On Fri, Feb 17, 2017 at 3:14 PM, Verma, Shally wrote:
> Hi
>
> I was looking at linux-generic/odp_crypto.c implementation and it looks like
> that each odp_crypto_operation() call assumes that each Packet is contained
> within 1-segment or user passing either packet or
Hi
I was looking at linux-generic/odp_crypto.c implementation and it looks like
that each odp_crypto_operation() call assumes that each Packet is contained
within 1-segment or user passing either packet or segment len, whichever is
smaller.
As I understand ODP Packet structure, it is
I've posted patch http://patches.opendataplane.org/patch/8155/ to
address this issue. It goes on api-next on top of patches
http://patches.opendataplane.org/patch/7879/ and
http://patches.opendataplane.org/patch/8154/
On Fri, Feb 17, 2017 at 2:39 PM, Bill Fischofer
https://bugs.linaro.org/show_bug.cgi?id=2892
--- Comment #1 from Bill Fischofer ---
Patch http://patches.opendataplane.org/patch/8155/ posted to address this
issue.
--
You are receiving this mail because:
You are on the CC list for the bug.
Resolve bug https://bugs.linaro.org/show_bug.cgi?id=2892 by setting
unshared_len prior to potentially freeing segments.
Reported-by: Janne Peltonen
Signed-off-by: Bill Fischofer
---
platform/linux-generic/odp_packet.c | 4 ++--
1 file
While reference counts are implemented as atomics, try to avoid
unnecessary atomic decrement operations in free paths. This streamlines
free processing in the expected case where packets do not contain
shared segments.
Signed-off-by: Bill Fischofer
---
https://bugs.linaro.org/show_bug.cgi?id=2892
Bug ID: 2892
Summary: Race condition in setting unshared_len during
packet_free() processing
Product: OpenDataPlane - linux- generic reference
Version: api-next
Hardware: Other
First off, thank you very much for this review.
Please note that this code has been streamlined in patch
http://patches.opendataplane.org/patch/7879/ and has been further
refined with patch http://patches.opendataplane.org/patch/8145/ but
the exposure you identify still exists in that code.
On
tested and merged this patch.
On 02/16/17 14:48, Petri Savolainen wrote:
> Added symbolic link to the installed include directory. The link
> points to the arch specific abi dir, so that application does
> not need to add the arch specific dir into its makefile.
>
> Signed-off-by: Petri
Branch: refs/heads/master
Home: https://github.com/Linaro/odp
Commit: 52f32ce1fa6b5416c59ead45ff27d731d98b8f87
https://github.com/Linaro/odp/commit/52f32ce1fa6b5416c59ead45ff27d731d98b8f87
Author: Petri Savolainen
Date: 2017-02-17 (Fri, 17 Feb
On 02/17/17 18:45, Oriol Arcas wrote:
> I tried setting the MAC addresses. In my local test, the problem
> disappeared, but I doubt that it's been fixed.
>
> On our larger testbed, with OpenVPN tunnels, the bug persists event with
> the MAC addresses. But our setup may be problematic, for
I need somebody to review this patch. ip frag example required this
change to compile in our env. CI things. Looks like ip frag is ready to
be merged and this patch is show stopper this that.
Thank you,
Maxim.
On 02/16/17 23:26, Maxim Uvarov wrote:
> upcoming patch ip fragmentation example fails
I'm trying to run it on Ubuntu 14.04.4.
But some problems there. Any hints where to look?
+ out=cset: --> failed to create shield, hint: do other cpusets exist?
cset: **> attempt to create already existing set: "/user"
+ die cset failed; cset: --> failed to create shield, hint: do other
cpusets
My bash does not understand that syntax:
[ $UID -eq 0 ] || die "You need to be root!"
+ [ -eq 0 ]
./scripts/task-isolation/isolate-cpu.sh: 152: [: -eq: unexpected operator
On 02/17/17 17:34, Mike Holmes wrote:
> checkpatch is designed for the kernel C code so we have to use some
> judgment,
Hi,
I took a look at the packet references and it seems to me that
either the implementation is a bit racy or I confused myself
when reading the code. Or maybe I got the intended concurrency
semantics of the packet references wrong?
My first issue is that packet_free() may access freed packet
On Fri, Feb 17, 2017 at 8:20 AM, Petri Savolainen
wrote:
> Packet input parsing level configuration is added. An application
> may express the maximum layer it is interested about.
> Implementations may optimize packet input performance as parsing
> can be stopped on
I tried setting the MAC addresses. In my local test, the problem
disappeared, but I doubt that it's been fixed.
On our larger testbed, with OpenVPN tunnels, the bug persists event with
the MAC addresses. But our setup may be problematic, for instance in this
interface chain:
veth0 -|- veth1
The wrapper script; odp_run_app_isolated.sh can be used to run ODP
testcases in a isolated environment. Background noise can also be
generated.
Signed-off-by: Ravineet Singh
v2: moved task-isolation dir to odp/scripts, requested my Maxim Uvarov
v3: fixed checkpatch.pl
checkpatch is designed for the kernel C code so we have to use some
judgment, as for git there are cases it makes no sence
On 17 February 2017 at 09:10, Maxim Uvarov wrote:
> interesting if checpatch is ok, git am warns on spaces in intent:
>
>
> git am -s
Packet input parsing level configuration is added. An application
may express the maximum layer it is interested about.
Implementations may optimize packet input performance as parsing
can be stopped on the application required level. Implementations
are free to parse more layers than application
Fill default parser configuration and capability. All pktios
use same parser code, so the capability is the same (all layers).
Signed-off-by: Petri Savolainen
---
platform/linux-generic/odp_packet_io.c| 13 +++--
interesting if checpatch is ok, git am warns on spaces in intent:
git am -s /tmp/11/\[PATCH\ v3\]\ validation\:\ A\ wrapper\ script\ to\
run\ test\ isolated..eml
Applying: validation: A wrapper script to run test isolated.
.git/rebase-apply/patch:24: indent with spaces.
the
Branch: refs/heads/api-next
Home: https://github.com/Linaro/odp
Commit: e971043e275307634472b35ce394326216c3e301
https://github.com/Linaro/odp/commit/e971043e275307634472b35ce394326216c3e301
Author: Andriy Berestovskyy
Date: 2017-02-17 (Fri, 17
Branch: refs/heads/master
Home: https://github.com/Linaro/odp
Commit: 05f8f96ae606eecfff48e3544885d43b9f541f3c
https://github.com/Linaro/odp/commit/05f8f96ae606eecfff48e3544885d43b9f541f3c
Author: Maxim Uvarov
Date: 2017-02-17 (Fri, 17 Feb 2017)
Merged with rewording commit message.
Maxim.
On 02/17/17 14:18, Bill Fischofer wrote:
> Thanks for spotting and fixing this.
>
> On Fri, Feb 17, 2017 at 4:41 AM, Andriy Berestovskyy
> wrote:
>> Signed-off-by: Andriy Berestovskyy
Branch: refs/heads/master
Home: https://github.com/Linaro/odp
Commit: e971043e275307634472b35ce394326216c3e301
https://github.com/Linaro/odp/commit/e971043e275307634472b35ce394326216c3e301
Author: Andriy Berestovskyy
Date: 2017-02-17 (Fri, 17
Branch: refs/heads/api-next
Home: https://github.com/Linaro/odp
Commit: f59d87a65cf1d08f8715a01dceeaf370a29e51f3
https://github.com/Linaro/odp/commit/f59d87a65cf1d08f8715a01dceeaf370a29e51f3
Author: Bill Fischofer
Date: 2017-02-10 (Fri, 10 Feb 2017)
On 14 February 2017 at 15:32, Maxim Uvarov wrote:
> make doxygen-doc does not return negative code on
> errors. Do it manually.
>
> Signed-off-by: Maxim Uvarov
>
Reviewed-by: Mike Holmes
> ---
> .travis.yml | 4 +++-
On Fri, Feb 17, 2017 at 5:34 AM, Petri Savolainen
wrote:
> Added stubs for functions so that applications can be built
> already. A proper implementation follows later on.
>
> Signed-off-by: Petri Savolainen
Reviewed-and-tested-by: Bill
For this series:
Reviewed-and-tested-by: Bill Fischofer
On Fri, Feb 17, 2017 at 2:11 AM, Balasubramanian Manoharan
wrote:
> Adds implementation for outer and inner ethernet type packet matching rule
>
> Signed-off-by: Balasubramanian
> On 17 Feb 2017, at 14:03, Oriol Arcas wrote:
>
> Hi,
>
> Thanks for your reply Marias.
>
> I tried a simpler setup and the bug persists. With a linux bridge it works
> fine.
>
> My setup is the following:
>
> | nginx <---> veth0 -|- veth1 <---> l2fwd <--->
Hi,
Thanks for your reply Marias.
I tried a simpler setup and the bug persists. With a linux bridge it works
fine.
My setup is the following:
| nginx <---> veth0 -|- veth1 <---> l2fwd <---> veth2 -|- veth3 <---> wget |
where the | delimiters mean a network namespace.
I have tried it with
Added stubs for functions so that applications can be built
already. A proper implementation follows later on.
Signed-off-by: Petri Savolainen
---
platform/linux-generic/odp_ipsec.c | 111 +
1 file changed, 111 insertions(+)
diff
Thanks for spotting and fixing this.
On Fri, Feb 17, 2017 at 4:41 AM, Andriy Berestovskyy
wrote:
> Signed-off-by: Andriy Berestovskyy
Reviewed-and-tested-by: Bill Fischofer
> ---
> CONTRIBUTING | 6
Hi Oriol,
This seems rather odd indeed (especially point e). Just to be clear, are you
using OFP in any part of the test setup or is the simplified setup as follows?
standard nginx <> odp_l2fwd <> standard wget
You could try testing with different odp pktio types (preferably
Signed-off-by: Andriy Berestovskyy
---
CONTRIBUTING | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/CONTRIBUTING b/CONTRIBUTING
index a81fd8d..ab77fd3 100644
--- a/CONTRIBUTING
+++ b/CONTRIBUTING
@@ -13,7 +13,8 @@ the contributing
On 17 February 2017 at 00:56, Bill Fischofer
wrote:
> On Thu, Feb 16, 2017 at 3:20 PM, Brian Brooks
> wrote:
> > On Mon, Feb 13, 2017 at 4:47 PM, Bill Fischofer
> > wrote:
> >> Clarify and expand on portability and
On 17 February 2017 at 11:51, Francois Ozog
wrote:
> I think this is quite useful for cloud applications that do not know
> the underlying hardware specs and need to check what is effectively
> possible. "hardware" resolution is nothing without all surrounding
>
ok, thanks.
On 17 February 2017 at 12:39, Savolainen, Petri (Nokia - FI/Espoo) <
petri.savolai...@nokia-bell-labs.com> wrote:
>
>
> > -Original Message-
> > From: lng-odp [mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of
> Maxim
> > Uvarov
> > Sent: Thursday, February 16, 2017 10:55
> -Original Message-
> From: lng-odp [mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of Maxim
> Uvarov
> Sent: Thursday, February 16, 2017 10:55 PM
> To: lng-odp@lists.linaro.org
> Subject: Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to
> linux helpers
>
> On
I think this is quite useful for cloud applications that do not know
the underlying hardware specs and need to check what is effectively
possible. "hardware" resolution is nothing without all surrounding
software layers, and virtualization in particular...
On 17 February 2017 at 09:43, Kevin Wang
clock_getres() is to find the hardware resolution of specific clock source.
It shows 1ns in most of modern system.
What this API trys to do is to find out the resolution without overrun of
this timer. Applications are able to deal with each timer event with that
timer resolution.
2017-02-17 3:00
Adds implementation for outer and inner ethernet type packet matching rule
Signed-off-by: Balasubramanian Manoharan
---
.../include/odp_classification_inlines.h | 40 +-
1 file changed, 32 insertions(+), 8 deletions(-)
diff --git
43 matches
Mail list logo