider
On 3/27/20 10:53 AM, pbhagavat...@marvell.com wrote:
> From: Pavan Nikhilesh
>
> Add device arguments to lock Rx/Tx contexts.
> Application can either choose to lock Rx or Tx contexts by using
> 'lock_rx_ctx' or 'lock_tx_ctx' respectively per each port.
>
> Example:
> -w 0002:02:00.0,lock_
Le 27/03/2020 à 16:06, Thomas Monjalon a écrit :
27/03/2020 15:24, Tom Barbette:
Le 27/03/2020 à 14:55, Thomas Monjalon a écrit :
27/03/2020 13:35, Tom Barbette:
Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
27/03/2020 10:14, Tom Barbette:
CC'ing original participants as I don't see a
On 03/27, Haiyue Wang wrote:
>A DCF (Device Config Function) based approach is proposed where a device
>bound to the device's VF0 can act as a sole controlling entity to exercise
>advance functionality (such as switch, ACL) for rest of the VFs.
>
>The DCF works as a standalone PMD to support this f
27/03/2020 15:36, Ray Kinsella:
> On 27/03/2020 14:32, Van Haaren, Harry wrote:
> > From: Thomas Monjalon
> >> 27/03/2020 14:44, Neil Horman:
> >>> On Fri, Mar 27, 2020 at 01:24:12PM +0100, David Marchand wrote:
> On Wed, Mar 25, 2020 at 12:11 PM Kevin Laatz
> >> wrote:
> > --- a/lib/lib
On Fri, Mar 27, 2020 at 9:10 AM Olivier Matz wrote:
>
> This patchset fixes a buffer overflow in kvargs when parsing an invalid
> string, and fixes the kvargs unit tests.
>
> Olivier Matz (2):
> tests/kvargs: fix to consider empty elements as valid
> tests/kvargs: fix check of invalid cases
>
27/03/2020 15:47, Stephen Hemminger:
> On Fri, 27 Mar 2020 02:15:32 +0100
> Thomas Monjalon wrote:
> > v2:
> > - add missing meson and make files in the include/ directory
> > - fix ppc build
> > - cosmetic improvements in meson files
> > - split single patch into 8 pieces
> >
> >
> > Th
27/03/2020 15:24, Tom Barbette:
>
> Le 27/03/2020 à 14:55, Thomas Monjalon a écrit :
> > 27/03/2020 13:35, Tom Barbette:
> >> Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
> >>> 27/03/2020 10:14, Tom Barbette:
> CC'ing original participants as I don't see a way out of this.
>
> L
On Fri, Mar 27, 2020 at 2:18 PM Van Haaren, Harry
wrote:
>
> > -Original Message-
> > From: David Marchand
> > Sent: Friday, March 27, 2020 12:24 PM
> > To: Laatz, Kevin
> > Cc: dev ; Richardson, Bruce ; Van
> > Haaren, Harry ; Neil Horman
> > ; Thomas Monjalon ; Honnappa
> > Nagarahalli
On Fri, 27 Mar 2020 11:17:56 +0100
Michal Krawczyk wrote:
> From: Igor Chauskin
>
> Memory allocation region id could possibly be non-unique
> due to non-atomic increment, causing allocation failure.
>
> Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
> Cc: sta...@dpdk.org
>
> S
Le 27/03/2020 à 15:44, Andrew Rybchenko a écrit :
On 3/27/20 5:29 PM, Tom Barbette wrote:
Hi all,
It seems rte_flow_item_eth takes its ethertype in host byte order with
i40e, but in network byte order with mlx5.
If so, it is definitely bug in i40e, since struct rte_flow_item_eth
defines type
On Fri, 27 Mar 2020 11:17:55 +0100
Michal Krawczyk wrote:
> + /* ENA isn't supporting buffers smaller than 1400 bytes */
> + buffer_size = mp->elt_size - sizeof(struct rte_mbuf) -
> + RTE_PKTMBUF_HEADROOM;
This should use rte_pktmbuf_data_room_size(mp) - RTE_PKTMBUF_HEADROOM
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Friday, March 20, 2020 6:32 PM
> To: Van Haaren, Harry ; Phil Yang
> ; tho...@monjalon.net; Ananyev, Konstantin
> ; step...@networkplumber.org;
> maxime.coque...@redhat.com; dev@dpdk.org
> Cc: david.march...@redhat.com; jer...@marve
On Fri, 27 Mar 2020 02:15:32 +0100
Thomas Monjalon wrote:
> Some clean-up is done in EAL sub-directories.
> The goal is to make organization easier to understand,
> and to prepare moving some files from common to Unix-only place.
>
> Since the kernel modules are moved to kernel/ directory,
> the
On 3/27/20 5:29 PM, Tom Barbette wrote:
> Hi all,
>
> It seems rte_flow_item_eth takes its ethertype in host byte order with
> i40e, but in network byte order with mlx5.
If so, it is definitely bug in i40e, since struct rte_flow_item_eth
defines type as rte_be16_t type.
> Wouldn't it be nice to
On 27/03/2020 14:32, Van Haaren, Harry wrote:
>> -Original Message-
>> From: Thomas Monjalon
>> Sent: Friday, March 27, 2020 2:16 PM
>> To: Neil Horman ; Dodji Seketeli ;
>> m...@ashroe.eu
>> Cc: David Marchand ; Laatz, Kevin
>> ; dev ; Richardson, Bruce
>> ; Van Haaren, Harry ;
>> Honn
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, March 27, 2020 2:16 PM
> To: Neil Horman ; Dodji Seketeli ;
> m...@ashroe.eu
> Cc: David Marchand ; Laatz, Kevin
> ; dev ; Richardson, Bruce
> ; Van Haaren, Harry ;
> Honnappa Nagarahalli
> Subject: Re: [dpdk-dev] [PATCH v2] eal
Hi all,
It seems rte_flow_item_eth takes its ethertype in host byte order with
i40e, but in network byte order with mlx5.
Wouldn't it be nice to unify that? Else is there a way to know in which
byte order the spec should be given? I guess that expands to all fields,
but I only compared the e
Le 27/03/2020 à 14:55, Thomas Monjalon a écrit :
27/03/2020 13:35, Tom Barbette:
Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
27/03/2020 10:14, Tom Barbette:
CC'ing original participants as I don't see a way out of this.
Le 12/03/2020 à 13:04, Tom Barbette a écrit :
Hi all,
If the us
27/03/2020 14:44, Neil Horman:
> On Fri, Mar 27, 2020 at 01:24:12PM +0100, David Marchand wrote:
> > On Wed, Mar 25, 2020 at 12:11 PM Kevin Laatz wrote:
> > > --- a/lib/librte_eal/common/include/arch/x86/rte_cpuflags.h
> > > +++ b/lib/librte_eal/common/include/arch/x86/rte_cpuflags.h
> > > @@ -113
On 3/26/20 10:14 AM, Wei Hu (Xavier) wrote:
> This series are fixes for hns3 PMD driver.
>
> Chengwen Feng (1):
> net/hns3: fix the return value of setting VLAN offload
>
> Lijun Ou (2):
> net/hns3: fix RSS indirection table configuration
> net/hns3: fix configuring RSS hash when rules are
27/03/2020 13:35, Tom Barbette:
> Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
> > 27/03/2020 10:14, Tom Barbette:
> >> CC'ing original participants as I don't see a way out of this.
> >>
> >> Le 12/03/2020 à 13:04, Tom Barbette a écrit :
> >>> Hi all,
> >>>
> >>> If the user follows the quick
On Fri, Mar 27, 2020 at 01:24:12PM +0100, David Marchand wrote:
> On Wed, Mar 25, 2020 at 12:11 PM Kevin Laatz wrote:
> >
> > This patch adds CPU flags which will enable the detection of ISA
> > features available on more recent x86 based CPUs.
> >
> > The CPUID leaf information can be found in Se
In nitrox_sym_pmd_create() the name array will overflow if the pci
device name is greater than 57 bytes. To fix this issue subtract pci
device name length from array length while appending substring to the
name.
Coverity issue: 349926
Fixes: 9fdef0cc2385 ("crypto/nitrox: create symmetric cryptode
If the NPS_PKT ring/port is greater than 8191 the NPS_PKT*() macros will
evaluate to incorrect values due to unintended sign extension from int
to unsigned long. To fix this, add UL suffix to the constants in these
macros. The same problem is with AQMQ_QSZX() macro also.
Coverity issue: 349899, 34
> -Original Message-
> From: David Marchand
> Sent: Friday, March 27, 2020 12:24 PM
> To: Laatz, Kevin
> Cc: dev ; Richardson, Bruce ; Van
> Haaren, Harry ; Neil Horman
> ; Thomas Monjalon ; Honnappa
> Nagarahalli ; Dodji Seketeli
> Subject: Re: [dpdk-dev] [PATCH v2] eal/cpuflags: add x8
> -Original Message-
> From: Di, ChenxuX
> Sent: Tuesday, March 24, 2020 4:18 PM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Xing, Beilei
> ; Zhao1, Wei ; Di, ChenxuX
>
> Subject: [PATCH v5] net/i40e: implement hash function in rte flow API
>
> implement set hash global configurations, se
Le 27/03/2020 à 11:35, Thomas Monjalon a écrit :
27/03/2020 10:14, Tom Barbette:
CC'ing original participants as I don't see a way out of this.
Le 12/03/2020 à 13:04, Tom Barbette a écrit :
Hi all,
If the user follows the quick guide
(http://core.dpdk.org/doc/quick-start/) DPDK will be compil
On Wed, Mar 25, 2020 at 12:11 PM Kevin Laatz wrote:
>
> This patch adds CPU flags which will enable the detection of ISA
> features available on more recent x86 based CPUs.
>
> The CPUID leaf information can be found in Section 1.7 of this
> document:
> https://software.intel.com/sites/default/fil
> -Original Message-
> From: Cui, LunyuanX
> Sent: Wednesday, March 18, 2020 11:15 AM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Zhang, Qi Z ;
> Wu, Jingjing ; Cui, LunyuanX
>
> Subject: [PATCH v2] net/i40e: enable MAC address as FDIR input set
>
> FVL enable both src MAC address and dst
On Fri, Mar 27, 2020 at 02:15:33AM +0100, Thomas Monjalon wrote:
> When moving files to the directory kernel/,
> the file BSDmakefile.meson was left in eal/.
>
> Also the intermediate makefiles in linux/ and freebsd/ became useless.
>
> Fixes: acaa9ee991b5 ("move kernel modules directories")
> Cc
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Adding missing implementation for the interrupt tests
for LDPC encoder and decoders.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 202 ++-
1 file c
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Adding support for the offload latency tests when
using the LDPC encoder and decoder operations.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 26 +++---
1 file cha
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Includes support for BLER (Block Error Rate) wireless
performance test with new arguments for SNR and number
of iterations for 5G. This generates LLRs for a given
SNR level then measures the ratio of code bloc
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Adding functionality to validate HARQ for different
devices implementation.
Adding capacity to fetch HARQ data when required as
part of this validation.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_b
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Self-contained and cosmetic renaming of macro
so that to be more explicit for future extension.
Signed-off-by: Nic Chautru
---
app/test-bbdev/test_bbdev_perf.c | 51 +++-
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
This exposes the HARQ buffer size at the device driver level
instead of using the capability of a specific operation.
This is currently not yet used by a device until
future commit.
Signed-off-by: Nic Chautr
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
This is to support cases when the input data for
decoding a code block is larger than 64kB and would
not fit as a contiguous block of data into one
mbuf. In that case the length from the operation
supersedes t
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
The actual LLR representation was incorrectly assumed to be 2
instead of 4. This would impact wireless performance but is not
critical to be back ported on LTS branches.
Fixes: c769c711757a ("baseband/turbo_s
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
From: Nic Chautru
Adding capability flag for device variants when HARQ buffer
may or may not include the filler bits.
Minor cosmetic changes in same file.
Signed-off-by: Nic Chautru
---
lib/librte_bbdev/rte_bbdev.h| 2
Acked-by: Dave Burley
On 26/03/2020 03:27, Nicolas Chautru wrote:
v5: cosmetic change
v4: Changes based on review comments from Akhil. Also taking the new PMD out of
this serie
to be pushed in separate serie.
v3: squash the release notes updates into the related commits
v2: including release n
On 3/27/20 1:18 PM, Michal Krawczyk wrote:
> Some ENA devices can pass to the driver descriptor with length 0. To
> avoid extra allocation, the descriptor can be reused by simply putting
> it back to the device.
>
> Signed-off-by: Michal Krawczyk
> Reviewed-by: Igor Chauskin
> Reviewed-by: Guy T
On 3/27/20 1:18 PM, Michal Krawczyk wrote:
> If the device supports larger LLQ (Low Latency Queue) headers, the user
> can activate them by enabling CONFIG_RTE_LIBRTE_ENA_LARGE_LLQ_HEADERS
> flag in the configuration file.
>
> If the device isn't supporting this feature, the default value will be
On 3/27/20 1:17 PM, Michal Krawczyk wrote:
> The RSS hash key was present in the device, but it wasn't exposed to
> the user. The other key still cannot be set, but now it can be accessed
> if one needs to do that.
>
> By default, the random hash key is used and it is generated only once
> when re
On 3/27/20 1:17 PM, Michal Krawczyk wrote:
> Some of the ENA devices can't handle buffers which are smaller than a
> 1400B. Because of this limitation, size of the buffer is being checked
> and limited during the Rx queue setup.
>
> If it's below the allowed value, PMD won't finish it's configurat
27/03/2020 07:49, Jerin Jacob:
> In case if someone interested to know the steps to host DPDK
> documentation for free in netlify.
>
> 1) Create a DPDK repo with your code(documentation files) in GitHub
>
> 2) Open https://app.netlify.com/ URL
>
> 3) Sign in netlify with GitHub account
>
> 4)
27/03/2020 10:14, Tom Barbette:
> CC'ing original participants as I don't see a way out of this.
>
> Le 12/03/2020 à 13:04, Tom Barbette a écrit :
> > Hi all,
> >
> > If the user follows the quick guide
> > (http://core.dpdk.org/doc/quick-start/) DPDK will be compiled in the
> > "build" folder.
The v2.1.0 making changes in the ena_ethdev files were done this year,
so the copyright notice should be updated.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_plat_dpdk.h | 2 +-
drivers/net/ena/ena_ethdev.c | 2 +-
driv
The v2.1.0 is refactoring Tx and Rx paths, including few bug fixes and
is also adding a new features which are going to be available with the
newest hardware:
* Accelerated LLQ mode
* Disabling meta descriptor caching is required for that
* Handling Rx descriptor which length is 0
* Tx drops are
Some ENA devices can pass to the driver descriptor with length 0. To
avoid extra allocation, the descriptor can be reused by simply putting
it back to the device.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/ena_ethdev.c | 74 +++
As AWS metal instances are supporting IOMMU, the usage of igb_uio or
vfio-pci can lead to a problems (when to use which module), especially
that the vfio-pci isn't supporting SMMU on arm64.
To clear up the problem of using those modules in various setup
conditions (with or without IOMMU) on metal
In the LLQ mode, the device can indicate that meta data descriptor
caching is disabled. In that case the driver should send valid meta
descriptor on every Tx packet.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/ena_ethdev.c | 28
* Split main Rx function into multiple ones - the body of the main
was very big and further there were 2 nested loops, which were
making the code hard to read
* Rework how the Rx mbuf chains are being created - Instead of having
while loop which has conditional check if it's first segment, ha
If the device supports larger LLQ (Low Latency Queue) headers, the user
can activate them by enabling CONFIG_RTE_LIBRTE_ENA_LARGE_LLQ_HEADERS
flag in the configuration file.
If the device isn't supporting this feature, the default value will be
used.
Signed-off-by: Michal Krawczyk
Reviewed-by: I
ENA device can report in the AENQ handler amount of Tx packets that were
dropped and not sent.
This statistic is showing global value for the device and because
rte_eth_stats is missing field that could indicate this value (it
isn't the Tx error), it is being presented as a extended statistic.
As
The doorbell code is already issuing the doorbell by using rte_write.
Because of that, there is no need to do that before calling the
function.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/ena_ethdev.c | 9 +
1 file changed, 1 in
The current ena_com version was generated on 25.09.2019.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_defs/ena_gen_info.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ena/base/ena_defs/en
As the alignemnt of the defines wasn't valid, it was removed at all, so
instead of using multiple spaces or tabs, the single space after define
name is being used.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.h | 8
Reading values from the device is about the maximum capabilities of the
device. Because of that, the names of the fields storing those values,
functions and temporary variables, should be more descriptive in order
to improve self documentation fo the code.
In connection with this, the way of getti
ENA device is using 48-bit memory for IO. because of that, the upper
limit had to be updated.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.c | 2 +-
drivers/net/ena/base/ena_defs/ena_common_defs.h | 6 +-
To make the debugging easier, the error logs were added in the Tx path.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_eth_com.c | 24 +++-
1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers
Because ena_com is being used by multiple platforms which are using
different C versions, PRIu64 cannot be used directly and must be defined
in the platform file.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.c | 2 +-
IO rings were configured with the maximum allowed size for the Tx/Rx
rings. However, the application could decide to create smaller rings.
This patch is using value stored in the ring instead of the value from
the adapter which is indicating the maximum allowed value.
Fixes: df238f84c0a2 ("net/en
In order to use the accelerated LLQ, the driver must limit the Tx burst
and be aware that the device has the meta caching disabled. In that
situation, the meta descriptor must be valid on each Tx packet.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
driv
This feature allows for adaptive interrupt moderation. It's not used by
the DPDK PMD, but is a part of the newest HAL version.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.c | 171 +--
drivers/n
This buffer was never used by the ENA PMD. It could be used for
debugging, but it's presence is redundant now.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.c | 56 --
drivers/net/ena/base/ena_
The documentation format was aligned and few typos were fixed.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.h | 24
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ena/bas
The spaces instead of tabs were used for the indent.
Signed-off-by: Michal Krawczyk
Reviewed-by: Igor Chauskin
Reviewed-by: Guy Tzalik
---
drivers/net/ena/base/ena_com.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ena/base/ena_com.c b/drivers/net/ena
The RSS hash key was present in the device, but it wasn't exposed to
the user. The other key still cannot be set, but now it can be accessed
if one needs to do that.
By default, the random hash key is used and it is generated only once
when requested for the first time.
Signed-off-by: Michal Kraw
Hi,
This patchset is including severeal changes, including:
* ena_com (HAL) update
* Support for upcoming device features
* Refactor of the IO path
* Documentation update about ENA usage on metal instances
Igor Chauskin (2):
net/ena/base: make allocation macros thread-safe
net/ena/base: preve
From: Igor Chauskin
rte_memzone_reserve() will reserve the biggest contiguous memzone
available if received 0 as size param.
Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
Cc: sta...@dpdk.org
Signed-off-by: Igor Chauskin
Reviewed-by: Michal Krawczyk
Reviewed-by: Guy Tzalik
---
From: Igor Chauskin
Memory allocation region id could possibly be non-unique
due to non-atomic increment, causing allocation failure.
Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
Cc: sta...@dpdk.org
Signed-off-by: Igor Chauskin
Reviewed-by: Michal Krawczyk
Reviewed-by: Guy Tz
Some of the ENA devices can't handle buffers which are smaller than a
1400B. Because of this limitation, size of the buffer is being checked
and limited during the Rx queue setup.
If it's below the allowed value, PMD won't finish it's configuration
successfully..
Signed-off-by: Michal Krawczyk
R
On Fri, Mar 13, 2020 at 3:52 PM Ferruh Yigit wrote:
>
> This is a helper function in case components would like to do more work
> than just logging a message based on log level, like for example
> collecting some stats if the log type is DEBUG etc..
>
> A few existing relevant usage converted to t
On Wed, Mar 25, 2020 at 3:39 PM David Marchand
wrote:
>
> On Fri, Feb 7, 2020 at 12:11 PM Anatoly Burakov
> wrote:
> >
> > When --no-huge mode is used, the memory is currently allocated with
> > mmap(NULL, ...). This is fine in most cases, but can fail in cases
> > where DPDK is run on a machine
On Tue, Feb 25, 2020 at 2:25 PM Anatoly Burakov
wrote:
>
> Currently, when we are creating DMA mappings for memory that's
> either external or is backed by hugepages in IOVA as PA mode, we
> assume that each page is necessarily discontiguous. This may not
> actually be the case, especially for ext
From: Pavan Nikhilesh
Add device arguments to lock Rx/Tx contexts.
Application can either choose to lock Rx or Tx contexts by using
'lock_rx_ctx' or 'lock_tx_ctx' respectively per each port.
Example:
-w 0002:02:00.0,lock_rx_ctx=1 -w 0002:03:00.0,lock_tx_ctx=1
Signed-off-by: Pavan Nikhil
Packed ring vectorized datapath will be selected when requirements are
fulfilled.
1. AVX512 is allowed in config file and supported by compiler
2. Host cpu support AVX512F
3. ring size is power of two
4. virtio VERSION_1 and in_order features are negotiated
5. LRO and mergeable feature disabled in
Document packed virtqueue vectorized datapath selection logic in virtio
net PMD. Add packed virtqueue vectorized datapath features to new ini
file.
Signed-off-by: Marvin Liu
diff --git a/doc/guides/nics/features/virtio-packed_vec.ini
b/doc/guides/nics/features/virtio-packed_vec.ini
new file mod
Move xmit offload and packed ring xmit enqueue function to header file.
These functions will be reused by packed ring vectorized Tx function.
Signed-off-by: Marvin Liu
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index ac417232b..b8b4d3c25 100644
--- a/drivers
This patch set introduced vectorized datapath for packed ring.
The size of packed ring descriptor is 16Bytes. Four batched descriptors
are just placed into one cacheline. AVX512 instructions can well handle
this kind of data. Packed ring TX datapath can fully transformed into
vectorized datapath.
Optimize packed ring Rx datapath when AVX512 enabled and mergeable
buffer/Rx LRO offloading are not required. Solution of optimization
is pretty like vhost, is that split datapath into batch and single
functions. Batch function is further optimized by vector instructions.
Also pad desc extra struct
Optimize packed ring Tx datapath alike Rx datapath. Split Tx datapath
into batch and single Tx functions. Batch function further optimized by
vector instructions.
Signed-off-by: Marvin Liu
diff --git a/drivers/net/virtio/virtio_ethdev.h
b/drivers/net/virtio/virtio_ethdev.h
index 10e39670e..c9aa
Introduce free threshold setting in Rx queue, default value of it is 32.
Limiated threshold size to multiple of four as only vectorized packed Rx
function will utilize it. Virtio driver will rearm Rx queue when more
than rx_free_thresh descs were dequeued.
Signed-off-by: Marvin Liu
diff --git a/
Add new parameter "packed_vec" which can disable vectorized packed ring
datapath explicitly. When "packed_vec" option is on, driver will check
packed ring vectorized datapath prerequisites. If any one of them not
matched, vectorized datapath won't be selected.
Signed-off-by: Marvin Liu
diff --gi
CC'ing original participants as I don't see a way out of this.
Le 12/03/2020 à 13:04, Tom Barbette a écrit :
Hi all,
If the user follows the quick guide
(http://core.dpdk.org/doc/quick-start/) DPDK will be compiled in the
"build" folder.
However, external applications will always fail to bu
From: Pavan Nikhilesh
Use c11 atomics with RELAXED ordering instead of rte_atomic ops which
enforce unnessary barries on arm64.
Signed-off-by: Pavan Nikhilesh
---
drivers/event/octeontx2/otx2_tim_evdev.c | 5 +++--
drivers/event/octeontx2/otx2_tim_evdev.h | 2 +-
drivers/event/octeontx2/otx2
On Thu, Mar 26, 2020 at 10:30 PM wrote:
>
> From: Pavan Nikhilesh
>
> Add IPv4 lookup process function for ip4_lookup
> rte_node. This node performs LPM lookup using x86_64
> vector supported RTE_LPM API on every packet received
> and forwards it to a next node that is identified by
> lookup resu
Tested-by: Han,YingyaX
BRs,
Yingya
-Original Message-
From: stable On Behalf Of Li, Xiaoyun
Sent: Thursday, March 5, 2020 10:03 AM
To: Jiang, JunyuX ; dev@dpdk.org
Cc: Yang, Qiming ; sta...@dpdk.org
Subject: Re: [dpdk-stable] [PATCH] examples/vmdq: fix RSS configuration
> -Original
The command line to create RTE flow for specific proto_id of PPPOES is
not correct. This patch is to fix this issue.
Fixes: 226c6e60c35b ("ethdev: add PPPoE to flow API")
Cc: sta...@dpdk.org
Signed-off-by: Xiao Zhang
---
app/test-pmd/cmdline_flow.c | 13 +++--
1 file changed, 3 insertio
Hi,
On Fri, Mar 20, 2020 at 03:55:15PM +, Alexander Kozyrev wrote:
> Introduction of pinned external buffers doubled memory loads in the
> rte_pktmbuf_prefree_seg() function. Analysis of the generated assembly
> code shows unnecessary load of the pool field of the rte_mbuf structure.
> Here is
From: Yunjian Wang
When the input string is "key=[", the ending '\0' is replaced
by a ',', leading to a heap buffer overflow.
Check the content of ctx1 to avoid this problem.
Fixes: cc0579f2339a ("kvargs: support list value")
Cc: sta...@dpdk.org
Signed-off-by: Yunjian Wang
Signed-off-by: Oliv
The return was not properly placed, and only the first test case
was validated.
Fixes: e495f5435524 ("kvargs: add test case in app/test")
Cc: sta...@dpdk.org
Signed-off-by: Olivier Matz
---
app/test/test_kvargs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test/test_
1 - 100 of 102 matches
Mail list logo
