On 3/5/15, 4:10 PM, "Stephen Hemminger" wrote:
>From: Stephen Hemminger
>
>No reason to inline large functions. Compiler will decide already
>based on optimization level.
>
>Also register array should be const.
>
>Signed-off-by: Stephen Hemminger
One comment below.
Acked-by: Yong Wang
>---
On 3/5/15, 4:10 PM, "Stephen Hemminger" wrote:
>From: Stephen Hemminger
>
>It is possible that some rogue application might pass a segment
>larger than 16K to the vmxnet3 transmit routine. In which case
>just drop it and increment counter.
>
>Signed-off-by: Stephen Hemminger
One minor comment
On Fri, Mar 6, 2015 at 5:55 PM, Stephen Hemminger <
stephen at networkplumber.org> wrote:
> No virtio_dev_init is called too late, after interrupt handling
> threads are spawned.
>
> /* Launch threads, called at application init(). */
> int
> rte_eal_init(int argc, char **argv)
> {
> int i
Hi,
Can you show the log output of OVS? and the ouput of following command
cd path/to/ovs/utilities/
./ovs-ofctl show br0
./ovs-ofctl dump-flows br0
(Assum that br0 is a bridge name that you had created)
On Fri, Mar 6, 2015 at 10:14 PM, Arkajit Ghosh
wrote:
> Hi,
>
> Can anyone please suggest
On 3/5/15, 4:10 PM, "Stephen Hemminger" wrote:
>By defining macro as a stub it is possible to get rid of #ifdef's
>in the actual code. Always evaluate the argument (even in the stub)
>so that there are no extra unused variable errors.
>
>Signed-off-by: Stephen Hemminger
Acked-by: Yong Wang
>-
On 3/5/15, 4:10 PM, "Stephen Hemminger" wrote:
>From: Stephen Hemminger
>
>Support the VLAN filter functionality of the VMXNET3 interface.
>
>Signed-off-by: Stephen Hemminger
Acked-by: Yong Wang
>---
> lib/librte_pmd_vmxnet3/vmxnet3_ethdev.c | 105
>+---
> lib/libr
Hi,
Can anyone please suggest how to proceed.
Thanks & Regards
Arkajit Ghosh
-Arkajit Ghosh/DEL/TCS wrote: -
To: dev at dpdk.org
From: Arkajit Ghosh/DEL/TCS
Date: 03/04/2015 12:39PM
Subject: Guest Machine is not Pingable from Host Machine
Hi Team,
Guest machine is not pingable from H
This avoids closing -1 in our case.
Signed-off-by: Huawei Xie
---
lib/librte_vhost/virtio-net.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 6917fcf..4672e67 100644
--- a/lib/librte_vhost/virtio-ne
Previous vhost implementation wrongly name kickfd as callfd and callfd as
kickfd.
It is functional correct, but causes confusion.
Signed-off-by: Huawei Xie
---
examples/vhost/main.c | 6 +++---
lib/librte_vhost/rte_virtio_net.h | 4 ++--
lib/librte_vhost/vh
To avoid any possible confusion or breakage, rename all the structures
of ixgbe driver to use ixgbe_ rather than igb_ because igb is a
different driver.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 2 +-
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 124 ++
All global functions in a driver should use the same prefix
to avoid any future name collisions.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 2 +-
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 2 +-
lib/librte_pmd_ixgbe/ixgbe_rxtx.h | 2 +-
3 files changed, 3 insertions(
Only used in this file, make it static.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.h | 5 -
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 2 +-
2 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
b/lib/librte_pmd_ixgbe/ixgbe_
These are const data structures, just put them in txt segment
rather than having compiler emit code to set them up on the stack.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixg
All virtual function tables should be const so they are put
in text segment rather than data.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 2 +-
lib/librte_pmd_ixgbe/ixgbe_rxtx.h | 2 +-
lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 2 +-
3 files changed, 3 insertio
These are things found while reviewing ixgbe driver.
No bugs or functionality changes, just minor things like naming
and use of const.
Stephen Hemminger (5):
ixgbe: make txq_ops const
ixgbe: make register maps const
ixgbe: make bulk alloc static
ixgbe: rename set_tx_function
ixgbe: renam
On Fri, 6 Mar 2015 23:54:23 +
Yong Wang wrote:
> Since there is only one caller of this routine, inlining it should be
> fine. But I have no problem with letting the compiler decide (which
> probably will inline it anyway for this particular case).
Sometimes compiler will not inline because
Because of the changing of unified flow type, commands for flow
director need to be updated.
Signed-off-by: Jingjing Wu
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 19 ++-
1 file changed, 10 insertions(+), 9 deletions(-)
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs
Ixgbe doesn't support the ipv4-frag and ipv6-frag flow types, remove them.
Ixgbe doesn't support configure flex mask on each kind of flow type, this
patch uses RTE_ETH_FLOW_UNKNOWN to specify global flex mask setting.
This patch also changes the string "raw" to "none" to indicate flex mask
setting
Due the unified flow type changes, this patchset updates the commands for flow
director
and correct the flow types ixgbe supported.
Jingjing Wu (2):
ixgbe: correct the flow types supported
doc: update flow director commands
app/test-pmd/cmdline.c | 18 +++---
Hello Stephen,
On Fri, Mar 6, 2015 at 5:20 PM, Stephen Hemminger <
stephen at networkplumber.org> wrote:
> The issue is that virtio has no place it can do iopl() and have the IRQ
> thread
> work. It only shows up on real code where application is daemon, not in a
> toy
> demo or test application.
Update the testpmd doc as there are new HW VLAN commands/options.
Signed-off-by: Changchun Ouyang
---
doc/guides/testpmd_app_ug/run_app.rst | 12 +++
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 33 +
2 files changed, 45 insertions(+)
diff --git a/doc/
This patch enables testpmd user can config port hw_vlan with more fine
granularity:
hw vlan filter, hw vlan strip, and hw vlan extend.
Don't remove the original command(hw-vlan) considering that some user still
want to use
only one command to switch on/off all 3 options.
Signed-off-by: Changchu
This patch enables testpmd user can config port hw_vlan with more fine
granularity:
hw vlan filter, hw vlan strip, and hw vlan extend;
Update testpmd doc accordingly.
Changchun Ouyang (2):
testpmd: HW vlan command
doc: Update for new HW vlan command
app/test-pmd/cmdline.c
Update the testpmd doc as there are new HW VLAN commands/options.
Signed-off-by: Changchun Ouyang
---
doc/guides/testpmd_app_ug/run_app.rst | 12 +++
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 33 +
2 files changed, 45 insertions(+)
diff --git a/doc/
This patch enables testpmd user can config port hw_vlan with more fine
granularity:
hw vlan filter, hw vlan strip, and hw vlan extend.
Don't remove the original command(hw-vlan) considering that some user still
want to use
only one command to switch on/off all 3 options.
Signed-off-by: Changchu
This patch enables testpmd user can config port hw_vlan with more fine
granularity:
hw vlan filter, hw vlan strip, and hw vlan extend;
Update testpmd doc accordingly.
Changchun Ouyang (2):
testpmd: HW vlan command
doc: Update for new HW vlan command
app/test-pmd/cmdline.c
v2:
Instead of changing all the affected files,
define 'typeofi' and 'asm' if needed.
When compiling C++11-code or above (--std=c++11), the build fails with
lots of
rte_eth_ctrl.h:517:3: note: in expansion of macro RTE_ALIGN
(RTE_ALIGN(RTE_ETH_FLOW_MAX, UINT32_BIT)/UINT32_BIT)
^
When r
It could be a potential not safe issue.
Signed-off-by: Michael Qiu
---
lib/librte_pmd_fm10k/fm10k_ethdev.c | 14 +++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/lib/librte_pmd_fm10k/fm10k_ethdev.c
b/lib/librte_pmd_fm10k/fm10k_ethdev.c
index 07ea1e7..30962d3 100644
On Fri, 6 Mar 2015 23:04:33 +0100
David Marchand wrote:
> In the end, the fix would be to move rte_eal_intr_init() after
> rte_eal_dev_init().
That would work, but was worried it would break other devices.
Hi,
On 3/2/2015 5:03 PM, zhihong.wang at intel.com wrote:
> Fixed strict-aliasing rules breaking errors for some GCC version.
>
> Signed-off-by: Zhihong Wang
> ---
> .../common/include/arch/x86/rte_memcpy.h | 44
> --
> 1 file changed, 24 insertions(+), 20 deleti
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Michael Qiu
> Sent: Monday, March 02, 2015 8:32 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] app/test-pmd: Fix log issue without nic binded
>
> As hotplug has been enabled, start the testpmd with no
On 2015-03-06 11:30, Ananyev, Konstantin wrote:
>
> Hi Simon,
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Simon K?gstr?m
>> Sent: Friday, March 06, 2015 8:28 AM
>> To: dev at dpdk.org
>> Subject: Re: [dpdk-dev] [PATCH] headers: typeof -> __typeof__ t
From: "Chen Jing D(Mark)"
Add feature list for fm10k driver.
Signed-off-by: Chen Jing D(Mark)
---
doc/guides/rel_notes/new_features.rst | 20
1 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/doc/guides/rel_notes/new_features.rst
b/doc/guides/rel_notes/new
From: "Chen Jing D(Mark)"
DPDK introduced pmd driver for PCIE host-interface of Intel Ethernet
Switch FM1 Series, update programming guide to describe the new
driver and usage.
Signed-off-by: Chen Jing D(Mark)
---
.../prog_guide/i40e_ixgbe_igb_virt_func_drv.rst| 37 ++
Hi Michael,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Qiu, Michael
> Sent: Thursday, March 05, 2015 1:33 PM
> To: Tetsuya Mukawa; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] testpmd: Fix port validation code of "port
> stop all" command
>
> Hi, T
This patch reorder the code a bit to use loop instead of goto.
Besides, remove abudant check 'fd != -1'.
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_user/fd_man.c | 26 +++---
1 file changed, 11 insertions(+), 15 deletions(-)
diff --git a/lib/librte_vhost/vhost_user
combine sleep into select when there is no file descriptors to be monitored.
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_user/fd_man.c | 13 +++--
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/lib/librte_vhost/vhost_user/fd_man.c
b/lib/librte_vhost/vhost_user/fd
> -Original Message-
> From: Tetsuya Mukawa [mailto:mukawa at igel.co.jp]
> Sent: Thursday, March 05, 2015 7:30 AM
> To: dev at dpdk.org
> Cc: De Lara Guarch, Pablo; Tetsuya Mukawa
> Subject: [PATCH] testpmd: Fix port validation code of "port stop all"
> command
>
> When "port stop all"
Superseded by http://dpdk.org/ml/archives/dev/2015-February/014438.html
Hi Bruce!
Oh yea, this patch is quite old :)
I'm currently not working actively with DPDK. If no one else wants to do
it, I could do the update and add a unit test
/Tomas
On 2015-03-06 12:10, Bruce Richardson wrote:
> On Tue, Aug 12, 2014 at 11:47:57PM +0200, Tomas Vestelind wrote:
>> I added
On Fri, Mar 06, 2015 at 01:02:56PM +0100, Tomas Vestelind wrote:
> Hi Bruce!
>
> Oh yea, this patch is quite old :)
>
> I'm currently not working actively with DPDK. If no one else wants to do it,
> I could do the update and add a unit test
>
> /Tomas
Hi Tomas,
no pressure, since there doesn't
test_hash.c: In function ?test_crc32_hash_alg_equiv?:
error: format ?%lu? expects argument of type ?long unsigned int?,
but argument 2 has type ?size_t? [-Werror=format]
According to C99, for size_t type should use format "%zu"
Signed-off-by: Michael Qiu
Acked-by: Bruce Richardson
---
v3 --> v2
Hi,
On 3/2/2015 8:25 PM, Ouyang Changchun wrote:
> X550 should use the correct macro to set the VFTDT and VFRDT register address.
> This patch fixes the VF TX issue for Sageville.
>
> Signed-off-by: Changchun Ouyang
> ---
>
> Change in v2
>-- Fix one more mac type: ixgbe_mac_X550EM_x_vf.
>
>
Hi Stephen,
Have you considered supporting LSC interrupts in vmxnet3?
--
Thanks,
Robert
>From: Stephen Hemminger
>
>The Intel version of VMXNET3 driver does not handle link state properly.
>The VMXNET3 API returns 1 if connected and 0 if disconnected.
>Also need to return correct value to indi
On Thu, Mar 05, 2015 at 02:12:12AM +, Xuelin Shi wrote:
> Hi Bruce,
>
> Yes, it needs to swap the fields. The bit field is first identified as the
> uint8_t and then packed.
>
> Thanks,
> Shi xuelin
>
Am I right in thinking that this patch set supercedes that for
"lpm: use field access inst
./i686-native-linuxapp-gcc/include/rte_memcpy.h:592:23: error:
cast from pointer to integer of different size
[-Werror=pointer-to-int-cast]
dstofss = 16 - (int)((long long)(void *)dst & 0x0F) + 16;
Type 'long long' is 64-bit in i686 platform while 'void *'
is 32-bit.
Signed-off-by: Michael Qiu
On Tue, Aug 12, 2014 at 11:47:57PM +0200, Tomas Vestelind wrote:
> I added rte_hash_clear which clear the map from all previously added
> keys.
>
This patch is now quite old and needs an update to add the new API to the
rte_hash_version.map. A unit test for the new function would also be good to
h
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Tetsuya Mukawa
> Sent: Wednesday, March 4, 2015 3:12 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 1/3] BSD: Support Port Hotplug function
>
> This patch adds Hotplug support to BSD.
>
> Signed-off-by:
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Michal Jastrzebski
> Sent: Friday, March 06, 2015 7:39 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] testpmd: bond port creation did not enable
> bond port
>
> When invoking creation of bonded device
Hi Simon,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Simon K?gstr?m
> Sent: Friday, March 06, 2015 8:28 AM
> To: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] headers: typeof -> __typeof__ to unbreak
> C++11 code
>
> Ping? Konstantins simpler patc
> -Original Message-
> From: Xie, Huawei
> Sent: Friday, March 06, 2015 5:53 AM
> To: dev at dpdk.org
> Cc: Ananyev, Konstantin; Xie, Huawei
> Subject: [PATCH] lib/librte_vhost: use loop instead of goto
>
> This patch reorder the code a bit to use loop instead of goto.
> Besides, remove
> -Original Message-
> From: Xie, Huawei
> Sent: Friday, March 06, 2015 5:52 AM
> To: dev at dpdk.org
> Cc: Ananyev, Konstantin; Xie, Huawei
> Subject: [PATCH] lib/librte_vhost: combine select with sleep
>
> combine sleep into select when there is no file descriptors to be monitored.
>
Hi Keith,
On 03/04/2015 06:13 PM, Keith Wiles wrote:
> Move the rte.extvars.mk to an internal directory and
> update rte.vars.mk to find the file in the new location.
>
> Signed-off-by: Keith Wiles
> ---
> mk/internal/rte.extvars.mk | 81
> ++
> mk/r
Ping? Konstantins simpler patch is fine for me, but at least one of
these two would be very nice to have so that modern C++ code can use DPDK.
// Simon
On 2015-03-02 08:55, Simon K?gstr?m wrote:
> On 2015-02-27 17:24, Ananyev, Konstantin wrote:
>> Actually, I wonder wouldn't something like the on
Hi Michael,
> -Original Message-
> From: Qiu, Michael
> Sent: Friday, March 06, 2015 4:07 PM
> To: Chen, Jing D; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 2/2] doc: update release note for fm10k
> pmd driver
>
> On 3/6/2015 2:40 PM, Chen Jing D(Mark) wrote:
> > From: "Chen Jing D(M
On Fri, 6 Mar 2015 17:33:58 +0100
David Marchand wrote:
> Is eth_virtio_dev_init() not a better place rather than eal ?
>
> I prefer avoiding #ifdef pmd in eal.
No virtio_dev_init is called too late, after interrupt handling
threads are spawned.
/* Launch threads, called at application init().
On 05/03/2015 10:57, Alexandra Sava wrote:
> ping :-) ? Any thoughts about this ?
>
Sorry for the delay.
I'm not able to reproduce your issue with testpmd app.
I gather that you are using your own app, have you tried to use testpmd
to get queue stats?
If so, what command line options did you use
Hi Michael,
> -Original Message-
> From: Qiu, Michael
> Sent: Friday, March 6, 2015 4:23 PM
> To: Ouyang, Changchun; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 1/2] testpmd: HW vlan command
>
> On 3/6/2015 4:11 PM, Ouyang Changchun wrote:
> > This patch enables testpmd user can c
When invoking creation of bonded device using:
create bonded device mode socket in testpmd the bonded port was not
enabled at the end of cmd_create_bonded_device_parsed function.
This caused commands 'show port info' and 'show port stats' not working
properly with bonding device. This patch fixed
On 3/6/2015 4:10 PM, Ouyang Changchun wrote:
> Update the testpmd doc as there are new HW VLAN commands/options.
>
> Signed-off-by: Changchun Ouyang
> ---
Acked-by: Michael Qiu
> doc/guides/testpmd_app_ug/run_app.rst | 12 +++
> doc/guides/testpmd_app_ug/testpmd_funcs.rst | 33
>
On Fri, 6 Mar 2015 03:39:47 +
"Ouyang, Changchun" wrote:
>
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen
> > Hemminger
> > Sent: Friday, March 6, 2015 8:45 AM
> > To: dev at dpdk.org
> > Subject: [dpdk-dev] [PATCH 2/2] virtio: allow run
On 3/6/2015 4:11 PM, Ouyang Changchun wrote:
> This patch enables testpmd user can config port hw_vlan with more fine
> granularity:
> hw vlan filter, hw vlan strip, and hw vlan extend.
>
> Don't remove the original command(hw-vlan) considering that some user still
> want to use
> only one comman
On Fri, 6 Mar 2015 03:41:25 +
"Ouyang, Changchun" wrote:
>
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen
> > Hemminger
> > Sent: Friday, March 6, 2015 8:45 AM
> > To: dev at dpdk.org
> > Subject: [dpdk-dev] [PATCH 1/2] virtio: initializ
> -Original Message-
> From: Ouyang, Changchun
> Sent: Friday, March 6, 2015 4:00 PM
> To: dev at dpdk.org
> Cc: Butler, Siobhan A; De Lara Guarch, Pablo; Cao, Waterman; Ouyang,
> Changchun
> Subject: [PATCH v2 0/2]
>
> This patch enables testpmd user can config port hw_vlan with more fine
On 3/6/2015 2:40 PM, Chen Jing D(Mark) wrote:
> From: "Chen Jing D(Mark)"
>
> Add feature list for fm10k driver.
>
> Signed-off-by: Chen Jing D(Mark)
> ---
> doc/guides/rel_notes/new_features.rst | 20
> 1 files changed, 20 insertions(+), 0 deletions(-)
>
> diff --git a/do
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Cunming Liang
> Sent: Monday, February 16, 2015 7:34 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v1] doc: prog guide update for eal multi-pthread
>
> The patch add the multi-pthread section under EAL
On Thu, Mar 5, 2015 at 2:57 PM, Michael Qiu wrote:
> include/rte_cpuflags.h:154:2: error: redeclaration of enumerator ?REG_EAX?
> In file included from /usr/include/signal.h:358:0,
> from /usr/include/sys/wait.h:30,
> from /root/dpdk/app/test/test_mp_secondary.c:
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen
> Hemminger
> Sent: Friday, March 6, 2015 8:45 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 1/2] virtio: initialize iopl when device is
> initialized
>
> The virtio driver needs to use in/out
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen
> Hemminger
> Sent: Friday, March 6, 2015 8:45 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 2/2] virtio: allow running w/o vlan filtering
>
> Vlan filtering is an option, and not a requirement
On 3/6/2015 1:28 AM, Thomas Monjalon wrote:
> 2015-03-05 22:00, Michael Qiu:
>> test_hash.c: In function ?test_crc32_hash_alg_equiv?:
>> error: format ?%lu? expects argument of type ?long unsigned int?,
>> but argument 2 has type ?size_t? [-Werror=format]
>>
>> According to C99, for size_t type sho
On 3/6/2015 1:11 AM, Thomas Monjalon wrote:
> 2015-03-06 00:55, Michael Qiu:
>> CC rte_hash.o
>> Error: unsupported instruction `crc32'
>>
>> The root cause is that i686 platform does not support 'crc32q'
>> Need make it only available in x86_64 platform
>>
>> Signed-off-by: Michael Qiu
>> ---
>>
CC rte_hash.o
Error: unsupported instruction `crc32'
The root cause is that i686 platform does not support 'crc32q'
Need make it only available in x86_64 platform
Signed-off-by: Michael Qiu
---
v2 --> v1:
Make crc32 instruction only works in X86 platform
lib/librte_hash/rte_hash_crc.h
72 matches
Mail list logo
