The __sync builtin based implementation generates full memory barriers
('dmb ish') on Arm platforms. Using C11 atomic builtins to generate one way
barriers.
Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
0x0090f1b0 <+16>:e0
Instead of getting timestamps per iteration, amortize its overhead
can help getting more precise benchmarking results.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
Reviewed-by: Joyce Kong
Reviewed-by: ruifeng wang
Reviewed-by: honnappa nagarahalli
-
The test is to benchmark the performance of spinlock by counting the
number of spinlock acquire and release operations within the specified
time.
A typical pair of lock and unlock operations costs tens or hundreds of
nano seconds, in comparison to this, delaying 1 us outside of the locked
region is
V8: Remove internal ChangeId
V7: Update the 1/3 patch headline and commit message
V6: Rebase and drop the first patch as a similar fix was already merged.
V5: Remove ChangeId(sorry for that)
V4:
1. Drop one patch for the test case to get time precisely as the overhead
of getting time is amor
Instead of getting timestamps per iteration, amortize its overhead
can help getting more precise benchmarking results.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Change-Id: I5460f585937f65772c2eabe9ebc3d23a682e8af2
Jira: ENTNET-1047
Signed-off-by: Gavin Hu
Reviewed-by: Joyc
The __sync builtin based implementation generates full memory barriers
('dmb ish') on Arm platforms. Using C11 atomic builtins to generate one way
barriers.
Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
0x0090f1b0 <+16>:e0
V7: Update the 1/3 patch headline and commit message
V6: Rebase and drop the first patch as a similar fix was already merged.
V5: Remove ChangeId(sorry for that)
V4:
1. Drop one patch for the test case to get time precisely as the overhead
of getting time is amortized already in another patch
The test is to benchmark the performance of spinlock by counting the
number of spinlock acquire and release operations within the specified
time.
A typical pair of lock and unlock operations costs tens or hundreds of
nano seconds, in comparison to this, delaying 1 us outside of the locked
region is
The __sync builtin based implementation generates full memory barriers
('dmb ish') on Arm platforms. Using C11 atomic builtins to generate one way
barriers.
Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
0x0090f1b0 <+16>:e0
Instead of getting timestamps per iteration, amortize its overhead
can help getting more precise benchmarking results.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
Reviewed-by: Joyce Kong
Reviewed-by: ruifeng wang
Reviewed-by: honnappa nagarahalli
-
Quickly taking and releasing the spinlock can't hit the contentions,
delay 1 us to create contention stress, this can help really show
the performance of spinlock implementation.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
Reviewed-by: Ruifeng Wang
R
V6: Rebase and drop the first patch as a similar fix was already merged.
V5: Remove ChangeId(sorry for that)
V4:
1. Drop one patch for the test case to get time precisely as the overhead
of getting time is amortized already in another patch.
2. Drop the ticket lock patch from this series as th
Hi, David Harton
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of David Harton
> Sent: Wednesday, March 6, 2019 11:24 PM
> To: dev@dpdk.org; Lu, Wenzhuo ; Ananyev,
> Konstantin
> Cc: David Harton
> Subject: [dpdk-dev] [PATCH] net/ixgbe: Restore vlan filter/ext
> -Original Message-
> From: Zhao1, Wei
> Sent: Friday, March 8, 2019 10:46 AM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Zhang, Qi Z
> Subject: [PATCH v4 0/2] net/ixgbe: promiscuous mode enable on VF
>
> There is need to enable promiscuous mode enable on VF, pf host should also
> enabl
Comparing dpdk VA spaces to dpdk 16.11, the dpdk app process's VA spaces
increase to above 30G.
Here we can unmap the unneed VA spaces in rte_memseg_list.
Signed-off-by: Lilijun
---
lib/librte_eal/linuxapp/eal/eal_memory.c | 13 -
1 file changed, 12 insertions(+), 1 deletion(-)
dif
Hi Konstantin,
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Friday, March 8, 2019 11:21 AM
> To: Ananyev, Konstantin ; Gavin Hu (Arm
> Technology China) ; Ilya Maximets
> ; dev@dpdk.org
> Cc: nd ; tho...@monjalon.net; jer...@marvell.com;
> hemant.agra...@nxp.com; nipun.gu...@
> -Original Message-
> From: dev On Behalf Of Kevin Traynor
> Sent: Friday, March 8, 2019 12:09 AM
> To: Rasesh Mody ; dev@dpdk.org
> Cc: Kevin Traynor ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/qede: support IOVA VA mode
>
> Set RTE_PCI_DRV_IOVA_AS_VA in drv_flags. This allows i
> > > >> On 07.03.2019 9:45, gavin hu wrote:
> > > >>> In weak memory models, like arm64, reading the {prod,cons}.tail
> > > >>> may
> > get
> > > >>> reordered after reading or writing the ring slots, which
> > > >>> corrupts the
> > ring
> > > >>> and stale data is observed.
> > > >>>
> > > >>> T
> -Original Message-
> From: Gavin Hu (Arm Technology China)
> Sent: Thursday, March 7, 2019 6:45 PM
> To: Ilya Maximets ; dev@dpdk.org
> Cc: nd ; tho...@monjalon.net; jer...@marvell.com;
> hemant.agra...@nxp.com; nipun.gu...@nxp.com; Honnappa Nagarahalli
> ; olivier.m...@6wind.com;
> bru
> Hi Gavin,
>
> > > >>> In weak memory models, like arm64, reading the {prod,cons}.tail
> > > >>> may get reordered after reading or writing the ring slots, which
> > > >>> corrupts the ring and stale data is observed.
> > > >>>
> > > >>> This issue was reported by NXP on 8-A72 DPAA2 board. The pr
Hi ,qi
New v4 has been commit, thanks.
> -Original Message-
> From: Zhang, Qi Z
> Sent: Friday, March 1, 2019 3:53 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: RE: [PATCH v3 1/2] net/ixgbe: promiscuous mode enable on VF
>
> HI
>
> > -Original Message---
There is need to enable promiscuous mode enable on VF,
pf host should also enable to support that.
v2:
--fix typo in commit log.
v3:
--delete unnecessary commit log infomation
--merge 2 patch into 1
--change patch headline name
--add promiscuous enable support infomation into doc
v4:
--add infor
There is need to PF host promiscuous mode enable. For ixgbe,
in order to support VF vlan promiscuous or unicast promiscuous,
we need to set PF host register PFVML2FLT of bit UPE and VPE.
It also align to ixgbe kernel code version 5.5.3. And also
it need to update to the latest API version in order
There is need to enable two ops of promiscuous_enable and
promiscuous_disable on VF.
Signed-off-by: Wei Zhao
---
doc/guides/nics/features/ixgbe_vf.ini | 1 +
doc/guides/rel_notes/release_19_05.rst | 5 +
drivers/net/ixgbe/ixgbe_ethdev.c | 20
3 files changed, 26
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, March 06, 2019 20:45
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Zhang, Tianfei ; Wei, Dan
> ; Pei, Andy ; Yang, Qiming
> ; Wang, Haiyue ; Chen,
> Santos ; Zhang, Zhang
> Subject: Re: [PATCH v1 10/11] doc: add IPN3KE document
>
> On
Oops, I missed this email somehow,
probably out of mind during my long vacation. :-)
I've also encountered this issue with 17.11.6.
http://git.dpdk.org/dpdk-stable/commit/?h=17.11&id=63f06f3fccc87c55adb33248e5c68a0175d213f1
I'll send a backport to you.
Sorry for late reply.
Yongseok
> On Feb 2
> -Original Message-
> From: Yigit, Ferruh [mailto:ferruh.yi...@linux.intel.com]
> Sent: Wednesday, March 06, 2019 20:45
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Yigit, Ferruh ; Zhang, Tianfei
> ; Wei, Dan ; Pei, Andy
> ; Yang, Qiming ; Wang,
> Haiyue ; Chen, Santos ;
> Zhang, Zhang
> Subjec
> -Original Message-
> From: Yigit, Ferruh [mailto:ferruh.yi...@linux.intel.com]
> Sent: Wednesday, March 06, 2019 20:46
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Yigit, Ferruh ; Zhang, Tianfei
> ; Wei, Dan ; Pei, Andy
> ; Yang, Qiming ; Wang,
> Haiyue ; Chen, Santos ;
> Zhang, Zhang
> Subjec
Hi,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, March 06, 2019 20:46
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Zhang, Tianfei ; Wei, Dan
> ; Pei, Andy ; Yang, Qiming
> ; Wang, Haiyue ; Chen,
> Santos ; Zhang, Zhang
> Subject: Re: [PATCH v1 11/11] MAINTAINERS: add MAINTAINERS
> -Original Message-
> From: Yigit, Ferruh [mailto:ferruh.yi...@linux.intel.com]
> Sent: Wednesday, March 06, 2019 20:46
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Yigit, Ferruh ; Zhang, Tianfei
> ; Wei, Dan ; Pei, Andy
> ; Yang, Qiming ; Wang,
> Haiyue ; Chen, Santos ;
> Zhang, Zhang
> Subjec
> On Mar 7, 2019, at 4:25 PM, olegpoly123 wrote:
>
> If the value _SC_IOV_MAX is missing, sysconf returns -1.
> In this case, iov_max is set to a default value of 1024.
>
> Cc: sta...@dpdk.org
>
> Signed-off-by: Oeg Polyakov
> ---
> drivers/net/tap/rte_eth_tap.c | 5 +
> 1 file changed,
+ Honnappa
Hi Yipeng,
Thank you for the review comments!
> On Mar 7, 2019, at 11:49 AM, Wang, Yipeng1 wrote:
>
> Thanks for this patch! Some initial comments inlined:
>
>> -Original Message-
>> From: Dharmik Thakkar [mailto:dharmik.thak...@arm.com]
>> Sent: Friday, March 1, 2019 4:24
13/02/2019 21:06, David Marchand:
> -l and -c options are two ways to select the cores used by DPDK.
> Their format differs, but the checks on the selected cores are the same.
> Use an intermediate array to separate the specific parsing checks from
> the common consistency checks.
> The parsing fun
> -Original Message-
> From: Jozwiak, TomaszX
> Sent: Thursday, March 7, 2019 12:02 PM
> To: dev@dpdk.org; Trahe, Fiona ; Jozwiak, TomaszX
>
> Subject: [PATCH v4 1/1] compress/qat: add dynamic sgl allocation
>
> This patch adds dynamic SGL allocation instead of static one.
> The number
On 3/7/2019 9:03 AM, Kovacevic, Marko wrote:
Added documentation to build helloworld example on windows using meson
and clang. Updated the maintainers list to include windows maintainers.
Signed-off-by: Anand Rawat
Signed-off-by: Pallavi Kadam
Reviewed-by: Jeff Shaw
Reviewed-by: Ranjit Menon
Set RTE_PCI_DRV_IOVA_AS_VA in drv_flags. This allows initializing qede
PMD as non-root also on Linux v4.x, where /proc/self/pagemap can't be
acccessed without CAP_SYS_ADMIN privileges.
The flag was introduced generically but not in pmds in commit:
815c7deaed2d ("pci: get IOMMU class on Linux")
C
25/02/2019 09:33, Olivier Matz:
> On Wed, Feb 20, 2019 at 04:01:33PM +, Burakov, Anatoly wrote:
> > On 19-Feb-19 8:41 PM, David Marchand wrote:
> > > Spawning the ctrl threads on anything that is not part of the eal
> > > coremask is not that polite to the rest of the system, especially
> > > w
Thanks for this patch! Some initial comments inlined:
>-Original Message-
>From: Dharmik Thakkar [mailto:dharmik.thak...@arm.com]
>Sent: Friday, March 1, 2019 4:24 PM
>To: Wang, Yipeng1 ; Gobriel, Sameh
>; Richardson, Bruce
>; De Lara Guarch, Pablo
>; Mcnamara, John
>; Kovacevic, Marko
> Added documentation to build helloworld example on windows using meson
> and clang. Updated the maintainers list to include windows maintainers.
>
> Signed-off-by: Anand Rawat
> Signed-off-by: Pallavi Kadam
> Reviewed-by: Jeff Shaw
> Reviewed-by: Ranjit Menon
> ---
> MAINTAINERS
> From: Damian Nowak
>
> This patch enables plain SHA algorithm CAVP test support in fips_validation
> sample application.
>
> Signed-off-by: Damian Nowak
> Acked-by: Fan Zhang
> ---
> examples/fips_validation/Makefile | 1 +
> examples/fips_validation/fips_validation.c |
20/02/2019 17:02, Burakov, Anatoly:
> On 19-Feb-19 8:38 PM, David Marchand wrote:
> > pthread_getaffinity_np returns a >0 value when failing.
> >
> > This is mainly for the sake of correctness.
> > The only case where it could fail is when passing an incorrect cpuset
> > size wrt to the kernel.
>
>
> - Original Message -
> From: "shahafs"
> To: "Mit Matelske"
>
> What you print here is the verbs layer, and looks OK. I am more interested on
> the values before the command reach the device.
> Can you print the values of: rx_hash_fn and rx_hash_toeplitz_key from the
> CREATE_T
> -Original Message-
> From: Anoob Joseph [mailto:ano...@marvell.com]
> Sent: Thursday, March 7, 2019 10:40 AM
> To: Akhil Goyal ; Trahe, Fiona ;
> De Lara Guarch, Pablo
>
> Cc: Anoob Joseph ; Jerin Jacob Kollanukkaran
> ; Narayana
> Prasad Raju Athreya ; Shally Verma
> ; Suheil Chan
Remove workaround in tun_aesgcm_defs.sh and trs_aesgcm_defs.sh
to get around the bug where the first inbound packet is dropped
for inline crypto.
Fixes: 929784452094 ("examples/ipsec-secgw: add scripts for functional test")
Cc: sta...@dpdk.org
Signed-off-by: Bernard Iremonger
---
examples/ipsec
Inline crypto installs a flow rule in the NIC. This flow
rule must be installed before the first inbound packet is
received.
The create_session() function installs the flow rule,
create_session() has been refactored into create_inline_session()
and create_lookaside_session(). The create_inline_ses
This patchset fixes the issue of the first inbound packet
being dropped for inline crypto.
Changes in v2:
-
The first three patches of the v1 have been squashed.
The commit message for the squashed patch has been updated.
Patches 4,5 and 6 of the v1 have been dropped from this patchs
Hi,
> I see netcope-common provides a pkg-config file, that's great.
> However it's a bit broken at the moment:
>
> Name: netcope-common
> Version: 6.3.0
> Description: Common software package for NetCOPE platform
> Libs: -L${libdir}
> Cflags: -I${includedir}
>
> There is no linker flag, and Libs.
in 18.08 new cache-aligned structure rte_crypto_asym_op was introduced.
As it also was included into rte_crypto_op, it caused implicit change
in rte_crypto_op layout and alignment: now rte_crypto_op is cahce-line
aligned has a hole of 40/104 bytes between phys_addr and sym/asym op.
It looks like un
This patch rename file test_power_acpi_cpufreq.c ->
app/test/test_power_cpufreq.c.
Signed-off-by: Lukasz Krakowiak
---
app/test/Makefile| 2 +-
app/test/meson.build | 2 +-
app/test/{test_power_acpi_cpufreq.c =>
This patch remove prefix _acpi from power UT function/test names.
Signed-off-by: Lukasz Krakowiak
---
app/test/autotest_data.py | 4 ++--
app/test/meson.build | 2 +-
app/test/test_power_cpufreq.c | 12 ++--
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/ap
This patch rename test_power_acpi_cpufreq.c to test_power_cpufreq.c,
remove prefix _acpi from UT power functions/test names,
add UT for power turbo feature.
Lukasz Krakowiak (3):
test: rename test_power_acpi_cpufreq.c ->
app/test/test_power_cpufreq.c
test: remove prefix _acpi from UT power
Add UT check_power_turbo.
Signed-off-by: Lukasz Krakowiak
---
app/test/test_power_cpufreq.c | 72 +++
1 file changed, 72 insertions(+)
diff --git a/app/test/test_power_cpufreq.c b/app/test/test_power_cpufreq.c
index d099f2f47..c75c9bf1c 100644
--- a/app/test/test
Hi,
> -Original Message-
> From: Zhang, Qi Z
> Sent: Thursday, March 07, 2019 8:11 AM
> To: David Harton (dharton) ; dev@dpdk.org; Lu, Wenzhuo
> ; Ananyev, Konstantin
> Subject: RE: [dpdk-dev] [PATCH] net/ixgbe: Restore vlan filter/extend for
> ixgbvef
>
> Hi
>
> > -Original Messag
On Thu, 2019-03-07 at 14:24 +0100, Rastislav Cernay wrote:
> From: Rastislav Cernay
>
> Note: New netcope-commong pcg on which is support for pkg-config,
> will be released soon and uploaded on official site.
>
> Added new net driver for Netcope nfb cards
>
> Signed-off-by: Rastislav Cernay
>
> -Original Message-
> From: Kevin Traynor [mailto:ktray...@redhat.com]
> Sent: Wednesday, March 6, 2019 12:31 AM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Kevin Traynor ; sta...@dpdk.org;
> Yan, Zhirun
> Subject: [PATCH 1/2] net/i40e: fix negative check on unsigned queue pairs
>
> Fix th
> -Original Message-
> From: wangyunjian [mailto:wangyunj...@huawei.com]
> Sent: Tuesday, February 26, 2019 3:22 PM
> To: Zhang, Qi Z ; dev@dpdk.org
> Cc: xudingke ; sta...@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH] net/ixgbe: fix crash when on remove
>
>
>
> > -Original Message--
To keep the top-level meson.build file as clean and clear as
possible, we move the version handling - which was originally short
but now is a lot longer - to the config/meson.build file, where the
rest of the build configuration is already being set up.
Signed-off-by: Bruce Richardson
Acked-by: L
The version number in the DPDK_VERSION file will never have an offset
that needs to be subtracted, so remove that logic from the version
string generation.
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
V2: No changes - added Luca's ack
---
lib/librte_eal/common/include/rte_version
Since we have the version number in a separate file at the root level,
we should not need to duplicate this in rte_version.h too. Best
approach here is to move the macros for specifying the year/month/etc.
parts from the version header file to the build config file - leaving
the other utility macro
Add a new file DPDK_VERSION to hold the current DPDK version number.
Have meson use this file for it's project version, and have make use
it for reporting out "showversion" and "showversionum".
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
v2: fix typos and include Luca's ack.
---
Right now with DPDK we have two sources of version information - the
rte_version.h header file containing macros for C use, and the project
version number in the project definition in meson.build. This is not
optimal, so this patchset aims to provide a single source for the DPDK
version. The option
From: Rastislav Cernay
Note: New netcope-commong pcg on which is support for pkg-config,
will be released soon and uploaded on official site.
Added new net driver for Netcope nfb cards
Signed-off-by: Rastislav Cernay
---
v2: remove unnecessary cast
remove unnecessary zeroing
move decla
On Thu, Mar 07, 2019 at 01:42:36PM +0100, David Marchand wrote:
>On Thu, Mar 7, 2019 at 1:37 PM David Marchand
><[1]david.march...@redhat.com> wrote:
>
>On Thu, Mar 7, 2019 at 12:55 PM Bruce Richardson
><[2]bruce.richard...@intel.com> wrote:
>
> Since we have the version numb
Hi
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of David Harton
> Sent: Wednesday, March 6, 2019 11:24 PM
> To: dev@dpdk.org; Lu, Wenzhuo ; Ananyev, Konstantin
>
> Cc: David Harton
> Subject: [dpdk-dev] [PATCH] net/ixgbe: Restore vlan filter/extend for ixgbvef
On Thu, Mar 07, 2019 at 01:37:08PM +0100, David Marchand wrote:
>On Thu, Mar 7, 2019 at 12:55 PM Bruce Richardson
><[1]bruce.richard...@intel.com> wrote:
>
> Since we have the version number in a separate file at the root
> level,
> we should not need to duplicate this in rt
1. clean flow entry's action structure after remove it.
2. initialized priority when add a new flow entry
3. remove RSS configuration before deleting the flow profile.
Fixes: aa1cd410fa64 ("net/ice/base: add flow module")
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Signed-o
Revert the workaround for allocating TCAM and FV entries to align
with latest firmware.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c| 11 +-
drivers/net/ice/base/ice_common.h| 2 +-
drivers/net/ice/base/ic
OS package's format is changed, field vector's protocol offset size is
changed from 8 bit to 16 bit. So base code also need to align to this, or
PMD will not be able to load OS package correctly.
Signed-off-by: Qi Zhang
Signed-off-by: Paul M Stillwell Jr
---
drivers/net/ice/base/ice_flex_type.h
This patch ensure that TCAM allocations made by a newly added VSIG
that has the same characteristic list of an existing VSIG are removed.
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Signed-off-by: Vignesh Sridhar
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
1. Add call to replay RSS configurations
2. Add RSS configurations to end of list and not the head to avoid
inversion on replay.
Signed-off-by: Vignesh Sridhar
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 5 -
drivers/net/ice/base/ice_
Add module to support DCB related features.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/Makefile |1 +
drivers/net/ice/base/ice_adminq_cmd.h | 243 ++
drivers/net/ice/base/ice_common.c | 12 +
drivers/net/ice/base/ice_dcb.c|
Improved the profile reference counting, by moving it from being
based on how many TCAM entries using the profile to how many
profile map entries are using the profile.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flex_pipe.c
Add flow director related support base code.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/Makefile | 1 +
drivers/net/ice/base/ice_adminq_cmd.h | 13 +
drivers/net/ice/base/ice_common.c | 36 ++
drivers/net/ice/base/ice_common.h | 1 +
Code added to check the FW recovery mode. This function will be
used by the drivers during init to check whether the FW is in
recovery mode or not. If FW is in recovery mode then the drivers
need to run in a recovery mode where it can allow only limited
operations. Link should be down, allow only c
strcat does not check the destination length and there might be
chances of string overflow so instead of strcat, strlcat is used.
Fixes: 6f4eec2565 ("test/crypto: enhance scheduler unit tests")
Fixes: 540a211084 ("bnx2x: driver core")
Fixes: e163c18a15 ("net/i40e: update ptype and pctype info")
Cc
If there is no queue to disable, return appropriate configuration error
earlier without acquiring the lock.
Signed-off-by: Akeem G Abodunrin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 17 ++---
1 file changed, 10 insertions(+)
1. Fix some problems with filling the HW tables.
2. Fix a logic error in ice_rem_prof_from_list.
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flex_pipe.c | 18 +++---
1 fil
Update copyright time to 2019.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h| 2 +-
drivers/net/ice/base/ice_alloc.h | 2 +-
drivers/net/ice/base/ice_common.c| 2 +-
drivers/net/ice/base/ice_common.h| 2 +-
drive
Klocwork points out some code is unreachable in
ice_get_itr_intrl_gran and ice_ptg_find_ptype.
The patch removed the unreachable code and resolved the static
analysis reported issues.
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Fixes: 453d087ccaff ("net/ice/base: add common
If allocating a VSI to a VSIG fails the local allocations made for VSIG
profiles and change-lists will not be removed. Adding calls to free these
entries on error in VSIG management calls.
Signed-off-by: Vignesh Sridhar
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net
Profile TCAM entry removal is handled by the firmware when
freeing the resource, so the driver does not need to write these
default entries back with an update Package action.
This patch removes writing of the TCAM entry using Update Package
command when removing it, since the entry has already be
Add define for 52 byte RSS hash key size, and add struct
ice_aqc_get_set_rss_keys comments regarding setting 40 bytes and
52 byte hash key.
Signed-off-by: Paul Greenwalt
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 13 +
1 f
Change below function as static and also relocated code line
to align with kernel driver.
ice_aq_move_sched_elems
ice_sched_get_agg_node
ice_sched_set_node_bw_lmt
ice_sched_cfg_node_bw_alloc
ice_sched_add_agg_cfg
ice_sched_rm_agg_cfg
ice_sched_move_vsi_to_agg
ice_sched_del_rl_profile
ice_sched_rm_
In the ice_aq_set_phy_cfg AQ command, the 16.4 bit is reserved.
This patch will make sure that this bit will never be set to 1.
Signed-off-by: Chinh T Cao
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 1 +
drivers/net/ice/base/ice_common
Extend the functionality of the admin queue command by including
additional status and ID bits to improve link topology configuration.
Signed-off-by: Matthew Vick
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 7 ++-
1 file changed, 6
The patch added to retrieve the queue context and update the queue
handle for lan queues.
Signed-off-by: Victor Raj
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 60 ---
drivers/net/ice/base/ice_common.h |
1. ICE_SW_LKUP_LAST need to be handled correctly in
ice_aq_alloc_free_vsi_list and ice_update_vsi_list_rule
2. ICE_SW_LKUP_ETHERTYPE_MAC need to be handled correctly in
ice_update_vsi_lkup_fltr
3. free package segment pointer during ice_deinit_hw
Fixes: c7dd15931183 ("net/ice/base: add virtual swi
Update macros for metadata and package flags.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c| 36 -
drivers/net/ice/base/ice_flow.h | 17 ++--
drivers/net/ice/base/ice_lan_tx_rx.h | 77 +++
1. ice_rem_all_sw_rules_info - remove all switch rules.
2. ice_reply_all_fltr - replay all filters stored in book keeping list.
These APIs will be used when switch rule feature is enabled.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 107 ++
1. ice_alloc_res_cntr - allocate resource counter
2. ice_free_res_cntr - free resource counter
3. ice_alloc_vlan_res_counter - allocate vlan resource counter
4. ice_free_vlan_res_counter - free vlan resource counter
These APIs will be used when try to count the number of a flow be
hitted.
Signed-
1. ice_get_vsi_promisc - get promiscuous mode of give VSI.
2. ice_get_vsi_vlan_promisc - get VLAN promiscuous mode of given VSI.
PMD may use these APIs to check the real HW status, but not rely on
a software flag when something abnormal.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
1. ice_add_mac_with_sw_marker - add filter with software marker.
2. ice_add_mac_with_counter - add filter with counter enabled.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 328 ++
drivers/net/ice/base/ice
1. ice_aq_get_res_alloc - get allocated resources.
2. ice_aq_get_res_descs - get allocated resource descriptors.
These APIs may help to PMD to enable some debug utilities to
dump the resource allocation status.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base
Remove static of below functions and declare them as external
APIs.
ice_aq_add_vsi
ice_aq_free_vsi
ice_aq_update_vsi
ice_aq_add_lan_txq
ice_init_pkg
So far the purpose is just to sync with kernel driver.
They are reserved for future use.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhan
Add API ice_remove_eth_mac and ice_add_eth_mac to support
adding / removing ethertype (or MAC) based filter rules.
PMD driver can use these APIs to enable related rte_flow rule.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 57 ++
Add below APIs in switch module
1. ice_aq_get_vsi_params - get VSI context info
2. ice_aq_add_update_mir_rule - add/update mirror rule
3. ice_aq_delete_mir_rule - delete mirror rule
4. ice_aq_set_storm_ctrl - set storm control configuration
5. ice_aq_get_storm_ctrl - get storm control configurati
For components that make a copy of an external pipeline package file (i.e.
the Linux and FreeBSD drivers), save the size of the package file along
with the copy so that both can be used when calling ice_init_pkg() after a
CORER/GLOBR reset. Also, do not free the copy of the package file in
ice_ini
Remove unnecessary macro and data structure.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 2 -
drivers/net/ice/base/ice_flex_pipe.c | 2 -
drivers/net/ice/base/ice_flow.c | 136 --
drivers/net/i
1. Add macro ice_for_each_traffic_class to loop for each
traffic class.
2. Add macro MIN_T to wrap min with type conversion.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 2 +-
drivers/net/ice/base/ice_nvm.c| 7 ---
drivers/net/ice/
Added code to allocate VSI queue contexts to save the queue specific
information like bandwidth etc.
Signed-off-by: Victor Raj
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_sched.c | 52 +++
drivers/net/ice/base/ice
1 - 100 of 149 matches
Mail list logo
