Hi, Qi
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, November 12, 2019 3:51 PM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Yang, Qiming ; Xing, Beilei
> ; Wang, ShougangX
> Subject: RE: [dpdk-dev] [PATCH v3 2/4] net/ice: fix removal of FDIR profile
>
>
>
> > -Original Me
On Fri, Nov 08, 2019 at 10:00:35AM -0800, Stephen Hemminger wrote:
> The #ifdef to conditionally include on BSD
> is unnecessary. It is harmless to include the header on other
> OS's. An extra include is better than an #ifdef.
>
> Signed-off-by: Stephen Hemminger
Acked-by: Olivier Matz
Thanks
This patch adds a structure to include a flag to indicate if it
is a simple_xor flow so that it's easier to remove the config
when destroying the flow. The patch also simplifies code implementation
logic in ice_hash_create().
In ice_hash_create(), whatever the hash_function is, the filter_ptr->sym
On 19-11-08 14:45, David Marchand wrote:
> External Email
>
> --
> On Fri, Nov 8, 2019 at 12:05 PM David Marchand
> wrote:
> >
> > On Fri, Nov 8, 2019 at 11:21 AM wrote:
> > >
> > > Hi David,
> > >
> > > Thanks for review, hopef
Hi Team,
Like in Java, there is a method called getTimeInMillis() which returns the
current timestamp in milliseconds. I want to know if there's a way to find
out timestamp in milliseconds (or in Microseconds) in the C language or in
the DPDK?
I did some googling and I got the solution which retu
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v19.11-rc2
289 patches were integrated.
The release notes so far:
http://doc.dpdk.org/guides/rel_notes/release_19_11.html
It should be completed with a list of tested hardware.
Highlights of 19.11
When a rte_device is unplugged, the driver should be detached from the
device.
The PCI detach driver operation wrongly didn't clear the driver from the
device structure what remain the device in probe state from the EAL
point of view.
Clear the driver in driver detach successful operation.
Fixes
The port was not validated before detaching.
Ignore port detach operation when the port is not valid.
Fixes: f8e5baa2662d ("app/testpmd: check not detaching device twice")
Cc: tho...@monjalon.net
Cc: sta...@dpdk.org
Signed-off-by: Matan Azrad
---
app/test-pmd/testpmd.c | 3 +++
1 file changed,
On 12/11/2019 07:55, Thomas Monjalon wrote:
> 11/11/2019 12:57, Ray Kinsella:
>> TL;DR abbreviation:
>> A major ABI version that all DPDK releases during an agreed period support.
>> ABI
>> versioning is managed at a project-level, in place of library-level
>> management.
>> ABI changes to add
Host adapter attributes are queried from kernel via multiple
DevX calls. The retrieved data were erroneously overwritten,
the order of querying is fixed.
Fixes: e470ec789d4d ("net/mlx5: fill meter capabilities using DevX")
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_devx_cmds.
On 11/11/19 2:57 PM, Bruce Richardson wrote:
> On Mon, Nov 11, 2019 at 01:27:23PM +0100, David Marchand wrote:
[...]
>> Did you try with the custom apt repository that the LTO job was using ?
>> - apt:
>> -sources:
>> -- ubuntu-toolchain-r-test
>>
> Yes, that repo was neede
From: Viacheslav Ovsiienko
> Host adapter attributes are queried from kernel via multiple DevX calls. The
> retrieved data were erroneously overwritten, the order of querying is fixed.
>
> Fixes: e470ec789d4d ("net/mlx5: fill meter capabilities using DevX")
>
> Signed-off-by: Viacheslav Ovsiie
Retrieve burst mode information according to the selected Rx/Tx mode and
offloads.
Signed-off-by: Sunil Kumar Kori
---
v6:
- Remove unnecessary macro
v5:
- Removed redundent code using flag to string mapping.
v4:
- Review comments incorporated.
v3:
- Rebased the patch over patches.dpdk.org/p
Hi,
DPDK has a function called /rte_get_tsc_cycles() /to get the number of
CPU cycles since boot. If I'm not wrong, it can be used to calculate
time elapsed in milliseconds (or any other precision needed).
The following code snippet shows how to calculated time elapsed:
```
uint64_t start
On Mon, Nov 11, 2019 at 11:28:03AM -0800, Stephen Hemminger wrote:
> Use an explicit statement fallthrough attibute, rather than relying on
> having correct fallthrough comments (that match the magic set of regex
> which depends on the value of compiler flags). This is more robust and
> safer.
>
>
Hello Dpdk Champions,
We have a scenario where we need to support bonding via the dpdk like the
way linux bonding options "fail_over_mac=1".
What is the fail_over_mac Bonding Option?
In active backup bonding mode, the mac address of the bond interface is
typically set to that of the first active
All the counter resources should be cleaned up when teardown.
Fixes: 0f880c3df192 ("net/ice: add flow director counter resource init/release")
Signed-off-by: Wang ShougangX
Acked-by: Qi Zhang
---
drivers/net/ice/ice_fdir_filter.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/n
These patches include FDIR memory resource fixes related to ICE driver.
Patch 1: fix memzone reserve and release in FDIR
Patch 2: fix removal of FDIR profile
Patch 3: fix FDIR counter resource release
Patch 4: fix wild pointer
---
v4 changes:
Removed unnecessary pointer initialization operations
To avoid wild pointer, pointers should be set to NULL after free them.
Fixes: 1a2fc1799f09 ("net/ice: reject duplicated flow for flow director")
Fixes: 84dc7a95a2d3 ("net/ice: enable flow director engine")
Fixes: 0f880c3df192 ("net/ice: add flow director counter resource init/release")
Signed-off
To avoid memzone reserve failure and memory leak, following
resources management should be added.
- Check if the FDIR Memzone already exists before reserving.
- Free FDIR memzone when teardown and other failure scenarios.
Fixes: 84dc7a95a2d3 ("net/ice: enable flow director engine")
Signed-off-by:
The removal of FDIR profile should start from the next
of ICE_FLTR_PTYPE_NONF_NONE.
Fixes: 109e8e06249e ("net/ice: configure HW flow director rule")
Signed-off-by: Wang ShougangX
---
drivers/net/ice/ice_fdir_filter.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/ne
https://bugs.dpdk.org/show_bug.cgi?id=362
Bug ID: 362
Summary: rte_pktmbuf_attach_extbuf does not update pkt_len
Product: DPDK
Version: 19.08
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Hi,
> -Original Message-
> From: Wang, ShougangX
> Sent: Tuesday, November 12, 2019 11:50 AM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Zhang, Qi Z
> ; Wang, ShougangX
> Subject: [PATCH v4 2/4] net/ice: fix removal of FDIR profile
>
> The removal of FDIR profile should start from the next o
https://bugs.dpdk.org/show_bug.cgi?id=363
Bug ID: 363
Summary: CVE-2019-14818
Product: DPDK
Version: 19.08
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: critical
Priority: Normal
C
On 12 Nov 2019, at 1:52, Zhang, Xiao wrote:
Hi Eelco,
Seems you missed this mail.
Not sure why I missed this email, as it does not show up in my email
client :(
See below…
Hi Eelco,
I think you may need add more detailed message in the commit log
or comments.
My interpretation of
> -Original Message-
> From: Matan Azrad
> Sent: Tuesday, November 12, 2019 8:48 AM
> To: dev@dpdk.org
> Cc: Gaetan Rivet ; Iremonger, Bernard
> ; tho...@monjalon.net; sta...@dpdk.org
> Subject: [PATCH 2/2] app/testpmd: fix invalid port detaching
>
> The port was not validated before deta
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Tuesday, November 12, 2019 10:54 AM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Ori Kam
> Subject: [PATCH] net/mlx5: fix query host adapter attributes
>
> Host adapter attributes are queried from kernel via mu
On 12-Nov-19 2:22 AM, Wangyu (Eric) wrote:
NIC address conflicts on 64K pagesize when using multiple NICs,
as system will mmap 64K pagesize for NIC,
but dev->mem_resource[i].len is 16K.
Suggested rewording:
===
bus/pci: align next mapping address on page boundary
Currently, the next address
Caught when compiling this example with pkg-config:
## Building l2fwd
...
main.c: In function ‘main’:
main.c:716:3: warning: ‘rte_eth_dev_set_ptypes’ is deprecated: Symbol
is not yet part of stable ABI [-Wdeprecated-declarations]
716 | ret = rte_eth_dev_set_ptypes(portid, RTE_PTYPE_UNKNO
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, November 11, 2019 4:25 PM
> To: Jakub Grajciar -X (jgrajcia - PANTHEON TECH SRO at Cisco)
>
> Cc: dev@dpdk.org; Ferruh Yigit ; David Marchand
> ; Anatoly Burakov
>
> Subject: Re: [dpdk-dev] [PATCH v6] net/memif: zero-copy sl
This patch functionally reverts the patch in fixes line to not have any
hardcoded library path in the final binary for the security reasons, in
case this binary distributed to production environment.
RPATH only added in RTE_DEVEL_BUILD case and this binary shouldn't
distributed, but still removing
> -Original Message-
> From: Su, Simei
> Sent: Tuesday, November 12, 2019 4:12 PM
> To: Zhang, Qi Z ; Ye, Xiaolong ;
> Yang, Qiming
> Cc: dev@dpdk.org; Su, Simei
> Subject: [PATCH] net/ice: add a structure for RSS
Add a structure is not the patch's purpose, we want to fix the flow d
When compiling with 16B descriptor support enabled, clang compiles gave an
error, complaining that the final parameter of _mm256_blend_epi32() had to
be an immediate value (i.e. compile-time constant). While it appears that
GCC was able to convert the constant variable value "fdir_blend_mask" into
Order intermediate VSIG list correct in order to correctly match existing
VSIG lists.
When overriding pre-existing TCAM entries, properly delete the existing
entry and remove it from the change/update list.
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Signed-off-by: Dan Now
https://bugs.dpdk.org/show_bug.cgi?id=364
Bug ID: 364
Summary: Do not generate temporary doc files in the sources
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: enha
From: Dekel Peled
> RSS action validation function checks the queues included in RSS to make
> sure they are valid.
> A Queue is considered valid if the pointer to the queue (item at location
> queue-index of RxQ array) is not a null value.
> The queue indices are not checked. If a large value i
From: Dekel Peled
> Function mlx5_rxq_get_type() uses the input queue index, without checking
> it, as index to the Rx queues array.
> If this value is too high, it will result in pointer to memory out of Rx
> queues
> array bounds.
>
> This patch adds check of the input queue index, to verify
Function flow_verbs_counter_query() was recently modified.
The new 'if' condition uses a pointer to flow counter-set.
This pointer is valid only if flow contains a count action.
This patch adds check to verify the pointer is valid.
Fixes: d85c7b5ea59f ("net/mlx5: split hairpin flows")
Cc: or...@m
> -Original Message-
> From: Dekel Peled
> Sent: Tuesday, November 12, 2019 16:19
> To: Matan Azrad ; Shahaf Shuler
> ; Slava Ovsiienko
> Cc: Ori Kam ; dev@dpdk.org
> Subject: [PATCH] net/mlx5: fix verbs flow counter query
>
> Function flow_verbs_counter_query() was recently modified.
>
Currently, multiple rte_flow RSS rules may mapping to the same
hardware rule if a later rule is just for inputset change or symm
turn on/off. so after one of the rules be destroyed, we will
get error ICE_ERR_DOES_NOT_EXIST when destroying any other rules.
The patch simply fix this by ignore this er
When resize a memory with next element, the original element size grows.
If the orginal element has padding, the real inner element size didn't
grow as well and this causes trailer verification failure when malloc
debug enabled.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Sig
In rte_realloc, if the old element has pad and need to allocate a new
memory, the padding size was not deducted, so more data was copied to
new data area.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Xueming Li
---
lib/librte_eal/common/rte_malloc.c | 3 ++-
1
Hi all,
Here is a new stable release:
https://fast.dpdk.org/rel/dpdk-16.11.10.tar.xz
The git tree is at:
https://dpdk.org/browse/dpdk-stable/?h=16.11
This stable release fixes CVE-2019-14818, all users of the vhost
library are strongly encouraged to upgrade as soon as possible.
Hi all,
Here is a new LTS release:
https://fast.dpdk.org/rel/dpdk-17.11.8.tar.xz
The git tree is at:
https://dpdk.org/browse/dpdk-stable/?h=17.11
This stable release fixes CVE-2019-14818, all users of the vhost
library are strongly encouraged to upgrade as soon as possible.
Test
Hi all,
Here is a new LTS release:
https://fast.dpdk.org/rel/dpdk-18.11.4.tar.xz
The git tree is at:
https://dpdk.org/browse/dpdk-stable/?h=18.11
This stable release fixes CVE-2019-14818, all users of the vhost
library are strongly encouraged to upgrade as soon as possible.
Kevi
Hi all,
Here is a new stable release:
https://fast.dpdk.org/rel/dpdk-19.08.1.tar.xz
The git tree is at:
https://dpdk.org/browse/dpdk-stable/?h=19.08
This stable release fixes CVE-2019-14818, all users of the vhost
library are strongly encouraged to upgrade as soon as possible.
K
A vulnerability was fixed in DPDK.
Some downstream stakeholders were warned in advance in order to coordinate the
release of fixes and reduce the vulnerability window.
Problem:
A malicious container which has direct access to the vhost-user socket can keep
sending messages which may cause leaking
vhost_user_set_vring_num() performs multiple allocations
without checking whether data were previously allocated.
It may cause a denial of service because of the memory leaks
that happen if a malicious vhost-user master keeps sending
VHOST_USER_SET_VRING_NUM request until the slave runs out
of mem
From: Stefan Hajnoczi
[ backported from upstream commit eb7c574b21cc92792ea5a1f219ddf6dd3cf3b1e1 ]
Check the virtqueue size constraints so that invalid values don't cause
bugs later on in the code. For example, sometimes the virtqueue size is
stored as unsigned int and sometimes as uint16_t, so
As soon as some ancillary data (fds) are received, it is copied
without checking its length.
This patch adds the number of fds received to the message,
which is set in read_vhost_message().
This is preliminary work to support sending fds to Qemu.
Signed-off-by: Dr. David Alan Gilbert
Signed-off
A malicious Vhost-user master could send in loop hand-crafted
vhost-user messages containing more file descriptors the
vhost-user slave expects. Doing so causes the application using
the vhost-user library to run out of FDs.
This issue has been assigned CVE-2019-14818
Fixes: 8f972312b8f4 ("vhost:
As soon as some ancillary data (fds) are received, it is copied
without checking its length.
This patch adds the number of fds received to the message,
which is set in read_vhost_message().
This is preliminary work to support sending fds to Qemu.
Signed-off-by: Dr. David Alan Gilbert
Signed-off
vhost_user_set_vring_num() performs multiple allocations
without checking whether data were previously allocated.
It may cause a denial of service because of the memory leaks
that happen if a malicious vhost-user master keeps sending
VHOST_USER_SET_VRING_NUM request until the slave runs out
of mem
From: Stefan Hajnoczi
[ backported from upstream commit eb7c574b21cc92792ea5a1f219ddf6dd3cf3b1e1 ]
Check the virtqueue size constraints so that invalid values don't cause
bugs later on in the code. For example, sometimes the virtqueue size is
stored as unsigned int and sometimes as uint16_t, so
vhost_user_set_vring_num() performs multiple allocations
without checking whether data were previously allocated.
It may cause a denial of service because of the memory leaks
that happen if a malicious vhost-user master keeps sending
VHOST_USER_SET_VRING_NUM request until the slave runs out
of mem
A malicious Vhost-user master could send in loop hand-crafted
vhost-user messages containing more file descriptors the
vhost-user slave expects. Doing so causes the application using
the vhost-user library to run out of FDs.
This issue has been assigned CVE-2019-14818
Fixes: 8f972312b8f4 ("vhost:
A malicious Vhost-user master could send in loop hand-crafted
vhost-user messages containing more file descriptors the
vhost-user slave expects. Doing so causes the application using
the vhost-user library to run out of FDs.
This issue has been assigned CVE-2019-14818
Fixes: 8f972312b8f4 ("vhost:
vhost_user_set_vring_num() performs multiple allocations
without checking whether data were previously allocated.
It may cause a denial of service because of the memory leaks
that happen if a malicious vhost-user master keeps sending
VHOST_USER_SET_VRING_NUM request until the slave runs out
of mem
A malicious Vhost-user master could send in loop hand-crafted
vhost-user messages containing more file descriptors the
vhost-user slave expects. Doing so causes the application using
the vhost-user library to run out of FDs.
This issue has been assigned CVE-2019-14818
Fixes: 8f972312b8f4 ("vhost:
On 12/11/2019 16:19, Maxime Coquelin wrote:
> vhost_user_set_vring_num() performs multiple allocations
> without checking whether data were previously allocated.
>
> It may cause a denial of service because of the memory leaks
> that happen if a malicious vhost-user master keeps sending
> VHOST_US
On 12/11/2019 16:19, Maxime Coquelin wrote:
> A malicious Vhost-user master could send in loop hand-crafted
> vhost-user messages containing more file descriptors the
> vhost-user slave expects. Doing so causes the application using
> the vhost-user library to run out of FDs.
>
> This issue has be
On 12/11/2019 15:19, Maxime Coquelin wrote:
> vhost_user_set_vring_num() performs multiple allocations
> without checking whether data were previously allocated.
>
> It may cause a denial of service because of the memory leaks
> that happen if a malicious vhost-user master keeps sending
> VHOST_US
On 12/11/2019 15:19, Maxime Coquelin wrote:
> A malicious Vhost-user master could send in loop hand-crafted
> vhost-user messages containing more file descriptors the
> vhost-user slave expects. Doing so causes the application using
> the vhost-user library to run out of FDs.
>
> This issue has be
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Monday, November 11, 2019 4:33 PM
> To: Matan Azrad ; Shahaf Shuler
> ; Slava Ovsiienko
> Cc: Ori Kam ; dev@dpdk.org; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix RSS action validation of queue idx
>
>
On 11/12/2019 3:15 PM, Ferruh Yigit wrote:
> A vulnerability was fixed in DPDK.
>
> Some downstream stakeholders were warned in advance in order to coordinate the
> release of fixes and reduce the vulnerability window.
>
> Problem:
> A malicious container which has direct access to the vhost-user
Two small changes to improve FreeBSD build and install with meson
Bruce Richardson (2):
freebsd: allow installing kernel modules
freebsd: always use clang for kmod compilation
kernel/freebsd/meson.build | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
--
2.22.0
Clang is the system compiler for FreeBSD and kernel module builds can fail
when built with gcc, e.g. when testing with test-meson-builds.sh.
Therefore, it's safer to always use clang to build the kmods since the
actual flags used are outside of DPDK's control and cannot be guaranteed to
work with a
Set the install path for the kernel modules as /boot/modules. This may
ease the integration with the official FreeBSD ports system as all
components should be correctly located in the staging directory after
running "ninja install"
Signed-off-by: Bruce Richardson
---
kernel/freebsd/meson.build |
On 11/12/2019 12:37 PM, David Marchand wrote:
> Caught when compiling this example with pkg-config:
>
> ## Building l2fwd
> ...
> main.c: In function ‘main’:
> main.c:716:3: warning: ‘rte_eth_dev_set_ptypes’ is deprecated: Symbol
> is not yet part of stable ABI [-Wdeprecated-declarations]
>
Since Linux kernel is going to drop support for iopl real soon now.
Is there any ongoing effort to either drop Legacy virtio support,
or replace iopl with ioperm, or at least test with iopl failing?
Note: it looks like the current code does not match comment.
/*
* Request iopl privilege for all
> -Original Message-
> From: Matan Azrad
> Sent: Monday, November 11, 2019 8:01 AM
> To: Ananyev, Konstantin ; Yigit, Ferruh
> ; Dekel Peled ;
> Mcnamara, John ; Kovacevic, Marko
> ; nhor...@tuxdriver.com;
> ajit.khapa...@broadcom.com; somnath.ko...@broadcom.com; Burakov, Anatoly
> ;
On Tue, Nov 12, 2019 at 9:11 AM Olivier Matz wrote:
>
> On Fri, Nov 08, 2019 at 10:00:35AM -0800, Stephen Hemminger wrote:
> > The #ifdef to conditionally include on BSD
> > is unnecessary. It is harmless to include the header on other
> > OS's. An extra include is better than an #ifdef.
> >
> >
On Tue, Nov 12, 2019 at 6:09 PM Ferruh Yigit wrote:
>
> On 11/12/2019 12:37 PM, David Marchand wrote:
> > Caught when compiling this example with pkg-config:
> >
> > ## Building l2fwd
> > ...
> > main.c: In function ‘main’:
> > main.c:716:3: warning: ‘rte_eth_dev_set_ptypes’ is deprecated: Sym
Add missing _.
Fixes: 2977a13657ab ("doc: fix AESNI_MB guide")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
Changelog since v1:
- rebased on master, still the same issue
---
doc/guides/cryptodevs/aesni_mb.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guid
Shoot repeated words in all our guides.
Signed-off-by: David Marchand
---
doc/guides/contributing/coding_style.rst | 8
doc/guides/cryptodevs/zuc.rst | 2 +-
doc/guides/linux_gsg/nic_perf_intel_platform.rst | 2 +-
doc/guides/nics
From: Krzysztof Kanas
Caught while investigating timeouts on a ARM64 server.
Stracing a test process running the eal_flags_autotest, we can see that
the fork helper is checking all possible file descriptors from
getdtablesize() to 2, and close the existing ones.
We can do better by inspecting th
On Tue, Nov 12, 2019 at 9:29 AM Krzysztof Kanas wrote:
>
> On 19-11-08 14:45, David Marchand wrote:
> > External Email
> >
> > --
> > On Fri, Nov 8, 2019 at 12:05 PM David Marchand
> > wrote:
> > >
> > > On Fri, Nov 8, 2019 at 11
On Fri, Nov 8, 2019 at 5:47 PM Stephen Hemminger
wrote:
>
> These are a couple of small cleanups for 19.10 which
Stephen, we might be a bit late for this release, but it is still 19.11 :-)
> came out of work on pcapng support. Full pcapng support
> and BPF are planned for DPDK 20.02.
>
> Stephen
Rather than overloading USER1 and USER2 logtypes,
use a DPDK dynamic log type.
Signed-off-by: Stephen Hemminger
---
lib/librte_vhost/vhost.c | 12
lib/librte_vhost/vhost.h | 5 +++--
2 files changed, 15 insertions(+), 2 deletions(-)
diff --git a/lib/librte_vhost/vhost.c b/lib/libr
This reverts commit 304ffe576f239e5405228c0feec04b6138d525b7.
Commit 304ffe576f23 tried to optimize the amount of the default flow
rules and created it only once on top of the PF representor.
For each FDB rule, the default port ID to match on is like of the port
that triggers the flow.
Hence, th
This reverts commit 304ffe576f239e5405228c0feec04b6138d525b7.
It tried to optimize the amount of the default flow
rules and created it only once on top of the PF representor.
For each FDB rule, the default port ID to match on is like of the port
that triggers the flow.
Hence, the single default
Hi, Qi
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, November 12, 2019 9:38 PM
> To: Su, Simei ; Ye, Xiaolong ;
> Yang, Qiming
> Cc: dev@dpdk.org
> Subject: RE: [PATCH] net/ice: add a structure for RSS
>
>
>
> > -Original Message-
> > From: Su, Simei
> > Sent: Tue
> -Original Message-
> From: Eelco Chaudron [mailto:echau...@redhat.com]
> Sent: Tuesday, November 12, 2019 7:09 PM
> To: Zhang, Xiao
> Cc: Zhang, Qi Z ; dev@dpdk.org; Xing, Beilei
>
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: force promiscuous state after VF
> reset
>
>
>
> On 12 No
In ice_hash_create(), whatever the hash_function is, the filter_ptr->symm
is always 0 and when we destroy the flow, the ice_rem_rss_cfg() is never
carried out. So the destroy function never works well. The patch fixes
this issue and at the same time distinguishes semanteme between simple_xor
and sy
On 11/07, Simei Su wrote:
>This patch fixes core dump issue when entering safe mode with a
>wrong ice.pkg. In safe mode, rte_flow is not supported and it
>won't initialize any flow engine.
>
>Fixes: 7615a6895009 ("net/ice: rework for generic flow enabling")
>
>Signed-off-by: Simei Su
>---
> driver
On 11/12, Di ChenxuX wrote:
>testpmd will occur infinite loops when device hotplug remove.
>We can fix the issue by using the pci generic remove function
>
>Fixes: f2f4990eff94 ("net/ixgbe: release port upon close")
>
>Signed-off-by: Di ChenxuX
>
>v4:
>used generic remove function for ixgbe_vf_rep
On 11/12, Di ChenxuX wrote:
>testpmd will occur infinite loops when device hotplug remove.
>We can fix the issue by using the pci generic remove function
>
>Fixes: ac89d46096d5 ("net/i40e: release port upon close")
>
>Signed-off-by: Di ChenxuX
>
>v4:
>used generic remove function for i40e_vf_repre
On 11/12, Qi Zhang wrote:
>Order intermediate VSIG list correct in order to correctly match existing
>VSIG lists.
>
>When overriding pre-existing TCAM entries, properly delete the existing
>entry and remove it from the change/update list.
>
>Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline
On 11/12, Leyi Rong wrote:
>Fix iavf vf_checksum_sw case fail in X710/XXV710, set bit2 to 1
>of CMD field in Tx descriptor of AVX Tx path according to Spec.
>
>Fixes: af0c246a3800 ("net/iavf: enable AVX2 for iavf")
>
>Signed-off-by: Leyi Rong
>
>---
>v2:
>- Use IAVF_TX_DESC_CMD_ICRC instead of 0x0
On 11/12, Bruce Richardson wrote:
>When compiling with 16B descriptor support enabled, clang compiles gave an
>error, complaining that the final parameter of _mm256_blend_epi32() had to
>be an immediate value (i.e. compile-time constant). While it appears that
>GCC was able to convert the constant
On 11/12, Wei Zhao wrote:
>Correct an error in the IPV6 header bitmask used for programming switch
>rules. Also, change other programming switch headers to use big endian
>fields in order to make setting these easier.
>
>Fixes: 04b8ec1ea807 ("net/ice/base: add protocol structures and defines")
>
>S
Thank you for your advice, it's helpful.
I will follow your advice to write a new one.
-邮件原件-
发件人: Gavin Hu (Arm Technology China) [mailto:gavin...@arm.com]
发送时间: 2019年11月12日 15:02
收件人: Wangyu (Eric) ; dev@dpdk.org
抄送: ferruh.yi...@intel.com; Linuxarm ; humin (Q)
; dengxiaofeng ; Liyuan
The link status got from link status register was not correct,
because register has been reset when ports reset.
After port reset, set the link status down.
Fixes: c431ec66c54c ("net/igb: support setting link up or down")
Cc: sta...@dpdk.org
Signed-off-by: Lunyuan Cui
---
drivers/net/e1000/igb_
After ports reset, tx laser register will be reset. The link
status for 82599eb got from link status register was not correct.
Set tx laser disable after ports reset.
Fixes: 0408f47ba4d6 ("net/ixgbe: fix busy polling while fiber link update")
Cc: sta...@dpdk.org
Signed-off-by: Lunyuan Cui
---
d
When VHOST_USER_VRING_NOFD_MASK is set, the fd_num is 0.
Fixes: bf47225 ("vhost: fix possible denial of service by leaking FDs")
Signed-off-by: Zhike Wang
---
lib/librte_vhost/vhost_user.c | 13 ++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/lib/librte_vhost/vhost_u
Hi ,
We are using 'rte_mempool_create' for allocation of flow memory. This has
been there for a while. We just migrated to dpdk-18.11 from dpdk-17.05. Now
here is problem statement
Problem statement :
In new dpdk ( 18.11 ), the 'rte_mempool_create' take approximately ~4.4 sec
for allocation compar
Hi,
Few more points
Operating system : Centos 7.6
Logging mechanism : syslog
We have logged using syslog before the call and syslog after the call.
Thanks & Regards
Venu
On Wed, 13 Nov 2019 at 10:37, Venumadhav Josyula wrote:
> Hi ,
> We are using 'rte_mempool_create' for allocation of flow
On Tue, Nov 12, 2019 at 09:23:31AM -0800, Stephen Hemminger wrote:
> Since Linux kernel is going to drop support for iopl real soon now.
> Is there any ongoing effort to either drop Legacy virtio support,
I think it's not a good idea to drop the legacy virtio
support at present.
> or replace iop
https://bugs.dpdk.org/show_bug.cgi?id=361
Kalesh A P (kalesh-anakkur.pura...@broadcom.com) changed:
What|Removed |Added
CC||dev@dpdk.org
--
Hi, Qiming
> -Original Message-
> From: Yang, Qiming
> Sent: Tuesday, November 12, 2019 6:37 PM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Zhang, Qi Z
> Subject: RE: [PATCH v4 2/4] net/ice: fix removal of FDIR profile
>
> Hi,
>
> > -Original Message-
> > From: Wang, ShougangX
>
1 - 100 of 135 matches
Mail list logo
