[dpdk-dev] [PATCH] net/virtio-user: fix dev_init in legacy-mem mode

In legacy-mem mode, memory event callback registering is not supported, we should not return error in dev_init on this case. Fixes: 12ecb2f63b12 ("net/virtio-user: support memory hotplug") Signed-off-by: Xiao Wang Suggested-by: Tiwei Bie --- drivers/net/virtio/virtio_user/virtio_user_dev.c | 7

[dpdk-dev] [PATCH] doc: update release notes for mlx drivers

Signed-off-by: Shahaf Shuler --- doc/guides/rel_notes/release_18_05.rst | 27 +++ 1 file changed, 27 insertions(+) diff --git a/doc/guides/rel_notes/release_18_05.rst b/doc/guides/rel_notes/release_18_05.rst index 74ca3cf280..27241f3ea4 100644 --- a/doc/guides/rel_notes/

Re: [dpdk-dev] [PATCH] net/virtio-user: fix dev_init in legacy-mem mode

Hi Xiao, Next time, could you please devtools/check-git-log.sh script before posting. I tihnk the commit title should be changed to: net/virtio-user: fix device init in legacy-mem mode On 05/17/2018 09:35 AM, Xiao Wang wrote: In legacy-mem mode, memory event callback registering is not support

Re: [dpdk-dev] [PATCH V2] librte_hash: new hash del abi to return stored value

Hi Vijaya, > -Original Message- > From: Vijaya Mohan Guvva [mailto:vgu...@caviumnetworks.com] > Sent: Thursday, May 17, 2018 2:27 AM > To: Richardson, Bruce ; De Lara Guarch, Pablo > > Cc: dev@dpdk.org; Vijaya Mohan Guvva > Subject: [PATCH V2] librte_hash: new hash del abi to return stor

Re: [dpdk-dev] [PATCH] net/virtio-user: fix dev_init in legacy-mem mode

Hi, > -Original Message- > From: Maxime Coquelin [mailto:maxime.coque...@redhat.com] > Sent: Thursday, May 17, 2018 4:03 PM > To: Wang, Xiao W > Cc: dev@dpdk.org; Bie, Tiwei ; Yao, Lei A > > Subject: Re: [PATCH] net/virtio-user: fix dev_init in legacy-mem mode > > Hi Xiao, > > Next ti

[dpdk-dev] [PATCH] eventdev/eth_rx_adapter: update the note field

rte_event_eth_rx_adapter_create allocates eth_devices for currently available eth devices. For dynamically created eth devices a new instance for rx adapter has to be created. Signed-off-by: Vipin Varghese --- lib/librte_eventdev/rte_event_eth_rx_adapter.h | 5 - 1 file changed, 4 insertions

Re: [dpdk-dev] [PATCH] net/virtio-user: fix dev_init in legacy-mem mode

On 05/17/2018 09:35 AM, Xiao Wang wrote: In legacy-mem mode, memory event callback registering is not supported, we should not return error in dev_init on this case. Fixes: 12ecb2f63b12 ("net/virtio-user: support memory hotplug") Signed-off-by: Xiao Wang Suggested-by: Tiwei Bie --- drivers/

Re: [dpdk-dev] [PATCH v4 09/23] rte_mbuf.h: explicit casts for int16 to uint16

On Mon, May 14, 2018 at 01:10:12PM +0800, Andy Green wrote: > differences to the atomic16 are signed, but the > atomic16 itself is unsigned. It needs to be > made explicit with casts. > > Signed-off-by: Andy Green > --- > lib/librte_mbuf/rte_mbuf.h | 12 ++-- > 1 file changed, 6 inser

Re: [dpdk-dev] [PATCH v4 06/23] rte_ring_generic.h: stack declarations before code

On Mon, May 14, 2018 at 01:09:57PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_ring_generic.h: > In function '__rte_ring_move_prod_head': > /projects/lagopus/src/dpdk/build/include/rte_ring_generic.h:76:3: > warning: ISO C90 forbids mixed declarations and code > [-Wdecla

Re: [dpdk-dev] [PATCH v4 07/23] rte_ring.h: remove signed type flipflopping

On Mon, May 14, 2018 at 01:10:02PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_ring.h:350:46: > warning: conversion to 'uint32_t' {aka 'unsigned int'} > from 'int' may change the sign of the result > [-Wsign-conversion] > update_tail(&r->prod, prod_head, prod_next, is_

Re: [dpdk-dev] [PATCH v4 08/23] rte_mbuf.h: avoid warnings from inadvertant promotion

On Mon, May 14, 2018 at 01:10:07PM +0800, Andy Green wrote: > "1 + value", where value is an uint16_t causes promotion > to a signed int. The compiler complained that we are > shoving an int into a uint16_t return type with different > size and sign. > > Bumping and returning value directly inste

[dpdk-dev] [PATCH v3 0/4] Cryptodev API/ABI deprecation notices

v3: - Added an extra deprecation announcement (replacing rte_pci_device with rte_device) - Rebased against latest DPDK code v2: - Added an extra deprecation announcement - Bonded the other two deprecation notices with the new one in a patchset Pablo de Lara (4): doc: announce ABI change for

[dpdk-dev] [PATCH v3 1/4] doc: announce ABI change for crypto sym info struct

Since the API changes made in 17.08, the session mempool is not created anymore in each crypto device. Therefore, there is no need to have, in the cryptodev info structure, the maximum number of sessions supported per device and per queue pair. Signed-off-by: Pablo de Lara Acked-by: Fiona Trahe

[dpdk-dev] [PATCH v3 3/4] doc: announce deprecation for attach/detach crypto session

Functions rte_cryptodev_queue_pair_attach_sym_session and rte_cryptodev_queue_pair_detach_sym_sessions are not really used in any of the crypto drivers (only one driver implements it and it just return 0). Therefore, this API can be deprecated from 18.05 and removed in 18.08. Signed-off-by: Pablo

[dpdk-dev] [PATCH v3 2/4] doc: announce ABI change for crypto info struct

Cryptodev info structure currently contains a pointer to an rte_pci_device structure. This field depends on a specific bus type (PCI), which is not following a bus independent design. Following the same approach taken in ethdev, the field will be replaced with a pointer to an rte_device structure.

[dpdk-dev] [PATCH v3 4/4] doc: announce deprecation in crypto queue pair start/stop

Functions rte_cryptodev_queue_pair_start/stop are not really used in any of the crypto drivers (they all just return 0 or -ENOTSUP). Therefore, this API can be deprecated from 18.02 and removed in 18.05. Signed-off-by: Pablo de Lara Acked-by: Akhil Goyal --- doc/guides/rel_notes/deprecation.rst

Re: [dpdk-dev] How to dump DPDK log?

On 5/17/2018 3:41 AM, Sam wrote: > Oh, it should be user1,8 in dpdk-17.05 Yes, loglevel numbers are converted to more human readable format in this release, old releases are using numbers. > > OMG > > 2018-05-17 10:26 GMT+08:00 Sam >: > > How to set this p

Re: [dpdk-dev] [PATCH] maintainers: fix responsibility of flow API bits

Hi Adrien, > > > Subject: [PATCH] maintainers: fix responsibility of flow API bits > > > > > > The following commits lack MAINTAINERS entries for this mess. > > > > > > Fixes: 4d73b6fb9907 ("doc: add generic flow API guide") > > > Fixes: 19c90af6285c ("app/testpmd: add flow command") > > > Cc: s

Re: [dpdk-dev] [PATCH] bus/vdev: don't double space log messages

On 5/16/2018 10:51 PM, Stephen Hemminger wrote: > The VDEV_LOG() macro already adds a newline, don't duplicate. > > Signed-off-by: Stephen Hemminger Fixes: d22fcb225c24 ("bus/vdev: change log type") Reviewed-by: Ferruh Yigit

[dpdk-dev] [PATCH] maintainers: handoff ownership of Tap PMD

I have unfortunately no longer time enough for maintaining Tap PMD. Keith has kindly volunteered to take over maintainership. He's been at the origin of this PMD and knows well how it works. Signed-off-by: Pascal Mazon Acked-by: Keith Wiles --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+)

[dpdk-dev] [PATCH v2] net/tap: fix device removal when no queues exist

TAP device is created following its first queue creation. Multiple queues can be added or removed over time. In Linux terminology those are file descriptors which are opened or closed over time. As long as the number of opened file descriptors is positive - TAP device will appear as a Linux device.

[dpdk-dev] [PATCH] test/eventdev: add multi port test to suite

Add a new test to enhance the test suite, to allow multiple eth ports rx queue to be added to rx bridge adapter. Update the test function to reflect change of port index from 8 to 16 bit Signed-off-by: Vipin Varghese --- test/test/test_event_eth_rx_adapter.c | 87

Re: [dpdk-dev] [PATCH v4 01/23] lib/librte_eal: import libbsd strlcpy

On Mon, May 14, 2018 at 01:09:32PM +0800, Andy Green wrote: > Signed-off-by: Andy Green > --- > lib/librte_eal/common/eal_common_string_fns.c | 34 > > lib/librte_eal/common/include/rte_string_fns.h |7 + > 2 files changed, 36 insertions(+), 5 deletions(-) >

Re: [dpdk-dev] [PATCH v4 05/23] /lib/librte_eal: stage cast from uint64 to long

On Mon, May 14, 2018 at 01:09:52PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_random.h: > In function 'rte_srand': > /projects/lagopus/src/dpdk/build/include/rte_random.h:34:10: > warning: conversion to 'long int' from 'long unsigned int' > may change the sign of the re

Re: [dpdk-dev] [PATCH v2] net/mlx5: add bluefield device ID

On 5/15/2018 10:28 AM, Nélio Laranjeiro wrote: > On Tue, May 15, 2018 at 09:12:50AM +0300, Shahaf Shuler wrote: >> Signed-off-by: Shahaf Shuler > > Acked-by: Nelio Laranjeiro Is web patch coming to introduce the device support in https://dpdk.org/doc/nics?

Re: [dpdk-dev] [PATCH v4 10/23] rte_mbuf.h: make sure RTE-MIN compares same types

On Mon, May 14, 2018 at 01:10:17PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_common.h:384:2: > warning: conversion from 'int' to 'uint16_t' > {aka 'short unsigned int'} may change value [-Wconversion] > __extension__ ({ \ > ^ > /projects/lagopus/src/dpd

Re: [dpdk-dev] [PATCH v4 11/23] rte_mbuf.h: explicit cast restricting ptrdiff to uint16

On Mon, May 14, 2018 at 01:10:22PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_common.h:141:34: > warning: conversion from 'long unsigned int' to 'uint16_t' > {aka 'short unsigned int'} may change value [-Wconversion] > #define RTE_PTR_DIFF(ptr1, ptr2) ((uintptr_t)(ptr1

Re: [dpdk-dev] [PATCH v4 12/23] rte_mbuf.h: explicit cast for size type to uint32

On Mon, May 14, 2018 at 01:10:27PM +0800, Andy Green wrote: > Signed-off-by: Andy Green > --- > lib/librte_mbuf/rte_mbuf.h |2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h > index 0580ec8a0..169f3d3b0 100644 > ---

[dpdk-dev] [PATCH] ethdev: update description for functions

Change adds extra information on name parameter for API rte_eth_dev_get_name_by_port and rte_eth_dev_get_port_by_name. Signed-off-by: Vipin Varghese --- lib/librte_ethdev/rte_ethdev.h | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib

Re: [dpdk-dev] [PATCH v4 13/23] rte_mbuf.h: explicit casts to uint16 to avoid warnings

On Mon, May 14, 2018 at 01:10:32PM +0800, Andy Green wrote: > Signed-off-by: Andy Green > --- > lib/librte_mbuf/rte_mbuf.h | 15 --- > 1 file changed, 8 insertions(+), 7 deletions(-) > > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h > index 169f3d3b0..3cd76ab

Re: [dpdk-dev] [PATCH v4 14/23] rte_ether.h: explicit cast avoiding truncation warning

On Mon, May 14, 2018 at 01:10:37PM +0800, Andy Green wrote: > /projects/lagopus/src/dpdk/build/include/rte_ether.h:213:13: > warning: conversion from 'int' to 'uint8_t' > {aka 'unsigned char'} may change value [-Wconversion] > addr[0] &= ~ETHER_GROUP_ADDR; > /* clear multicast bit */ > > Signed-

Re: [dpdk-dev] [PATCH v4 11/23] rte_mbuf.h: explicit cast restricting ptrdiff to uint16

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson > Sent: Thursday, May 17, 2018 11:51 AM > To: Andy Green > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v4 11/23] rte_mbuf.h: explicit cast > restricting ptrdiff to uint16 > > On Mon, May

[dpdk-dev] [PATCH v1] net/mlx4: add an RSS hash update callback

Add an RSS hash update callback to eth_dev_ops. Signed-off-by: Ophir Munk --- drivers/net/mlx4/Makefile | 1 + drivers/net/mlx4/mlx4.c | 1 + drivers/net/mlx4/mlx4.h | 7 ++ drivers/net/mlx4/mlx4_rss.c | 59 + 4 files changed, 68 inser

Re: [dpdk-dev] [PATCH v3 3/4] doc: announce deprecation for attach/detach crypto session

Hi Pablo, > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Thursday, May 17, 2018 10:01 AM > To: Doherty, Declan ; akhil.go...@nxp.com > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH v3 3/4] doc: announce deprecatio

Re: [dpdk-dev] [PATCH v3 2/4] doc: announce ABI change for crypto info struct

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Thursday, May 17, 2018 10:01 AM > To: Doherty, Declan ; akhil.go...@nxp.com > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH v3 2/4] doc: announce ABI change for crypto

Re: [dpdk-dev] [PATCH] maintainers: fix responsibility of flow API bits

On Thu, May 17, 2018 at 09:26:15AM +, Iremonger, Bernard wrote: > Hi Adrien, > > > > > > > Subject: [PATCH] maintainers: fix responsibility of flow API bits > > > > > > > > The following commits lack MAINTAINERS entries for this mess. > > > > > > > > Fixes: 4d73b6fb9907 ("doc: add generic fl

Re: [dpdk-dev] [PATCH] app/testpmd: add to call detach for vdev when quitting

Hi Zhiyong, > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of > zhiyong.y...@intel.com > Sent: Thursday, May 17, 2018 2:00 PM > To: dev@dpdk.org > Cc: maxime.coque...@redhat.com; Yigit, Ferruh ; Bie, > Tiwei ; Yao, Lei A ; Yang, Zhiyong > > Subject: [dpdk-dev] [P

Re: [dpdk-dev] [PATCH v2] crypto/scheduler: fix multicore rings re-use

Hi, > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Kirill Rybalchenko > Sent: Wednesday, May 16, 2018 3:25 PM > To: dev@dpdk.org > Cc: sta...@dpdk.org; Rybalchenko, Kirill ; > Zhang, Roy Fan > Subject: [dpdk-dev] [PATCH v2] crypto/scheduler: fix multicore ring

Re: [dpdk-dev] [PATCH] maintainers: fix responsibility of flow API bits

Hi Adrien, > > > > > Subject: [PATCH] maintainers: fix responsibility of flow API > > > > > bits > > > > > > > > > > The following commits lack MAINTAINERS entries for this mess. > > > > > > > > > > Fixes: 4d73b6fb9907 ("doc: add generic flow API guide") > > > > > Fixes: 19c90af6285c ("app/test

Re: [dpdk-dev] [PATCH v3 4/4] doc: announce deprecation in crypto queue pair start/stop

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Thursday, May 17, 2018 10:01 AM > To: Doherty, Declan ; akhil.go...@nxp.com > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH v3 4/4] doc: announce deprecation in crypto

Re: [dpdk-dev] [PATCH v3] igb_uio: fail and log if kernel lock down is enabled

On Wed, May 16, 2018 at 03:42:20PM +0100, Ferruh Yigit wrote: > When EFI secure boot is enabled, it is possible to lock down kernel and > prevent accessing device BARs and this makes igb_uio unusable. > > Lock down patches are not part of the vanilla kernel but they are > applied and used by some

[dpdk-dev] [PATCH] net/avf: fix AVF traffic blocked issue

When resetting ports, traffic will be blocked. There is a mistake when getting hw info at avf_dev_stop. This causes the device stop without stopping queues. This patch fixes this issue. Fixes: 69dd4c3d0898 ("net/avf: enable queue and device") Cc: sta...@dpdk.org Signed-off-by: Xiaoyun Li --- dr

Re: [dpdk-dev] [PATCH v3] vhost: improve dirty pages logging performance

On 05/17/2018 06:50 AM, Tiwei Bie wrote: On Thu, May 17, 2018 at 06:06:34AM +0300, Michael S. Tsirkin wrote: On Wed, May 16, 2018 at 06:54:23PM +0200, Maxime Coquelin wrote: This patch caches all dirty pages logging until the used ring index is updated. The goal of this optimization is to fi

[dpdk-dev] [PATCH v4] vhost: improve dirty pages logging performance

This patch caches all dirty pages logging until the used ring index is updated. The goal of this optimization is to fix a performance regression introduced when the vhost library started to use atomic operations to set bits in the shared dirty log map. While the fix was valid as previous implement

Re: [dpdk-dev] [PATCH v4] vhost: improve dirty pages logging performance

Hi Tiwei, On 05/17/2018 01:44 PM, Maxime Coquelin wrote: This patch caches all dirty pages logging until the used ring index is updated. The goal of this optimization is to fix a performance regression introduced when the vhost library started to use atomic operations to set bits in the shared

Re: [dpdk-dev] [PATCH v4] vhost: improve dirty pages logging performance

On Thu, May 17, 2018 at 02:01:52PM +0200, Maxime Coquelin wrote: > Hi Tiwei, > > On 05/17/2018 01:44 PM, Maxime Coquelin wrote: > > This patch caches all dirty pages logging until the used ring index > > is updated. > > > > The goal of this optimization is to fix a performance regression > > intr

Re: [dpdk-dev] [PATCH] ethdev: update description for functions

On 5/17/2018 11:59 AM, Vipin Varghese wrote: > Change adds extra information on name parameter for API > rte_eth_dev_get_name_by_port and rte_eth_dev_get_port_by_name. > > Signed-off-by: Vipin Varghese > --- > lib/librte_ethdev/rte_ethdev.h | 9 - > 1 file changed, 8 insertions(+), 1 del

Re: [dpdk-dev] [dpdk-stable] [PATCH v4] vhost: improve dirty pages logging performance

On 5/17/2018 1:01 PM, Maxime Coquelin wrote: > Hi Tiwei, > > On 05/17/2018 01:44 PM, Maxime Coquelin wrote: >> This patch caches all dirty pages logging until the used ring index >> is updated. >> >> The goal of this optimization is to fix a performance regression >> introduced when the vhost libr

Re: [dpdk-dev] [PATCH v4 01/23] lib/librte_eal: import libbsd strlcpy

On 05/17/2018 06:36 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:09:32PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- lib/librte_eal/common/eal_common_string_fns.c | 34 lib/librte_eal/common/include/rte_string_fns.h |7 + 2 files ch

Re: [dpdk-dev] [PATCH v2] net/mlx5: add bluefield device ID

Thursday, May 17, 2018 1:49 PM, Ferruh Yigit: > Subject: Re: [dpdk-dev] [PATCH v2] net/mlx5: add bluefield device ID > > On 5/15/2018 10:28 AM, Nélio Laranjeiro wrote: > > On Tue, May 15, 2018 at 09:12:50AM +0300, Shahaf Shuler wrote: > >> Signed-off-by: Shahaf Shuler > > > > Acked-by: Nelio Lara

Re: [dpdk-dev] [PATCH] app/testbbdev: fix unchecked return value

> -Original Message- > From: Chalupnik, KamilX > Sent: Wednesday 16 May 2018 14:57 > To: Mokhtar, Amr ; De Lara Guarch, Pablo > > Cc: dev@dpdk.org; Chalupnik, KamilX > Subject: [PATCH] app/testbbdev: fix unchecked return value > > Fixing CHECKED_RETURN issue by checking values returned

Re: [dpdk-dev] [PATCH] maintainers: handoff ownership of Tap PMD

> On May 17, 2018, at 2:44 AM, Pascal Mazon wrote: > > I have unfortunately no longer time enough for maintaining Tap PMD. > Keith has kindly volunteered to take over maintainership. He's been at > the origin of this PMD and knows well how it works. > > Signed-off-by: Pascal Mazon > Acked-by:

Re: [dpdk-dev] [PATCH v4 01/23] lib/librte_eal: import libbsd strlcpy

On Thu, May 17, 2018 at 08:35:21PM +0800, Andy Green wrote: > > > On 05/17/2018 06:36 PM, Bruce Richardson wrote: > > On Mon, May 14, 2018 at 01:09:32PM +0800, Andy Green wrote: > > > Signed-off-by: Andy Green > > > --- > > > lib/librte_eal/common/eal_common_string_fns.c | 34 > > > +++

Re: [dpdk-dev] [PATCH v4 05/23] /lib/librte_eal: stage cast from uint64 to long

On 05/17/2018 06:47 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:09:52PM +0800, Andy Green wrote: /projects/lagopus/src/dpdk/build/include/rte_random.h: In function 'rte_srand': /projects/lagopus/src/dpdk/build/include/rte_random.h:34:10: warning: conversion to 'long int' from 'long

Re: [dpdk-dev] [PATCH v2] net/tap: fix device removal when no queues exist

> On May 17, 2018, at 2:47 AM, Ophir Munk wrote: > > TAP device is created following its first queue creation. Multiple > queues can be added or removed over time. In Linux terminology those > are file descriptors which are opened or closed over time. As long as > the number of opened file desc

Re: [dpdk-dev] [PATCH v4 01/23] lib/librte_eal: import libbsd strlcpy

On 05/17/2018 08:56 PM, Bruce Richardson wrote: On Thu, May 17, 2018 at 08:35:21PM +0800, Andy Green wrote: On 05/17/2018 06:36 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:09:32PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- lib/librte_eal/common/eal_common_string_

Re: [dpdk-dev] [PATCH v4 12/23] rte_mbuf.h: explicit cast for size type to uint32

On 05/17/2018 06:53 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:10:27PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- lib/librte_mbuf/rte_mbuf.h |2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.

Re: [dpdk-dev] [PATCH] doc: advise to specify LTS branch when backporting patches

16/05/2018 19:03, Luca Boccassi: > On Wed, 2018-05-16 at 16:19 +0100, Kevin Traynor wrote: > > On 05/16/2018 03:31 PM, luca.bocca...@gmail.com wrote: > > > From: Luca Boccassi > > > > > > We have many stable branches being maintaned at the same time, and > > > > typo > > > > > sometimes it's no

Re: [dpdk-dev] [PATCH] net/ixgbe: fix dcb configuration issue

Hi Qiming > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] > Sent: Thursday, May 17, 2018 9:23 PM > To: dev@dpdk.org > Cc: Wu, Jingjing ; Lu, Wenzhuo > ; Yang, Qiming ; > sta...@dpdk.org > Subject: [dpdk-dev] [PATCH] net/ixgbe: fix dcb configuration issue > > This patch remo

Re: [dpdk-dev] [PATCH] igb_uio: fail and log if kernel lock down is enabled

On 5/16/2018 12:47 PM, Neil Horman wrote: > On Tue, May 15, 2018 at 05:56:12PM +0100, Ferruh Yigit wrote: >> When EFI secure boot is enabled, it is possible to lock down kernel and >> prevent accessing device BARs and this makes igb_uio unusable. >> >> Lock down patches are not part of the vanilla

Re: [dpdk-dev] [PATCH v3] igb_uio: fail and log if kernel lock down is enabled

On 5/17/2018 12:34 PM, Neil Horman wrote: > On Wed, May 16, 2018 at 03:42:20PM +0100, Ferruh Yigit wrote: >> When EFI secure boot is enabled, it is possible to lock down kernel and >> prevent accessing device BARs and this makes igb_uio unusable. >> >> Lock down patches are not part of the vanilla

Re: [dpdk-dev] [PATCH] net/mlx5: fix default RSS level

On Tue, May 15, 2018 at 04:23:24PM +0300, Shahaf Shuler wrote: > Using inner RSS by default for GRE leads to memory corruption as the > extra flow items added for the inner RSS are not counted in the flow > attributes buffer size. > > Fixing by enforcing the default RSS level to be outer. This muc

Re: [dpdk-dev] [PATCH v4 13/23] rte_mbuf.h: explicit casts to uint16 to avoid warnings

On 05/17/2018 06:58 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:10:32PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- lib/librte_mbuf/rte_mbuf.h | 15 --- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte

Re: [dpdk-dev] [PATCH] net/ixgbe: fix too many interrupts

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wenzhuo Lu > Sent: Thursday, May 17, 2018 1:34 PM > To: dev@dpdk.org > Cc: Lu, Wenzhuo ; Luo, Michael > > Subject: [dpdk-dev] [PATCH] net/ixgbe: fix too many interrupts > > To support kernel VF, PBA bit is always

[dpdk-dev] [PATCH v5 02/21] rte_string_fns.h: fix gcc8.1 sign conv warning in lstrcpy

In file included from ./dpdk/dpdk.c:88: /projects/lagopus/src/dpdk/build/include/rte_string_fns.h: In function 'rte_strlcpy': /projects/lagopus/src/dpdk/build/include/rte_string_fns.h:58:9: warning: conversion to 'size_t' {aka 'long unsigned int'} from 'int' may change the sign of the result [-Wsig

[dpdk-dev] [PATCH v5 00/21] Fixes for GCC8 against lagopus

The following series fixes build problems in dpdk master headers, found when using it as the dpdk subproject in lagopus. These errors are coming when you try to use the dpdk headers, not when you build dpdk itself. v5 applies list comment from today. gcc8.1 errors corresponding to the problem pr

[dpdk-dev] [PATCH v5 01/21] lib/librte_ethdev: change eth-dev-ops API to return int

Signed-off-by: Andy Green --- drivers/net/ark/ark_ethdev_rx.c |4 ++-- drivers/net/ark/ark_ethdev_rx.h |3 +-- drivers/net/avf/avf_rxtx.c |4 ++-- drivers/net/avf/avf_rxtx.h |2 +- drivers/net/bnxt/bnxt_ethdev.c |5 +++-- drivers/net/dpaa/dpaa_et

Re: [dpdk-dev] [PATCH v4 01/23] lib/librte_eal: import libbsd strlcpy

On Thu, May 17, 2018 at 09:00:25PM +0800, Andy Green wrote: > > > On 05/17/2018 08:56 PM, Bruce Richardson wrote: > > On Thu, May 17, 2018 at 08:35:21PM +0800, Andy Green wrote: > > > > > > > > > On 05/17/2018 06:36 PM, Bruce Richardson wrote: > > > > On Mon, May 14, 2018 at 01:09:32PM +0800, A

[dpdk-dev] [PATCH v5 04/21] /lib/librte_eal: stage cast from uint64 to long

/projects/lagopus/src/dpdk/build/include/rte_random.h: In function 'rte_srand': /projects/lagopus/src/dpdk/build/include/rte_random.h:34:10: warning: conversion to 'long int' from 'long unsigned int' may change the sign of the result [-Wsign-conversion] srand48((long unsigned int)seedval); /proj

[dpdk-dev] [PATCH v5 05/21] rte_ring_generic.h: stack declarations before code

/projects/lagopus/src/dpdk/build/include/rte_ring_generic.h: In function '__rte_ring_move_prod_head': /projects/lagopus/src/dpdk/build/include/rte_ring_generic.h:76:3: warning: ISO C90 forbids mixed declarations and code [-Wdeclaration-after-statement] const uint32_t cons_tail = r->cons.tail;

[dpdk-dev] [PATCH v5 03/21] lib/librte_eal: explicit tmp cast

/projects/lagopus/src/dpdk/build/include/rte_memcpy.h: 793:2: note: in expansion of macro 'MOVEUNALIGNED_LEFT47' MOVEUNALIGNED_LEFT47(dst, src, n, srcofs); ^~~~ /projects/lagopus/src/dpdk/build/include/rte_memcpy.h: 649:51: warning: conversion from 'size_t' {aka 'long unsigned i

[dpdk-dev] [PATCH v5 07/21] rte_mbuf.h: avoid warnings from inadvertant promotion

"1 + value", where value is an uint16_t causes promotion to a signed int. The compiler complained that we are shoving an int into a uint16_t return type with different size and sign. Bumping and returning value directly instead removes the promotion and the problem. Signed-off-by: Andy Green --

[dpdk-dev] [PATCH v5 06/21] rte_ring.h: remove signed type flipflopping

/projects/lagopus/src/dpdk/build/include/rte_ring.h:350:46: warning: conversion to 'uint32_t' {aka 'unsigned int'} from 'int' may change the sign of the result [-Wsign-conversion] update_tail(&r->prod, prod_head, prod_next, is_sp, 1); The visible apis take unsigned int, then call a private api t

[dpdk-dev] [PATCH v5 08/21] rte_mbuf.h: explicit casts for int16 to uint16

differences to the atomic16 are signed, but the atomic16 itself is unsigned. It needs to be made explicit with casts. Signed-off-by: Andy Green If we want it for 18.05: Acked-by: Olivier Matz --- lib/librte_mbuf/rte_mbuf.h | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) d

[dpdk-dev] [PATCH v5 09/21] rte_mbuf.h: make sure RTE-MIN compares same types

/projects/lagopus/src/dpdk/build/include/rte_common.h:384:2: warning: conversion from 'int' to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] __extension__ ({ \ ^ /projects/lagopus/src/dpdk/build/include/rte_mbuf.h:1204:16: note: in expansion of macro 'RTE_MIN

[dpdk-dev] [PATCH v5 10/21] rte_mbuf.h: explicit cast restricting ptrdiff to uint16

/projects/lagopus/src/dpdk/build/include/rte_common.h:141:34: warning: conversion from 'long unsigned int' to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] #define RTE_PTR_DIFF(ptr1, ptr2) ((uintptr_t)(ptr1) - (uintptr_t)(ptr2)) ^ /projects

[dpdk-dev] [PATCH v5 11/21] rte_ether.h: explicit cast avoiding truncation warning

/projects/lagopus/src/dpdk/build/include/rte_ether.h:213:13: warning: conversion from 'int' to 'uint8_t' {aka 'unsigned char'} may change value [-Wconversion] addr[0] &= ~ETHER_GROUP_ADDR; /* clear multicast bit */ Signed-off-by: Andy Green Acked-by: Bruce Richardson --- lib/librte_net/rte_et

[dpdk-dev] [PATCH v5 12/21] rte_rwlock.h: gcc8 sign conversion warnings

In file included from /projects/lagopus/src/dpdk/ build/include/rte_rwlock.h:12, from ./mgr/lock.h:24, from ./mgr/sock_io.c:54: /projects/lagopus/src/dpdk/build/include/generic/ rte_rwlock.h: In function 'rte_rwlock_read_lock': /projects/lagopus/src/dpdk/build/incl

[dpdk-dev] [PATCH v5 14/21] rte_ip.h: cast around promotion to int

/projects/lagopus/src/dpdk/build/include/ rte_ip.h: In function 'rte_ipv4_cksum': /projects/lagopus/src/dpdk/build/include/ rte_ip.h:256:35: warning: conversion from 'int' to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] return (cksum == 0x) ? cksum : ~cksum;

[dpdk-dev] [PATCH v5 16/21] rte_ip.h: cast return checksum size to uint16

In file included from ./dpdk/worker.c:94: /projects/lagopus/src/dpdk/build/include/rte_ip.h: 332:9: warning: conversion from 'uint32_t' {aka 'unsigned int'} to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] return cksum; ^ /projects/lagopus/src/dpdk/build/incl

[dpdk-dev] [PATCH v5 17/21] rte_ip.h: cast away gcc8 warning on rte_ipv6_phdr_cksum

/projects/lagopus/src/dpdk/build/include/rte_ip.h: In function 'rte_ipv6_phdr_cksum': /projects/lagopus/src/dpdk/build/include/rte_ip.h: 378:18: warning: conversion to 'uint32_t' {aka 'unsigned int'} from 'int' may change the sign of the result [-Wsign-conversion] psd_hdr.proto = (ipv6_hdr->proto

[dpdk-dev] [PATCH v5 13/21] rte_ip.h: cast input to bswap16 to be uint16

In file included from /projects/lagopus/src/dpdk/ build/include/rte_ether.h:24, from /projects/lagopus/src/dpdk/ build/include/rte_ethdev.h:158, from ./dpdk/worker.c:90: /projects/lagopus/src/dpdk/build/include/rte_ip.h: In function 'rte_raw_cksum_mbuf': /projects/

[dpdk-dev] [PATCH v5 15/21] rte_ip.h: cast type decided by sizeof to uint32

/projects/lagopus/src/dpdk/build/include/rte_ip.h: In function 'rte_ipv4_udptcp_cksum': /projects/lagopus/src/dpdk/build/include/rte_byteorder.h: 51:24: warning: conversion from 'long unsigned int' to 'uint32_t' {aka 'unsigned int'} may change value [-Wconversion] #define rte_bswap16(x) ((uint16_t

[dpdk-dev] [PATCH v5 18/21] rte_mbuf.h: explicit cast for size type to uint32

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_pktmbuf_detach': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 1580:14: warning: conversion from 'long unsigned int' to 'uint32_t' {aka 'unsigned int'} may change value [-Wconversion] mbuf_size = sizeof(struct rte_mbuf)

[dpdk-dev] [PATCH v5 19/21] rte_mbuf.h: explicit casts to uint16 to avoid warnings

/projects/lagopus/src/dpdk/build/include/rte_mbuf.h: In function 'rte_pktmbuf_detach': /projects/lagopus/src/dpdk/build/include/rte_mbuf.h: 1583:17: warning: conversion from 'uint32_t' {aka 'unsigned int'} to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] m->priv_size = pri

[dpdk-dev] [PATCH v5 20/21] rte_ethdev.h: align sign and scope of temp var

/projects/lagopus/src/dpdk/build/include/rte_ethdev.h: In function 'rte_eth_rx_burst': /projects/lagopus/src/dpdk/build/include/rte_ethdev.h: 3836:18: warning: conversion to 'int16_t' {aka 'short int'} from 'uint16_t' {aka 'short unsigned int'} may change the sign of the result [-Wsign-conversion]

[dpdk-dev] [PATCH v5 21/21] rte_byteorder.h: explicit cast for return promotion

/projects/lagopus/src/dpdk/build/include/generic/ rte_byteorder.h: In function 'rte_constant_bswap16': /projects/lagopus/src/dpdk/build/include/generic/ rte_byteorder.h:54:45: warning: conversion from 'int' to 'uint16_t' {aka 'short unsigned int'} may change value [-Wconversion] uint16_t)(v)

[dpdk-dev] [PATCH v3] doc: advise to specify LTS branch when backporting patches

From: Luca Boccassi We have many stable branches being maintained at the same time, and sometimes it's not clear which branch a patch is being backported for. Note in the guidelines that it should be specified via the cover letter, annotation or using --subject-prefix. Also note to send only to s

Re: [dpdk-dev] [PATCH] doc: advise to specify LTS branch when backporting patches

On Thu, 2018-05-17 at 15:12 +0200, Thomas Monjalon wrote: > 16/05/2018 19:03, Luca Boccassi: > > On Wed, 2018-05-16 at 16:19 +0100, Kevin Traynor wrote: > > > On 05/16/2018 03:31 PM, luca.bocca...@gmail.com wrote: > > > > From: Luca Boccassi > > > > > > > > We have many stable branches being main

Re: [dpdk-dev] [PATCH v4 15/23] rte_ethdev.h: align sign and scope of temp var

On Mon, May 14, 2018 at 01:10:43PM +0800, Andy Green wrote: > Signed-off-by: Andy Green > --- > lib/librte_ethdev/rte_ethdev.h | 25 +++-- > 1 file changed, 15 insertions(+), 10 deletions(-) > While I dislike the changes below, since I believe it's always more readable to

Re: [dpdk-dev] [PATCH v5 01/21] lib/librte_ethdev: change eth-dev-ops API to return int

On Thu, May 17, 2018 at 09:48:57PM +0800, Andy Green wrote: > Signed-off-by: Andy Green > --- What's the reason for this change of type?

Re: [dpdk-dev] [PATCH v5 02/21] rte_string_fns.h: fix gcc8.1 sign conv warning in lstrcpy

On Thu, May 17, 2018 at 09:49:02PM +0800, Andy Green wrote: > In file included from ./dpdk/dpdk.c:88: > /projects/lagopus/src/dpdk/build/include/rte_string_fns.h: In > function 'rte_strlcpy': > /projects/lagopus/src/dpdk/build/include/rte_string_fns.h:58:9: > warning: conversion to 'size_t' {aka 'l

Re: [dpdk-dev] [PATCH] maintainers: handoff ownership of Tap PMD

On 5/17/2018 1:47 PM, Wiles, Keith wrote: > > >> On May 17, 2018, at 2:44 AM, Pascal Mazon wrote: >> >> I have unfortunately no longer time enough for maintaining Tap PMD. >> Keith has kindly volunteered to take over maintainership. He's been at >> the origin of this PMD and knows well how it wo

[dpdk-dev] [PATCH] rte_string_fns.h: fix gcc8.1 sign conv warning in lstrcpy

In file included from ./dpdk/dpdk.c:88: /projects/lagopus/src/dpdk/build/include/rte_string_fns.h: In function 'rte_strlcpy': /projects/lagopus/src/dpdk/build/include/rte_string_fns.h:58:9: warning: conversion to 'size_t' {aka 'long unsigned int'} from 'int' may change the sign of the result [-Wsig

Re: [dpdk-dev] [PATCH v5 01/21] lib/librte_ethdev: change eth-dev-ops API to return int

On 05/17/2018 09:55 PM, Bruce Richardson wrote: On Thu, May 17, 2018 at 09:48:57PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- What's the reason for this change of type? I was asked to do it on the list... the original patch I sent was triggered by gcc8 warnings and just caste

Re: [dpdk-dev] [dpdk-stable] [PATCH v3] net/tap: fix isolation mode toggling

On 5/14/2018 11:46 PM, Wiles, Keith wrote: > > >> On May 14, 2018, at 5:26 PM, Ophir Munk wrote: >> >> Running testpmd command "flow isolae 0" (i.e. disabling flow >> isolation) followed by command "flow isolate 1" (i.e. enabling >> flow isolation) may result in a TAP error: >> PMD: Kernel ref

Re: [dpdk-dev] [PATCH v4 15/23] rte_ethdev.h: align sign and scope of temp var

On 05/17/2018 09:54 PM, Bruce Richardson wrote: On Mon, May 14, 2018 at 01:10:43PM +0800, Andy Green wrote: Signed-off-by: Andy Green --- lib/librte_ethdev/rte_ethdev.h | 25 +++-- 1 file changed, 15 insertions(+), 10 deletions(-) While I dislike the changes below,

Re: [dpdk-dev] [PATCH v4 15/23] rte_ethdev.h: align sign and scope of temp var

On Thu, May 17, 2018 at 10:17:04PM +0800, Andy Green wrote: > > > On 05/17/2018 09:54 PM, Bruce Richardson wrote: > > On Mon, May 14, 2018 at 01:10:43PM +0800, Andy Green wrote: > > > Signed-off-by: Andy Green > > > --- > > > lib/librte_ethdev/rte_ethdev.h | 25 +++-- > >

Re: [dpdk-dev] [PATCH] app/testpmd: add to call detach for vdev when quitting

Bernard, Thanks for your review. > -Original Message- > From: Iremonger, Bernard > Sent: Thursday, May 17, 2018 7:23 PM > To: Yang, Zhiyong ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Yigit, Ferruh ; Bie, > Tiwei ; Yao, Lei A ; Yang, Zhiyong > > Subject: RE: [dpdk-dev] [PATCH] app/t

Re: [dpdk-dev] [PATCH] igb_uio: fail and log if kernel lock down is enabled

On Thu, 17 May 2018 14:23:46 +0100 Ferruh Yigit wrote: > On 5/16/2018 12:47 PM, Neil Horman wrote: > > On Tue, May 15, 2018 at 05:56:12PM +0100, Ferruh Yigit wrote: > >> When EFI secure boot is enabled, it is possible to lock down kernel and > >> prevent accessing device BARs and this makes igb

  1   2   >