The standard Virtual Ethernet Bridge(VEB) definition in 1Qbg is a bridge
which has an uplink port to the outside world (maybe another bridge), but
a "floating" VEB is a special VEB without an uplink port to the outside.
Instead, traffic can be sent from one VF to another using the floating
VEB -
The standard Virtual Ethernet Bridge(VEB) definition in 1Qbg is a bridge
which has an uplink port to the outside world (maybe another bridge),
but a "floating" VEB is a special VEB without an uplink port to the
outside. Instead, traffic can be sent from one VF to another using the
floating VEB -
This patch-set add the support for floating VEB in i40e.
All the VFs VSIs can decide whether to connect to the legacy VEB/VEPA or
the floating VEB. When connect to the floating VEB a new floating VEB is
created. Now all the VFs need to connect to floating VEB or legacy VEB,
cannot connect to both
To prevent compile error when compiling for shared library:
nicvf_hw.o: In function `nicvf_qsize_regbit':
nicvf_hw.c:(.text+0xe64): undefined reference to `log2'
nicvf_hw.o: In function `nicvf_rss_reta_update':
nicvf_hw.c:(.text+0x19dd): undefined reference to `log2'
nicvf_hw.o: In function
The old structure rte_eth_xstats contained names and values.
The new structure rte_eth_xstat contains ids and values.
Fixes: bd6aa172cf35 ("ethdev: fetch extended statistics with integer ids")
Fixes: e2aae1c1ced9 ("ethdev: remove name from extended statistic fetch")
Signed-off-by: Thomas
2016-06-29 17:03, Remy Horton:
> On 29/06/2016 16:38, Olivier MATZ wrote:
> > And assume that the id field in rte_eth_xstat corresponds to
> > the index in the rte_eth_xstat_name table?
>
> It was an assumption I wanted to avoid setting in stone, even though at
> the moment it is actually true
On 06/29/2016 06:02 PM, Wiles, Keith wrote:
>
> On 6/29/16, 11:00 AM, "dev on behalf of Bruce Richardson" dpdk.org on behalf of bruce.richardson at intel.com> wrote:
>
>> On Wed, Jun 29, 2016 at 05:55:27PM +0200, Thomas Monjalon wrote:
>>> 2016-06-29 14:55, Bruce Richardson:
The
2016-06-29 14:55, Bruce Richardson:
> The mempool_count and mempool_free_count behaved contrary to what their
> names suggested. The free_count function actually returned the number of
> elements that were allocated from the pool, not the number unallocated as
> the name implied.
>
> Fix this by
Hi Remy,
While adapting an application to the new xstats API, I discovered
that it may not be so efficient to display the statistics and their
names.
I think the test-pmd code illustrates the issue pretty well:
/* Display xstats */
for (idx_xstat = 0; idx_xstat < cnt_xstats; idx_xstat++)
+ Correct email for Thomas :-(
On Wed, Jun 29, 2016 at 05:27:15PM +0100, Bruce Richardson wrote:
> The mempool_count and mempool_free_count behaved contrary to what their
> names suggested. The free_count function actually returned the number of
> elements that were allocated from the pool, not
The mempool_count and mempool_free_count behaved contrary to what their
names suggested. The free_count function actually returned the number of
elements that were allocated from the pool, not the number unallocated as
the name implied.
Fix this by introducing two new functions to replace the old
On Wed, Jun 29, 2016 at 01:25:35PM +0200, Thomas Monjalon wrote:
> 2016-06-29 16:48, Jerin Jacob:
> > On Mon, Jun 27, 2016 at 04:59:42PM +0200, Thomas Monjalon wrote:
> > > 2016-06-27 20:18, Jerin Jacob:
> > > > On Mon, Jun 27, 2016 at 04:19:57PM +0200, Thomas Monjalon wrote:
> > > > > 2016-06-27
'noon,
On 29/06/2016 16:38, Olivier MATZ wrote:
[..]
> And assume that the id field in rte_eth_xstat corresponds to
> the index in the rte_eth_xstat_name table?
It was an assumption I wanted to avoid setting in stone, even though at
the moment it is actually true in implementation.
The
On Wed, Jun 29, 2016 at 05:55:27PM +0200, Thomas Monjalon wrote:
> 2016-06-29 14:55, Bruce Richardson:
> > The mempool_count and mempool_free_count behaved contrary to what their
> > names suggested. The free_count function actually returned the number of
> > elements that were allocated from the
On Tue, Jun 28, 2016 at 02:17:41PM +0800, Jianbo Liu wrote:
> On 27 June 2016 at 19:54, Jerin Jacob
> wrote:
> > split out SSE instruction based virtio simple rx
> > implementation to a separate file
> >
> > Signed-off-by: Jerin Jacob
> > ---
> > drivers/net/virtio/virtio_rxtx_simple.c |
On Mon, Jun 27, 2016 at 04:59:42PM +0200, Thomas Monjalon wrote:
> 2016-06-27 20:18, Jerin Jacob:
> > On Mon, Jun 27, 2016 at 04:19:57PM +0200, Thomas Monjalon wrote:
> > > 2016-06-27 17:24, Jerin Jacob:
> > > > --- a/config/common_base
> > > > +++ b/config/common_base
> > > > @@ -267,6 +267,7 @@
The commit id of a fixed commit must be in the current branch.
It avoids referencing a local branch or a next-* branch when
pushing in the master.
Signed-off-by: Thomas Monjalon
---
scripts/check-git-log.sh | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git
Hi Dave,
On 06/20/2016 02:59 PM, Hunt, David wrote:
> Hi Olivier,
>
> On 20/6/2016 9:17 AM, Olivier Matz wrote:
>> Hi David,
>>
>> On 06/17/2016 04:18 PM, Hunt, David wrote:
After reading it, I realize that it's nearly exactly the same code than
in "app/test: test external mempool
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Wednesday, June 29, 2016 5:05 PM
> To: Wiles, Keith ; Richardson, Bruce
> ; Thomas Monjalon 6wind.com>
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] mempool: rename functions with confusing
>
'noon,
The tool does not work for static PMD libraries (e.g. librte_pmd_i40e.a)
- is this an intended limitation?
DPDK doesn't to my knowledge have any coding guidelines for Python, so
the comments below should be considered advisory rather than
merge-blocking issues.
On 17/06/2016 19:46,
If you stop then start a port that had already received some packets,
the NIC could fetch discriptors from the wrong location. This could
effectivly reduce the size of the Rx queue by a random amount and
cause packet drop or reduced performance.
Reset the NIC fetch index to 0 when allocating and
From: Nelson Escobar
If you stop then start a port that had already sent some packets,
there was a segfault due to not resetting the number of completed
sends to zero.
Fixes: d5d882fe1a11 ("Tx path rewrite to reduce Host CPU overhead")
Signed-off-by: Nelson Escobar
On 6/29/16, 11:00 AM, "dev on behalf of Bruce Richardson" wrote:
>On Wed, Jun 29, 2016 at 05:55:27PM +0200, Thomas Monjalon wrote:
>> 2016-06-29 14:55, Bruce Richardson:
>> > The mempool_count and mempool_free_count behaved contrary to what their
>> > names suggested. The free_count function
hi ,
The below error is because invalid coremask , your VM has only one core ,
but you are trying to assign eal option as -c 0xf that means you are
assigning 1,2,3,4 cores to dpdk application which are not available in your
VM .
you can increase sufficient number of cores while u launch virtual
Hi,
Based on 18. Multi-process Support (
http://dpdk.org/doc/guides-16.04/prog_guide/multi_proc_support.html), we
cannot create one process which works as primary and secondary at the same.
Is it true?
For example, there are three applications.
A <-> B <-> C.
A : primary for B
B : secondary
On Wed, Jun 29, 2016 at 01:47:27PM +, Mcnamara, John wrote:
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zhe Tao
> > Sent: Wednesday, June 29, 2016 2:06 PM
> > To: dev at dpdk.org
> > Cc: Tao, Zhe ; Wu, Jingjing
> > Subject: [dpdk-dev] [PATCH v15
The example is calling rte_eal_wait_lcore without checking return value.
Now it is fixed by checking the value and print proper message.
Coverity issue: 37789
Coverity issue: 37790
Fixes: cc7e8ae84faa ("examples/bond: add example application for link bonding
mode 6")
Signed-off-by: Piotr
Hi Jan,
On Friday 06 May 2016 07:18 PM, Jan Viktorin wrote:
> Signed-off-by: Jan Viktorin
> ---
> lib/librte_ether/rte_ethdev.c | 127
> +-
> lib/librte_ether/rte_ethdev.h | 31 +++
> 2 files changed, 157 insertions(+), 1 deletion(-)
>
> diff
>
> Commit 550c9d27d143 ("vhost: set/reset device flags internally") moves
> the VIRTIO_DEV_RUNNING set/reset to vhost lib. But I missed one reset
> on stop; here fixes it.
>
> Fixes: 550c9d27d143 ("vhost: set/reset device flags internally")
>
> Reported-by: Loftus Ciara
> Signed-off-by:
The mempool_count and mempool_free_count behaved contrary to what their
names suggested. The free_count function actually returned the number of
elements that were allocated from the pool, not the number unallocated as
the name implied.
Fix this by introducing two new functions to replace the old
Overrunning array crypto_statistics of 32 64-byte elements
at element index 63 using index cdevid.
Fixed by extend crypto_statistics array.
Fixes: 387259bd6c67 ("examples/l2fwd-crypto: add sample application")
Coverity ID 120145
Signed-off-by: Slawomir Mrozowicz
---
Hi Lazaros,
On 06/29/2016 01:47 AM, Lazaros Koromilas wrote:
> The mempool cache is only available to EAL threads as a per-lcore
> resource. Change this so that the user can create and provide their own
> cache on mempool get and put operations. This works with non-EAL threads
> too. This commit
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zhe Tao
> Sent: Wednesday, June 29, 2016 2:06 PM
> To: dev at dpdk.org
> Cc: Tao, Zhe ; Wu, Jingjing
> Subject: [dpdk-dev] [PATCH v15 2/2] i40e: add device args to enable a
> floating VEB
>
> The standard
On 06/29/2016 12:15 PM, Bruce Richardson wrote:
> On Mon, Jun 27, 2016 at 07:05:45PM +0200, Thomas Monjalon wrote:
>> 2016-06-27 17:44, Olivier Matz:
>>> The ixgbe driver does not compile if CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n
>>> because the macro has not the proper number of parameters.
>>
>>
On Wed, Jun 29, 2016 at 01:23:48PM +0200, Thomas Monjalon wrote:
> > Signed-off-by: Bruce Richardson
>
> Applied with -i case option to catch also lowercase form.
Which suggests another good check to add, would be to check that the commmit
message starts with a capital letter.
/Bruce
Bruce,
We've got a small minor fixes and we will create V3 version later this week
(targeting Friday).
What's final deadline for 16.07 integration?
Regards,
Jan
2016-06-29 13:01 GMT+02:00 Bruce Richardson :
> On Fri, Jun 24, 2016 at 12:52:39PM +0100, Bruce Richardson wrote:
> > On Tue, Jun
On Wed, Jun 29, 2016 at 01:35:15PM +0200, Olivier MATZ wrote:
>
>
> On 06/29/2016 12:15 PM, Bruce Richardson wrote:
> >On Mon, Jun 27, 2016 at 07:05:45PM +0200, Thomas Monjalon wrote:
> >>2016-06-27 17:44, Olivier Matz:
> >>>The ixgbe driver does not compile if
On Wed, Jun 29, 2016 at 01:31:12PM +0200, Jan M?dala wrote:
> Bruce,
>
> We've got a small minor fixes and we will create V3 version later this week
> (targeting Friday).
> What's final deadline for 16.07 integration?
>
> Regards,
>
> Jan
>
ASAP. The integration deadline for final patches
2016-06-29 11:30, Thomas Monjalon:
> The driver qede can be automatically enabled if libz is available.
>
> Fixes: ec94dbc57362 ("qede: add base driver")
>
> Signed-off-by: Thomas Monjalon
Applied
>> What is not clear to me is motivation to use weak here instead of simply
>> using >CONFIG_RTE_I40E_INC_VECTOR
>> macro to exclude stubs in i40e_rxtx.c. It will make library smaller and
>> avoid issues like this one
>> which are quite hard to troubleshoot.
>
>Since this issue seen in fd.io, I
2016-06-29 16:48, Jerin Jacob:
> On Mon, Jun 27, 2016 at 04:59:42PM +0200, Thomas Monjalon wrote:
> > 2016-06-27 20:18, Jerin Jacob:
> > > On Mon, Jun 27, 2016 at 04:19:57PM +0200, Thomas Monjalon wrote:
> > > > 2016-06-27 17:24, Jerin Jacob:
> > > > > --- a/config/common_base
> > > > > +++
> Signed-off-by: Bruce Richardson
Applied with -i case option to catch also lowercase form.
On Wed, Jun 29, 2016 at 04:12:21PM +0100, Remy Horton wrote:
> 'noon,
>
> The tool does not work for static PMD libraries (e.g. librte_pmd_i40e.a) -
> is this an intended limitation?
>
Yes, because .a files are archives, not ELF files. If you want to run pmdinfo
on an archive, you have to
On Fri, Jun 24, 2016 at 12:52:39PM +0100, Bruce Richardson wrote:
> On Tue, Jun 21, 2016 at 02:05:57PM +0200, Jan Medala wrote:
> > As requested, big patch splitted into logical pieces for easier review.
> > Improved style and fixed icc compiler issues.
> >
>
> Thanks for the patch split.
On Tue, Jun 28, 2016 at 12:14:50PM -0400, Chas Williams wrote:
> We need sc->igu_sb_cnt determined before calculating the number of queues
> we can support.
>
> Fixes: a787538ee754 ("bnx2x: fix MSIX vector and VF resource counts")
>
> Signed-off-by: Chas Williams <3chas3 at gmail.com>
> ---
Hi
On Tue, Jun 21, 2016 at 08:18:46AM -0400, Chas Williams wrote:
> If the PF hasn't assigned an address, assign one randomly. While here,
> convert to use DPDK's ether address utility routines.
>
> Fixes: 540a211084a7 ("bnx2x: driver core")
>
> Signed-off-by: Chas Williams <3chas3 at gmail.com>
On Tue, Jun 28, 2016 at 11:49:11AM -0700, Nelson Escobar wrote:
> The Rx scatter patch failed to make a few changes and resulted in
> problems when using multiple receive queues in dpdk (ie RSS) since the
> wrong adapter resources were being used.
>
> - get and use the correct completion queue
On Wed, Jun 29, 2016 at 11:39:51AM +0100, Bruce Richardson wrote:
> On Tue, Jun 28, 2016 at 09:56:02AM +0100, Ferruh Yigit wrote:
> > On 6/27/2016 5:16 PM, Jerin Jacob wrote:
> > > Fix the following error with clang
> > > error: unused function 'nicvf_mbox_msg_str'
> > >
> > > The
On Wed, Jun 29, 2016 at 11:39:07AM +0100, Bruce Richardson wrote:
> On Tue, Jun 28, 2016 at 09:55:55AM +0100, Ferruh Yigit wrote:
> > On 6/27/2016 5:16 PM, Jerin Jacob wrote:
> > > 'fno-prefetch-loop-arrays' optimization flag is not supported with clang
> > >
> > > Fixes: dcc49041 (net/thunderx:
On Tue, Jun 28, 2016 at 09:55:55AM +0100, Ferruh Yigit wrote:
> On 6/27/2016 5:16 PM, Jerin Jacob wrote:
> > 'fno-prefetch-loop-arrays' optimization flag is not supported with clang
> >
> > Fixes: dcc49041 (net/thunderx: add single and multi-segment Tx functions")
> >
> > Signed-off-by: Jerin
The driver qede can be automatically enabled if libz is available.
Fixes: ec94dbc57362 ("qede: add base driver")
Signed-off-by: Thomas Monjalon
---
scripts/test-build.sh | 2 ++
1 file changed, 2 insertions(+)
diff --git a/scripts/test-build.sh b/scripts/test-build.sh
index 7a9f623..24c0202
On Tue, Jun 14, 2016 at 07:53:17PM -0400, Zhihong Wang wrote:
> This patch explains all the versions of current virtio pmd implementation,
> what's the difference, and how to choose the right version.
>
> --
> Changes in v2:
>
>1. Changes on format and few descriptions.
Change
On Mon, Jun 27, 2016 at 07:05:45PM +0200, Thomas Monjalon wrote:
> 2016-06-27 17:44, Olivier Matz:
> > The ixgbe driver does not compile if CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n
> > because the macro has not the proper number of parameters.
>
> We really need to understand why this build option is
On Fri, Jun 24, 2016 at 03:29:27PM -0700, John Daley wrote:
> Pull in common VNIC code which enables querying for max egress
> packet size with newer firmware via a device command. If the
> field is non-zero, it is the max egress packet size. If it is
> 0, the default value (9022) can safely be
On Mon, Jun 27, 2016 at 11:21:45PM +, Rasesh Mody wrote:
> > From: Ferruh Yigit [mailto:ferruh.yigit at intel.com]
> > Sent: Monday, June 27, 2016 9:03 AM
> >
> > Fix icc warning:
> > error #188: enumerated type mixed with another type
> >
> > Fixed the code for simple cases caused the
On Mon, Jun 27, 2016 at 03:20:14PM +0800, Zhe Tao wrote:
> This patch-set add the support for floating VEB in i40e.
> All the VFs VSIs can decide whether to connect to the legacy VEB/VEPA or
> the floating VEB. When connect to the floating VEB a new floating VEB is
> created. Now all the VFs need
Morning,
Compile error with virtio_user_ethdev.c - looks like a new addition
(commit ce2eabdd43ec) that also needs to be converted.
Regards,
..Remy
On 17/06/2016 19:46, Neil Horman wrote:
> Hey all-
> So heres attempt number 2 at a method for exporting PMD hardware support
>
On Tue, Jun 28, 2016 at 10:41:24AM +0100, Ferruh Yigit wrote:
> On 6/26/2016 2:49 PM, Jianfeng Tan wrote:
> > On some older systems, such as SUSE 11, the compiling error shows
> > as:
> >.../dpdk/drivers/net/virtio/virtio_user/virtio_user_dev.c:67:22:
> > error: ?O_CLOEXEC? undeclared
When use strcpy() to copy string with length exceeding the last
parameter of strcpy(), it may lead to the destination string
unterminated.
We replaced strncpy with snprintf to make sure it's NULL terminated.
Coverity issue: 127476
Fixes: ce2eabdd43ec ("net/virtio-user: add virtual device")
The return value by rte_kvargs_parse is not free(d), which leads
to memory leak.
Coverity issue: 127482
Fixes: ce2eabdd43ec ("net/virtio-user: add virtual device")
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_user_ethdev.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
When parsing /proc/self/maps to get hugepage information, the string
was being copied with strcpy(), which could, theoretically but in fact
not possiblly, overflow the destination buffer. Anyway, to avoid the
false alarm, we replaced strncpy with snprintf for safely copying the
strings.
Coverity
When return values of function calls are not checked, Coverity will
report errors like:
if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_PATH) == 1)
>>> CID 127477:(CHECKED_RETURN)
>>> Calling "rte_kvargs_process" without checking return value
(as is done elsewhere
Patch 1: fix return value not checked, Coverity issue: 127344, 127478
Patch 2: fix string overflow, Coverity issue: 127484
Patch 3: fix resource leaks, Coverity issue: 127482
Patch 4: fix string unterminated, Coverity issue: 127476
Jianfeng Tan (4):
net/virtio-user: fix return value not checked
On Wed, Jun 29, 2016 at 10:18:26AM +0100, Remy Horton wrote:
> Morning,
>
> Compile error with virtio_user_ethdev.c - looks like a new addition (commit
> ce2eabdd43ec) that also needs to be converted.
>
> Regards,
>
> ..Remy
>
diff --git a/drivers/net/virtio/virtio_user_ethdev.c
On some older systems, such as SUSE 11, the compiling error shows
as:
.../dpdk/drivers/net/virtio/virtio_user/virtio_user_dev.c:67:22:
error: ?O_CLOEXEC? undeclared (first use in this function)
The fix is to use EFD_CLOEXEC, which is defined in sys/eventfd.h,
instead of O_CLOEXEC
With current config structure, all configuration parameters put into
common_base with a default value, and overwritten in environment file
if required, CONFIG_RTE_VIRTIO_USER is missing in common_base.
This fix is simple, by adding CONFIG_RTE_VIRTIO_USER=n as the default
macro value.
Fixes:
The mempool cache is only available to EAL threads as a per-lcore
resource. Change this so that the user can create and provide their own
cache on mempool get and put operations. This works with non-EAL threads
too. This commit introduces the new API calls:
rte_mempool_cache_create(size,
Pass the same flags as in rte_mempool_create(). Changes API calls:
rte_mempool_generic_put(mp, obj_table, n, flags)
rte_mempool_generic_get(mp, obj_table, n, flags)
Signed-off-by: Lazaros Koromilas
Acked-by: Olivier Matz
---
lib/librte_mempool/rte_mempool.h | 58
This commit introduces the API calls:
rte_mempool_generic_put(mp, obj_table, n, is_mp)
rte_mempool_generic_get(mp, obj_table, n, is_mc)
Deprecates the API calls:
rte_mempool_mp_put_bulk(mp, obj_table, n)
rte_mempool_sp_put_bulk(mp, obj_table, n)
rte_mempool_mp_put(mp, obj)
Updated version of the user-owned cache patchset. It applies on top of
the latest v15 external mempool manager patches from David Hunt [1].
[1] http://dpdk.org/ml/archives/dev/2016-June/042004.html
v5 changes:
* Rework error path macros in tests.
* Update documentation.
* Style fixes.
v4
Hi Asim,
> -Original Message-
> From: Asim Jamshed [mailto:asim.jamshed at gmail.com]
> Sent: Tuesday, June 28, 2016 5:23 PM
> To: Lu, Wenzhuo
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] Fwd: dpdk ixgbe PMD lro limits
>
> On Tue, Jun 28, 2016 at 5:42 PM, Lu, Wenzhuo wrote:
> > Hi
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Tuesday, June 28, 2016 7:34 AM
>
> 2016-05-11 17:06, Rasesh Mody:
> > Add extended stats support to provide additional statistical info.
> >
> > Signed-off-by: Rasesh Mody
> > Signed-off-by: Harish Patil
>
> This bnx2x patch
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Tuesday, June 28, 2016 7:32 AM
>
> 2016-06-15 22:47, Rasesh Mody:
> > This patch adds support for extended statistics for QEDE PMD.
> >
> > Signed-off-by: Rasesh Mody
>
> This qede patch and a bnx2x one cannot be merged in
73 matches
Mail list logo