Re: [dpdk-dev] [PATCH] eal/ppc: fix secondary process to map hugepages in correct order

Thomas, We have several different internal fixes and didn't get a conclusion. Let me summarize them and give a final patch sets. Thanks for your reminder! -Original Message- From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] Sent: 2017年2月15日 16:52 To: Sergio Gonzalez Monroy ; Chao

Re: [dpdk-dev] [PATCH 1/7] eal: use different constructor priorities for initcalls

On Wednesday 15 February 2017 08:35 PM, Jan Blunck wrote: On Wed, Feb 15, 2017 at 3:37 PM, Shreyansh Jain wrote: On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: --- a/lib/librte_eal/common/include/rte_eal.h +++ b/lib/librte_eal/common/include/rte_eal.h @@ -258,8 +258,16 @@ static in

Re: [dpdk-dev] [PATCHv7 03/47] common/dpaa2: adding qbman driver

Hello Ferruh, On Thursday 16 February 2017 06:09 AM, Hemant Agrawal wrote: QBMAN, is a hardware block which interfaces with the other accelerating hardware blocks (For e.g., WRIOP) on NXP's DPAA2 SoC for queue, buffer and packet scheduling. This patch introduces a userspace driver for interfaci

[dpdk-dev] [PATCH] eventdev: event device to contain rte device holder

Signed-off-by: Nipun Gupta rte_device is a generic device which is available to the applications and EAL. This patch replaces rte_pci_device in 'struct rte_eventdev' and in 'struct rte_event_dev_info' with common rte_device. --- drivers/event/skeleton/skeleton_eventdev.c | 2 +- lib/librte_event

[dpdk-dev] [PATCH] net/i40e: fix wrong TC bitmap of VEB

When setting up the VEB, default TC bitmap is used. But after setting the default TC bitmap, it's not stored. So when we're trying to get the enabled TCs on the VEB, it's always wrong. Fixes: 5135f3ca49a7 ("i40e: enable DCB in VMDQ VSIs") CC: sta...@dpdk.org Signed-off-by: Wenzhuo Lu --- driver

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> On Feb 15, 2017, at 2:06 PM, Jan Blunck wrote: > > On Wed, Feb 15, 2017 at 7:09 PM, Wiles, Keith wrote: >> >> I guess I see this differently, meaning we modified the system to put vdev >> devices last only because we do not have clean way to startup the system for >> pdev/vdev devices. The

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wed, Feb 15, 2017 at 7:09 PM, Wiles, Keith wrote: > > I guess I see this differently, meaning we modified the system to put vdev > devices last only because we do not have clean way to startup the system for > pdev/vdev devices. The application should be agnostic to the devices being > start

[dpdk-dev] [PATCHv7 46/47] bus/fslmc: frame queue based dq storage alloc

This patch adds generic functions for allowing dq storage for the frame queues. As the frame queues are common resource for different drivers this is helpful. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c| 32 + drivers/bus/fslmc/porta

[dpdk-dev] [PATCHv7 47/47] net/dpaa2: enable frame queue based dequeuing

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 6dddc3b..c6ee406 100644 --- a/drivers/net/dpaa2/dpaa2_ethdev.c +++ b/drivers/net

[dpdk-dev] [PATCHv7 43/47] config: add configuration for toggling physical addressing

Signed-off-by: Hemant Agrawal --- config/common_base| 1 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 1 + 2 files changed, 2 insertions(+) diff --git a/config/common_base b/config/common_base index 664cafc..3f5a356 100644 --- a/config/common_base +++ b/config/common_bas

[dpdk-dev] [PATCHv7 45/47] net/dpaa2: enable DMA Mapping during device scanning

Signed-off-by: Shreyansh Jain --- drivers/net/dpaa2/dpaa2_ethdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 64f41d9..6dddc3b 100644 --- a/drivers/net/dpaa2/dpaa2_ethdev.c +++ b/drivers/net/dpaa2/dpaa2_ethdev.c

[dpdk-dev] [PATCHv7 44/47] bus/fslmc: add support for DMA mapping for ARM SMMU

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 96 + drivers/bus/fslmc/fslmc_vfio.h | 1 + drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 + 3 files changed, 98 insertions(+) diff --git a/drivers/bus/fslmc/fslmc_vfio.c

[dpdk-dev] [PATCHv7 42/47] net/dpaa2: enable physical addressing for packet buffers

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 4 ++-- drivers/net/dpaa2/dpaa2_rxtx.c | 16 +--- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c index

[dpdk-dev] [PATCHv7 40/47] bus/fslmc: add physical-virtual address translation helpers

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 66 + 1 file changed, 66 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index c26360d3..ad8a22f 100644 --- a/drivers/bus/fslm

[dpdk-dev] [PATCHv7 41/47] pool/dpaa2: enable physical addressing for pool buffers

Signed-off-by: Hemant Agrawal --- drivers/pool/dpaa2/dpaa2_hw_mempool.c | 19 --- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/pool/dpaa2/dpaa2_hw_mempool.c b/drivers/pool/dpaa2/dpaa2_hw_mempool.c index 0c8de51..ca42418 100644 --- a/drivers/pool/dpaa2/dp

[dpdk-dev] [PATCHv7 39/47] net/dpaa2: handle non-hardware backed buffer pool

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_rxtx.c | 75 -- 1 file changed, 73 insertions(+), 2 deletions(-) diff --git a/drivers/net/dpaa2/dpaa2_rxtx.c b/drivers/net/dpaa2/dpaa2_rxtx.c index c1ea33a..a94761c 100644 --- a/drivers/net/dpaa2/dp

[dpdk-dev] [PATCHv7 37/47] net/dpaa2: basic stats support

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 86 ++ 2 files changed, 87 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index 0660cab..d43f

[dpdk-dev] [PATCHv7 38/47] net/dpaa2: enable stashing for LS2088A devices

As the hardware determines which core will process which packet, performance is boosted by direct cache warming/stashing as well as by providing biasing for core-to-flow affinity, which ensures that flow-specific data structures can remain in the core’s cache. This patch enables the one cache line

[dpdk-dev] [PATCHv7 34/47] net/dpaa2: enable packet Rx and Tx operations

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 4 + drivers/net/dpaa2/dpaa2_ethdev.h | 3 + drivers/net/dpaa2/dpaa2_rxtx.c | 260 +++ 4 files changed, 268 insertions(+) create mode 100644 dr

[dpdk-dev] [PATCHv7 36/47] net/dpaa2: link status update

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 107 + 2 files changed, 108 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index 0746d4b..06

[dpdk-dev] [PATCHv7 35/47] net/dpaa2: support for Rx packet parsing and packet type

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/base/dpaa2_hw_dpni_annot.h | 257 +++ drivers/net/dpaa2/dpaa2_ethdev.c | 23 +++ drivers/net/dpaa2/dpaa2_rxtx.c | 91 +- 4 files ch

[dpdk-dev] [PATCHv7 31/47] bus/fslmc: define VLAN header length

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 4 1 file changed, 4 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 1af93a5..2a8d9e5 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h +++ b/dr

[dpdk-dev] [PATCHv7 33/47] bus/fslmc: add packet FLE definitions

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 53 + 1 file changed, 53 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 2a8d9e5..c26360d3 100644 --- a/drivers/bus/fslm

[dpdk-dev] [PATCHv7 32/47] net/dpaa2: add MTU configuration support

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 34 ++ 2 files changed, 35 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index b7c274a..a6b7964

[dpdk-dev] [PATCHv7 30/47] net/dpaa2: add support for promiscuous mode

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 41 ++ 2 files changed, 42 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index d50c62e..b7c2

[dpdk-dev] [PATCHv7 29/47] net/dpaa2: add support for L3 and L4 checksum offload

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 2 ++ drivers/net/dpaa2/dpaa2_ethdev.c | 72 +++--- 2 files changed, 70 insertions(+), 4 deletions(-) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini in

[dpdk-dev] [PATCHv7 28/47] bus/fslmc: introduce true and false macros

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 6 ++ 1 file changed, 6 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 8efac2d..1af93a5 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h +++ b/

[dpdk-dev] [PATCHv7 27/47] net/dpaa2: attach the buffer pool to dpni

This patch configures a MC-DPNI based DPAA2 PMD network port with a DPBP based buffer pool. Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 4 +++ drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 57 +++ drivers/net/dpaa2/dpaa2_ethdev.c | 62

[dpdk-dev] [PATCHv7 25/47] net/dpaa2: configure MAC address at init

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 28 drivers/net/dpaa2/dpaa2_ethdev.h | 3 +++ 2 files changed, 31 insertions(+) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index c14b4df..ab9dfe6 100644 --- a/

[dpdk-dev] [PATCHv7 26/47] bus/fslmc: define hardware annotation area size

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 10 ++ 1 file changed, 10 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 42c5517..8efac2d 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h

[dpdk-dev] [PATCHv7 23/47] net/dpaa2: adding eth ops to dpaa2

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/Makefile | 4 + drivers/net/dpaa2/dpaa2_ethdev.c | 410 - drivers/net/dpaa2/dpaa2_ethdev.h | 15 ++ 4 files changed, 429 insertions(+), 1 deletion(-)

[dpdk-dev] [PATCHv7 24/47] net/dpaa2: add RSS flow distribution

Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 287 + drivers/net/dpaa2/dpaa2_ethdev.c | 31 +++- drivers/net/dpaa2/dpaa2_ethdev.h

[dpdk-dev] [PATCHv7 22/47] bus/fslmc: define queues for DPAA2 devices

Before DPAA2 devices can communicate using hardware queues, this patch adds queue definitions in the FSLMC bus which the DPAA2 devices would instantitate. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 20 1 file changed, 20 insertions(+) diff -

[dpdk-dev] [PATCHv7 21/47] bus/fslmc: affine dpio to crypto threads

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c| 45 + drivers/bus/fslmc/portal/dpaa2_hw_dpio.h| 3 ++ drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 + 3 files changed, 49 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2

[dpdk-dev] [PATCHv7 20/47] pool/dpaa2: add DPAA2 hardware offloaded mempool

Adding NXP DPAA2 architecture specific mempool support Each mempool instance is represented by a DPBP object from the FSL-MC bus. This patch also registers a dpaa2 type MEMPOOL OPS Signed-off-by: Hemant Agrawal --- MAINTAINERS | 1 + config/common_base

[dpdk-dev] [PATCHv7 19/47] bus/fslmc: dpio portal driver

The portal driver is bound to DPIO objects discovered on the fsl-mc bus and provides services that: - allow other drivers, such as the Ethernet driver, to enqueue and dequeue frames for their respective objects A system will typically allocate 1 DPIO object per CPU to allow queuing operations to

[dpdk-dev] [PATCHv7 16/47] net/dpaa2: add debug log support

Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 5 + drivers/net/dpaa2/dpaa2_ethdev.c | 9 +++-- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/dpaa2/Makefile b/drivers/net/dpaa2/Makefile index c6a2764..966377a 100644 --- a/drivers/net/dpa

[dpdk-dev] [PATCHv7 18/47] config: enable support for DPAA2 debug logging

Signed-off-by: Hemant Agrawal --- config/common_base| 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 5 + 2 files changed, 10 insertions(+) diff --git a/config/common_base b/config/common_base index 11760a4..781d97b 100644 --- a/config/common_base +++ b/config/c

[dpdk-dev] [PATCHv7 17/47] common/dpaa2: add debug log support

Signed-off-by: Hemant Agrawal --- drivers/common/dpaa2/qbman/Makefile | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/common/dpaa2/qbman/Makefile b/drivers/common/dpaa2/qbman/Makefile index 18bca6b..771bdc6 100644 --- a/drivers/common/dpaa2/qbman/Makefile +++ b/drivers/common/dp

[dpdk-dev] [PATCHv7 13/47] net/dpaa2: introducing NXP DPAA2 PMD driver

add support for fsl-mc bus based dpaa2 pmd driver. Signed-off-by: Hemant Agrawal --- MAINTAINERS | 1 + config/common_base | 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 5 + drivers/bus/Makefile| 2 +

[dpdk-dev] [PATCHv7 11/47] bus/fslmc: add vfio support

Add support for using VFIO for dpaa2 based fsl-mc bus. There are some differences in the way vfio used for fsl-mc bus from the eal vfio. - The scanning of bus for individual objects on the basis of the DPRC container. - The use and mapping of MC portal for object access With the evolution of

[dpdk-dev] [PATCHv7 12/47] bus/fslmc: scan for net and sec devices

This patch will add support in fslmc vfio process to scan and parse the dpni and dpseci object for net and crypto devices. It will add the scanned devices to the fslmc bus. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 63 +- 1 file ch

[dpdk-dev] [PATCHv7 15/47] bus/fslmc: add debug log support

Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 5 +++ drivers/bus/fslmc/fslmc_logs.h | 76 ++ 2 files changed, 81 insertions(+) create mode 100644 drivers/bus/fslmc/fslmc_logs.h diff --git a/drivers/bus/fslmc/Makefile b/drivers/bus/fs

[dpdk-dev] [PATCHv7 14/47] doc: add DPAA2 NIC details

This patch adds the NXP dpaa2 architecture and pmd details in the Network interfaces section. Signed-off-by: Hemant Agrawal Acked-by: John McNamara --- MAINTAINERS| 1 + doc/guides/nics/dpaa2.rst | 593 + doc/guides/nics

[dpdk-dev] [PATCHv7 10/47] eal/vfio: adding vfio utility functions in map file

adding extra vfio utility functions to map file. They will be used by other vfio supported buses like fslmc bus for NXP DPAA2 devices Signed-off-by: Hemant Agrawal --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 3 +++ lib/librte_eal/linuxapp/eal/rte_eal_version.map | 3 +++ 2 files change

[dpdk-dev] [PATCHv7 09/47] bus/fslmc: add mc dpseci object support

dpseci represent a instance of SEC HW in DPAA2. Signed-off-by: Cristian Sovaiala Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/mc/dpseci.c | 534 ++ drivers/bus/fslmc/mc/fsl_dpseci.h | 668 +++

[dpdk-dev] [PATCHv7 08/47] bus/fslmc: add mc dpbp object support

DPBP object represent a hw based buffer pool instance in the DPAA2 hardware. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/mc/dpbp.c | 237 drivers/bus/fslmc/mc/

[dpdk-dev] [PATCHv7 07/47] bus/fslmc: add mc dpio object support

This patch adds the DPIO object support in MC driver. DPIO - Data Path Input Output represent the processing context to access the QBMAN HW for packet I/O. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/mc/

[dpdk-dev] [PATCHv7 06/47] bus/fslmc: add mc dpni object support

This patch add support for dpni object support in MC driver. DPNI represent a network interface object in DPAA2. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile |1 + drivers/bus/fslmc/mc/dpni.c | 739

[dpdk-dev] [PATCHv7 05/47] bus/fslmc: introduce MC object functions

This patch intoduces the DPAA2 MC(Management complex Driver). This is a minimal set of low level functions to send and receive commands to the fsl-mc. It includes support for basic management commands and commands to manipulate MC objects. This is common to be used by various DPAA2 PMDs. e.g.net,

[dpdk-dev] [PATCHv7 02/47] mk: handle intra drivers dependencies for shared build

From: Shreyansh Jain Suggested-by: Ferruh Yigit Signed-off-by: Shreyansh Jain --- mk/rte.lib.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mk/rte.lib.mk b/mk/rte.lib.mk index 33a5f5a..ac4df9a 100644 --- a/mk/rte.lib.mk +++ b/mk/rte.lib.mk @@ -79,7 +79,7 @@ endif # T

[dpdk-dev] [PATCHv7 04/47] bus/fslmc: introducing fsl-mc bus driver

The fslmc bus driver is a rte_bus driver which scans the fsl-mc bus for NXP DPAA2 SoCs. Signed-off-by: Hemant Agrawal --- MAINTAINERS | 1 + config/common_base | 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 8 +- drivers/Makefi

[dpdk-dev] [PATCHv7 01/47] mk/dpaa2: add the crc support to the machine type

Signed-off-by: Hemant Agrawal Acked-by: Jerin Jacob --- mk/machine/dpaa2/rte.vars.mk | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/mk/machine/dpaa2/rte.vars.mk b/mk/machine/dpaa2/rte.vars.mk index 8541633..e4735c2 100644 --- a/mk/machine/dpaa2/rte.vars.mk +++ b/mk/mach

[dpdk-dev] [PATCHv7 00/47] NXP DPAA2 PMD

The patch series adds NXP’s QorIQ-Layerscape DPAA2 Architecture based fsl-mc bus driver and network SoC PMD. This version of the driver supports NXP LS208xA, LS204xA and LS108x families Network SoCs. DPAA2, or Data Path Acceleration Architecture, is a hardware architecture designed for high-speed

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> On Feb 15, 2017, at 11:25 AM, Jerin Jacob > wrote: > > On Wed, Feb 15, 2017 at 02:27:47PM +, Shreyansh Jain wrote: >>> -Original Message- >>> From: Wiles, Keith [mailto:keith.wi...@intel.com] >>> Sent: Wednesday, February 15, 2017 7:53 PM >>> To: Shreyansh Jain >>> Cc: Jan Blunck

Re: [dpdk-dev] [PATCH v3 3/4] bonding: take queue spinlock in rx/tx burst functions

On 6/16/2016 7:38 PM, thomas.monjalon at 6wind.com (Thomas Monjalon) wrote: > 2016-06-16 16:41, Iremonger, Bernard: >> Hi Thomas, >> >>> 2016-06-16 15:32, Bruce Richardson: On Mon, Jun 13, 2016 at 01:28:08PM +0100, Iremonger, Bernard wrote: >> Why does this particular PMD need spinlocks w

Re: [dpdk-dev] [PATCH 3/4] mk: add new test-run make rule

On 2/15/2017 5:07 PM, Bruce Richardson wrote: > On Wed, Feb 15, 2017 at 03:26:31PM +, Ferruh Yigit wrote: >> Since "make test" and "make test-build" does dependency resolving, they >> check for all dependent components (lib and drivers) which takes a few >> seconds. >> >> This is a good feature

Re: [dpdk-dev] [PATCH 2/4] mk: do not build tests by default

On 2/15/2017 4:58 PM, Thomas Monjalon wrote: > 2017-02-15 15:26, Ferruh Yigit: >> +.PHONY: test-buid >> +test-build: >> +$(Q)$(MAKE) -f $(RTE_SDK)/mk/rte.sdkconfig.mk checkconfig >> +$(Q)$(MAKE) -f $(RTE_SDK)/mk/rte.sdkbuild.mk test > > Why not rely on default rule below? > > # all other

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wed, Feb 15, 2017 at 02:27:47PM +, Shreyansh Jain wrote: > > -Original Message- > > From: Wiles, Keith [mailto:keith.wi...@intel.com] > > Sent: Wednesday, February 15, 2017 7:53 PM > > To: Shreyansh Jain > > Cc: Jan Blunck ; dev@dpdk.org > > Subject: Re: [dpdk-dev] [PATCH 3/7] eal:

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> On Feb 15, 2017, at 11:10 AM, Wiles, Keith wrote: > > >> On Feb 15, 2017, at 11:06 AM, Jan Blunck wrote: >> >> On Wed, Feb 15, 2017 at 3:22 PM, Wiles, Keith wrote: >>> On Feb 15, 2017, at 8:15 AM, Shreyansh Jain wrote: Just ignore this comment - I am misunderstood s

Re: [dpdk-dev] [PATCH 7/7] eal: make virtual bus use rte_vdev_device

On 2/15/2017 10:02 AM, Jan Blunck wrote: > This allows the virtual bus to be rescanned and probed by tracking the > creation of rte_vdev_device. > > Signed-off-by: Jan Blunck <...> > + > + dev->device.devargs = devargs; > + dev->device.numa_node = -1; SOCKET_ID_ANY can be used instead

Re: [dpdk-dev] [PATCH 4/7] eal: remove unused rte_eal_dev_init()

On 2/15/2017 10:02 AM, Jan Blunck wrote: > Signed-off-by: Jan Blunck <...> > -int > -rte_eal_dev_init(void) > -{ > - return 0; > -} > - API should be removed from .map files too (rte_eal_version.map).

Re: [dpdk-dev] [PATCH 6/7] eal: add struct rte_vdev_device

On 2/15/2017 10:02 AM, Jan Blunck wrote: > This adds the rte_vdev_device structure which embeds a generic rte_device. > > Signed-off-by: Jan Blunck <...> > > +struct rte_vdev_device { > + TAILQ_ENTRY(rte_vdev_device) next; /**< Next attached vdev */ > + struct rte_device device;

Re: [dpdk-dev] [PATCH 0/7] Rework vdev probing to use rte_bus infrastructure

On 2/15/2017 10:02 AM, Jan Blunck wrote: > With the rte_bus infrastructure present in 17.02 it is possible to refactor > the virtual device probing into a bus. This series also introduces the > rte_vdev_device to better keep track of devices. > > Jan Blunck (7): > eal: use different constructor

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> On Feb 15, 2017, at 11:06 AM, Jan Blunck wrote: > > On Wed, Feb 15, 2017 at 3:22 PM, Wiles, Keith wrote: >> >>> On Feb 15, 2017, at 8:15 AM, Shreyansh Jain wrote: >>> >>> >>> Just ignore this comment - I am misunderstood something. >>> >>> But another question: Is there specific reason V

[dpdk-dev] [PATCH v2] eventdev: Add rte_errno return values to the enqueue and dequeue functions

This change allows user software to differentiate between an invalid argument (such as an invalid queue_id or sched_type in an enqueued event) and backpressure from the event device. The port and device ID checks are placed in RTE_LIBRTE_EVENTDEV_DEBUG header guards to avoid the performance hit in

Re: [dpdk-dev] [PATCH 3/4] mk: add new test-run make rule

On Wed, Feb 15, 2017 at 03:26:31PM +, Ferruh Yigit wrote: > Since "make test" and "make test-build" does dependency resolving, they > check for all dependent components (lib and drivers) which takes a few > seconds. > > This is a good feature during development, but if the target is just > run

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wed, Feb 15, 2017 at 3:22 PM, Wiles, Keith wrote: > >> On Feb 15, 2017, at 8:15 AM, Shreyansh Jain wrote: >> >> >> Just ignore this comment - I am misunderstood something. >> >> But another question: Is there specific reason VDEV should be >> registered/scanned *after* other devices? Is there

Re: [dpdk-dev] [PATCH 2/4] mk: do not build tests by default

2017-02-15 15:26, Ferruh Yigit: > +.PHONY: test-buid > +test-build: > + $(Q)$(MAKE) -f $(RTE_SDK)/mk/rte.sdkconfig.mk checkconfig > + $(Q)$(MAKE) -f $(RTE_SDK)/mk/rte.sdkbuild.mk test Why not rely on default rule below? # all other build targets %: $(Q)$(MAKE) -f $(RTE_SDK)/mk/rte.sdk

[dpdk-dev] [PATCH 2/4] mk: do not build tests by default

Don't build tests with default "make" command. Require explicit command to build tests because not everybody interested in running unit tests. Following changes done in make rules: "make test-build" <--- Added "make test"<--- Updated functionality (build + run) Now "make test" builds al

[dpdk-dev] [PATCH 3/4] mk: add new test-run make rule

Since "make test" and "make test-build" does dependency resolving, they check for all dependent components (lib and drivers) which takes a few seconds. This is a good feature during development, but if the target is just running unit test, that step is unnecessary, it is possible to compile onece

[dpdk-dev] [PATCH 4/4] mk: rename test related make rules

Make rules renamed to; fast_test-> test-fast ring_test-> test-ring mempool_test -> test-mempool perf_test-> test-perf These are to run various sub-set of the unit tests. Not touched to the rules that already follows the syntax: test-run test-build test Signed-off-by: Ferruh Yigit --

[dpdk-dev] [PATCH 1/4] test: move tests to separate folder

This is to logically group unit tests into their own folder separating them from "app" folder. Hopefully this will make the unit test in DPDK more visible. Following binaries moved to "test" folder: cmdline-test test-acl test-pipeline test <-- various DPDK unit tests Signed-off-by: Ferruh Yigi

Re: [dpdk-dev] [PATCH 1/7] eal: use different constructor priorities for initcalls

On Wed, Feb 15, 2017 at 3:37 PM, Shreyansh Jain wrote: > On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: >> >> --- a/lib/librte_eal/common/include/rte_eal.h >> +++ b/lib/librte_eal/common/include/rte_eal.h >> @@ -258,8 +258,16 @@ static inline int rte_gettid(void) >> return RTE_P

Re: [dpdk-dev] [PATCH v1] doc: add template release notes for 17.05

2017-02-15 12:38, John McNamara: > + Build the docs and view the output file to ensure the changes are > correct:: > + > + make doc-guides-html > + > + firefox build/doc/html/guides/rel_notes/release_17_05.html I would suggest xdg-open instead of firefox. It is more open regarding chr

Re: [dpdk-dev] [PATCH v3] eventdev: amend comments for events limit and threshold

On Wed, Feb 15, 2017 at 01:53:45PM +, Van Haaren, Harry wrote: > > From: Nipun Gupta [mailto:nipun.gu...@nxp.com] > > Sent: Tuesday, February 14, 2017 12:43 PM > > To: dev@dpdk.org > > Cc: hemant.agra...@nxp.com; jerin.ja...@caviumnetworks.com; Richardson, > > Bruce > > ; Eads, Gage ; Van Haar

Re: [dpdk-dev] [PATCH] eventdev: limit port link operation to configured queues

On Tue, Feb 07, 2017 at 10:00:10AM +, Nipun Gupta wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com] > > Sent: Monday, February 06, 2017 11:00 > > To: dev@dpdk.org > > Cc: bruce.richard...@intel.com; Hemant Agrawal > > ; gage.e...@intel.com

Re: [dpdk-dev] [RFC] eal: provide option to set vhost_user socket owner/permissions

Thomas Monjalon writes: > Was there any progress on this topic? > Can we close the request? > http://dpdk.org/patch/1/ No update in almost a year is probably a bad sign. >From the OVS side, we've dropped our patches due to too many corner cases handling this - instead we're opting to

Re: [dpdk-dev] [PATCH 1/7] eal: use different constructor priorities for initcalls

On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: This introduces different initcall macros to allow for late registration of the virtual device bus. Signed-off-by: Jan Blunck --- lib/librte_eal/common/include/rte_bus.h | 17 - lib/librte_eal/common/include/rte_eal.h

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> -Original Message- > From: Wiles, Keith [mailto:keith.wi...@intel.com] > Sent: Wednesday, February 15, 2017 7:53 PM > To: Shreyansh Jain > Cc: Jan Blunck ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a > bus > > > > On Feb 15, 2017, at 8:15

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

> On Feb 15, 2017, at 8:15 AM, Shreyansh Jain wrote: > > On Wednesday 15 February 2017 07:41 PM, Shreyansh Jain wrote: >> On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: >>> This is a refactoring of the virtual device probing which moves into into >>> a proper bus structure. >>> >>> S

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wednesday 15 February 2017 07:43 PM, Jan Blunck wrote: On Wed, Feb 15, 2017 at 3:11 PM, Shreyansh Jain wrote: On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: + +static struct rte_bus rte_vdev_bus = { + .scan = vdev_scan, + .probe = vdev_probe, +}; + +RTE_REGISTER_B

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wed, Feb 15, 2017 at 3:11 PM, Shreyansh Jain wrote: > On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: >> > >> + >> +static struct rte_bus rte_vdev_bus = { >> + .scan = vdev_scan, >> + .probe = vdev_probe, >> +}; >> + >> +RTE_REGISTER_BUS_LATE(virtual, rte_vdev_bus); >> > >

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wednesday 15 February 2017 07:41 PM, Shreyansh Jain wrote: On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: This is a refactoring of the virtual device probing which moves into into a proper bus structure. Signed-off-by: Jan Blunck --- lib/librte_eal/common/eal_common_dev.c | 22

Re: [dpdk-dev] [PATCH 3/7] eal: move virtual device probing into a bus

On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: This is a refactoring of the virtual device probing which moves into into a proper bus structure. Signed-off-by: Jan Blunck --- lib/librte_eal/common/eal_common_dev.c | 22 - lib/librte_eal/common/eal_common_vdev.c | 44

[dpdk-dev] [RFC] eal: use busname and devargs to attach devices

Using just the device name to attach a device on the EAL level is not enough for a unique identification of the bus it should get attached to. Therefore lets change rte_eal_dev_attach() introduced in 16.11 to take the busname and the raw devargs string. Signed-off-by: Jan Blunck --- lib/librte_e

Re: [dpdk-dev] [PATCH] kni: remove KNI vhost support

On Wed, Feb 15, 2017 at 01:15:38PM +, Ferruh Yigit wrote: > Signed-off-by: Ferruh Yigit > --- > config/common_base | 3 - > devtools/test-build.sh | 1 - > doc/guides/prog_guide/index.rst| 4 - > doc/guides/prog_guide/k

Re: [dpdk-dev] [PATCH v1] doc: add template release notes for 17.05

On Wed, Feb 15, 2017 at 12:38:58PM +, John McNamara wrote: > Add template release notes for DPDK 17.05 with inline > comments and explanations of the various sections. > > Signed-off-by: John McNamara > --- > doc/guides/rel_notes/index.rst | 1 + > doc/guides/rel_notes/release_17_0

Re: [dpdk-dev] [PATCH 2/7] eal: probe legacy PCI devices before other bus devices

On Wednesday 15 February 2017 03:32 PM, Jan Blunck wrote: Make sure that the PCI devices are probed before the virtual devices after the legacy virtual device probing has been moved to a bus. Signed-off-by: Jan Blunck --- Acked-by: Shreyansh Jain

Re: [dpdk-dev] [PATCH v3] eventdev: amend comments for events limit and threshold

> From: Nipun Gupta [mailto:nipun.gu...@nxp.com] > Sent: Tuesday, February 14, 2017 12:43 PM > To: dev@dpdk.org > Cc: hemant.agra...@nxp.com; jerin.ja...@caviumnetworks.com; Richardson, Bruce > ; Eads, Gage ; Van Haaren, > Harry > ; Nipun Gupta > Subject: [PATCH v3] eventdev: amend comments for e

[dpdk-dev] [PATCH] kni: remove KNI vhost support

Signed-off-by: Ferruh Yigit --- config/common_base | 3 - devtools/test-build.sh | 1 - doc/guides/prog_guide/index.rst| 4 - doc/guides/prog_guide/kernel_nic_interface.rst | 113 doc/guides/rel_notes/deprecation.rst

[dpdk-dev] [PATCH v1] doc: add template release notes for 17.05

Add template release notes for DPDK 17.05 with inline comments and explanations of the various sections. Signed-off-by: John McNamara --- doc/guides/rel_notes/index.rst | 1 + doc/guides/rel_notes/release_17_05.rst | 195 + 2 files changed, 196 insertion

Re: [dpdk-dev] DPDK 17.02 RC-3 performance degradation of ~10%

Hi Thomas and John, We found that the performance degradation is not related to DPDK 17.02 for Intel XL710/ixgbe. Now It is back to normal. The fix was to add a one unrelated line to a specific file. This probably changed the instructions trace. This line is not related to DP or CP. (We still

Re: [dpdk-dev] [PATCH v11 07/13] pci: split match and probe

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > Sent: Wednesday, February 15, 2017 4:53 PM > To: Jan Blunck ; Shreyansh Jain > > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v11 07/13] pci: split match and probe > > 2017-02-15 11:45, Jan Blunck: > >

Re: [dpdk-dev] [PATCH v11 12/13] pci: use bus driver for attach/detach

On Wed, Feb 15, 2017 at 12:26 PM, Thomas Monjalon wrote: > 2017-02-15 12:08, Jan Blunck: >> > int rte_eal_dev_attach(const char *name, const char *devargs) >> > { >> > - struct rte_pci_addr addr; >> > + int ret = 1; >> > + struct rte_bus *bus; >> > >> > if (name == NULL

Re: [dpdk-dev] [RFC 17.05] test: move tests to separate folder

On 2/15/2017 11:16 AM, Thomas Monjalon wrote: > 2017-02-15 10:06, Ferruh Yigit: >> On 2/15/2017 2:11 AM, Yuanhan Liu wrote: >>> On Tue, Feb 14, 2017 at 05:30:14PM +, Richardson, Bruce wrote: Just to be awkward :-), one last question: Why separate building and running the tests?

Re: [dpdk-dev] [PATCH v11 12/13] pci: use bus driver for attach/detach

2017-02-15 12:08, Jan Blunck: > > int rte_eal_dev_attach(const char *name, const char *devargs) > > { > > - struct rte_pci_addr addr; > > + int ret = 1; > > + struct rte_bus *bus; > > > > if (name == NULL || devargs == NULL) { > > RTE_LOG(ERR, EAL, "Inval

Re: [dpdk-dev] [PATCH v11 07/13] pci: split match and probe

On Wednesday 15 February 2017 04:15 PM, Jan Blunck wrote: On Thu, Jan 19, 2017 at 5:45 AM, Thomas Monjalon wrote: From: Shreyansh Jain Matching of PCI device address and driver ID table is being done at two discreet locations duplicating the code. (rte_eal_pci_probe_one_driver and rte_eal_pci

Re: [dpdk-dev] [PATCH v11 07/13] pci: split match and probe

2017-02-15 11:45, Jan Blunck: > > /** > > + * Match the PCI Driver and Device using the ID Table > > + * > > + * @param pci_drv > > + * PCI driver from which ID table would be extracted > > + * @param pci_dev > > + * PCI device to match against the driver > > + * @return > > + * 0 for

Re: [dpdk-dev] [PATCH v11 09/13] pci: add bus driver

2017-02-15 11:42, Jan Blunck: > > /** > > + * Add a PCI device to the PCI Bus (append to PCI Device list). This > > function > > + * also updates the bus references of the PCI Device (and the generic > > device > > + * object embedded within. > > + * > > + * @param pci_dev > > + * PCI device

  1   2   >