Hi Marko,
Thanks for reviewing.
I will update the below links and also replace tab with 8 spaces for the code
blocks.
Regards
Abhinandan
> -Original Message-
> From: Kovacevic, Marko
> Sent: Wednesday, April 25, 2018 4:02 PM
> To: Gujjar, Abhinandan S ;
> jerin.ja...@caviumnetworks.com;
Hi all
From: Ferruh Yigit, Thursday, April 19, 2018 2:08 PM
> > But rte_eth_dev_release_port() is still broken because of this change,
> > please check _rte_eth_dev_callback_process() which uses dev->data-
> >port_id.
The issue is that a DESTROY callback gets port_id=0 all the time, regardless
t
On 24/04/2018 8:37 PM, Thomas Monjalon wrote:
16/04/2018 15:06, Declan Doherty:
Add new device flag to specify that an ethdev port is a port representor.
Extend rte_eth_dev_info structure to expose device flags to the user which
enables applications to discover if a port is a representor port.
Hi Ferruh,
I started working on a patch.
No need for your test example.
> -Original Message-
> From: Ophir Munk
> Sent: Wednesday, April 25, 2018 3:00 PM
> To: 'Ferruh Yigit' ; Pascal Mazon
>
> Cc: dev@dpdk.org; Mordechay Haimovsky ; Olga
> Shern ; Thomas Monjalon ;
> Raslan Darawsheh ; S
25/04/2018 14:17, Doherty, Declan:
> On 24/04/2018 8:37 PM, Thomas Monjalon wrote:
> > I think dev_capa and dev_flags are the same thing.
> > They could be merged.
>
> Do you have a preference for which one to keep, as dev_flags within
> rte_eth_dev_data is widely used by PMDs and passing this sam
As has been suggested [1], all DPDK runtime paths should be put
into a single place. This patchset accomplishes exactly that.
If running as root, all files will be put under /var/run/dpdk/,
otherwise they will be put under $XDG_RUNTIME_PATH/dpdk/, or, if
that environment variable is not defined, a
The original name for this path was not too descriptive and
confusing. Rename it to a more appropriate and descriptive name:
it stores data about hugepages, so name it eal_hugepage_data_path().
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/eal_filesystem.h | 2 +-
lib/librte_eal/li
Fix all calls to functions in eal_filesystem to produce paths
residing inside dedicated DPDK runtime directory.
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/bsdapp/eal/eal.c| 2 +
lib/librte_eal/common/eal_filesystem.h | 71 +-
lib/librte_eal/linuxap
The define was a leftover from IVSHMEM library.
Fixes: c711ccb30987 ("ivshmem: remove library and its EAL integration")
Cc: david.march...@6wind.com
Cc: sta...@dpdk.org
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/eal_filesystem.h | 2 --
1 file changed, 2 deletions(-)
diff --git a
Currently, during runtime, DPDK will store a bunch of files here
and there (in /var/run, /tmp or in $HOME). Fix it by creating a
DPDK-specific runtime directory, under which all runtime data
will be placed. The template for creating this runtime directory
is the following:
/dpdk//
Where is set
Hi
I vote for 2.3.
Ori
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Matan Azrad
> Sent: Wednesday, April 25, 2018 3:16 PM
> To: Ferruh Yigit ; Thomas Monjalon
> ; Gaetan Rivet ; Jingjing
> Wu
> Cc: dev@dpdk.org; Neil Horman ; Bruce
> Richardson ; Konstanti
Hi Abhinandan,
On 4/24/2018 6:13 PM, Abhinandan Gujjar wrote:
Signed-off-by: Abhinandan Gujjar
Signed-off-by: Nikhil Rao
Signed-off-by: Gage Eads
---
lib/librte_eventdev/rte_event_crypto_adapter.h | 532 +
1 file changed, 532 insertions(+)
create mode 100644 lib/librt
+CC Thomas, would you take this one asap it fixes a build warning with
Meson/GCC 5.4 on Ubuntu with fortified headers.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Van Haaren, Harry
> Sent: Monday, April 23, 2018 3:21 PM
> To: Pavan Nikhilesh
> Cc: dev@dpd
On 4/25/2018 1:16 PM, Matan Azrad wrote:
> Hi all
>
> From: Ferruh Yigit, Thursday, April 19, 2018 2:08 PM
>>> But rte_eth_dev_release_port() is still broken because of this change,
>>> please check _rte_eth_dev_callback_process() which uses dev->data-
>>> port_id.
>
> The issue is that a DESTROY
> > This commit removes the experimental tags from the
> > service cores functions, they now become part of the
> > main DPDK API/ABI.
> >
> > Signed-off-by: Harry van Haaren
>
> Acked-by: Jerin Jacob
Acked-by: Thomas Monjalon
Applied, congratulations!
Signed-off-by: Hemant Agrawal
---
doc/guides/cryptodevs/dpaa_sec.rst | 13 +
doc/guides/nics/dpaa.rst | 10
drivers/bus/dpaa/dpaa_bus.c| 101 ++---
drivers/bus/dpaa/rte_dpaa_bus.h| 2 -
4 files changed, 106 insertions(+), 20 delet
Signed-off-by: Hemant Agrawal
---
doc/guides/cryptodevs/dpaa2_sec.rst | 11
doc/guides/nics/dpaa2.rst | 11
drivers/bus/fslmc/fslmc_bus.c | 107
drivers/bus/fslmc/rte_fslmc.h | 4 ++
4 files changed, 122 insertions(+), 11 de
Some of the applications are expecting that if n is 0, it shall
return the supported number of stats. e.g. VPP
Fixes: b21ed3e2a16d ("net/dpaa: support extended statistics")
Cc: sta...@dpdk.org
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa/dpaa_ethdev.c | 6 +++---
1 file changed, 3 inserti
Signed-off-by: Hemant Agrawal
---
drivers/bus/fslmc/fslmc_bus.c| 4 ++--
drivers/bus/fslmc/fslmc_vfio.c | 7 ++-
drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 1 -
drivers/net/dpaa2/dpaa2_ethdev.c | 2 +-
4 files changed, 5 insertions(+), 9 deletions(-)
diff --git
Signed-off-by: Hemant Agrawal
---
drivers/bus/dpaa/base/fman/fman.c | 2 +-
drivers/bus/dpaa/dpaa_bus.c | 16 +---
drivers/bus/dpaa/rte_dpaa_logs.h | 11 ++-
3 files changed, 12 insertions(+), 17 deletions(-)
diff --git a/drivers/bus/dpaa/base/fman/fman.c
b/drivers/b
The options --server-socket-path and --client-socket-path
were said to be deprecated and will be removed soon.
No need to wait for removing application options which have
no effect, and can confuse the user.
Fixes: 660098d61f57 ("pdump: use generic multi-process channel")
Cc: jianfeng@intel.co
>
> On Mon, Apr 23, 2018 at 11:53:04AM +, Ananyev, Konstantin wrote:
> [...]
> > > @@ -693,9 +711,14 @@ rte_mbuf_to_baddr(struct rte_mbuf *md)
> > > #define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF)
> > >
> > > /**
> > > + * Returns TRUE if given mbuf has external buffer
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, April 24, 2018 11:19 AM
> To: dev@dpdk.org
> Cc: Pattan, Reshma ; Burakov, Anatoly
>
> Subject: [PATCH v3 1/3] mem: fix 32-bit memory upper limit for non-legacy
> mode
>
> 32-bit mode has an upper limit on amount of VA space
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, April 24, 2018 11:19 AM
> To: dev@dpdk.org
> Cc: Pattan, Reshma
> Subject: [PATCH v3 2/3] mem: improve memory preallocation on 32-bit
>
> Previously, if we couldn't preallocate VA space on 32-bit for one page size,
> we
> s
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, April 24, 2018 11:19 AM
> To: dev@dpdk.org
> Cc: Pattan, Reshma
> Subject: [PATCH v3 3/3] mem: improve autodetection of hugepage counts on
> 32-bit
>
> For non-legacy mode, we are preallocating space for hugepages, so we kno
>
> This patch introduces a new way of attaching an external buffer to a mbuf.
>
> Attaching an external buffer is quite similar to mbuf indirection in
> replacing buffer addresses and length of a mbuf, but a few differences:
> - When an indirect mbuf is attached, refcnt of the direct mbuf wou
On 4/24/2018 11:00 PM, Thomas Monjalon wrote:
> Hi,
>
> First, this is my summary after the survey answers and comments:
>
> 1/ allow "forgetting" port offloads in queue offloads setup
>
> 2/ update documentation, applications and remove checks in PMDs for 18.05-rc2
>
> 3/ an offload enabled at
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, April 25, 2018 8:04 PM
> To: Zhang, Qi Z ; adrien.mazarg...@6wind.com
> Cc: tho...@monjalon.net; dev@dpdk.org
> Subject: Re: [PATCH v2] app/testpmd: fix testpmd failure due to RSS offload
> check
>
> On 4/25/2018 8:43 AM, Qi Z
After add RSS hash offload check, default rss_hf will fail on
devices that not support all bits, the patch take rss_hf as
a suggest value and only set bits that device supported base on
rte_eth_dev_get_info, also rss_hf will only be updated when new
rss offload is successfully updated on all ports
When heap initializes, we need to add already allocated segments
onto the heap. However, in doing that, we never increased total
heap size. Fix it by adding segment length to total heap length
when initializing the heap.
Fixes: 66cc45e293ed ("mem: replace memseg with memseg lists")
Cc: anatoly.bur
I could get only 18.02 tag, which is from February.
I want to see exactly which commits are in 18.02.1 and there is no such a
git tag
or github release etc.
Downloading 18.02.1 tarball without git history and comparing sources to
git tree seems quite stupid.
Also the question is why there is no suc
The purpose of this patch series is to cleanup the library code
from paths that end up aborting the process,
and move to checking error values, in order to allow the running process
perform an orderly teardown or other mitigation of the event.
This patch modifies the majority of rte_panic calls
un
replace panic calls with log and return value.
Signed-off-by: Arnon Warshavsky
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 8 +---
drivers/crypto/dpaa_sec/dpaa_sec.c | 10 ++
2 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/dpaa
replace panic calls with log and return value.
Local function to this file,
changing from void to int is non-abi-breaking
Signed-off-by: Arnon Warshavsky
---
drivers/net/ixgbe/ixgbe_ethdev.c | 6 --
drivers/net/ixgbe/ixgbe_ethdev.h | 2 +-
drivers/net/ixgbe/ixgbe_pf.c | 15 ++--
Replace panic calls with log and return value.
Local functions to this file,
changing from void to int are non-abi-breaking
Signed-off-by: Arnon Warshavsky
---
drivers/net/bonding/rte_eth_bond_8023ad.c | 29 ++-
drivers/net/bonding/rte_eth_bond_8023ad_private.h | 2 +
replace panic calls with log and return value.
Local function to this file,
changing from void to int is non-abi-breaking
Signed-off-by: Arnon Warshavsky
---
drivers/net/e1000/e1000_ethdev.h | 2 +-
drivers/net/e1000/igb_ethdev.c | 4 +++-
drivers/net/e1000/igb_pf.c | 15 +-
replace panic calls with log and return value.
Signed-off-by: Arnon Warshavsky
---
lib/librte_eventdev/rte_eventdev_pmd_pci.h | 8 +---
lib/librte_eventdev/rte_eventdev_pmd_vdev.h | 8 +---
2 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/lib/librte_eventdev/rte_eventdev_
replace panic calls with log and return value.
Local function to this file,
changing from void to int is non-abi-breaking
Signed-off-by: Arnon Warshavsky
---
lib/librte_kni/rte_kni.c | 18 --
lib/librte_kni/rte_kni_fifo.h | 11 ---
2 files changed, 20 insertions(+),
replace panic calls with log and return value.
Signed-off-by: Arnon Warshavsky
---
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 37 +
1 file changed, 26 insertions(+), 11 deletions(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_hugepage_info.c
b/lib/librte_eal/lin
Change some local functions return type from void to int.
This change does not break ABI as the functions are internal.
Panic thrown from threads was not handled in this patch
Signed-off-by: Arnon Warshavsky
---
lib/librte_eal/bsdapp/eal/eal.c | 69 +++---
lib/librte_eal/l
Local function to this file,
changing from void to int is non-abi-breaking
Signed-off-by: Arnon Warshavsky
---
lib/librte_ether/rte_ethdev.c | 42 ++
lib/librte_ether/rte_ethdev.h | 4 +++-
2 files changed, 33 insertions(+), 13 deletions(-)
diff --git a/
This patch adds a new function that is called
per every checked patch,
and alerts for new instances of rte_panic/rte_exit.
The check excludes comments, and alerts in the case
of a positive balance between additions and removals.
Signed-off-by: Arnon Warshavsky
---
devtools/checkpatches.sh | 95 +
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Andrii
> Sent: Wednesday, April 25, 2018 2:45 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] how can I get a git version of Latest Major release?
> (18.02.1)
>
> I could get only 18.02 tag, which is from February.
> I want to see exactly which co
On 25-Apr-18 2:45 PM, Arnon Warshavsky wrote:
replace panic calls with log and return value.
Signed-off-by: Arnon Warshavsky
---
I think i've already acked this. You should keep acks etc. between
versions (unless you're making significant enough changes that you think
would invalidate a pri
On 25-Apr-18 2:45 PM, Arnon Warshavsky wrote:
Change some local functions return type from void to int.
This change does not break ABI as the functions are internal.
Panic thrown from threads was not handled in this patch
Signed-off-by: Arnon Warshavsky
---
<...>
retval = fcntl(mem_
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
> Sent: Tuesday, April 24, 2018 11:59 PM
> To: Yigit, Ferruh ; Zhang, Qi Z
> Cc: dev@dpdk.org; Doherty, Declan ; Chandran,
> Sugesh ; Glynn, Michael J
> ; Liu, Yu Y ; Ananyev,
> Konstantin ; Richardson, Bruce
A .svg extension was added instead of .* which caused
the pdf docs to not build this change fixes that.
Fixes: a5e1231f099b ("net/szedata2: do not affect Ethernet interfaces")
Cc: v...@cesnet.cz
Signed-off-by: Marko Kovacevic
---
doc/guides/nics/szedata2.rst | 2 +-
1 file changed, 1 insertion(
Hi Ferruh
From: Ferruh Yigit, Wednesday, April 25, 2018 3:54 PM
> On 4/25/2018 1:16 PM, Matan Azrad wrote:
> > Hi all
> >
> > From: Ferruh Yigit, Thursday, April 19, 2018 2:08 PM
> >>> But rte_eth_dev_release_port() is still broken because of this
> >>> change, please check _rte_eth_dev_callback
Nice.
Thanks Harry.
Yep I got 18.02.1 from dpdk-stable
Is that possible to have tags like v18.02.1 in http://dpdk.org/git/dpdk
Because the only one I can get from it is v18.02
That would be great also if dpdk.org would provide some link to dpdk-stable
Because now it points only to http://dpdk.o
> I think i've already acked this. You should keep acks etc. between
> versions (unless you're making significant enough changes that you think
> would invalidate a prior ack). Having acks makes it easier to track what
> still needs to be reviewed and what is good to go, and it makes it easier
> to
On 4/25/2018 2:38 PM, Qi Zhang wrote:
> After add RSS hash offload check, default rss_hf will fail on
> devices that not support all bits, the patch take rss_hf as
> a suggest value and only set bits that device supported base on
> rte_eth_dev_get_info, also rss_hf will only be updated when new
>
Add APIs to read information from the DPDK applictions.
It can be used to dump the EEPROM of plugin modules (SFP+, QSFP, etc.).
Two APIs are introduced to access eeprom:
- rte_eth_dev_get_module_info
- rte_eth_dev_get_module_eeprom
Applications based on DPDK can dump eeprom by calling those two A
Add a new command "module-eeprom" to get the data of plugin
module EEPROM.
Signed-off-by: Zijie Pan
Acked-by: Remy Horton
---
Cc: remy.hor...@intel.com
Cc: or...@mellanox.com
Cc: bruce.richard...@intel.com
Cc: pablo.de.lara.gua...@intel.com
Cc: radu.nico...@intel.com
Cc: akhil.go...@nxp.com
Cc:
add new APIs:
- rte_eth_dev_get_module_info
- rte_eth_dev_get_module_eeprom
Signed-off-by: Zijie Pan
Acked-by: Remy Horton
Acked-by: Thomas Monjalon
---
Cc: remy.hor...@intel.com
Cc: john.mcnam...@intel.com
Cc: marko.kovace...@intel.com
Cc: tho...@monjalon.net
doc/guides/nics/features.rst
Add new callbacks for eth_dev_ops of ixgbe to get the information
and data of plugin module eeprom.
Signed-off-by: Zijie Pan
Acked-by: Remy Horton
---
Cc: remy.hor...@intel.com
Cc: wenzhuo...@intel.com
Cc: konstantin.anan...@intel.com
doc/guides/nics/features/ixgbe.ini |1 +
doc/guides
Add new callbacks for eth_dev_ops of e1000 to get the information and
data of plugin module EEPROM.
Signed-off-by: Zijie Pan
Acked-by: Remy Horton
---
Cc: wenzhuo...@intel.com
doc/guides/nics/features/igb.ini |1 +
drivers/net/e1000/base/e1000_phy.h |8
drivers/net/e1000/igb_eth
Add new callbacks for eth_dev_ops of i40e to get the information
and data of plugin module eeprom.
Signed-off-by: Zijie Pan
Acked-by: Remy Horton
---
Cc: beilei.x...@intel.com
Cc: qi.z.zh...@intel.com
doc/guides/nics/features/i40e.ini |1 +
doc/guides/nics/features/i40e_vec.ini |1
Previously, reserving IOVA-contiguous memzones with zero
size (which would reserve biggest available memzone) was
not allowed. Now that we can have biggest IOVA-contiguous
malloc element statistic exposed through a malloc stats
call, this now becomes possible.
Signed-off-by: Anatoly Burakov
---
User might be interested to find out what is the biggest chunk of
IOVA-contiguous free space that can be allocated from malloc. Add
relevant malloc-internal functions and expose this through malloc
stats calculation call.
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/include/rte_mallo
On 4/24/2018 6:13 PM, Abhinandan Gujjar wrote:
Signed-off-by: Abhinandan Gujjar
Signed-off-by: Nikhil Rao
Signed-off-by: Gage Eads
---
[snip..]
+int __rte_experimental
+rte_event_crypto_adapter_start(uint8_t id)
+{
+ struct rte_event_crypto_adapter *adapter;
+
+ RTE_EVENT_CRYPTO
On 25-Apr-18 3:02 PM, Arnon Warshavsky wrote:
I think i've already acked this. You should keep acks etc. between
versions (unless you're making significant enough changes that you
think would invalidate a prior ack). Having acks makes it easier to
track what still needs to be rev
A per port per queue log is too verbose with multiple port/queue log is
longer than full screen, make it less verbose:
- Reduced log to only first queue of the port, as a sample
- Merged a few lines
- Indent queue logs for readability
The log becomes as following after update:
testpmd> start tx_f
On 4/25/2018 3:02 PM, Zijie Pan wrote:
> Add APIs to read information from the DPDK applictions.
> It can be used to dump the EEPROM of plugin modules (SFP+, QSFP, etc.).
>
> Two APIs are introduced to access eeprom:
> - rte_eth_dev_get_module_info
> - rte_eth_dev_get_module_eeprom
>
> Applicatio
Thanks for the feedback on the patch set Pablo,
V4 in progress.
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Tuesday, April 24, 2018 12:07 PM
> To: Daly, Lee ; dev@dpdk.org
> Cc: Tucker, Greg B ; Jain, Deepak K
> ; Trahe, Fiona
> Subject: RE: [PATCH v3 10/11] compress/isal:
25/04/2018 15:59, Marko Kovacevic:
> A .svg extension was added instead of .* which caused
> the pdf docs to not build this change fixes that.
>
> Fixes: a5e1231f099b ("net/szedata2: do not affect Ethernet interfaces")
> Cc: v...@cesnet.cz
>
> Signed-off-by: Marko Kovacevic
Applied, thanks
new
On 4/25/2018 3:24 PM, Ferruh Yigit wrote:
> On 4/25/2018 3:02 PM, Zijie Pan wrote:
>> Add APIs to read information from the DPDK applictions.
>> It can be used to dump the EEPROM of plugin modules (SFP+, QSFP, etc.).
>>
>> Two APIs are introduced to access eeprom:
>> - rte_eth_dev_get_module_info
>
On 25-Apr-18 3:10 PM, Anatoly Burakov wrote:
User might be interested to find out what is the biggest chunk of
IOVA-contiguous free space that can be allocated from malloc. Add
relevant malloc-internal functions and expose this through malloc
stats calculation call.
Signed-off-by: Anatoly Burako
Hi Abhinandan,
On 4/24/2018 6:13 PM, Abhinandan Gujjar wrote:
Signed-off-by: Abhinandan Gujjar
---
test/test/Makefile| 1 +
test/test/test_event_crypto_adapter.c | 915 ++
2 files changed, 916 insertions(+)
create mode 100644 test/test/test
Hi,
25/04/2018 16:02, Andrii:
> Nice.
>
> Thanks Harry.
>
> Yep I got 18.02.1 from dpdk-stable
>
> Is that possible to have tags like v18.02.1 in http://dpdk.org/git/dpdk
> Because the only one I can get from it is v18.02
No, the main repo is not managing stable branches.
You will have backpo
On 04/25/2018 02:34 AM, Yongseok Koh wrote:
On Tue, Apr 24, 2018 at 09:15:38PM +0200, Olivier Matz wrote:
On Tue, Apr 24, 2018 at 09:21:00PM +0300, Andrew Rybchenko wrote:
On 04/24/2018 07:02 PM, Olivier Matz wrote:
+ m->ol_flags |= EXT_ATTACHED_MBUF;
+ m->shinfo = shinfo;
+
+
On 4/25/2018 3:02 PM, Andrii wrote:
> Nice.
>
> Thanks Harry.
>
> Yep I got 18.02.1 from dpdk-stable
>
> Is that possible to have tags like v18.02.1 in http://dpdk.org/git/dpdk
> Because the only one I can get from it is v18.02
It is not possible to create a tag in dpdk.org/git/dpdk for stable
25/04/2018 14:54, Van Haaren, Harry:
>
> +CC Thomas, would you take this one asap it fixes a build warning with
> Meson/GCC 5.4 on Ubuntu with fortified headers.
>
> > > Bugzilla-ID: 28
> > > Fixes: f874c1eb1519 ("event/octeontx: create and free timer adapter")
> > >
> > > Reported-by: Harry van
On Wed, 25 Apr 2018 11:38:21 +0200
Thomas Monjalon wrote:
> 25/04/2018 05:17, Stephen Hemminger:
> > --- a/lib/librte_eal/rte_eal_version.map
> > +++ b/lib/librte_eal/rte_eal_version.map
> > @@ -209,6 +209,13 @@ DPDK_18.02 {
> >
> > } DPDK_17.11;
> >
> > +DPDK_18.05 {
> > + global:
> > +
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Wednesday, April 25, 2018 3:56 PM
> To: Pavan Nikhilesh
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: Re: [dpdk-dev] [PATCH] event/octeontx: fix snprintf mempool name
> overflow
>
> 25/04/2018 14:54, Van Haaren, Harry:
> >
> > +CC T
On 4/25/2018 12:59 PM, Xiao Wang wrote:
> Live migration feature will be based on future development on ifc driver,
> including port representor implementation and potential change in QEMU
> and vhost user lib.
>
> This patch removes live migration in ifcvf driver, if possible we could
> squash th
On Tue, 24 Apr 2018 22:22:45 +0200
Thomas Monjalon wrote:
> > >
> > > I guess the problem that it changes INDIRECT semantics since EXTBUF
> > > is added as well. I think strictly speaking it is an API change.
> > > Is it OK to make it without announcement?
> >
> > In any case, there will be a
25/04/2018 15:32, Ferruh Yigit:
> On 4/24/2018 11:00 PM, Thomas Monjalon wrote:
> > Hi,
> >
> > First, this is my summary after the survey answers and comments:
> >
> > 1/ allow "forgetting" port offloads in queue offloads setup
> >
> > 2/ update documentation, applications and remove checks in
These enable more precise reporting of objects responsible for errors.
This breaks ABI compatibility for the following public functions:
- rte_flow_create()
- rte_flow_destroy()
- rte_flow_error_set()
- rte_flow_flush()
- rte_flow_isolate()
- rte_flow_query()
- rte_flow_validate()
Signed-off-by:
As summarized in a prior RFC [1], the flow API (rte_flow) was chosen as a
means to manage switch offloads supported by many devices (usually going by
names such as E-Switch or vSwitch) through user-specified flow rules.
Combined with the need to support encap/decap actions, this requires a
change
Although pattern items and actions examples end with "and so on", these
lists include all existing definitions and as a result are updated almost
every time new types are added. This is cumbersome and pointless.
This patch also synchronizes Doxygen and external API documentation wording
with a sli
This section has become less relevant since the flow API (rte_flow) is now
a mature DPDK API with applications developed directly on top of it instead
of an afterthought.
This patch removes it for the following reasons:
- It has never been updated to track the latest changes in the legacy
filte
This patch makes the following changes to flow rule actions:
- List order now matters, they are redefined as performed first to last
instead of "all simultaneously".
- Repeated actions are now supported (e.g. specifying QUEUE multiple times
now duplicates traffic among them). Previously only
This patch replaces C99-style flexible arrays in struct rte_flow_action_rss
and struct rte_flow_item_raw with standard pointers to the same data.
They proved difficult to use in the field (e.g. no possibility of static
initialization) and unsuitable for C++ applications.
Affected PMDs and example
Upcoming changes in relation to the handling of actions list will make the
DUP action redundant as specifying several QUEUE actions will achieve the
same behavior. Besides, no PMD implements this action.
By removing an entry from enum rte_flow_action_type, this patch breaks ABI
compatibility for t
Since its inception, the rte_flow RSS action has been relying in part on
external struct rte_eth_rss_conf for compatibility with the legacy RSS API.
This structure lacks parameters such as the hash algorithm to use, and more
recently, a method to tell which layer RSS should be performed on [1].
Gi
By definition, RSS involves some kind of hash algorithm, usually Toeplitz.
Until now it could not be modified on a flow rule basis and PMDs had to
always assume RTE_ETH_HASH_FUNCTION_DEFAULT, which remains the default
behavior when unspecified (0).
This breaks ABI compatibility for the following
RSS hash types (ETH_RSS_* macros defined in rte_ethdev.h) describe the
protocol header fields of a packet that must be taken into account while
computing RSS.
When facing encapsulated (e.g. tunneled) packets, there is an ambiguity as
to whether these should apply to inner or outer packets. Applica
TPID handling in rte_flow VLAN and E_TAG pattern item definitions is not
consistent with the normal stacking order of pattern items, which is
confusing to applications.
Problem is that when followed by one of these layers, the EtherType field
of the preceding layer keeps its "inner" definition, an
VLAN TCI is a 16-bit field broken down as PCP (3b), DEI (1b) and VID (12b).
The default mask used by PMDs for the VLAN pattern when one isn't provided
by the application comprises the entire TCI, which is problematic because
most devices only support VID matching.
This forces applications to alwa
This new attribute enables applications to create flow rules that do not
simply match traffic whose origin is specified in the pattern (e.g. some
non-default physical port or VF), but actively affect it by applying the
flow rule at the lowest possible level in the underlying device.
It breaks ABI
Contrary to all other pattern items, these are inconsistently documented as
affecting traffic instead of simply matching its origin, without provision
for the latter.
This commit clarifies documentation and updates PMDs since the original
behavior now has to be explicitly requested using the new t
While RTE_FLOW_ITEM_TYPE_PORT refers to physical ports of the underlying
device using specific identifiers, these are often confused with DPDK port
IDs exposed to applications in the global name space.
Since this pattern item is seldom used, rename it RTE_FLOW_ITEM_PHY_PORT
for better clarity.
No
This patch adds the missing action counterpart to the PHY_PORT pattern
item, that is, the ability to directly inject matching traffic into a
physical port of the underlying device.
It breaks ABI compatibility for the following public functions:
- rte_flow_copy()
- rte_flow_create()
- rte_flow_que
RTE_FLOW_ACTION_TYPE_PORT_ID brings the ability to inject matching traffic
into a different device, as identified by its DPDK port ID.
This is normally only supported when the target port ID has some kind of
relationship with the port ID the flow rule is created against, such as
being exposed by a
When creation of a flow rule fails during dev_start(), the usage count of
the common RSS context is not decremented, which triggers an assertion
failure in debug mode during dev_close().
This is addressed by tracking the initialization status of the common RSS
context in order to add missing clean
The NFP driver init messages would come out under PMD not net.pmd.nfp.init.
Signed-off-by: Stephen Hemminger
---
drivers/net/nfp/nfp_net_logs.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/nfp/nfp_net_logs.h b/drivers/net/nfp/nfp_net_logs.h
index 3fe24e96b347
These are several small changes to make the Netronome driver
use logging macros in the same way as other drivers.
Compile tested only. I don't have Netronome hardware.
Stephen Hemminger (5):
net/nfp: use correct logtype for init messages
net/nfp: add implied new line to PMD_DRV_LOG
net/nfp:
The PMD_INIT_LOG macro always adds a newline, and other drivers version
of PMD_DRV_LOG always adds a newline. Therefore change nfp driver
to be consitent with others.
Signed-off-by: Stephen Hemminger
---
drivers/net/nfp/nfp_net.c | 22 +++---
drivers/net/nfp/nfp_net_logs.h |
Shouldn't pass extra newline.
Signed-off-by: Stephen Hemminger
---
drivers/net/nfp/nfp_net.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c
index bf9d821c8c21..f32104ae7327 100644
--- a/drivers/net/nfp/nfp_net.c
+++ b/dri
Drivers should only log with their assigned logtype, not with the
generic PMD log type.
Signed-off-by: Stephen Hemminger
---
drivers/net/nfp/nfp_net.c | 132 +++---
1 file changed, 66 insertions(+), 66 deletions(-)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers
101 - 200 of 296 matches
Mail list logo
