[dpdk-dev] [PATCH v3 1/2] ethdev: add tunnel and port RSS offload types

Hi Jerin, I wanted to push this patch which is now a dependency of ThunderX but I do not fully understand it. 2016-03-31 02:21, Jerin Jacob: > - added VXLAN, GENEVE and NVGRE tunnel flow types > - added PORT flow type for accounting physical/virtual > port or channel number in flow creation

[dpdk-dev] [PATCH] ip_pipeline: fix parsing error in TM port section

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Tuesday, June 21, 2016 9:49 PM > To: Dumitrescu, Cristian > Cc: dev at dpdk.org; Singh, Jasvinder > Subject: Re: [dpdk-dev] [PATCH] ip_pipeline: fix parsing error in TM port > section > >

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

Hi Jerin, > -Original Message- > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > Sent: Tuesday, June 21, 2016 10:29 PM > To: Ananyev, Konstantin > Cc: Lu, Wenzhuo; Stephen Hemminger; dev at dpdk.org; Richardson, Bruce; Chen, > Jing D; Liang, Cunming; Wu, Jingjing; Zhang,

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Wed, Jun 22, 2016 at 01:35:37AM +, Lu, Wenzhuo wrote: > Hi Jerin, > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Tuesday, June 21, 2016 10:29 PM > > To: Ananyev, Konstantin > > Cc: Lu, Wenzhuo; Stephen Hemminger; dev at dpdk.org;

[dpdk-dev] [PATCH v3] i40e: fix the type issue of a single VLAN type

In current i40e codebase, if single VLAN header is added in a packet, it's treated as inner VLAN. Generally, a single VLAN header is treated as the outer VLAN header. So change corresponding register for single VLAN. Fixes: 19b16e2f6442 ("ethdev: add vlan type when setting ether type")

[dpdk-dev] Assembly code

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Mahdi Moradmand > Badie > Sent: Wednesday, June 22, 2016 5:21 AM > To: dev at dpdk.org > Subject: [dpdk-dev] Assembly code > > Dear All, > > I used the default format of Makefile (as follow) which is

[dpdk-dev] [PATCH v3 1/2] ethdev: add tunnel and port RSS offload types

On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote: > Hi Jerin, Hi Thomas, > > I wanted to push this patch which is now a dependency of ThunderX > but I do not fully understand it. > > 2016-03-31 02:21, Jerin Jacob: > > - added VXLAN, GENEVE and NVGRE tunnel flow types > > - added

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

Hi Jerin, > -Original Message- > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > Sent: Wednesday, June 22, 2016 10:38 AM > To: Lu, Wenzhuo > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson, > Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang,

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Wed, Jun 22, 2016 at 03:32:16AM +, Lu, Wenzhuo wrote: > Hi Jerin, > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Wednesday, June 22, 2016 10:38 AM > > To: Lu, Wenzhuo > > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

> -Original Message- > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > Sent: Wednesday, June 22, 2016 12:15 PM > To: Lu, Wenzhuo > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson, > Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang, Helin; >

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Wed, Jun 22, 2016 at 05:05:14AM +, Lu, Wenzhuo wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Wednesday, June 22, 2016 12:15 PM > > To: Lu, Wenzhuo > > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org;

[dpdk-dev] regarding coverity-scan-id : 127350

hi, i just looked at the CID: 127350 which raises a STRING_OVERFLOW bug for pdump_prepare_client_request(...) callers of pdump_prepare_client_request(...) pass 'device' parameter which is always of DEVICE_ID_SIZE (64) bytes long. hence it is not possible to overflow

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

Hi Jerin, > -Original Message- > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > Sent: Wednesday, June 22, 2016 2:10 PM > To: Lu, Wenzhuo > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; Richardson, > Bruce; Chen, Jing D; Liang, Cunming; Wu, Jingjing; Zhang,

[dpdk-dev] [PATCH v3 1/2] ethdev: add tunnel and port RSS offload types

2016-06-22 09:00, Jerin Jacob: > On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote: > > Hi Jerin, > > Hi Thomas, > > > > > I wanted to push this patch which is now a dependency of ThunderX > > but I do not fully understand it. > > > > 2016-03-31 02:21, Jerin Jacob: > > > - added

[dpdk-dev] [PATCH 3/3] app/pdump: fix string overflow

> if (!strcmp(key, PDUMP_RX_DEV_ARG)) { > - strncpy(pt->rx_dev, value, strlen(value)); > + strncpy(pt->rx_dev, value, sizeof(pt->rx_dev)-1); I guess size-1 is to give room for terminating null byte, but for this case is it guarantied that pt->rx_dev last byte is

[dpdk-dev] PATCH] mbuf: rte_pktmbuf_dump: don't add 0x when using %p in format strings

On 2016-06-21 15:11, Ferruh Yigit wrote: > On 6/20/2016 5:19 PM, Stephen Hemminger wrote: >> On Mon, 20 Jun 2016 12:44:35 +0200 >> Simon Kagstrom wrote: >> >>> I.e., avoid dump messages with double 0x0x, e.g., >>> >>> dump mbuf at 0x0x7fac7b17c800, phys=17b17c880, buf_len=2176 >>>

[dpdk-dev] [PATCH v3 1/2] ethdev: add tunnel and port RSS offload types

On Wed, Jun 22, 2016 at 08:43:52AM +0200, Thomas Monjalon wrote: > 2016-06-22 09:00, Jerin Jacob: > > On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote: > > > Hi Jerin, > > > > Hi Thomas, > > > > > > > > I wanted to push this patch which is now a dependency of ThunderX > > > but I

[dpdk-dev] [PATCH v3 11/25] mlx5: add support for configuration through kvargs

On Tue, Jun 21, 2016 at 05:42:42PM +0100, Ferruh Yigit wrote: > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote: > > The intent is to replace the remaining compile-time options and environment > > variables with a common mean of runtime configuration. This commit only > > adds the kvargs handling

[dpdk-dev] [PATCH v3 1/2] ethdev: add tunnel and port RSS offload types

2016-06-22 12:45, Jerin Jacob: > On Wed, Jun 22, 2016 at 08:43:52AM +0200, Thomas Monjalon wrote: > > 2016-06-22 09:00, Jerin Jacob: > > > On Tue, Jun 21, 2016 at 11:02:59PM +0200, Thomas Monjalon wrote: > > > > 2016-03-31 02:21, Jerin Jacob: > > > > > +#define RTE_ETH_FLOW_PORT 18 >

[dpdk-dev] [PATCH v15 0/3] mempool: add mempool handler feature

2016-06-19 13:05, David Hunt: > v15 changes: > > * Changed rte_mempool_ops_get() to rte_mempool_get_ops() I don't find this change in the patch. But I wonder wether it is really needed.

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Wed, Jun 22, 2016 at 06:42:43AM +, Lu, Wenzhuo wrote: > Hi Jerin, > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Wednesday, June 22, 2016 2:10 PM > > To: Lu, Wenzhuo > > Cc: Ananyev, Konstantin; Stephen Hemminger; dev at

[dpdk-dev] [PATCH 1/3] pdump: check getenv return value

Hi Ferruh, > -Original Message- > From: Yigit, Ferruh > Sent: Tuesday, June 21, 2016 5:56 PM > To: Pattan, Reshma ; dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH 1/3] pdump: check getenv return value > > On 6/21/2016 4:18 PM, Reshma Pattan wrote: > > dir =

[dpdk-dev] [PATCH v15 0/3] mempool: add mempool handler feature

2016-06-22 09:56, Thomas Monjalon: > 2016-06-19 13:05, David Hunt: > > v15 changes: > > > > * Changed rte_mempool_ops_get() to rte_mempool_get_ops() > > I don't find this change in the patch. > But I wonder wether it is really needed. If we assume that rte_mempool_ops_* are wrappers on top of

[dpdk-dev] [PATCH] arm64: change rte_memcpy to inline function

On 17 June 2016 at 18:30, Thomas Monjalon wrote: > 2016-05-19 17:56, Thomas Monjalon: >> 2016-05-19 21:48, Jianbo Liu: >> > On 13 May 2016 at 23:49, Thomas Monjalon >> > wrote: >> > > 2016-05-10 14:01, Jianbo Liu: >> > >> Other APP may call rte_memcpy by function pointer, >> > >> so change it

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

2016-06-22 13:29, Jerin Jacob: > Thomas, > As a librte_ether maintainer any comments on this? +1 for adding details and make sure naming is good. I don't really need to comment here because I have already done this comment earlier: http://dpdk.org/ml/archives/dev/2016-June/041845.html

[dpdk-dev] [PATCH v3 1/2] ethdev: add callback to get register size in bytes

Note that if we remove rte_eth_dev_get_reg_length() then it will break all of the drivers that implement it. Shall I remove it all leave it and modify only ethtool to use rte_eth_dev_get_regs() to get reg size? In the end the drivers will have to implement the part of setting the size in

[dpdk-dev] [PATCH v3 00/25] Refactor mlx5 to improve performance

On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote: > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote: > > Enhance mlx5 with a data path that bypasses Verbs. > > > > The first half of this patchset removes support for functionality completely > > rewritten in the second half

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

Hi Thomas, > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Wednesday, June 22, 2016 4:17 PM > To: Jerin Jacob > Cc: Lu, Wenzhuo; Ananyev, Konstantin; Stephen Hemminger; dev at dpdk.org; > Richardson, Bruce; Chen, Jing D; Liang, Cunming; Wu,

[dpdk-dev] [PATCH v3 1/2] ethdev: add callback to get register size in bytes

2016-06-22 10:19, Zyta Szpak: > Note that if we remove rte_eth_dev_get_reg_length() then it will break > all of the drivers that implement it. Shall I remove it all leave it and > modify only ethtool to use rte_eth_dev_get_regs() to get reg size? In > the end the drivers will have to implement

[dpdk-dev] [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8

>-Original Message- >From: Dumitrescu, Cristian >Sent: Tuesday, June 21, 2016 7:44 PM >To: Mrzyglod, DanielX T ; Singh, Jasvinder > >Cc: dev at dpdk.org >Subject: RE: [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8 > > > >> -Original Message- >> From: Mrzyglod,

[dpdk-dev] [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8

>From: Mrzyglod, DanielX T >Sent: Tuesday, June 21, 2016 11:36 AM >To: Singh, Jasvinder ; Dumitrescu, Cristian > >Cc: dev at dpdk.org; Mrzyglod, DanielX T >Subject: [PATCH v2] examples/ip_pipeline: fix build error for gcc 4.8 > >This patch fixes a maybe-uninitialized warning when compiling DPDK

[dpdk-dev] [PATCH] ip_pipeline: fix parsing error in TM port section

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jasvinder Singh > Sent: Thursday, June 16, 2016 10:05 AM > To: dev at dpdk.org > Cc: Dumitrescu, Cristian > Subject: [dpdk-dev] [PATCH] ip_pipeline: fix parsing error in TM port section > > Replace

[dpdk-dev] [PATCH 00/25] Refactor mlx5 to improve performance

Enhance mlx5 with a data path that bypasses Verbs. The first half of this patchset removes support for functionality completely rewritten in the second half (scatter/gather, inline send), while the data path is refactored without Verbs. The PMD remains usable during the transition. This

[dpdk-dev] [PATCH v4 01/25] drivers: fix PCI class id support

Fixes: 701c8d80c820 ("pci: support class id probing") Signed-off-by: Nelio Laranjeiro --- drivers/crypto/qat/rte_qat_cryptodev.c | 5 + drivers/net/mlx4/mlx4.c| 18 ++ drivers/net/mlx5/mlx5.c| 24

[dpdk-dev] [PATCH v4 02/25] mlx5: split memory registration function

Except for the first time when memory registration occurs, the lkey is always cached. Since memory registration is slow and performs system calls, performance can be improved by moving that code to its own function outside of the data path so only the lookup code is left in the original inlined

[dpdk-dev] [PATCH v4 03/25] mlx5: remove Tx gather support

This is done in preparation of bypassing Verbs entirely for the data path as a performance improvement. TX gather cannot be maintained during the transition and will be reimplemented later. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5_ethdev.c | 2

[dpdk-dev] [PATCH v5 00/17] Prepare for rte_device / rte_driver

* Original patch series is from David Marchand [1], [2]. * Cover letter text has been modified to make it author agnostic David created the original patchset based on the discussions on list [3]. Being a large piece of work, this patchset introduces first level of changes for generalizing the

[dpdk-dev] [PATCH v4 08/25] mlx5: split Rx queue structure

To keep the data path as efficient as possible, move fields only useful to the control path into new structure rxq_ctrl. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5.c | 6 +- drivers/net/mlx5/mlx5_fdir.c | 8 +- drivers/net/mlx5/mlx5_rxq.c

[dpdk-dev] [PATCH v4 07/25] mlx5: split Tx queue structure

To keep the data path as efficient as possible, move fields only useful to the control path into new structure txq_ctrl. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5.c| 21 +++-- drivers/net/mlx5/mlx5_ethdev.c | 28 +++---

[dpdk-dev] [PATCH v4 09/25] mlx5: update prerequisites for upcoming enhancements

The latest version of Mellanox OFED exposes hardware definitions necessary to implement data path operation bypassing Verbs. Update the minimum version requirement to MLNX_OFED >= 3.3 and clean up compatibility checks for previous releases. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien

[dpdk-dev] [PATCH v4 10/25] mlx5: add definitions for data path without Verbs

These structures and macros extend those exposed by libmlx5 (in mlx5_hw.h) to let the PMD manage work queue and completion queue elements directly. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5_prm.h | 163

[dpdk-dev] [PATCH v5 01/17] pci: no need for dynamic tailq init

These lists can be initialized once and for all at build time. With this, those lists are only manipulated in a common place (and we could even make them private). A nice side effect is that pci drivers can now register in constructors. Signed-off-by: David Marchand Reviewed-by: Jan Viktorin

[dpdk-dev] [PATCH v4 12/25] mlx5: add Tx/Rx burst function selection wrapper

These wrappers are meant to prevent code duplication later. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5.h| 2 ++ drivers/net/mlx5/mlx5_ethdev.c | 34 -- drivers/net/mlx5/mlx5_txq.c| 2 +- 3 files

[dpdk-dev] [PATCH v4 11/25] mlx5: add support for configuration through kvargs

The intent is to replace the remaining compile-time options and environment variables with a common mean of runtime configuration. This commit only adds the kvargs handling code, subsequent commits will update the rest. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil ---

[dpdk-dev] [PATCH v4 13/25] mlx5: refactor Rx data path

Bypass Verbs to improve RX performance. Signed-off-by: Nelio Laranjeiro Signed-off-by: Yaacov Hazan Signed-off-by: Adrien Mazarguil Signed-off-by: Vasily Philipov --- drivers/net/mlx5/mlx5_ethdev.c | 4 +- drivers/net/mlx5/mlx5_fdir.c | 2 +- drivers/net/mlx5/mlx5_rxq.c| 303

[dpdk-dev] [PATCH v4 14/25] mlx5: refactor Tx data path

Bypass Verbs to improve Tx performance. Signed-off-by: Nelio Laranjeiro Signed-off-by: Yaacov Hazan Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/Makefile | 5 - drivers/net/mlx5/mlx5_ethdev.c | 10 +- drivers/net/mlx5/mlx5_mr.c | 4 +- drivers/net/mlx5/mlx5_rxtx.c |

[dpdk-dev] [PATCH v4 15/25] mlx5: handle Rx CQE compression

Mini (compressed) CQEs are returned by the NIC when PCI back pressure is detected, in which case the first CQE64 contains common packet information followed by a number of CQE8 providing the rest, followed by a matching number of empty CQE64 entries to be used by software for decompression.

[dpdk-dev] [PATCH v5 02/17] crypto: no need for a crypto pmd type

This information is not used and just adds noise. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_cryptodev/rte_cryptodev.c | 8 +++- lib/librte_cryptodev/rte_cryptodev.h | 2 -- lib/librte_cryptodev/rte_cryptodev_pmd.h | 3 +-- 3 files changed, 4

[dpdk-dev] [PATCH v4 17/25] mlx5: add support for inline send

From: Yaacov Hazan Implement send inline feature which copies packet data directly into WQEs for improved latency. The maximum packet size and the minimum number of Tx queues to qualify for inline send are user-configurable. This feature is effective when HW causes a

[dpdk-dev] [PATCH v4 18/25] mlx5: add support for multi-packet send

This feature enables the TX burst function to emit up to 5 packets using only two WQEs on devices that support it. Saves PCI bandwidth and improves performance. Signed-off-by: Nelio Laranjeiro Signed-off-by: Adrien Mazarguil Signed-off-by: Olga Shern --- doc/guides/nics/mlx5.rst | 10

[dpdk-dev] [PATCH v4 19/25] mlx5: add debugging information about Tx queues capabilities

From: Adrien Mazarguil Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5_txq.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c index 4f17fb0..bae9f3d 100644 --- a/drivers/net/mlx5/mlx5_txq.c

[dpdk-dev] [PATCH v5 05/17] eal: introduce init macros

Introduce a RTE_INIT macro used to mark an init function as a constructor. Current eal macros have been converted to use this (no functional impact). RTE_EAL_PCI_REGISTER is added as a helper for pci drivers. Suggested-by: Jan Viktorin Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain

[dpdk-dev] [PATCH v4 20/25] mlx5: check remaining space while processing Tx burst

From: Adrien Mazarguil The space necessary to store segmented packets cannot be known in advance and must be verified for each of them. Signed-off-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5_rxtx.c | 136 ++- 1 file

[dpdk-dev] [PATCH v5 06/17] crypto: export init/uninit common wrappers for pci drivers

Preparing for getting rid of rte_cryptodev_driver, here are two wrappers that can be used by pci drivers that assume a 1 to 1 association between pci resource and upper interface. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_cryptodev/rte_cryptodev.c |

[dpdk-dev] [PATCH v5 08/17] drivers: convert all pdev drivers as pci drivers

Simplify crypto and ethdev pci drivers init by using newly introduced init macros and helpers. Those drivers then don't need to register as "rte_driver"s anymore. virtio and mlx* drivers use the general purpose RTE_INIT macro, as they both need some special stuff to be done before registering a

[dpdk-dev] [PATCH v4 24/25] mlx5: make Rx queue reinitialization safer

From: Adrien Mazarguil The primary purpose of rxq_rehash() function is to stop and restart reception on a queue after re-posting buffers. This may fail if the array that temporarily stores existing buffers for reuse cannot be allocated. Update rxq_rehash() to work on

[dpdk-dev] [PATCH v4 25/25] mlx5: resurrect Rx scatter support

From: Adrien Mazarguil This commit brings back Rx scatter and related support by the MTU update function. The maximum number of segments per packet is not a fixed value anymore (previously MLX5_PMD_SGE_WR_N, set to 4 by default) as it caused performance issues when

[dpdk-dev] [PATCH v5 10/17] ethdev: get rid of eth driver register callback

Now that all pdev are pci drivers, we don't need to register ethdev drivers through a dedicated channel. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_ether/rte_ethdev.c | 22 -- lib/librte_ether/rte_ethdev.h | 12

[dpdk-dev] [PATCH v5 09/17] crypto: get rid of crypto driver register callback

Now that all pdev are pci drivers, we don't need to register crypto drivers through a dedicated channel. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_cryptodev/rte_cryptodev.c | 22 --- lib/librte_cryptodev/rte_cryptodev_pmd.h | 30

[dpdk-dev] [PATCH v5 11/17] eal/linux: move back interrupt thread init before setting affinity

Now that virtio pci driver is initialized in a constructor, iopl() stuff happens early enough so that interrupt thread can be created right after plugin loading. This way, chelsio driver should be happy again [1]. [1] http://dpdk.org/ml/archives/dev/2015-November/028289.html Signed-off-by: David

[dpdk-dev] [PATCH v4 22/25] mlx5: work around spurious compilation errors

From: Adrien Mazarguil Since commit "mlx5: resurrect Tx gather support", older GCC versions (such as 4.8.5) may complain about the following: mlx5_rxtx.c: In function `mlx5_tx_burst': mlx5_rxtx.c:705:25: error: `wqe' may be used uninitialized in this function

[dpdk-dev] [PATCH v5 07/17] ethdev: export init/uninit common wrappers for pci drivers

Preparing for getting rid of eth_drv, here are two wrappers that can be used by pci drivers that assume a 1 to 1 association between pci resource and upper interface. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_ether/rte_ethdev.c | 14 +++---

[dpdk-dev] [PATCH v4 23/25] mlx5: remove redundant Rx queue initialization code

From: Adrien Mazarguil Toggling RX checksum offloads is already done at initialization time. This code does not belong in rxq_rehash(). Signed-off-by: Adrien Mazarguil Signed-off-by: Nelio Laranjeiro --- drivers/net/mlx5/mlx5_rxq.c | 10 -- 1 file changed,

[dpdk-dev] [PATCH v5 12/17] pci: add a helper for device name

eal is a better place than crypto / ethdev for naming resources. Add a helper in eal and make use of it in crypto / ethdev. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_cryptodev/rte_cryptodev.c| 27 ---

[dpdk-dev] [PATCH v5 13/17] pci: add a helper to update a device

This helper updates a pci device object with latest information it can find. It will be used mainly for hotplug code. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_eal/bsdapp/eal/eal_pci.c | 49 +

[dpdk-dev] [PATCH v5 14/17] ethdev: do not scan all pci devices on attach

No need to scan all devices, we only need to update the device being attached. Signed-off-by: David Marchand Signed-off-by: Shreyansh Jain --- lib/librte_eal/common/eal_common_pci.c | 11 --- lib/librte_ether/rte_ethdev.c | 3 --- 2 files changed, 8 insertions(+), 6

[dpdk-dev] [PATCH v5 16/17] ethdev: convert to eal hotplug

Remove bus logic from ethdev hotplug by using eal for this. Current api is preserved: - the last port that has been created is tracked to return it to the application when attaching, - the internal device name is reused when detaching. We can not get rid of ethdev hotplug yet since we still

[dpdk-dev] [PATCH v4 21/25] mlx5: resurrect Tx gather support

From: Adrien Mazarguil Compared to its previous incarnation, the software limit on the number of mbuf segments is no more (previously MLX5_PMD_SGE_WR_N, set to 4 by default) hence no need for linearization code and related buffers that permanently consumed a non

[dpdk-dev] [PATCH v3 00/25] Refactor mlx5 to improve performance

On Wed, Jun 22, 2016 at 10:20:54AM +0200, Adrien Mazarguil wrote: > On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote: > > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote: > > > Enhance mlx5 with a data path that bypasses Verbs. > > > > > > The first half of this patchset removes support

[dpdk-dev] [PATCH 3/3] app/pdump: fix string overflow

On Wed, Jun 22, 2016 at 12:16:27PM +0530, Anupam Kapoor wrote: > > if (!strcmp(key, PDUMP_RX_DEV_ARG)) { > > - strncpy(pt->rx_dev, value, strlen(value)); > > + strncpy(pt->rx_dev, value, sizeof(pt->rx_dev)-1); > > I guess size-1 is to give room for terminating null

[dpdk-dev] [PATCH 3/3] app/pdump: fix string overflow

Hi, > -Original Message- > From: Richardson, Bruce > Sent: Wednesday, June 22, 2016 10:22 AM > To: Anupam Kapoor > Cc: Yigit, Ferruh ; Pattan, Reshma > ; dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH 3/3] app/pdump: fix string overflow > > On Wed, Jun 22, 2016 at 12:16:27PM +0530,

[dpdk-dev] [PATCH v16 0/3] mempool: add mempool handler feature

Here's the latest version of the Mempool Handler patch set. It's re-based on top of the latest head as of 20/6/2016, including Olivier's 35-part patch series on mempool re-org [1] [1] http://dpdk.org/ml/archives/dev/2016-May/039229.html v16 changes: * Changed rte_mempool_ops_get() to

[dpdk-dev] [PATCH v16 1/3] mempool: support mempool handler operations

Until now, the objects stored in a mempool were internally stored in a ring. This patch introduces the possibility to register external handlers replacing the ring. The default behavior remains unchanged, but calling the new function rte_mempool_set_ops_byname() right after

[dpdk-dev] [PATCH v16 2/3] app/test: test mempool handler

Create a minimal custom mempool handler and check that it passes basic mempool autotests. Signed-off-by: Olivier Matz Signed-off-by: David Hunt Reviewed-by: Jan Viktorin Acked-by: Shreyansh Jain Acked-by: Olivier Matz --- app/test/test_mempool.c | 122

[dpdk-dev] [PATCH v16 3/3] mbuf: make default mempool ops configurable at build

By default, the mempool ops used for mbuf allocations is a multi producer and multi consumer ring. We could imagine a target (maybe some network processors?) that provides an hardware-assisted pool mechanism. In this case, the default configuration for this architecture would contain a different

[dpdk-dev] [PATCH v3 00/25] Refactor mlx5 to improve performance

On Wed, Jun 22, 2016 at 10:19:14AM +0100, Bruce Richardson wrote: > On Wed, Jun 22, 2016 at 10:20:54AM +0200, Adrien Mazarguil wrote: > > On Tue, Jun 21, 2016 at 05:42:29PM +0100, Ferruh Yigit wrote: > > > On 6/21/2016 8:23 AM, Nelio Laranjeiro wrote: > > > > Enhance mlx5 with a data path that

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Wed, Jun 22, 2016 at 11:18:21AM +0200, Thomas Monjalon wrote: > 2016-06-22 08:25, Lu, Wenzhuo: > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > > 2016-06-22 13:29, Jerin Jacob: > > > > Thomas, > > > > As a librte_ether maintainer any comments on this? > > > > > > +1 for

[dpdk-dev] [PATCH] port: fix build when KNI support is not enabled

Commit 9fc37d1c071c is missing a conditional in the dependencies, causing builds to fail when KNI is not enabled: == Build lib/librte_port LD librte_port.so.3 /usr/bin/ld: cannot find -lrte_kni collect2: error: ld returned 1 exit status Fixes: 9fc37d1c071c ("port: support KNI")

[dpdk-dev] [PATCH] port: fix build when KNI support is not enabled

2016-06-22 14:34, Panu Matilainen: > --- a/lib/librte_port/Makefile > +++ b/lib/librte_port/Makefile > @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool > DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ether > DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ip_frag >

[dpdk-dev] [PATCH] port: fix build when KNI support is not enabled

Hi Thomas, On 06/22/2016 01:49 PM, Thomas Monjalon wrote: > 2016-06-22 14:34, Panu Matilainen: >> --- a/lib/librte_port/Makefile >> +++ b/lib/librte_port/Makefile >> @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool >> DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_ether

[dpdk-dev] [PATCH] port: fix build when KNI support is not enabled

2016-06-22 13:57, Olivier Matz: > Hi Thomas, > > On 06/22/2016 01:49 PM, Thomas Monjalon wrote: > > 2016-06-22 14:34, Panu Matilainen: > >> --- a/lib/librte_port/Makefile > >> +++ b/lib/librte_port/Makefile > >> @@ -82,6 +82,8 @@ DEPDIRS-$(CONFIG_RTE_LIBRTE_PORT) += lib/librte_mempool > >>

[dpdk-dev] segfault in vt_pci_init

All, I am trying to debug a problem: I am running testpmd in a VM. The stack trace is below. Running uio_pci_generic. kvm-qemu 2.5.3, Centos 7 CentOS Linux release 7.2.1511 (Core) Problem can be reproduced using either igb_uio or virtio_pci kernel drivers. Currently running 3.18.35 kernel

[dpdk-dev] librte_meter compilation fails on IBM Power8

Hi Cristian, Chao, I have encountered a compilation failure on IBM Power8 when compiling master branch with EXTRA_CFLAGS='-O0 -g': /root/nl/dpdk.org/build/lib/librte_meter.a(rte_meter.o): In function `rte_meter_get_tb_params': /root/nl/dpdk.org/lib/librte_meter/rte_meter.c:57: undefined

[dpdk-dev] [dpdk-users] Get interface speed through IOCTL

2016-06-22 17:49, Gadre Nayan: > I need to get the interface speed though standard IOCTL call: [...] > > However, for 10G interface I do not read a correct speed, since it may > not be supported. Yes > Out 1G cards are I350 and 10G card is I40. [...] > There is no support for 1base. So to

[dpdk-dev] [PATCH v4 0/2] New RSS offload flags

v1..v2 - Added cover letter - Corrected typo in RET_ETH_FLOW_VXLAN name - Updated test-pmd application to access newly defined RSS offload flags v2..v3 -testpmd document update(Suggested by John and Pablo) v3..v4 - Added doxgen comments for new FLOW types(Suggested by Thomas) Jerin Jacob (2):

[dpdk-dev] [PATCH v4 2/2] ethdev: add ETH_RSS_RETA_SIZE_256

Signed-off-by: Jerin Jacob --- lib/librte_ether/rte_ethdev.h | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h index 1579cb0..6cf4c58 100644 --- a/lib/librte_ether/rte_ethdev.h +++ b/lib/librte_ether/rte_ethdev.h @@ -477,6 +477,7 @@

[dpdk-dev] [PATCH v5 09/17] crypto: get rid of crypto driver register callback

On Wed, Jun 22, 2016 at 02:36:28PM +0530, Shreyansh Jain wrote: > Now that all pdev are pci drivers, we don't need to register crypto drivers > through a dedicated channel. > > Signed-off-by: David Marchand > Signed-off-by: Shreyansh Jain > --- > lib/librte_cryptodev/rte_cryptodev.c

[dpdk-dev] [PATCH v5 10/17] ethdev: get rid of eth driver register callback

On Wed, Jun 22, 2016 at 02:36:29PM +0530, Shreyansh Jain wrote: > Now that all pdev are pci drivers, we don't need to register ethdev drivers > through a dedicated channel. > > Signed-off-by: David Marchand > Signed-off-by: Shreyansh Jain > --- > lib/librte_ether/rte_ethdev.c | 22

[dpdk-dev] segfault in vt_pci_init

2016-06-22 14:27, Thomas F Herbert: > Program received signal SIGSEGV, Segmentation fault. > 0x00616172 in vtpci_init (dev=0xbfb0f0, hw=0x7fffd57d0700, > dev_flags=0x7fffdf9c) > at /home/heat-admin/dpdk/drivers/net/virtio/virtio_pci.c:722 > 722

[dpdk-dev] [PATCH v5 09/17] crypto: get rid of crypto driver register callback

On Wednesday 22 June 2016 06:57 PM, Neil Horman wrote: > On Wed, Jun 22, 2016 at 02:36:28PM +0530, Shreyansh Jain wrote: >> Now that all pdev are pci drivers, we don't need to register crypto drivers >> through a dedicated channel. >> >> Signed-off-by: David Marchand >> Signed-off-by: Shreyansh

[dpdk-dev] [PATCH v5 10/17] ethdev: get rid of eth driver register callback

On Wednesday 22 June 2016 06:58 PM, Neil Horman wrote: > On Wed, Jun 22, 2016 at 02:36:29PM +0530, Shreyansh Jain wrote: >> Now that all pdev are pci drivers, we don't need to register ethdev drivers >> through a dedicated channel. >> >> Signed-off-by: David Marchand >> Signed-off-by: Shreyansh

[dpdk-dev] [PATCH v5 09/17] crypto: get rid of crypto driver register callback

2016-06-22 09:27, Neil Horman: > > +++ b/lib/librte_cryptodev/rte_cryptodev_version.map > > - rte_cryptodev_pmd_driver_register; > NAK, you can't just remove exported symbols without going through the > deprecation process. Better still would be to only expose it for DPDK_16.04 > and > hide it

[dpdk-dev] [PATCH v2 1/3] pdump: check getenv return value

inside pdump_get_socket_path(), getenv can return a NULL pointer if the match for SOCKET_PATH_HOME is not found in the environment. NULL check is added to return -1 immediately without calling mkdir. Since pdump_get_socket_path() returns -1 now, wherever this function is called there the return

[dpdk-dev] [PATCH v2 0/3] fix coverity issues in packet capture framework

This patchset fixes coverity issues in pdump library and pdump tool. v2: fixed code review comment to use snprintf instead of strncpy. Reshma Pattan (3): pdump: check getenv return value pdump: fix string overflow app/pdump: fix string overflow app/pdump/main.c | 4 ++--

[dpdk-dev] [PATCH v2 2/3] pdump: fix string overflow

replaced strncpy with snprintf for safely copying the strings. Cverity issue 127350: string overflow Fixes: 278f945402c5 ("pdump: add new library for packet capture") Signed-off-by: Reshma Pattan --- lib/librte_pdump/rte_pdump.c | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-)

[dpdk-dev] segfault in vt_pci_init

Thomas, Thanks. That fixes it of course. --TFH On 6/22/16 3:39 PM, Thomas Monjalon wrote: > 2016-06-22 14:27, Thomas F Herbert: >> Program received signal SIGSEGV, Segmentation fault. >> 0x00616172 in vtpci_init (dev=0xbfb0f0, hw=0x7fffd57d0700, >> dev_flags=0x7fffdf9c) >>

[dpdk-dev] [PATCH v4 1/2] ethdev: add tunnel and port RSS offload types

2016-06-22 18:33, Jerin Jacob: > - added VXLAN, GENEVE and NVGRE tunnel flow types > - added PORT flow type for accounting physical/virtual > port or channel number in flow creation [...] > +#define RTE_ETH_FLOW_PORT 18 > + /**< Physical/virtual port number based flow */ What

[dpdk-dev] [PATCH] port: fix build when KNI support is not enabled

On 06/22/2016 02:20 PM, Thomas Monjalon wrote: > 2016-06-22 13:57, Olivier Matz: >> Hi Thomas, >> >> On 06/22/2016 01:49 PM, Thomas Monjalon wrote: >>> 2016-06-22 14:34, Panu Matilainen: --- a/lib/librte_port/Makefile +++ b/lib/librte_port/Makefile @@ -82,6 +82,8 @@

[dpdk-dev] [PATCH v3] eal/linuxapp: fix resource leak

This patch fix all cases to do proper handle all munmap if pointer of hugepage is not NULL which prohibits resource leak. Coverity issue: 97920 Fixes: b6a468ad41d5 ("memory: add --socket-mem option") Signed-off-by: Daniel Mrzyglod --- lib/librte_eal/linuxapp/eal/eal_memory.c | 6 -- 1 file

[dpdk-dev] [PATCH] app/test: fix for icc compilation error

Icc complains about variable may be used without setting. Fixes: 97fe6461c7cbfb ("app/test: add SNOW 3G performance test) Signed-off-by: Deepak Kumar Jain --- app/test/test_cryptodev_perf.c | 10 -- 1 file changed, 4 insertions(+), 6 deletions(-) diff --git

  1   2   >