Re: [dpdk-dev] [PATCH v2 7/7] pci: Clarify interfaces for dynamic attach/detach of drivers

On Thursday 24 November 2016 01:37 AM, Ben Walker wrote: There are now two functions - rte_eal_pci_attach_driver and rte_eal_pci_detach_driver - that dynamically attempt to attach and detach drivers from PCI devices. These only control whether a registered PCI driver is loaded or not - they are i

[dpdk-dev] [PATCH 8/8] net/qede/base: fix to check FW override after rejection

Apparently VF over Legacy PF doesn't work, as VF would fail after getting the initial rejection message [instead of sending an additional one where it asks for a FW override and see if it works]. Fixes: 22d07d93 ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecor

[dpdk-dev] [PATCH 3/8] net/qede/base: fix multiple acquisition requests by VF

There are certain conditions under which VF would infinitely send ACQUIRE messages, as it will fail to understand that PF has rejected the ACQUIRE request. Fix to reject multiple acquisition requests by VF. Fixes: 22d07d93 ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qed

[dpdk-dev] [PATCH 7/8] net/qede/base: fix to handle acquire request from VF

Add a check and fail the VF's probe request if VF is already in VF_ACQUIRED state. Fixes: 22d07d93 ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_sriov.c | 12 1 file changed, 12 insertions(+) diff --git a/drivers/net/qede/base/ecore_sriov.c

[dpdk-dev] [PATCH 6/8] net/qede/base: fix Rx queue access by malicious VFs

8.10.x.x was supposed to prevent malicious VFs from using out-of-bound queue indices, but apparently Rx queue access is still done prior to the index being validated by PF. Fixes: 98bc693e ("net/qede/base: change queue start") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_sriov.c |

[dpdk-dev] [PATCH 5/8] net/qede/base: fix mutex in freeing context manager

Fix OSAL_MUTEX_DEALLOC() in freeing the context manager. Fixes: 22d07d93 ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_cxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/qede/base/ecore_cxt.c b/drivers/net/qede/base/ecor

[dpdk-dev] [PATCH 2/8] net/qede/base: fix sriov printouts

Remove unmeaningful value in print. Don't print the number of Multicast filters as part of Acquire response, as this is an obsolete field which isn't enforced by PF. Fixes: 86a2265e ("qede: add SRIOV support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_sriov.c | 9 - 1

[dpdk-dev] [PATCH 1/8] net/qede: fix to get vendor/device id info

Fixes: ec94dbc5 ("qede: add base driver") Signed-off-by: Rasesh Mody --- drivers/net/qede/qede_ethdev.c | 4 1 file changed, 4 insertions(+) diff --git a/drivers/net/qede/qede_ethdev.c b/drivers/net/qede/qede_ethdev.c index 9c2a5eae..b9a325df 100644 --- a/drivers/net/qede/qede_ethdev.c +++

[dpdk-dev] [PATCH 4/8] net/qede/base: fix error return code in resc alloc

Fix to return error code ECORE_INVAL instead of 0 when EQ elements is too large as done elsewhere in this function. Fixes: 22d07d93 ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_dev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/qede/bas

[dpdk-dev] [PATCH] maintainers: update for qede PMD and bnx2x PMD

Following Cavium's acquisition of QLogic we need to update all the qlogic PMD maintainer's entries to point to our new e-mail addresses. Update driver's maintainers as they are no longer working for Cavium. Thanks to Sony Chacko for his support and development of our various dpdk drivers. Signed-

[dpdk-dev] [PATCH 7/7] net/qede: restrict maximum queues for PF/VF

Fix to adverstise max_rx_queues by taking into account the number of PF connections instead of returning max_queues supported by the HW. Fixes: 2ea6f76a ("qede: add core driver") Signed-off-by: Harish Patil --- drivers/net/qede/qede_ethdev.c | 13 ++--- drivers/net/qede/qede_ethdev.h |

[dpdk-dev] [PATCH 6/7] net/qede: fix maximum VF count to 0

Set max_vfs to 0 since it is relevant only to SR-IOV PF which is not supported yet. Fixes: 2ea6f76a ("qede: add core driver") Signed-off-by: Harish Patil --- drivers/net/qede/qede_ethdev.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/qede/qede_ethdev.c b/d

[dpdk-dev] [PATCH 5/7] net/qede: fix RSS related issue

This patch includes the following: - Fix missing hash_key_size advertisement - Fix RSS hash query function - Update RSS offload flag - Accept user provided RSS configuration params via rx_adv_conf in dev_configure() - Decouple RSS configuration from common qed_update_vport() and instead make u

[dpdk-dev] [PATCH 4/7] net/qede: add fastpath support for VXLAN tunneling

- Support HW checksum and RSS offload for VXLAN traffic - Identify inner/outer packet_types using lookup table - Update documentation Signed-off-by: Harish Patil --- doc/guides/nics/features/qede.ini | 3 + doc/guides/nics/qede.rst | 3 +- drivers/net/qede/qede_eth_if.h| 3 +

[dpdk-dev] [PATCH 1/7] net/qede: reduce noise in debug logs

From: Rasesh Mody Replace CONFIG_RTE_LIBRTE_QEDE_DEBUG_DRIVER with CONFIG_RTE_LIBRTE_QEDE_DEBUG_VAL which is a 32-bit bitmapped value where each bit represent a particular submodule to debug. Also move notice messages under CONFIG_RTE_LIBRTE_QEDE_DEBUG_INFO. Signed-off-by: Harish Patil Signed-o

[dpdk-dev] [PATCH 2/7] net/qede: refactor filtering code

The filter_config in qed_eth_ops_pass is a wrapper call driving all the filtering configuration. This requires defining multiple structures and passing different function arguments for each filter type which is unnecessary. So as part of this refactoring we remove filter_config from qed_eth_ops_pas

[dpdk-dev] [PATCH 3/7] net/qede: add slowpath support for VXLAN tunneling

- Enable/disable VXLAN tunneling - Add/remove VXLAN classification rules - Destination UDP port configuration Signed-off-by: Harish Patil --- drivers/net/qede/base/ecore_l2.c | 3 + drivers/net/qede/base/ecore_l2_api.h | 1 + drivers/net/qede/qede_ethdev.c | 400 +++

[dpdk-dev] [PATCH 31/31] net/i40e: remove unused marco from PMD

Signed-off-by: Jingjing Wu --- drivers/net/i40e/Makefile | 2 +- drivers/net/i40e/i40e_ethdev.c | 40 2 files changed, 1 insertion(+), 41 deletions(-) diff --git a/drivers/net/i40e/Makefile b/drivers/net/i40e/Makefile index 13085fb..66997b6 100644 -

[dpdk-dev] [PATCH 27/31] net/i40e/base: add broadcast promiscuous control per VLAN

Add a new adminq function that allows driver to configure per-VLAN broadcast promiscuous mode, similar to how we handle unicast and multicast promiscuous modes. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c| 34 ++ drivers/net/i40e/base/i4

[dpdk-dev] [PATCH 30/31] net/i40e/base: remove unused marco

remove X722_SUPPORT and I40E_NDIS_SUPPORT MARCOs Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_adminq_cmd.h | 14 --- drivers/net/i40e/base/i40e_common.c | 18 +- drivers/net/i40e/base/i40e_devids.h | 2 -- drivers/net/i40e/base/i40e_nvm.c| 16 ---

[dpdk-dev] [PATCH 26/31] net/i40e/base: add ERROR state for NVM update state machine

This patch adds I40E_NVMUPD_STATE_ERROR state for NVM update. Without this patch driver has no possibility to return NVM image write failure.This state is being set when ARQ rises error. arq_last_status is also updated every time when ARQ event comes, not only on error cases. Signed-off-by: Jingji

[dpdk-dev] [PATCH 29/31] net/i40e/base: fix byte order

Big Endian platform will accidentally send the wrong data to the firmware command. This patch fixes the issue. Fixes: 788fc17b2dec ("i40e/base: support proxy config for X722") Fixes: 3c89193a36fd ("i40e/base: support WOL config for X722") Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e

[dpdk-dev] [PATCH 25/31] net/i40e/base: remove duplicate definitions

We already define I40E_AQ_PHY_TYPE_EXT_25G* flags in the response adminq structure above, and do not need to re-define these. See eee_capability for an example where we didn't re-define these. This prevents Linux driver from complaining about using these flags in an #ifdef when running cppkeep tool

[dpdk-dev] [PATCH 28/31] net/i40e/base: avoid division by zero

For some cases when reading from device are incorrect or image is incorrect, this part of code causes crash due to division by zero. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/i40e/base/

[dpdk-dev] [PATCH 22/31] net/i40e/base: acquire NVM lock before reads on all devices

Acquire NVM lock before reads on all devices. Previously, locks were only used for X722 and later. Fixes an issue where simultaneous X710 NVM accesses were interfering with each other. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_nvm.c | 16 1 file changed, 8 inse

[dpdk-dev] [PATCH 24/31] net/i40e/base: comment that udp port must be in Host order

The firmware expects the Port number to be in Little Endian format, and the i40e_aq_add_udp_tunnel command clearly expects the udp_port variable to be in Host order, as it uses CPU_TO_LE16(). It was recently discovered in the Linux driver that we were passing a Big Endian port number, which was the

[dpdk-dev] [PATCH 23/31] net/i40e/base: change shift values to hex

Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_type.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/i40e/base/i40e_type.h b/drivers/net/i40e/base/i40e_type.h index 99e080e..3784c8f 100644 --- a/drivers/net/i40e/base/i40e_type.h +++ b/drivers/net

[dpdk-dev] [PATCH 21/31] net/i40e/base: save link FEC info from link up event

Store the FEC status bits from the link up event into the hw_link_info structure. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 2 ++ drivers/net/i40e/base/i40e_type.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/net/i40e/base/i40e_common.c b/drivers/ne

[dpdk-dev] [PATCH 20/31] net/i40e/base: add defines for new aq command

By default the device clears all MAC filter information on PF Reset. However, this will cause Wake-On-LAN to fail because the wake filters are deleted on transition to D3 power state. To get around this, firmware is adding functionality to preserve certain MAC filters during PFR. These bits allow t

[dpdk-dev] [PATCH 19/31] net/i40e/base: implement set VSI full promisc mode

This patch implements a function to set a VSI to broadcast, multicast, and unicast promiscuous mode all at once. This is specifically needed to set the WoL/Proxy VSI created by FW to full promiscuous mode during power down for WoL patterns and protocol offloads to function properly. Signed-off-by:

[dpdk-dev] [PATCH 16/31] net/i40e/base: use BIT() macro instead of bit fields

Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_adminq_cmd.h | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/i40e/base/i40e_adminq_cmd.h b/drivers/net/i40e/base/i40e_adminq_cmd.h index 1884758..cef02b1 100644 --- a/drivers/net/i40e/base/i40e_a

[dpdk-dev] [PATCH 15/31] net/i40e/base: add FEC bits to PHY capabilities

Add FEC bits to the PHY capabilities AQ command struct. This is required for 25GbE support. Change the name of the generic mod_type_ext field to indicate that it is now used for handling FEC. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_adminq_cmd.h | 13 - drivers/net/i

[dpdk-dev] [PATCH 18/31] net/i40e/base: implement clear all WoL filters

This patch implements the clear Wake on LAN (WoL) filters admin queue function which clears out ALL WoL patterns programmed into the flex filters. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_adminq_cmd.h | 1 + drivers/net/i40e/base/i40e_common.c | 20 dri

[dpdk-dev] [PATCH 17/31] net/i40e/base: adjust 25G PHY type values

Define the values for the 25G PHY type bit-fields that match reported values from firmware. There was a gap in the bit fields but no corresponding gap i40e_aq_phy_type enum. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_type.h | 20 1 file changed, 16 insertions(

[dpdk-dev] [PATCH 14/31] net/i40e/base: remove FPK HyperV VF device ID

Microsoft recently removed the requirement for VFs to use the VMBus. The Fort Park Windows VF has been changed to use only the hardware mailbox, so the Hyper-V VF device ID can be removed. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 1 - drivers/net/i40e/base/i40e_devids

[dpdk-dev] [PATCH 10/31] net/i40e/base: add protocols when discover capabilities

Add logical_id to I40E_AQ_CAP_ID_MNG_MODE capability starting from major version 2. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 8 drivers/net/i40e/base/i40e_type.h | 4 2 files changed, 12 insertions(+) diff --git a/drivers/net/i40e/base/i40e_common.c

[dpdk-dev] [PATCH 13/31] net/i40e/base: deprecating unused macro

I40E_MAC_X710 was supposed to be for 10G and I40E_MAC_XL710 was supposed to be for 40G. But i40e_set_mac_type() sets I40E_MAC_XL710 for all device IDS. I40E_MAC_X710 is not used at all. Thus deprecating this extra macro. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_type.h | 1 - 1 f

[dpdk-dev] [PATCH 12/31] net/i40e/base: replace memcpy

To align with current memcpy use, replace existing legacy memcpy() calls with i40e_memcpy() calls. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 13 - drivers/net/i40e/base/i40e_nvm.c| 7 --- 2 files changed, 12 insertions(+), 8 deletions(-) diff --gi

[dpdk-dev] [PATCH 11/31] net/i40e/base: pass unknown PHY type for unknown PHYs

The PHY type value for unrecognized PHYs and cables was changed based on firmware version number. Newer hardware use lower firmware version numbers and this was causing some PHYs to be identified as type 0x16 instead of 0xe (unknown). Without this patch, newer card will incorrectly identify unknow

[dpdk-dev] [PATCH 06/31] net/i40e/base: fix long link down notification time

This patch fixes a problem where it could take a very long time (>100 msec) to print the link down notification. This problem is fixed by changing how often we update link info from fw, when link is down. Without this patch, it can take over 100msec to notify user link is down. Fixes: e6691b428eb1

[dpdk-dev] [PATCH 09/31] net/i40e/base: add bus number info

Currently i40e_bus_info has PCI device and function info only. However in log messages slot number (i.e hw->bus.device) is being printed as bus number. Another field should be added to provide bus number info and preserve existing information. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base

[dpdk-dev] [PATCH 08/31] net/i40e/base: add clause22 and clause45 implementation

Some external PHYs require Clause22 and Clause45 method for accessing registers. Mostly used for X722 support. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c| 245 +++-- drivers/net/i40e/base/i40e_prototype.h | 16 ++- drivers/net/i40e/base/i4

[dpdk-dev] [PATCH 07/31] net/i40e/base: add media type detection for 25G link

Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 4 1 file changed, 4 insertions(+) diff --git a/drivers/net/i40e/base/i40e_common.c b/drivers/net/i40e/base/i40e_common.c index 2ad9448..7eea189 100644 --- a/drivers/net/i40e/base/i40e_common.c +++ b/drivers/net/i40e/base

[dpdk-dev] [PATCH 05/31] net/i40e/base: group base mode VF offload flags

Group together the minimum set of offload capabilities that are always supported by VF in base mode. This define would be used by PF to make sure VF in base mode gets minimum of base capabilities. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_virtchnl.h | 4 1 file changed, 4 in

[dpdk-dev] [PATCH 04/31] net/i40e/base: fix bit test mask

Incorrect bit mask was used for testing "get link status" response. Instead of I40E_AQ_LSE_ENABLE (which is actually 0x03) it most probably should be I40E_AQ_LSE_IS_ENABLED (which is defined as 0x01). Fixes: 8db9e2a1b232 ("i40e: base driver") Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/

[dpdk-dev] [PATCH 01/31] net/i40e/base: add encap csum VF offload flag

Add ENCAP_CSUM offload negotiation flag. Currently VF assumes checksum offload for encapsulated packets is supported by default. Going forward, this feature needs to be negotiated with PF before advertising to the stack. Hence, we need a flag to control it. Signed-off-by: Jingjing Wu --- drivers

[dpdk-dev] [PATCH 02/31] net/i40e/base: preserve extended PHY type field

Prevents 25G PHY types from being disabled when setting the flow control modes. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/i40e/base/i40e_common.c b/drivers/net/i40e/base/i40e_common.c index 9a6b3ed..d67ad90

[dpdk-dev] [PATCH 03/31] net/i40e/base: remove unnecessary code

This patch changes some assignments and removing the unnecessary code to avoid error reported by static analysis tools. Signed-off-by: Jingjing Wu --- drivers/net/i40e/base/i40e_common.c | 4 drivers/net/i40e/base/i40e_lan_hmc.c | 5 - 2 files changed, 9 deletions(-) diff --git a/driv

[dpdk-dev] [PATCH 00/31] net/i40e: base code update

i40e base code upate. The main changes are: - add clause22 and clause45 implementation for PHY registers accessing - replace existing legacy memcpy() calls with i40e_memcpy() calls. - use BIT() macro instead of bit fields - add clear all WoL filters implementation - add ERROR state for NVM upd

Re: [dpdk-dev] [PATCH v12 0/6] add Tx preparation

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > Sent: Wednesday, November 30, 2016 10:27 AM > To: Ananyev, Konstantin > Cc: Harish Patil ; dev@dpdk.org; Rahul Lakkireddy > ; Stephen Hurd > ; Jan Medala ; Jakub > Palider ; John Daley ; Adrien > Mazarguil ;

Re: [dpdk-dev] [RFC] igb_uio: deprecate iomem and ioport mapping

On Thu, 1 Sep 2016 02:16:37 + Jianfeng Tan wrote: > Previously in igb_uio, iomem is mapped, and both ioport and io mem > are recorded into uio framework, which is duplicated and makes the > code too complex. > > For iomem, DPDK user space code never opens or reads files under > /sys/pci/bus

[dpdk-dev] Question about IXGBEVF reset

Hi I was having a discussion on the IXGBE mailing list regarding RESET due to lost link mailbox message and its handling in DPDK: http://lists.osuosl.org/pipermail/intel-wired-lan/Week-of-Mon-20161128/007389.html I was wondering what can be done regarding this issue. Particularly, the patch http

Re: [dpdk-dev] [RFC PATCH] eventdev: add buffered enqueue and flush APIs

On Fri, Dec 02, 2016 at 01:45:56PM -0600, Gage Eads wrote: > This commit adds buffered enqueue functionality to the eventdev API. > It is conceptually similar to the ethdev API's tx buffering, however > with a smaller API surface and no dropping of events. Hello Gage, Different implementation may

Re: [dpdk-dev] [PATCH 01/22] ethdev: introduce generic flow API

On 12/01/2016 08:36 AM, Adrien Mazarguil wrote: > Hi Kevin, > > On Wed, Nov 30, 2016 at 05:47:17PM +, Kevin Traynor wrote: >> Hi Adrien, >> >> On 11/16/2016 04:23 PM, Adrien Mazarguil wrote: >>> This new API supersedes all the legacy filter types described in >>> rte_eth_ctrl.h. It is slightly

[dpdk-dev] [RFC PATCH] EventDev buffered enqueue API

This patch extends the currently proposed libeventdev API with support for buffered enqueue operations. This functionality can improve application performance when using event devices that benefit from bulk enqueue operations, but due to its architecture the application cannot easily combine its e

[dpdk-dev] [RFC PATCH] eventdev: add buffered enqueue and flush APIs

This commit adds buffered enqueue functionality to the eventdev API. It is conceptually similar to the ethdev API's tx buffering, however with a smaller API surface and no dropping of events. Signed-off-by: Gage Eads --- lib/librte_eventdev/rte_eventdev.c | 29 ++ lib/librte_eventdev/rt

[dpdk-dev] [PATCH v2] net/i40evf: fix reporting of imissed packets

Missed packets on RX were erroneously being assigned to the ierrors struct member. Change it to be assigned to imissed. Fixes: 4861cde4 ("i40e: new poll mode driver") Signed-off-by: Tom Crugnale --- v2: * Fixed line breaks in original patch submission --- drivers/net/i40e/i40e_ethdev_vf.c | 8

[dpdk-dev] [PATCH v4] eal: restrict cores auto detection

This patch uses pthread_getaffinity_np() to narrow down used cores when none of below options is specified: * coremask (-c) * corelist (-l) * and coremap (--lcores) The purpose of this patch is to leave out these core related options when DPDK applications are deployed under container env, s

Re: [dpdk-dev] ixgbevf: support multicast packets from PF to VF

Adding wenzhuo...@intel.com From: Dey, Souvik Sent: Friday, December 2, 2016 12:27 PM To: 'dev@dpdk.org' Subject: ixgbevf: support multicast packets from PF to VF Hi All, I am trying to support multicast packet over SRIOV using kernel PF + DPDK VF(ix

[dpdk-dev] ixgbevf: support multicast packets from PF to VF

Hi All, I am trying to support multicast packet over SRIOV using kernel PF + DPDK VF(ixgbevf) drivers for ipv6. I am currently using 2.1 DPDK and found that there was a patch in 16.04 for "ixgbe: support multicast promiscuous mode on VF". So I have backported the patch to the 2.1

[dpdk-dev] [PATCH 4/4] test: add sgl unit tests for crypto devices

This patch provides unit tests for set of cipher/hash combinations covering currently implemented crypto PMD's and allowing to verify scatter gather support. Signed-off-by: Daniel Mrzyglod Signed-off-by: Tomasz Kulasek --- app/test/test_cryptodev.c | 456 +

[dpdk-dev] [PATCH 3/4] crypto: add sgl support for sw PMDs

This patch introduces RTE_CRYPTODEV_FF_MBUF_SCATTER_GATHER feature flag informing that selected crypto device supports segmented mbufs natively and doesn't need to be coalesced before crypto operation. While using segmented buffers in crypto devices may have unpredictable results, for PMDs which d

[dpdk-dev] [PATCH 2/4] test: add rte_pktmbuf_coalesce unit tests

This patch tests rte_pktmbuf_coalesce functionality: 1) Creates banch of segmented mbufs with different size and number of segments. 2) Generates pkt_len bytes of random data. 3) Fills noncontigouos mbuf with randomly generated data. 4) Uses rte_pktmbuf_coalesce to coalesce segmented buffe

[dpdk-dev] [PATCH 1/4] rte_mbuf: add rte_pktmbuf_coalesce

This patch adds function rte_pktmbuf_coalesce to let crypto PMD coalesce chained mbuf before crypto operation and extend their capabilities to support segmented mbufs when device cannot handle them natively. Signed-off-by: Tomasz Kulasek --- lib/librte_mbuf/rte_mbuf.h | 34 +++

[dpdk-dev] [PATCH 0/4] Chained Mbufs support in SW PMDs

This patch set adds support of scattered-gather list for SW PMDs. As of now, application needs to reserve continuous block of memory for mbufs which is not always the case. Hence needed to support chaining of mbufs which are smaller in size but can be used if chained. Above work involves: a) Cr

Re: [dpdk-dev] [PATCH 00/22] Generic flow API (rte_flow)

Hi Adrien, On 11/16/2016 4:23 PM, Adrien Mazarguil wrote: > As previously discussed in RFC v1 [1], RFC v2 [2], with changes > described in [3] (also pasted below), here is the first non-draft series > for this new API. > > Its capabilities are so generic that its name had to be vague, it may be >

[dpdk-dev] [PATCH] igb_uio: stop device when closing /dev/uioX

Depends-on: http://dpdk.org/dev/patchwork/patch/17493/ When a DPDK application grab a PCI device, device and driver work together to Rx/Tx packets. If the DPDK app crashes or gets killed, there's no chance for DPDK driver to stop the device, which means rte_eth_dev_stop() will not be called. This

[dpdk-dev] [PATCH v1] doc: add details of sub-trees and maintainers

Add a new section to the Code Contributors Guide to outline the roles of tree and component maintainers and how they can be added and removed. Signed-off-by: John McNamara --- doc/guides/contributing/patches.rst | 66 - 1 file changed, 58 insertions(+), 8 dele

Re: [dpdk-dev] Proposal for a new Committer model

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Mcnamara, John > Sent: Wednesday, November 30, 2016 9:59 AM > To: Neil Horman > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] Proposal for a new Committer model > > > -Original Message- > > From: Neil Horma

[dpdk-dev] [PATCH] igb_uio: deprecate iomem and ioport mapping

Previously in igb_uio, iomem is mapped, and both ioport and io mem are recorded into uio framework, which is duplicated and makes the code too complex. For iomem, DPDK user space code never opens or reads files under /sys/pci/bus/devices/:xx:xx.x/uio/uioY/maps/. Instead, /sys/pci/bus/devices/x

Re: [dpdk-dev] [PATCH] Scheduler: add driver for scheduler crypto pmd

On 02/12/16 14:57, Bruce Richardson wrote: On Fri, Dec 02, 2016 at 03:31:24PM +0100, Thomas Monjalon wrote: 2016-12-02 14:15, Fan Zhang: This patch provides the initial implementation of the scheduler poll mode driver using DPDK cryptodev framework. Scheduler PMD is used to schedule and enqueu

Re: [dpdk-dev] [PATCH v12 1/6] ethdev: add Tx preparation

Hi Olivier, > -Original Message- > From: Olivier Matz [mailto:olivier.m...@6wind.com] > Sent: Friday, December 2, 2016 8:24 AM > To: Ananyev, Konstantin > Cc: Thomas Monjalon ; Kulasek, TomaszX > ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v12 1/6] ethdev: add Tx preparation > > Hi

Re: [dpdk-dev] [PATCH v2 3/7] pci: Pass rte_pci_addr to functions instead of separate args

On Thu, 2016-12-01 at 11:56 +0530, Shreyansh Jain wrote: > Hello Ben, > > On Thursday 24 November 2016 01:37 AM, Ben Walker wrote: > > > > Instead of passing domain, bus, devid, func, just pass > > an rte_pci_addr. > > > > Signed-off-by: Ben Walker > > --- > >  lib/librte_eal/linuxapp/eal/eal_p

Re: [dpdk-dev] [PATCH 2/2] crypto/aesni_mb: add new option to select SIMD mode

On 02/12/16 10:37, Thomas Monjalon wrote: 2016-12-02 09:46, Declan Doherty: Add new initialisation option to the aesni_mb_pmd to allow the user to specify which set of SIMD functions to load from the AESNI Multi-Buffer Crypto for IPsec library. Why let user choose? Isn't the most recent the be

[dpdk-dev] [PATCH 2/2] app/crypto-perf: Introduce new performance test application

This patchset introduce new application which allows measuring performance parameters of PMDs available in crypto tree. The goal of this application is to replace existing performance tests in app/test. Parameters available are: throughput (--ptest throughput) and latency (--ptest latency). User ca

[dpdk-dev] [PATCH 1/2] lib/librte_cryptodev: functions for new performance test application

This patch adds helper functions for new performance application. Application can be used to measute throughput and latency of cryptography operation performed by crypto device. Signed-off-by: Declan Doherty Signed-off-by: Slawomir Mrozowicz Signed-off-by: Marcin Kerlin --- lib/librte_cryptode

[dpdk-dev] [PATCH 0/2] Introduce new performance test application

This patchset introduce new application which allows measuring performance parameters of PMDs available in crypto tree. The goal of this application is to replace existing performance tests in app/test. Parameters available are: throughput (--ptest throughput) and latency (--ptest latency). User ca

Re: [dpdk-dev] [PATCH v2 01/55] net/sfc: libefx-based PMD stub sufficient to build and init

On 12/02/2016 06:08 PM, Ferruh Yigit wrote: On 12/2/2016 3:03 PM, Andrew Rybchenko wrote: On 12/02/2016 05:54 PM, Ferruh Yigit wrote: On 11/29/2016 4:18 PM, Andrew Rybchenko wrote: The PMD is put into the sfc/efx subdirectory to have a place for .. into sfc subdirectory .. the second PMD an

Re: [dpdk-dev] [PATCH v2 01/55] net/sfc: libefx-based PMD stub sufficient to build and init

On 12/2/2016 3:03 PM, Andrew Rybchenko wrote: > On 12/02/2016 05:54 PM, Ferruh Yigit wrote: >> On 11/29/2016 4:18 PM, Andrew Rybchenko wrote: >>> The PMD is put into the sfc/efx subdirectory to have a place for >> .. into sfc subdirectory .. >> >>> the second PMD and library shared by both. >> Sinc

Re: [dpdk-dev] [PATCH v2 01/55] net/sfc: libefx-based PMD stub sufficient to build and init

On 12/02/2016 05:54 PM, Ferruh Yigit wrote: On 11/29/2016 4:18 PM, Andrew Rybchenko wrote: The PMD is put into the sfc/efx subdirectory to have a place for .. into sfc subdirectory .. the second PMD and library shared by both. Since all will go into same (sfc) folder, should mention from thi

Re: [dpdk-dev] [PATCH v2 00/55] Solarflare libefx-based PMD

On 11/29/2016 4:18 PM, Andrew Rybchenko wrote: > The patch series adds Solarflare libefx-based network PMD. > > This version of the driver supports Solarflare SFN7xxx and SFN8xxx > families of 10/40 Gbps adapters. > > libefx is a platform-independent library to implement drivers for > Solarflare

Re: [dpdk-dev] [PATCH] Scheduler: add driver for scheduler crypto pmd

On Fri, Dec 02, 2016 at 03:31:24PM +0100, Thomas Monjalon wrote: > 2016-12-02 14:15, Fan Zhang: > > This patch provides the initial implementation of the scheduler poll mode > > driver using DPDK cryptodev framework. > > > > Scheduler PMD is used to schedule and enqueue the crypto ops to the > > h

Re: [dpdk-dev] [PATCH v2 01/55] net/sfc: libefx-based PMD stub sufficient to build and init

On 11/29/2016 4:18 PM, Andrew Rybchenko wrote: > The PMD is put into the sfc/efx subdirectory to have a place for .. into sfc subdirectory .. > the second PMD and library shared by both. Since all will go into same (sfc) folder, should mention from this? This looks like justification of previous

[dpdk-dev] [PATCH 2/2] examples/flow_distributor: sample app to demonstrate EFD usage

This new sample app, based on the client/server sample app, shows the user an scenario using the EFD library. It consists of: - A front-end server which has an EFD table that stores the node id for each flow key, which will distribute the incoming packets to the different nodes - A back-end n

[dpdk-dev] [PATCH 1/2] efd: new Elastic Flow Distributor library

Elastic Flow Distributor (EFD) is a distributor library that uses perfect hashing to determine a target/value for a given incoming flow key. It has the following advantages: - First, because it uses perfect hashing, it does not store the key itself and hence lookup performance is not dependent o

[dpdk-dev] [PATCH 0/2] Elastic Flow Distributor

EFD is a distributor library that uses perfect hashing to determine a target/value for a given incoming flow key. It has the following advantages: first, because it uses perfect hashing it does not store the key itself and hence lookup performance is not dependent on the key size. Second, the targe

Re: [dpdk-dev] [PATCH 0/3] virtio_user as an alternative exception path

2016-12-02 14:31, Jianfeng Tan: > In v16.07, we upstreamed a virtual device, virtio_user (with vhost-user > as the backend). The path to go with a vhost-kernel backend has been > dropped for bad performance comparing to vhost-user and code simplicity. > > But after a second thought, virtio_user +

Re: [dpdk-dev] [PATCH 00/31] Support VFD and DPDK PF + kernel VF on i40e

2016-12-02 14:25, Iremonger, Bernard: > Hi Thomas, > > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > > > > Do you agree to copy the remaining VF-specific functions from the generic > > ethdev API to ixgbe in 17.02? > > After a deprecation notice, we could remove them from the generic

Re: [dpdk-dev] [PATCH] Scheduler: add driver for scheduler crypto pmd

2016-12-02 14:15, Fan Zhang: > This patch provides the initial implementation of the scheduler poll mode > driver using DPDK cryptodev framework. > > Scheduler PMD is used to schedule and enqueue the crypto ops to the > hardware and/or software crypto devices attached to it (slaves). The > dequeue

[dpdk-dev] [PATCH 3/3] net/virtio_user: fix wrongly set features

Before the commit 86d59b21468a ("net/virtio: support LRO"), features in virtio PMD, is decided and properly set at device initialization and will not be changed. But afterward, features could be changed in virtio_dev_configure(), and will be re-negotiated if it's changed. In virtio_user, host feat

[dpdk-dev] [PATCH 2/3] net/virtio_user: add vhost kernel support

This patch add support vhost kernel support under vhost abstraction layer. Three main hook functions are added: - vhost_kernel_setup() to open char device, each vq pair (Rx and Tx) would need open it once; - vhost_kernel_ioctl() to communicate control messages with vhost kernel module;

[dpdk-dev] [PATCH 1/3] net/virtio_user: add vhost layer

To support vhost kernel as the backend of net_virtio_user in comming patches, we abstract a vhost layer to hide all vhost_user functions. - Move vhost_user specific structs and macros into vhost_user.c, and only keep common definitions in vhost.h; - Add a struct vhost_internal, and an array

[dpdk-dev] [PATCH 0/3] virtio_user as an alternative exception path

In v16.07, we upstreamed a virtual device, virtio_user (with vhost-user as the backend). The path to go with a vhost-kernel backend has been dropped for bad performance comparing to vhost-user and code simplicity. But after a second thought, virtio_user + vhost-kernel is a good candidate as an ex

Re: [dpdk-dev] [PATCH 00/31] Support VFD and DPDK PF + kernel VF on i40e

Hi Thomas, > -Original Message- > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > Sent: Friday, December 2, 2016 2:16 PM > To: Lu, Wenzhuo ; Iremonger, Bernard > ; Yigit, Ferruh > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 00/31] Support VFD and DPDK PF + kernel VF > on

Re: [dpdk-dev] [PATCH 00/31] Support VFD and DPDK PF + kernel VF on i40e

Do you agree to copy the remaining VF-specific functions from the generic ethdev API to ixgbe in 17.02? After a deprecation notice, we could remove them from the generic API in 17.05. So we will have a consistent status in 17.05 regarding VF functions. After some time (and experience) we will be a

[dpdk-dev] [PATCH 3/3] app/test: add DES tests to Intel QAT crypto test suite

This commit adds tests of Data Encryption Standard (DES) algorithm to Intel QuickAssist technology crypto test suites Signed-off-by: Arek Kusztal --- app/test/test_cryptodev.c | 18 + app/test/test_cryptodev_blockcipher.c | 5 ++ app/test/test_cryptodev_blockcipher.h

[dpdk-dev] [PATCH 2/3] crypto/qat: add DES capability to Intel QAT driver

This commit adds DES capability to Intel QuickAssist Technology Driver Signed-off-by: Arek Kusztal --- doc/guides/cryptodevs/qat.rst| 1 + doc/guides/rel_notes/release_17_02.rst | 6 + drivers/crypto/qat/qat_adf/qat_algs.h| 1 + drivers/crypto/qat

[dpdk-dev] [PATCH 0/3] Add DES capability to Intel QuickAssist Technology driver

This patchset adds Data Encryption Standard (DES) capability to Intel QuickAssist Technology driver and corresponding tests to test files. Arek Kusztal (3): lib/librte_cryptodev: add DES CBC cipher algorithm crypto/qat: add DES capability to Intel QAT driver app/test: add DES tests to Intel

[dpdk-dev] [PATCH 1/3] lib/librte_cryptodev: add DES CBC cipher algorithm

This commit adds DES CBC ciper algorithm to available algorithms Signed-off-by: Arek Kusztal --- lib/librte_cryptodev/rte_crypto_sym.h | 4 1 file changed, 4 insertions(+) diff --git a/lib/librte_cryptodev/rte_crypto_sym.h b/lib/librte_cryptodev/rte_crypto_sym.h index d694723..0e20b30 100

[dpdk-dev] [PATCH] Scheduler: add driver for scheduler crypto pmd

This patch provides the initial implementation of the scheduler poll mode driver using DPDK cryptodev framework. Scheduler PMD is used to schedule and enqueue the crypto ops to the hardware and/or software crypto devices attached to it (slaves). The dequeue operation from the slave(s), and the pos

  1   2   >