Re: [dpdk-dev] [PATCH] vhost: postpone ring addresses translations at kick time only

On 11/06/2017 04:26 AM, Yao, Lei A wrote: Hi, Maxime -Original Message- From: Maxime Coquelin [mailto:maxime.coque...@redhat.com] Sent: Friday, November 3, 2017 11:57 PM To: dev@dpdk.org; y...@fridaylinux.org; Yao, Lei A Cc: m...@redhat.com Subject: Re: [PATCH] vhost: postpone ring a

Re: [dpdk-dev] [PATCH v2] examples/l3fwd: fix aliasing in port grouping

The 11/06/2017 09:59, Jerin Jacob wrote: > -Original Message- > > Date: Fri, 3 Nov 2017 16:13:51 +0530 > > From: Guduri Prathyusha > > To: tomasz.kante...@intel.com > > CC: jianbo@arm.com, guduriprathyu...@gmail.com, > > konstantin.anan...@intel.com, dev@dpdk.org, Guduri Prathyusha >

Re: [dpdk-dev] [PATCH 1/3] net/failsafe: fix removal handling lack

Hello Matan, On Thu, Nov 02, 2017 at 03:42:02PM +, Matan Azrad wrote: > There is time between the physical removal of the device until > sub-device PMDs get a RMV interrupt. At this time DPDK PMDs and > applications still don't know about the removal and may call sub-device > control operation

Re: [dpdk-dev] [PATCH v4 02/15] mem: introduce IOVA type

06/11/2017 06:38, santosh: > > On Monday 06 November 2017 07:11 AM, Thomas Monjalon wrote: > > The IO virtual addresses may be used instead of physical addresses. > > As IOVA is more generic, it should be used in most places instead > > of physical address wording. > > > > Signed-off-by: Thomas Mo

Re: [dpdk-dev] [PATCH] bus/pci: fix namespace of sysfs path function

There are others namespace inconsistencies with my pci move, I will send additional fixes later. On Mon, Nov 06, 2017 at 03:08:47AM +0100, Thomas Monjalon wrote: > The function pci_get_sysfs_path was moved from EAL to the PCI driver. > > The namespace is now fixed by adding "rte_" prefix. > The m

Re: [dpdk-dev] [PATCH v4 15/15] doc: add IOVA aware API changes in release notes

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon > Sent: Monday, November 6, 2017 1:42 AM > To: Santosh Shukla > Cc: olivier.m...@6wind.com; Gonzalez Monroy, Sergio > ; Burakov, Anatoly > ; dev@dpdk.org > Subject: [dpdk-dev] [PATCH v4 15/15] doc

Re: [dpdk-dev] [PATCH v4 02/15] mem: introduce IOVA type

On Monday 06 November 2017 02:07 PM, Thomas Monjalon wrote: > 06/11/2017 06:38, santosh: >> On Monday 06 November 2017 07:11 AM, Thomas Monjalon wrote: >>> The IO virtual addresses may be used instead of physical addresses. >>> As IOVA is more generic, it should be used in most places instead >>>

Re: [dpdk-dev] [PATCH v4 02/15] mem: introduce IOVA type

06/11/2017 09:51, santosh: > > On Monday 06 November 2017 02:07 PM, Thomas Monjalon wrote: > > 06/11/2017 06:38, santosh: > >> On Monday 06 November 2017 07:11 AM, Thomas Monjalon wrote: > >>> The IO virtual addresses may be used instead of physical addresses. > >>> As IOVA is more generic, it sho

Re: [dpdk-dev] What's the point of RTE_MBUF_PREFETCH_TO_FREE()?

On Fri, Nov 03, 2017 at 01:28:18PM -0700, Mike Stolarchuk wrote: > It seems to be used to prefetch the mbuf in preparation for a free of an > mbuf. > > But RTE_MBUF_PREFETCH_TO_FREE() currently does a prefetch for the > ffirst cache line in the mbuf, but doesn't a free do a put to the mbuf's > me

[dpdk-dev] [PATCH] app/crypto-perf: fix crypto op init

The mempool and the physical address of the crypto operation at mempool initialization were not being set, leading to incorrect physical addresses. Fixes: bf9d6702eca9 ("app/crypto-perf: use single mempool") Signed-off-by: Pablo de Lara --- app/test-crypto-perf/cperf_test_common.c | 2 ++ 1 fil

[dpdk-dev] [PATCH] net/mlx5: fix flow director delete with drop action

Removing a flow director rule with a drop action ends by not removing it due to a missing verbs drop specification in the conversion process between the flow director and generic flow API. Fixes: 4c3e9bcdd52e ("net/mlx5: support flow director") Signed-off-by: Nelio Laranjeiro --- drivers/net/ml

Re: [dpdk-dev] [PATCH] remove useless memzone includes

On Sat, Nov 04, 2017 at 02:00:08AM +0100, Thomas Monjalon wrote: > The memzone header is often included without good reason. > > Signed-off-by: Thomas Monjalon > --- Acked-by: Bruce Richardson

Re: [dpdk-dev] [PATCH] maintainers: update ptp client app

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Tuesday, October 24, 2017 10:56 AM > To: tho...@monjalon.net > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH] maintainers: update ptp client app > > Signed-off-by: Pa

Re: [dpdk-dev] [PATCH] maintainers: update job stats library

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Tuesday, October 24, 2017 10:57 AM > To: tho...@monjalon.net > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH] maintainers: update job stats library > > Signed-off-by:

[dpdk-dev] [PATCH] net/ixgbe: fix build on gcc 4.5.1

Fixes: 9a0752f498d2 ("net/ixgbe: enable inline IPsec") Signed-off-by: Radu Nicolau --- drivers/net/ixgbe/ixgbe_ipsec.c | 16 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ixgbe/ixgbe_ipsec.c b/drivers/net/ixgbe/ixgbe_ipsec.c index 99c0a73..105da11 100

[dpdk-dev] [PATCH] mempool: increase ABI version

API and ABI of mempool library has been changed in 17.11. Fixes: 02604520b2f2 ("mempool: remove unused flags argument") Fixes: 0cc0f8aaa35d ("mempool: change flags from int to unsigned int") Fixes: 6eac187bff30 ("mempool: add flags arg in xmem size and usage") Signed-off-by: Thomas Monjalon ---

Re: [dpdk-dev] [PATCH] net/ixgbe: fix build on gcc 4.5.1

06/11/2017 11:54, Radu Nicolau: > Fixes: 9a0752f498d2 ("net/ixgbe: enable inline IPsec") > > Signed-off-by: Radu Nicolau Please show the compilation error in the commit message. It is also better to briefly explain what was wrong. Thanks

[dpdk-dev] [PATCH] mk: remove useless list of core libraries

When moving the library dependencies handling from top Makefiles to library Makefiles, the list core-libs became useless. Fixes: cbc12b0a96f5 ("mk: do not generate LDLIBS from directory dependencies") Signed-off-by: Thomas Monjalon --- drivers/bus/Makefile | 4 drivers/crypto/Makefile

Re: [dpdk-dev] [PATCH] mempool: increase ABI version

On Monday 06 November 2017 04:38 PM, Thomas Monjalon wrote: > API and ABI of mempool library has been changed in 17.11. > > Fixes: 02604520b2f2 ("mempool: remove unused flags argument") > Fixes: 0cc0f8aaa35d ("mempool: change flags from int to unsigned int") > Fixes: 6eac187bff30 ("mempool: add f

[dpdk-dev] [PATCH] maintainers: fill git trees for net and crypto API

The ethdev API (including rte_flow) is managed in the dpdk-next-net tree. The crypto and security API is managed in the dpdk-next-crypto tree. Signed-off-by: Thomas Monjalon --- Pablo, do you agree to manage rte_security patches in the crypto tree? --- MAINTAINERS | 4 1 file changed, 4 i

[dpdk-dev] [PATCH v2] net/ixgbe: fix build on gcc 4.5.1

Fixes: 9a0752f498d2 ("net/ixgbe: enable inline IPsec") On SUSE11 with gcc 4.5.1 the following build error occurred, most likely because of improper handling of annonymous unions: DPDK/drivers/net/ixgbe/ixgbe_ipsec.c:579:4: error: unknown field ‘ipsec’ specified in initializer compilation terminat

[dpdk-dev] [PATCH] doc: update ABI/API policy

Following agreement at the DPDK Technical Board meeting of 2017-10-13 [1], update the documentation with the ABI/API policy changes. [1] http://dpdk.org/ml/archives/dev/2017-October/079961.html Signed-off-by: Bruce Richardson --- doc/guides/contributing/versioning.rst | 19 ++-

Re: [dpdk-dev] [PATCH] app/crypto-perf: add help option

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Wednesday, October 11, 2017 1:29 AM > To: Doherty, Declan > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH] app/crypto-perf: add help option > > Signed-off-by: Pablo de

Re: [dpdk-dev] [PATCH] app/crypto-perf: fix crypto op init

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara > Sent: Monday, November 6, 2017 9:36 AM > To: Doherty, Declan > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [dpdk-dev] [PATCH] app/crypto-perf: fix crypto op init > > The mempool and the phy

Re: [dpdk-dev] [PATCH] vhost: postpone ring addresses translations at kick time only

On Fri, Nov 03, 2017 at 04:52:35PM +0100, Maxime Coquelin wrote: > If multiple queue pairs are created but all are not used, the > device is never started, as unused queues aren't enabled and > their ring addresses aren't translated. The device is changed > to running state when all rings addresses

Re: [dpdk-dev] [PATCH v3 01/19] Revert "vhost: workaround MQ fails to startup"

On Fri, Nov 03, 2017 at 03:28:36PM +0100, Maxime Coquelin wrote: > > > On 11/03/2017 02:05 PM, Yuanhan Liu wrote: > >On Thu, Nov 02, 2017 at 10:40:26AM +0100, Maxime Coquelin wrote: > >>>Moving from QEMU v2.7.0 to v2.10.0 resolves the issue. However, herein > >>>lies the issue: QEMU v2.10.0 was

Re: [dpdk-dev] [PATCH v3 01/19] Revert "vhost: workaround MQ fails to startup"

On 11/06/2017 01:00 PM, Yuanhan Liu wrote: On Fri, Nov 03, 2017 at 03:28:36PM +0100, Maxime Coquelin wrote: On 11/03/2017 02:05 PM, Yuanhan Liu wrote: On Thu, Nov 02, 2017 at 10:40:26AM +0100, Maxime Coquelin wrote: Moving from QEMU v2.7.0 to v2.10.0 resolves the issue. However, herein lie

Re: [dpdk-dev] [PATCH v3 01/19] Revert "vhost: workaround MQ fails to startup"

On Mon, Nov 06, 2017 at 01:07:15PM +0100, Maxime Coquelin wrote: > > > On 11/06/2017 01:00 PM, Yuanhan Liu wrote: > >On Fri, Nov 03, 2017 at 03:28:36PM +0100, Maxime Coquelin wrote: > >> > >> > >>On 11/03/2017 02:05 PM, Yuanhan Liu wrote: > >>>On Thu, Nov 02, 2017 at 10:40:26AM +0100, Maxime Coqu

Re: [dpdk-dev] [PATCH v3 01/19] Revert "vhost: workaround MQ fails to startup"

On 11/06/2017 01:24 PM, Yuanhan Liu wrote: On Mon, Nov 06, 2017 at 01:07:15PM +0100, Maxime Coquelin wrote: On 11/06/2017 01:00 PM, Yuanhan Liu wrote: On Fri, Nov 03, 2017 at 03:28:36PM +0100, Maxime Coquelin wrote: On 11/03/2017 02:05 PM, Yuanhan Liu wrote: On Thu, Nov 02, 2017 at 10:4

Re: [dpdk-dev] [PATCH v3 01/19] Revert "vhost: workaround MQ fails to startup"

On Mon, Nov 06, 2017 at 01:50:35PM +0100, Maxime Coquelin wrote: > > > On 11/06/2017 01:24 PM, Yuanhan Liu wrote: > >On Mon, Nov 06, 2017 at 01:07:15PM +0100, Maxime Coquelin wrote: > >> > >> > >>On 11/06/2017 01:00 PM, Yuanhan Liu wrote: > >>>On Fri, Nov 03, 2017 at 03:28:36PM +0100, Maxime Coqu

[dpdk-dev] [PATCH 2/2] net/ixgbe : backplane port MDIO support

Initialize MDIO read/write functions for backplan port (IXGBE_DEV_ID_X550EM_A_KR_L) to enable read/write registers via MDIO Signed-off-by: Shweta Choudaha Reviewed-by: Chas Williams Reviewed-by: Luca Boccassi --- drivers/net/ixgbe/base/ixgbe_x550.c | 1 + 1 file changed, 1 insertion(+) diff -

[dpdk-dev] [PATCH 1/2] net/ixgbe: add and export MDIO APIs

Add ixgbe MDIO access APIs to read and write PHY registers when being used as a backplane port. Export these APIs via the map file Signed-off-by: Shweta Choudaha Reviewed-by: Chas Williams Reviewed-by: Luca Boccassi --- drivers/net/ixgbe/rte_pmd_ixgbe.c | 53 +

[dpdk-dev] [PATCH v2] net/mlx5: fix flow creation on port start

While the PMD avoids from creating hash RXQ with no hash fields and array of queues after the port was allready started, it lacks such protection when re-creating the flows after the port restarts. This may lead to inconsist behaviour for flows depending if they were created before or after the po

[dpdk-dev] [PATCH] eal: fix check for default plugin directory

The check for the existence of the default plugin directory calls stat using an incorrect variable, which will cause a NULL pointer dereference error. Coverity issue: 198440 Fixes: d6a4399cdfc9 ("eal: avoid error for non-existent default PMD path") Signed-off-by: Bruce Richardson --- lib/librte

[dpdk-dev] [PATCH v1] app/testpmd: fix fwd between two failsafe devices

When defining two failsafe devices in testpmd the port numbers of the failsafe devices may not be consecutive. For example: if failsafe device includes a PCI device and a TAP device then failsafe port numbers would be 0 and 3. Port 0 - failsafe #1 device Port 1 - PCI #1 device Port 2 - TAP #1 devic

Re: [dpdk-dev] [PATCH] vhost: disable reply-ack protocol feature if iommu feature disabled

>From: Maxime Coquelin [mailto:maxime.coque...@redhat.com] >Sent: Friday, November 3, 2017 5:58 PM >To: dev@dpdk.org; y...@fridaylinux.org; Kavanagh, Mark B >; tho...@monjalon.net; ktray...@redhat.com >Cc: Maxime Coquelin >Subject: [PATCH] vhost: disable reply-ack protocol feature if iommu feature

[dpdk-dev] [PATCH v2 1/2] net/ixgbe: add and export MDIO APIs

From: Shweta Choudaha Add ixgbe MDIO access APIs to read and write PHY registers when being used as a backplane port. Export these APIs via the map file Signed-off-by: Shweta Choudaha Reviewed-by: Chas Williams Reviewed-by: Luca Boccassi --- drivers/net/ixgbe/rte_pmd_ixgbe.c | 53 +

[dpdk-dev] [PATCH v2 2/2] net/ixgbe : backplane port MDIO support

From: Shweta Choudaha Initialize MDIO read/write functions for backplan port (IXGBE_DEV_ID_X550EM_A_KR_L) to enable read/write registers via MDIO Signed-off-by: Shweta Choudaha Reviewed-by: Chas Williams Reviewed-by: Luca Boccassi --- drivers/net/ixgbe/base/ixgbe_x550.c | 1 + 1 file changed

Re: [dpdk-dev] [PATCH v2] net/mlx5: fix flow creation on port start

On Mon, Nov 06, 2017 at 04:00:25PM +0200, Shahaf Shuler wrote: > While the PMD avoids from creating hash RXQ with no hash fields and > array of queues after the port was allready started, it lacks such > protection when re-creating the flows after the port restarts. > > This may lead to inconsist

[dpdk-dev] [PATCH] doc: adjust column width of PMD overview tables

The net PMD overview table is big and required to be shrinked. The crypto PMD tables had variable column sizes: the latest columns were smaller. The minimum width is set to 0.9em without any forced padding. The maximum width is set to 2em. The width of the first column set by sphinx is overriden t

Re: [dpdk-dev] [PATCH] doc: adjust column width of PMD overview tables

> -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Monday, November 6, 2017 2:41 PM > To: Mcnamara, John > Cc: dev@dpdk.org > Subject: [PATCH] doc: adjust column width of PMD overview tables > > The net PMD overview table is big and required to be shrinked

[dpdk-dev] [PATCH] doc: move dom0 removal notice in removed items

Since the release notes has a new section for removed items, the dom0 removal notice can be moved there. Signed-off-by: Thomas Monjalon --- doc/guides/rel_notes/release_17_11.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/guides/rel_notes/release_17_11.rst b/doc

Re: [dpdk-dev] [PATCH] doc: update ABI/API policy

> -Original Message- > From: Richardson, Bruce > Sent: Monday, November 6, 2017 11:28 AM > To: Mcnamara, John > Cc: dev@dpdk.org; Richardson, Bruce > Subject: [PATCH] doc: update ABI/API policy > > Following agreement at the DPDK Technical Board meeting of 2017-10-13 [1], > update the

Re: [dpdk-dev] [PATCH v4 08/15] mempool: rename addresses from physical to IOVA

On Mon, Nov 06, 2017 at 02:41:34AM +0100, Thomas Monjalon wrote: > The struct fields phys_addr_t rte_mempool_objhdr.physaddr and > rte_mempool_memhdr.phys_addr are renamed to rte_iova_t iova. > The deprecated names are kept in an anonymous union to avoid breaking > the API. > > Signed-off-by: Thom

Re: [dpdk-dev] [PATCH v4 09/15] mempool: rename address mapping function to IOVA

On Mon, Nov 06, 2017 at 02:41:35AM +0100, Thomas Monjalon wrote: > The function rte_mempool_virt2phy() is renamed to rte_mempool_virt2iova(). > The new function has one less parameter because it is unused. > The deprecated function is kept as an alias to avoid breaking the API. > > Signed-off-by:

Re: [dpdk-dev] [PATCH v4 10/15] mempool: rename populate functions to IOVA

On Mon, Nov 06, 2017 at 02:41:36AM +0100, Thomas Monjalon wrote: > The functions rte_mempool_populate_phys() and > rte_mempool_populate_phys_tab() are renamed to > rte_mempool_populate_iova() and rte_mempool_populate_iova_tab(). > The deprecated functions are kept as aliases to avoid breaking the A

Re: [dpdk-dev] [PATCH v4 11/15] mbuf: rename physical address to IOVA

On Mon, Nov 06, 2017 at 02:41:37AM +0100, Thomas Monjalon wrote: > From: Santosh Shukla > > Rename buf_physaddr to buf_iova. > Keep the deprecated name in an anonymous union to avoid breaking > the API. > > Signed-off-by: Santosh Shukla > Reviewed-by: Anatoly Burakov > Signed-off-by: Thomas Mo

Re: [dpdk-dev] [PATCH v4 12/15] mbuf: rename data address helpers to IOVA

On Mon, Nov 06, 2017 at 02:41:38AM +0100, Thomas Monjalon wrote: > The following inline functions and macros have been renamed to be > consistent with the IOVA wording: > > rte_mbuf_data_dma_addr -> rte_mbuf_data_iova > rte_mbuf_data_dma_addr_default -> rte_mbuf_data_iova_default > rte_pkt

Re: [dpdk-dev] [PATCH v4 10/15] mempool: rename populate functions to IOVA

06/11/2017 16:49, Olivier MATZ: > On Mon, Nov 06, 2017 at 02:41:36AM +0100, Thomas Monjalon wrote: > > The functions rte_mempool_populate_phys() and > > rte_mempool_populate_phys_tab() are renamed to > > rte_mempool_populate_iova() and rte_mempool_populate_iova_tab(). > > The deprecated functions a

Re: [dpdk-dev] [PATCH v4 11/15] mbuf: rename physical address to IOVA

06/11/2017 16:52, Olivier MATZ: > On Mon, Nov 06, 2017 at 02:41:37AM +0100, Thomas Monjalon wrote: > > From: Santosh Shukla > > > > Rename buf_physaddr to buf_iova. > > Keep the deprecated name in an anonymous union to avoid breaking > > the API. > > > > Signed-off-by: Santosh Shukla > > Review

Re: [dpdk-dev] [PATCH v4 12/15] mbuf: rename data address helpers to IOVA

06/11/2017 16:56, Olivier MATZ: > On Mon, Nov 06, 2017 at 02:41:38AM +0100, Thomas Monjalon wrote: > > The following inline functions and macros have been renamed to be > > consistent with the IOVA wording: > > > > rte_mbuf_data_dma_addr -> rte_mbuf_data_iova > > rte_mbuf_data_dma_addr_def

[dpdk-dev] [PATCH v1 2/2] pci: fix PCI lib prefix

Some symbols were introduced with the wrong prefix. Add the usual "rte_" prefix when needed. Fixes: c752998b5e2e ("pci: introduce library and driver") Signed-off-by: Gaetan Rivet --- drivers/bus/pci/bsd/pci.c | 2 +- drivers/bus/pci/linux/pci.c| 2 +- drivers/bus/pci/linux/pc

[dpdk-dev] [PATCH v1 0/2] Fix namespaces for VFIO and PCI

Some symbols are lacking the proper rte_ prefix. Gaetan Rivet (2): eal: use proper namespace for VFIO symbols pci: fix PCI lib prefix drivers/bus/pci/bsd/pci.c| 2 +- drivers/bus/pci/linux/pci.c | 4 ++-- drivers/bus/pci/linux/pci_vfio.c | 14 +++---

[dpdk-dev] [PATCH v1 1/2] eal: use proper namespace for VFIO symbols

Exposed VFIO functions simply uses a "vfio" prefix. Use the proper "rte_vfio" prefix for those symbols. Fixes: 279b581c897d ("vfio: expose functions") Signed-off-by: Gaetan Rivet --- drivers/bus/pci/linux/pci.c | 2 +- drivers/bus/pci/linux/pci_vfio.c | 12 ++-- li

Re: [dpdk-dev] [PATCH] maintainers: fill git trees for net and crypto API

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon > Sent: Monday, November 6, 2017 11:37 AM > To: Yigit, Ferruh ; De Lara Guarch, Pablo > > Cc: dev@dpdk.org > Subject: [dpdk-dev] [PATCH] maintainers: fill git trees for net and > crypto API > > T

Re: [dpdk-dev] [PATCH v4 10/15] mempool: rename populate functions to IOVA

On Mon, Nov 06, 2017 at 04:58:13PM +0100, Thomas Monjalon wrote: > 06/11/2017 16:49, Olivier MATZ: > > On Mon, Nov 06, 2017 at 02:41:36AM +0100, Thomas Monjalon wrote: > > > The functions rte_mempool_populate_phys() and > > > rte_mempool_populate_phys_tab() are renamed to > > > rte_mempool_populate

Re: [dpdk-dev] [PATCH 2/3] net/mlx4: adjust removal error

Hi Matan, On Sun, Nov 05, 2017 at 06:52:59AM +, Matan Azrad wrote: > Hi Adrien, > Thanks for the review :) > > Please see below comments. > > > -Original Message- > > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > > Sent: Friday, November 3, 2017 3:06 PM > > To: Matan A

Re: [dpdk-dev] [PATCH v2] igb_uio: add config option to control reset

On 11/4/2017 3:08 AM, Stephen Hemminger wrote: > > > On Nov 4, 2017 01:03, "Ferruh Yigit" > wrote: > > On 11/3/2017 12:42 PM, Roberts, Lee A. wrote: > > > > > >> -Original Message- > >> From: dev [mailto:dev-boun...@dpdk.org

[dpdk-dev] [PATCH v2] igb_uio: prevent reset for a list of devices

Some devices are having problem on device reset that happens during DPDK application exit [1]. Create a static list of devices and exclude them from device reset. [1] http://dpdk.org/ml/archives/dev/2017-November/080927.html Fixes: b58eedfc7dd5 ("igb_uio: issue FLR during open and release of dev

Re: [dpdk-dev] [PATCH] lib: fix a typo in kni header file (doxygen)

On 11/4/2017 7:28 AM, Rami Rosen wrote: > This patch fixes a trivial typo in rte_kni.h header > file (librte_kni). > > Signed-off-by: Rami Rosen kni: fix a typo in header file Fixes: 3fc5ca2f6352 ("kni: initial import") Cc: sta...@dpdk.org Acked-by: Ferruh Yigit

Re: [dpdk-dev] [PATCH] net/kni: remove eth_kni_drv declaration

On 11/4/2017 5:03 AM, Rami Rosen wrote: > This patch removes the forward declaration of eth_kni_drv > in rte_eth_kni.c; this forward declaration was made unnecessary > by commit 050fe6e9ff970ff92d842912136be8f9f52e171f > ("drivers/net: use ethdev allocation helper for vdev"), which > removes the

Re: [dpdk-dev] [PATCH] net/pcap: fix memory leak from missing pcap_close

On 11/5/2017 9:24 AM, Stefan Baranoff wrote: > In open_single_tx_pcap there is a call to pcap_open_dead which calls > malloc to create and return a pcap_t. That object is never freed in > this case. Other places it is freed by passing it back similar to the > way the pcap_dumper_t is in this case.

Re: [dpdk-dev] [PATCH v2] vfio: noiommu check error handling

31/10/2017 16:59, Jonas Pfefferle: > Check and report errors on open/read in noiommu check. > > Signed-off-by: Jonas Pfefferle I cannot decide to apply this patch as it does not explain what it is fixing, and as it is not reviewed.

Re: [dpdk-dev] [PATCH] mem: warn if address hint is not respected

31/10/2017 10:08, Jonas Pfefferle: > Print a warning if the --base-virtaddr hint is not respected > since this might lead to problems when mapping memory in > the secondary process. > > Signed-off-by: Jonas Pfefferle Anatoly, please review this patch. It does not seem to fix something, so it is

Re: [dpdk-dev] [PATCH v1 0/2] Fix namespaces for VFIO and PCI

06/11/2017 17:08, Gaetan Rivet: > Some symbols are lacking the proper rte_ prefix. > > Gaetan Rivet (2): > eal: use proper namespace for VFIO symbols > pci: fix PCI lib prefix Applied, thanks

Re: [dpdk-dev] [PATCH] eal: fix check for default plugin directory

Bruce Richardson writes: > The check for the existence of the default plugin directory calls stat > using an incorrect variable, which will cause a NULL pointer dereference > error. > > Coverity issue: 198440 > Fixes: d6a4399cdfc9 ("eal: avoid error for non-existent default PMD path") > > Signed-

[dpdk-dev] [PATCH v2 1/3] vhost: disable reply-ack protocol feature if iommu feature disabled

If the application has disabled VIRTIO_F_IOMMU_PLATFORM, disable VHOST_USER_PROTOCOL_F_REPLY_ACK protocol feature that is only mandatory with IOMMU for now. This is done to provide a way for the application to support multiqueue with old Qemu versions (v2.7.0 to v2.9.0) that have reply-ack feature

[dpdk-dev] [PATCH v2 2/3] vhost: add flag to enable iommu support

Qemu versions from v2.7.0 to v2.9.0 have their reply-ack protocol feature implementation broken with multiqueue. The reply-ack protocol feature is optional except for IOMMU feature. This patch introduce a new RTE_VHOST_USER_IOMMU_SUPPORT flag to enable VIRTIO_F_IOMMU_PLATFORM virtio feature. By d

[dpdk-dev] [PATCH v2 0/3] vhost: disable iommu support by default

This series disables IOMMU feature by default, and introduce a new flag passed at vhost device registration time to enable it explicitly. When disabled, patch 1 also disables reply-ack protocol feature to avoid Qemu v2.7.0-v2.9.0 reply-ack bug with multiqueue. Last patch adds a Vhost PMD "iommu-s

[dpdk-dev] [PATCH v2 3/3] net: vhost: add iommu-support parameter to enable IOMMU feature

Introduce a new iommu-support parameter to Vhost PMD that passes the RTE_VHOST_USER_IOMMU_SUPPORT flag at vhost device register time. Default value is 0, meaning that IOMMU support is disabled if not specified explicitly. Example to enable IOMMU support for a given device: --vdev 'net_vhost0,ifa

Re: [dpdk-dev] [PATCH] buildtools: fix icc build

02/11/2017 01:25, Ferruh Yigit: > There are random build errors in test reports [1]. Build error > is not directly related to DPDK but observed during DPDK build. > > When I get similar unexpected build errors in my system, found > out that /dev/null is invalid. > > It seems ICC overwrites the /d

Re: [dpdk-dev] [dpdk-stable] [PATCH] config: fix bnx2x for armv7a defconfig

31/10/2017 18:39, Ferruh Yigit: > Fixes: 02a8686263de ("mk: introduce ARMv7 architecture") > Cc: sta...@dpdk.org > > Signed-off-by: Ferruh Yigit > --- > Cc: Jan Viktorin > Cc: Jianbo Liu > --- > config/defconfig_arm-armv7a-linuxapp-gcc | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) A

Re: [dpdk-dev] [PATCH v1] mk: allow use of toolchain cflags

03/11/2017 10:40, David Hunt: > From: Vipin Varghese > > with 'export TOOLCHAIN_CFLAGS' the values are > not inherited throuhout make system. The change > appends the user defined cflags. Why do you want to use export from the shell environment? The standard way of overriding a variable with mak

Re: [dpdk-dev] [PATCH] mk: remove useless list of core libraries

06/11/2017 12:24, Thomas Monjalon: > When moving the library dependencies handling from top Makefiles > to library Makefiles, the list core-libs became useless. > > Fixes: cbc12b0a96f5 ("mk: do not generate LDLIBS from directory dependencies") > > Signed-off-by: Thomas Monjalon Applied

Re: [dpdk-dev] [PATCH] use macro to declare constructor functions

02/11/2017 23:10, Thomas Monjalon: > It is easier to find all constructor functions when they use > the same macros RTE_INIT or RTE_INIT_PRIO. > > The macro definitions are moved from rte_eal.h to rte_common.h. > > Signed-off-by: Thomas Monjalon Applied

Re: [dpdk-dev] [PATCH] remove include of generated config header

02/11/2017 22:38, Thomas Monjalon: > The file rte_config.h is generated and automatically included > with -include option. > The explicit includes in drivers and libraries are useless. > > Signed-off-by: Thomas Monjalon Applied

Re: [dpdk-dev] [PATCH] remove useless memzone includes

06/11/2017 11:44, Bruce Richardson: > On Sat, Nov 04, 2017 at 02:00:08AM +0100, Thomas Monjalon wrote: > > The memzone header is often included without good reason. > > > > Signed-off-by: Thomas Monjalon > > --- > Acked-by: Bruce Richardson Applied

Re: [dpdk-dev] [PATCH] mem: remove old function from symbol list

03/11/2017 12:24, Thomas Monjalon: > The function rte_mem_phy2mch() was removed with the support > of Xen dom0. > > Fixes: a7cb2e20d23c ("mem: remove API to get physical address in dom0") > > Signed-off-by: Thomas Monjalon Applied

Re: [dpdk-dev] [PATCH v4 00/15] make DPDK IOVA aware

06/11/2017 02:41, Thomas Monjalon: > Santosh Shukla (5): > mem: rename segment address from physical to IOVA > malloc: use pointer diff macro in IOVA mapping > mbuf: rename physical address to IOVA > cryptodev: rename physical address type to IOVA > drivers/net: rename physical address ty

Re: [dpdk-dev] net/pcap: remove single interface constraint (v2)

On 11/5/2017 2:15 AM, Ilya Matveychikov wrote: > Hello folks, > > This patch removes single interface constraint from the libpcap-based PMD. > The problem it solves is to allow PCAP device consists of more than single > device: > > # testpmd --vdev net_pcap0,iface=vethA,iface=vethB,iface=vethC a

Re: [dpdk-dev] [PATCH] mempool: increase ABI version

06/11/2017 12:33, santosh: > > On Monday 06 November 2017 04:38 PM, Thomas Monjalon wrote: > > API and ABI of mempool library has been changed in 17.11. > > > > Fixes: 02604520b2f2 ("mempool: remove unused flags argument") > > Fixes: 0cc0f8aaa35d ("mempool: change flags from int to unsigned int")

Re: [dpdk-dev] [PATCH] eal: fix version map experimental export section

25/10/2017 14:29, Harry van Haaren: > Before this commit, the EXPERIMENTAL version of ABI > derived from the DPDK_17.08 tag. In parallel there > was a DPDK_17.11 tag. > > Experimental map should always derive from the latest ABI, > so this patch moves the 17.11 section above EXPERIMENTAL, > and up

Re: [dpdk-dev] [PATCH] eal: force IOVA PA mode if KNI module inserted

02/11/2017 01:06, Ferruh Yigit: > Fix kernel crash with KNI because KNI requires physical addresses. > > When IOVA VA mode used, memzones and mbufs physical address fields > contain virtual addresses. But KNI relies on these fields to enable > kernel access for buffers. Those fields having virtual

Re: [dpdk-dev] [PATCH] eal/ppc: revert fix mmap for memory initialization

02/11/2017 14:58, Jonas Pfefferle: > This reverts commit 284ae3e9ff9a92575c28c858efd2c85c8de6d440 > ("eal/ppc: fix mmap for memory initialization").The logic if the > address hint is respected on mmap is no different on POWER than > on x86 however the address layout of userspace applications might

Re: [dpdk-dev] [PATCH] pci: get IOMMU class sPAPR iommu fix

03/11/2017 13:05, Jonas Pfefferle: > PPC64 sPAPR iommu does not support iova as va. > Use pa mode instead. > > Signed-off-by: Jonas Pfefferle Applied, thanks

Re: [dpdk-dev] [PATCH] bus/pci: fix namespace of sysfs path function

06/11/2017 09:43, Gaëtan Rivet: > There are others namespace inconsistencies with my pci move, I will send > additional fixes later. > > On Mon, Nov 06, 2017 at 03:08:47AM +0100, Thomas Monjalon wrote: > > The function pci_get_sysfs_path was moved from EAL to the PCI driver. > > > > The namespace

Re: [dpdk-dev] [dpdk-stable] [PATCH v2] igb_uio: prevent reset for a list of devices

06/11/2017 19:48, Ferruh Yigit: > Some devices are having problem on device reset that happens during DPDK > application exit [1]. > > Create a static list of devices and exclude them from device reset. > > [1] > http://dpdk.org/ml/archives/dev/2017-November/080927.html > > Fixes: b58eedfc7dd5 (

[dpdk-dev] [PATCH 2/3] hash: run-time function selection

Compile-time function selection can potentially lead to lower performance on generic builds done by distros. Replaced compile time flag checks with run-time function selection. Signed-off-by: Elza Mathew --- lib/librte_hash/rte_fbk_hash.c | 11 ++- lib/librte_hash/rte_fbk_hash.h | 8 ---

[dpdk-dev] [PATCH 1/3] hash: run-time function selection

Compile-time function selection can potentially lead to lower performance on generic builds done by distros. Replaced compile time flag checks with run-time function selection. Signed-off-by: Elza Mathew --- lib/librte_hash/rte_cuckoo_hash.c | 10 +- lib/librte_hash/rte_cuckoo_hash.h |

[dpdk-dev] [PATCH 3/3] net: run-time function selection

Compile-time function selection can potentially lead to lower performance on generic builds done by distros. Replaced compile time flag checks with run-time function selection. Signed-off-by: Elza Mathew --- lib/librte_net/rte_net_crc.c | 22 +- 1 file changed, 13 insertions(

Re: [dpdk-dev] [PATCH] eal/x86: revert select optimized memcpy at run-time

03/11/2017 13:47, Xiaoyun Li: > This patch reverts the patchset run-time Linking support including the > following 3 commits: > commit 84cc318424d4 ("eal/x86: select optimized memcpy at run-time") > commit c7fbc80fe60f ("test: select memcpy alignment unit at run-time") > commit 5f180ae32962 ("efd:

Re: [dpdk-dev] [PATCH] eal: fix check for default plugin directory

06/11/2017 21:36, Aaron Conole: > Bruce Richardson writes: > > > The check for the existence of the default plugin directory calls stat > > using an incorrect variable, which will cause a NULL pointer dereference > > error. > > > > Coverity issue: 198440 > > Fixes: d6a4399cdfc9 ("eal: avoid error

Re: [dpdk-dev] [PATCH v2] service: fix race in service on app lcore function

02/11/2017 10:41, Bruce Richardson: > On Wed, Nov 01, 2017 at 06:48:01PM +, Harry van Haaren wrote: > > This commit fixes a possible race condition if an application > > uses the service-cores infrastructure and the function to run > > a service on an application lcore at the same time. > > >

Re: [dpdk-dev] [PATCH v3] eal: add counter size for efd clean

04/09/2017 04:49, Tan, Jianfeng: > From: Wu, Jingjing > > > > For virtual device, the rte_intr_handle struct is > > initialized by the virtual device driver, including > > the event fd assignment. If the event fd need to be > > read for clean, an argument is required for the proper > > event fd re

Re: [dpdk-dev] [PATCH] lib: fix a typo in kni header file (doxygen)

04/11/2017 15:28, Rami Rosen: > This patch fixes a trivial typo in rte_kni.h header > file (librte_kni). > > Signed-off-by: Rami Rosen Merged with my patch (fixing other typos in libs) with your SoB. Thanks

Re: [dpdk-dev] [PATCH] lib/librte_distributor: Fix a couple typos

30/10/2017 08:03, Pavel Shirshov: > Signed-off-by: Pavel Shirshov Applied, thanks

Re: [dpdk-dev] [PATCH] lib: fix some typos

02/11/2017 20:30, Thomas Monjalon: > Signed-off-by: Thomas Monjalon > --- > lib/librte_eal/common/include/arch/arm/rte_vect.h | 2 +- > lib/librte_eventdev/rte_event_eth_rx_adapter.c| 2 +- > lib/librte_eventdev/rte_eventdev_pmd.h| 2 +- > 3 files changed, 3 insertions(+), 3 delet

Re: [dpdk-dev] [PATCH] lib/librte_table: fix copy paste error in lru hash table

27/10/2017 12:47, Jasvinder Singh: > Fixes the copy paste error in lru hash table parameters check. > > Coverity issue: 198433 > Fixes: b5cde2cb8c81 ("table: rework variable size key lru hash table") > > Signed-off-by: Jasvinder Singh > Acked-by: Cristian Dumitrescu Applied with title "table:

Re: [dpdk-dev] [dpdk-stable] [PATCH] cfgfile: fix NULL pointer dereference

27/10/2017 17:08, Jastrzebski, MichalX K: > > > > Function memchr() could return NULL and assign it to split[1] pointer. > > Additional check and error handing is made after memchr() call. > > > > Coverity issue: 195004 > > Fixes: a6a47ac9c2c9 ("cfgfile: rework load function") > > Cc: jacekx.pias

Re: [dpdk-dev] [PATCH] cfgfile: fix resource leak

27/10/2017 17:08, Jastrzebski, MichalX K: > > > > Unsuccesfull memory allocation for elements inside cfgfile > > structure could result in resource leak. > > Fixed by pointer verification after each malloc, > > if malloc fail - error branch is proceeded with freeing memory. > > > > Coverity issue

  1   2   >