Re: [dpdk-dev] [PATCH] net/failsafe: stat support enhancement

Hi Gaetan, > -Original Message- > From: Gaëtan Rivet [mailto:gaetan.ri...@6wind.com] > Sent: Tuesday, September 5, 2017 7:34 PM > To: Matan Azrad > Cc: dev@dpdk.org > Subject: Re: [PATCH] net/failsafe: stat support enhancement > > On Tue, Sep 05, 2017 at 03:12:55PM +, Matan Azrad wro

Re: [dpdk-dev] long initialization of rte_eal_hugepage_init

Hi Stephen, Do you means “disable zero huge page” would improve the performance? How can the memory be guaranteed to be allocated? Would it introduce funct

Re: [dpdk-dev] [PATCH] eventdev: update doxygen

-Original Message- > Date: Tue, 5 Sep 2017 16:14:48 -0500 > From: Tim McDaniel > To: jerin.ja...@caviumnetworks.com > CC: dev@dpdk.org > Subject: [PATCH] eventdev: update doxygen It is better to update the log message with more appropriate comment. Something like eventdev: clarify us

Re: [dpdk-dev] long initialization of rte_eal_hugepage_init

Do you mean "pagesize" when you say "size" option? I have specified the pagesize as 1G. Also, I already use "--socket-mem " to specify that the application only needs 1G per NUMA node. The problem is that map_all_hugepages() would map all free huge pages, and then select the proper ones. If I h

Re: [dpdk-dev] [PATCH 4/4] ethdev: add helpers to move to the new offloads API

Tuesday, September 5, 2017 6:31 PM, Ananyev, Konstantin: > > > > > > > > > In fact, right now it is possible to query/change these 3 > > > > > > > vlan offload flags on the fly (after dev_start) on port > > > > > > > basis by > > > rte_eth_dev_(get|set)_vlan_offload API. > > > > Regarding this API

Re: [dpdk-dev] long initialization of rte_eal_hugepage_init

> -Original Message- > From: users [mailto:users-boun...@dpdk.org] On Behalf Of ??? > Sent: Wednesday, September 6, 2017 11:25 AM > To: us...@dpdk.org; dev@dpdk.org > Subject: [dpdk-users] long initialization of rte_eal_hugepage_init > > Hi All, > > I observed that rte_eal_hugepage_init

Re: [dpdk-dev] long initialization of rte_eal_hugepage_init

On Wed, Sep 06, 2017 at 03:24:52AM +, 王志克 wrote: > Hi All, > > I observed that rte_eal_hugepage_init() will take quite long time if there > are lots of huge pages. Example I have 500 1G huge pages, and it takes about > 2 minutes. That is too long especially for application restart case. > > I

Re: [dpdk-dev] [PATCH v4 2/3] eal: add u64 bit variant for reciprocal

On Tue, Sep 05, 2017 at 10:29:01AM -0700, Stephen Hemminger wrote: > On Tue, 5 Sep 2017 16:18:51 +0530 > Pavan Nikhilesh wrote: > > > +/** > > + * Unsigned 32-bit divisor structure. > > + */ > > +struct rte_reciprocal_u32 { > > uint32_t m; > > uint8_t sh1, sh2; > > -}; > > +} __rte_cache_

Re: [dpdk-dev] long initialization of rte_eal_hugepage_init

Linux zeros huge pages by default. There was a fix in later releases On Sep 5, 2017 8:24 PM, "王志克" wrote: > Hi All, > > I observed that rte_eal_hugepage_init() will take quite long time if there > are lots of huge pages. Example I have 500 1G huge pages, and it takes > about 2 minutes. That is t

[dpdk-dev] long initialization of rte_eal_hugepage_init

Hi All, I observed that rte_eal_hugepage_init() will take quite long time if there are lots of huge pages. Example I have 500 1G huge pages, and it takes about 2 minutes. That is too long especially for application restart case. If the application only needs limited huge page while the host hav

Re: [dpdk-dev] [PATCH 03/21] vhost: protect virtio_net device struct

> > > This lock has currently two purposes: > > > 1. Prevent referencing freed virtio_dev struct in case of numa_realloc. > > > 2. Protect vring pages against invalidation. > > > > > > For 2., it can be fixed by using the per-vq IOTLB lock (it was not the > > > case in my early prototypes that had

[dpdk-dev] DPDK techboard minutes of August 30

Hi all, Here are the meeting notes for the last DPDK technical board meeting held on 2017-08-30. Attendees: - Bruce Richardson - Declan Doherty - Hemant Agrawal - Jan Blunck - Jerin Jacob - Konstantin Ananyev - Keith Wiles - Olivier Matz - Stephen Hemminger - Thomas Monjalon 1) A "dpdk-draft-ips

Re: [dpdk-dev] [PATCH 03/21] vhost: protect virtio_net device struct

On Tue, Sep 05, 2017 at 01:00:42PM +0200, Maxime Coquelin wrote: > On 09/05/2017 12:07 PM, Tiwei Bie wrote: > > On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote: > > > On 09/05/2017 06:45 AM, Tiwei Bie wrote: > > > > On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote: >

Re: [dpdk-dev] [PATCH v2] librte_mbuf: modify port initialization value

Hi, helin: > > +#define MBUF_INVALID_PORT 0x > Replaced with below, or use UINT16_MAX directly? > #define MBUF_INVALID_PORT UINT16_MAX I prefer #define MBUF_INVALID_PORT UINT16_MAX Thanks Zhiyong

[dpdk-dev] [PATCH v3 6/7] test/member: add functional and perf tests

This patch adds functional and performance tests for membership library. Signed-off-by: Yipeng Wang --- test/test/Makefile | 3 + test/test/test_member.c | 682 +++ test/test/test_member_perf.c | 643 +++

[dpdk-dev] [PATCH v3 5/7] member: enable the library

This patch enables the Membership library. Signed-off-by: Yipeng Wang --- MAINTAINERS| 7 +++ config/common_base | 5 + lib/librte_member/Makefile | 2 ++ mk/rte.app.mk | 2 ++ 4 files changed, 16 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS

[dpdk-dev] [PATCH v3 4/7] member: add AVX for HT mode

For key search, the signatures of all entries are compared against the signature of the key that is being looked up. Since all signatures are contguously put in a bucket, they can be compared with vector instructions (AVX2), achieving higher lookup performance. This patch adds AVX2 implementation

[dpdk-dev] [PATCH v3 3/7] member: implement vBF mode

Bloom Filter (BF) [1] is a well-known space-efficient probabilistic data structure that answers set membership queries. Vector of Bloom Filters (vBF) is an extension to traditional BF that supports multi-set membership testing. Traditional BF will return found or not-found for each key. vBF will al

[dpdk-dev] [PATCH v3 2/7] member: implement HT mode

One of the set-summray structure is hash-table based set-summary (HTSS). One example is cuckoo filter [1]. Comparing to a traditional hash table, HTSS has a much more compact structure. For each element, only one signature and its corresponding set ID is stored. No key comparison is required duri

[dpdk-dev] [PATCH v3 1/7] member: implement main API

Membership library is an extension and generalization of a traditional filter (for example Bloom Filter) structure. In general, the Membership library is a data structure that provides a "set-summary" and responds to set-membership queries of whether a certain element belongs to a set(s). A members

[dpdk-dev] [PATCH v3 0/7] Add Membership Library

DPDK Membership Library provides an API that can be used by many DPDK applications to conduct one or more set-membership tests (we mention some possible use cases below, but interested readers can refer to [1] for a wider survey of use cases). The basic functionalities of the Membership Library in

Re: [dpdk-dev] [PATCH 1/2] net/i40e: queue region set and flush

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wei Zhao > Sent: Wednesday, August 23, 2017 8:26 PM > To: dev@dpdk.org > Cc: Zhao1, Wei > Subject: [dpdk-dev] [PATCH 1/2] net/i40e: queue region set and flush > > This feature enable queue regions configuration

Re: [dpdk-dev] [PATCH v2 1/3] timer: add per-installer pending lists for each lcore

Hi all, Another approach that I'd like to put out for consideration is as follows: Let's say we introduce one flag per lcore - multi_pendlists. This flag indicates whether that lcore supports multiple pending lists (one per source lcore) or not, and by default it's set to false. At rte_timer_

Re: [dpdk-dev] [PATCH v7 0/6] Reproducible build

On Tue, 2017-09-05 at 14:00 -0700, Stephen Hemminger wrote: > On Tue,  5 Sep 2017 21:51:53 +0100 > luca.bocca...@gmail.com wrote: > > > From: Luca Boccassi > > > > In the past couple of years a concerted effort among almost all > > Linux > > distros has been striving toward achieving reproducibl

[dpdk-dev] [PATCH] eventdev: update doxygen

Update doxygen to make it clear that RTE_EVENT_OP_FORWARD and RTE_EVENT_OP_RELEASE may only be enqueued to the same port that the original event was dequeued from. Signed-off-by: Tim McDaniel --- lib/librte_eventdev/rte_eventdev.h | 14 +- 1 file changed, 13 insertions(+), 1 deletion

Re: [dpdk-dev] [PATCH v7 0/6] Reproducible build

On Tue, 5 Sep 2017 21:51:53 +0100 luca.bocca...@gmail.com wrote: > From: Luca Boccassi > > In the past couple of years a concerted effort among almost all Linux > distros has been striving toward achieving reproducible builds. [1] > This involves changes to the toolchain, new tools and CI syste

Re: [dpdk-dev] [PATCH v7 0/6] Reproducible build

On Tue, 2017-09-05 at 21:51 +0100, luca.bocca...@gmail.com wrote: > From: Luca Boccassi > > In the past couple of years a concerted effort among almost all Linux > distros has been striving toward achieving reproducible builds. [1] > This involves changes to the toolchain, new tools and CI system

[dpdk-dev] [PATCH v7 4/6] mk: sort source files before passing them to the compiler

From: Luca Boccassi In order to achieve reproducible builds, always use the same order when listing files for compilation. Signed-off-by: Luca Boccassi --- drivers/net/cxgbe/Makefile| 2 +- drivers/net/e1000/Makefile| 2 +- drivers/net/fm10k/Makefile| 2 +- drivers/net/i40e/Makefil

[dpdk-dev] [PATCH v7 5/6] mk: sort object files when building deps lists

From: Luca Boccassi In order to achieve reproducible builds, always use the same order when listing object files to build dependencies lists. Signed-off-by: Luca Boccassi --- mk/rte.app.mk | 4 ++-- mk/rte.hostapp.mk | 4 ++-- mk/rte.shared.mk | 4 ++-- 3 files changed, 6 insertions(+), 6

[dpdk-dev] [PATCH v7 6/6] mk: install symlinks before build step

From: Luca Boccassi A race condition can happen during parallel builds, where a header might be installed in RTE_OUT/include before CFLAGS is recursively expanded. This causes GCC to sometimes pick the header path as SRCDIR/... and sometimes as RTE_OUT/include/... making the build unreproducible,

[dpdk-dev] [PATCH v7 3/6] mk: sort headers before wildcard inclusion

From: Luca Boccassi In order to achieve fully reproducible builds, always use the same inclusion order for headers in the Makefiles. Signed-off-by: Luca Boccassi --- examples/ip_pipeline/Makefile | 2 +- examples/multi_process/client_server_mp/mp_server/Makefile |

[dpdk-dev] [PATCH v7 1/6] mk: sort list of shared objects in linker script

From: Luca Boccassi The output of wildcard might not be stable and depend on the filesystem and other factors. This means the content libdpdk.so linker script might change between builds from the same sources. Run the list through sort to ensure reproducibility. Signed-off-by: Luca Boccassi ---

[dpdk-dev] [PATCH v7 2/6] mk: sort list of files in examples.dox

From: Luca Boccassi The result of find might not be stable depending on external conditions. Pipe it through LC_ALL=C sort to ensure reproducible results when generating examples.dox. Signed-off-by: Luca Boccassi --- mk/rte.sdkdoc.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff

[dpdk-dev] [PATCH v7 0/6] Reproducible build

From: Luca Boccassi In the past couple of years a concerted effort among almost all Linux distros has been striving toward achieving reproducible builds. [1] This involves changes to the toolchain, new tools and CI systems. [2] v1 fixed the documentation, examples and linker script generation. v

Re: [dpdk-dev] [PATCH 06/26] net/octeontx/base: probe PKI and PKO PCIe VF devices

On 8/31/2017 3:54 PM, Jerin Jacob wrote: > An octeontx ethdev device consists of multiple PKO VF devices and an PKI > VF device. On Octeontx HW, each Rx queues are enumerated as SSOVF device > which is exposed as event_octeontx device, Tx queues are enumerated as > PKOVF device, and ingress packet

Re: [dpdk-dev] [PATCH 00/26] DPDK PMD for OCTEONTX NW device

On 8/31/2017 3:54 PM, Jerin Jacob wrote: > This patch set provides the initial version of DPDK PMD for the > integrated NIC device found in Cavium OCTEONTX SoC(CN83xx) family. > > Introduction to OCTEONTX ARM processors can be found > here: http://www.cavium.com/OCTEON-TX_ARM_Processors.html > >

[dpdk-dev] Request to create the dpdk-next-packet-framework git tree

Dear DPDK Tech Board, Please approve the request to create the dpdk-next-packet-framework git tree. Please add this topic to the next Tech Board meeting agenda. Thanks and regards, Cristian

Re: [dpdk-dev] [PATCH v4 2/3] eal: add u64 bit variant for reciprocal

On Tue, 5 Sep 2017 16:18:51 +0530 Pavan Nikhilesh wrote: > +/** > + * Unsigned 32-bit divisor structure. > + */ > +struct rte_reciprocal_u32 { > uint32_t m; > uint8_t sh1, sh2; > -}; > +} __rte_cache_aligned; > + > +/** > + * Unsigned 64-bit divisor structure. > + */ > +struct rte_re

Re: [dpdk-dev] [PATCH] net/failsafe: stat support enhancement

On Tue, Sep 05, 2017 at 03:12:55PM +, Matan Azrad wrote: > Hi Gaetan, > > > -Original Message- > > From: Gaëtan Rivet [mailto:gaetan.ri...@6wind.com] > > Sent: Tuesday, September 5, 2017 4:23 PM > > To: Matan Azrad > > Cc: dev@dpdk.org > > Subject: Re: [PATCH] net/failsafe: stat suppo

Re: [dpdk-dev] [PATCH 1/2] service: fix service lcore stop function

On Tue, Sep 05, 2017 at 02:34:44PM +, Van Haaren, Harry wrote: > > From: Guduri Prathyusha [mailto:gprathyu...@caviumnetworks.com] > > Sent: Tuesday, September 5, 2017 3:11 PM > > To: Van Haaren, Harry > > Cc: dev@dpdk.org; Guduri Prathyusha > > Subject: [dpdk-dev] [PATCH 1/2] service: fix se

Re: [dpdk-dev] [PATCH] net/mlx5: fix tunnel offload detection

On 9/4/2017 4:07 PM, Nélio Laranjeiro wrote: > On Mon, Sep 04, 2017 at 07:43:51PM +0800, Xueming Li wrote: >> PMD driver got random tunnel_en value on ConnextX-4LX NIC, depends on >> compile optimization level. The variable was not initialized and >> detection logic was absent. Fixes: f5fde5205101

Re: [dpdk-dev] [PATCH] net/i40e: remove unused and incorrect definition

On 9/4/2017 10:14 AM, Bruce Richardson wrote: > On Mon, Sep 04, 2017 at 02:37:38AM +0800, Jingjing Wu wrote: >> Signed-off-by: Jingjing Wu > Acked-by: Bruce Richardson Applied to dpdk-next-net/master, thanks.

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/failsafe: fix adding MAC error report miss

On 9/4/2017 9:47 AM, Gaëtan Rivet wrote: > On Sun, Sep 03, 2017 at 06:26:45PM +0300, Matan Azrad wrote: >> The corrupted code don't reply error in case of MAC >> address adding failure while failsafe PMD was trying >> to apply configuration to the sub device. >> >> Hence, the application may get un

Re: [dpdk-dev] [PATCH 4/4] ethdev: add helpers to move to the new offloads API

> > > > > > > In fact, right now it is possible to query/change these 3 vlan > > > > > > offload flags on the fly (after dev_start) on port basis by > > rte_eth_dev_(get|set)_vlan_offload API. > > Regarding this API from ethdev. > > So this seems like a hack on ethdev. Currently there are 2

Re: [dpdk-dev] [PATCH 08/21] vhost: iotlb: add pending miss request list and helpers

On 09/05/2017 09:11 AM, Tiwei Bie wrote: On Thu, Aug 31, 2017 at 11:50:10AM +0200, Maxime Coquelin wrote: In order to be able to handle other ports or queues while waiting for an IOTLB miss reply, a pending list is created so that waiter can return and restart later on with sending again a mis

Re: [dpdk-dev] [PATCH 07/21] vhost: add iotlb helper functions

On 09/05/2017 08:02 AM, Tiwei Bie wrote: On Thu, Aug 31, 2017 at 11:50:09AM +0200, Maxime Coquelin wrote: [...] + +#define IOTLB_CACHE_SIZE 1024 + +static void vhost_user_iotlb_cache_remove_all(struct vhost_virtqueue *vq) +{ + struct vhost_iotlb_entry *node, *temp_node; + + rte_rwl

Re: [dpdk-dev] [PATCH] net/failsafe: stat support enhancement

Hi Gaetan, > -Original Message- > From: Gaëtan Rivet [mailto:gaetan.ri...@6wind.com] > Sent: Tuesday, September 5, 2017 4:23 PM > To: Matan Azrad > Cc: dev@dpdk.org > Subject: Re: [PATCH] net/failsafe: stat support enhancement > > Hi Matan, > > On Tue, Sep 05, 2017 at 12:56:34PM +0300,

Re: [dpdk-dev] [PATCH v3 1/4] net/softnic: add softnic PMD

On 8/11/2017 1:49 PM, Jasvinder Singh wrote: > Add SoftNIC PMD to provide SW fall-back for ethdev APIs. > > Signed-off-by: Cristian Dumitrescu > Signed-off-by: Jasvinder Singh > --- > v3 changes: > - rebase to dpdk17.08 release > > v2 changes: > - fix build errors > - rebased to TM APIs v6 plus

Re: [dpdk-dev] [PATCH v2] buildtools: zero elf info variable in pmdinfogen

On Tue, Sep 05, 2017 at 02:27:58PM +0100, Harry van Haaren wrote: > This commit zeros out the elf_info struct at startup of the > pmdinfogen code. If it is not zeroed, later in the code gcc > produces "may be unused" prints. Clang does not report any > issue. > > This issue is only observed when c

Re: [dpdk-dev] [PATCH 1/2] service: fix service lcore stop function

> From: Guduri Prathyusha [mailto:gprathyu...@caviumnetworks.com] > Sent: Tuesday, September 5, 2017 3:11 PM > To: Van Haaren, Harry > Cc: dev@dpdk.org; Guduri Prathyusha > Subject: [dpdk-dev] [PATCH 1/2] service: fix service lcore stop function > > lcore_states store the state of the lcore. Fix

[dpdk-dev] [PATCH 2/2] service: fix service lcore start stop unit test

Unit test case service_lcore_start_stop fails since the service core was stopped without stopping the service. This commit fixes the test by adding negative and positive cases of stopping the service lcore before and after stopping the service respectively. Fixes: f038a81e1c56 ("service: add unit

[dpdk-dev] [PATCH 1/2] service: fix service lcore stop function

lcore_states store the state of the lcore. Fixing the invalid dereference of lcore_states with service number Fixes: 21698354c832 ("service: introduce service cores concept") Signed-off-by: Guduri Prathyusha --- lib/librte_eal/common/rte_service.c | 2 +- 1 file changed, 1 insertion(+), 1 delet

Re: [dpdk-dev] [PATCH 4/4] ethdev: add helpers to move to the new offloads API

05/09/2017 12:51, Shahaf Shuler: > So looks like we all agree PMDs should report as part of the > rte_eth_dev_info_get which offloads are per port and which are per queue. > > Regarding the offloads configuration by application I see 2 options: > 1. have an API to set offloads per port as part of

Re: [dpdk-dev] [PATCH v3] net/mlx5: support upstream rdma-core

On Tue, Sep 05, 2017 at 01:19:08PM +, Shachar Beiser wrote: > This removes the dependency on specific Mellanox OFED libraries by > using the upstream rdma-core and linux upstream community code. > > --- > a. Compile with rdma-core commit f11292efd541 ("Merge pull request #202") > b. Tested wit

Re: [dpdk-dev] [PATCH v2 1/3] net/mlx5: replace network to host macros

On Tue, Sep 05, 2017 at 01:04:36PM +, Shachar Beiser wrote: > Signed-off-by: Shachar Beiser Acked-by: Nelio Laranjeiro Thanks, -- Nélio Laranjeiro 6WIND

Re: [dpdk-dev] [PATCH v2 2/3] net/mlx5: fix TSO MLNX OFED 3.3 verification

On Tue, Sep 05, 2017 at 01:04:37PM +, Shachar Beiser wrote: > Fixes: 3cf87e68d97b ("net/mlx5: remove old MLNX OFED 3.3 verification") > Cc: sta...@dpdk.org > > Signed-off-by: Shachar Beiser > --- > drivers/net/mlx5/mlx5_prm.h | 3 --- > 1 file changed, 3 deletions(-) > > diff --git a/driver

Re: [dpdk-dev] [PATCH v3] net/mlx5: support device removal event

Hi Adrien > -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > Sent: Tuesday, September 5, 2017 3:02 PM > To: Matan Azrad > Cc: Nélio Laranjeiro ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] net/mlx5: support device removal event > > Hi Matan, > > On

Re: [dpdk-dev] [PATCH v1 3/3] net/mlx4: merge interrupt collector function

On Tue, Sep 05, 2017 at 02:56:39PM +0200, Adrien Mazarguil wrote: > Since interrupt handler is the only function relying on it, merging them > simplifies the code as there is no need for an API to return collected > events. > > Signed-off-by: Adrien Mazarguil > --- > drivers/net/mlx4/mlx4_intr.c

[dpdk-dev] [PATCH v2] buildtools: zero elf info variable in pmdinfogen

This commit zeros out the elf_info struct at startup of the pmdinfogen code. If it is not zeroed, later in the code gcc produces "may be unused" prints. Clang does not report any issue. This issue is only observed when compiling pmdinfogen as an optimized build, hence this warning is not disabled

Re: [dpdk-dev] [PATCH v1 0/3] net/mlx4: additional interrupt handling fixes

On Tue, Sep 05, 2017 at 02:56:36PM +0200, Adrien Mazarguil wrote: > While the previous interrupt rework improved the situation, it failed to > address one last issue pointed out by Matan: RMV/LSC events may be missed > and not reported to the application. > > Adrien Mazarguil (3): > net/mlx4: fi

Re: [dpdk-dev] [PATCH v2 3/3] net/mlx5: fix interrupt enable return value

Hi Shachar, On Tue, Sep 05, 2017 at 01:04:38PM +, Shachar Beiser wrote: > return value is sometimes returned uninitialized > > Fixes: e1016cb73383 ("net/mlx5: fix Rx interrupts management") > Fixes: b18042fb8f49 ("net/mlx5: fix misplaced Rx interrupts functions") > > Cc: adrien.mazarg...@6wi

Re: [dpdk-dev] [PATCH] net/failsafe: stat support enhancement

Hi Matan, On Tue, Sep 05, 2017 at 12:56:34PM +0300, Matan Azrad wrote: > The previous stats code returned only the current TX sub > device stats. > > This enhancement extends it to return the sum of all sub > devices stats with history of removed sub-devices. > > Dedicated stats accumulator save

[dpdk-dev] [PATCH v3] net/mlx5: support upstream rdma-core

This removes the dependency on specific Mellanox OFED libraries by using the upstream rdma-core and linux upstream community code. --- a. Compile with rdma-core commit f11292efd541 ("Merge pull request #202") b. Tested with linux kernel 4.13-rc4 c. For performance testing recommended to wait till

Re: [dpdk-dev] [PATCH] buildtools: zero elf info variable in pmdinfogen

On Tue, Sep 05, 2017 at 02:03:33PM +0100, Harry van Haaren wrote: > This commit zeros out the elf_info struct at startup of the > pmdinfogen code. If it is not zeroed, later in the code gcc > produces "may be unused" prints. Clang does not report any > issue. > > This commit enables a simplificati

[dpdk-dev] [PATCH v2 3/3] net/mlx5: fix interrupt enable return value

return value is sometimes returned uninitialized Fixes: e1016cb73383 ("net/mlx5: fix Rx interrupts management") Fixes: b18042fb8f49 ("net/mlx5: fix misplaced Rx interrupts functions") Cc: adrien.mazarg...@6wind.com Cc: sta...@dpdk.org Signed-off-by: Shachar Beiser --- drivers/net/mlx5/mlx5_rxq.

[dpdk-dev] [PATCH v2 2/3] net/mlx5: fix TSO MLNX OFED 3.3 verification

Fixes: 3cf87e68d97b ("net/mlx5: remove old MLNX OFED 3.3 verification") Cc: sta...@dpdk.org Signed-off-by: Shachar Beiser --- drivers/net/mlx5/mlx5_prm.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h index 608072f..8b82b5e 100644

[dpdk-dev] [PATCH v2 1/3] net/mlx5: replace network to host macros

Signed-off-by: Shachar Beiser --- drivers/net/mlx5/mlx5_mac.c | 8 ++- drivers/net/mlx5/mlx5_mr.c | 2 +- drivers/net/mlx5/mlx5_rxmode.c | 8 ++- drivers/net/mlx5/mlx5_rxq.c | 9 +-- drivers/net/mlx5/mlx5_rxtx.c | 131 +++--

[dpdk-dev] [PATCH] buildtools: zero elf info variable in pmdinfogen

This commit zeros out the elf_info struct at startup of the pmdinfogen code. If it is not zeroed, later in the code gcc produces "may be unused" prints. Clang does not report any issue. This commit enables a simplification in the meson build system, removing the requirement for "-Wno-maybe-uniniti

[dpdk-dev] [PATCH v1 1/3] net/mlx4: fix unhandled event debug message

When LSC or RMV events are received by the PMD but are not requested by the application, a misleading debugging message implying the PMD does not support them is shown. Fixes: 6dd7b7056d7f ("net/mlx4: support device removal event") Cc: Gaetan Rivet Cc: sta...@dpdk.org Signed-off-by: Adrien Mazar

[dpdk-dev] [PATCH v1 3/3] net/mlx4: merge interrupt collector function

Since interrupt handler is the only function relying on it, merging them simplifies the code as there is no need for an API to return collected events. Signed-off-by: Adrien Mazarguil --- drivers/net/mlx4/mlx4_intr.c | 94 +-- 1 file changed, 30 insertions(+),

[dpdk-dev] [PATCH v1 0/3] net/mlx4: additional interrupt handling fixes

While the previous interrupt rework improved the situation, it failed to address one last issue pointed out by Matan: RMV/LSC events may be missed and not reported to the application. Adrien Mazarguil (3): net/mlx4: fix unhandled event debug message net/mlx4: fix rescheduled link status check

[dpdk-dev] [PATCH v1 2/3] net/mlx4: fix rescheduled link status check

Link status is sometimes inconsistent during a LSC event. When it occurs, the PMD refrains from immediately notifying the application; instead, an alarm is scheduled to check link status later and notify the application once it has settled. The problem is that subsequent link status checks are onl

Re: [dpdk-dev] [PATCH v2 0/8] Remove temporary digest allocation

Hi Pablo, Thanks, looks great! Regards, Fan > -Original Message- > From: De Lara Guarch, Pablo > Sent: Tuesday, September 5, 2017 3:20 AM > To: Doherty, Declan ; Zhang, Roy Fan > ; jerin.ja...@caviumnetworks.com > Cc: dev@dpdk.org; De Lara Guarch, Pablo > Subject: [PATCH v2 0/8] Remove

Re: [dpdk-dev] [PATCH v7 0/9] Infrastructure to detect iova mapping on the bus

Please note that this series break the DPAA2 BUS. Following patch series (Shreyansh) is required to fix DPAA2 bus working with this patch series: http://dpdk.org/dev/patchwork/patch/27950/ On 9/5/2017 5:58 PM, Hemant Agrawal wrote: Tested-by: Hemant Agrawal On 8/31/2017 8:56 AM, Santosh Sh

Re: [dpdk-dev] [PATCH v2] librte_mbuf: modify port initialization value

> -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Tuesday, September 5, 2017 3:28 PM > To: Yang, Zhiyong > Cc: dev@dpdk.org; Yigit, Ferruh ; > step...@networkplumber.org > Subject: Re: [PATCH v2] librte_mbuf: modify port initialization value > > 05/09/2017

Re: [dpdk-dev] [PATCH v7 0/9] Infrastructure to detect iova mapping on the bus

Tested-by: Hemant Agrawal On 8/31/2017 8:56 AM, Santosh Shukla wrote: v7: Includes no major change, minor change detailing: - patch sqashing (Aaron suggestion) - added run_once for device_parse() and bus_scan() in eal init (Aaron suggestion) - Moved rte_eal_device_parse() up in eal init

[dpdk-dev] [PATCH v7 2/6] igb_uio: fix irq disable on recent kernels

igb_uio already allocates irqs using pci_alloc_irq_vectors on recent kernels >= 4.8. The interrupt disable code was not using the corresponding pci_free_irq_vectors, but the also deprecated pci_disable_msix, before this fix. Fixes: 99bb58f3adc7 ("igb_uio: switch to new irq function for MSI-X") Cc:

[dpdk-dev] [PATCH v7 5/6] igb_uio: use kernel functions for masking MSI-X

This patch removes the custom MSI-X mask/unmask code and uses already existing kernel functions. Signed-off-by: Markus Theil --- lib/librte_eal/linuxapp/igb_uio/compat.h | 26 +--- lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 51 --- 2 files changed, 28 in

[dpdk-dev] [PATCH v7 6/6] igb_uio: MSI IRQ mode

This patch adds MSI IRQ mode in a way, that should also work on older kernel versions. The base for my patch was an attempt to do this in cf705bc36c which was later reverted in d8ee82745a. Compilation was tested on Linux 3.2, 4.10 and 4.12. Signed-off-by: Markus Theil --- lib/librte_eal/linuxapp

[dpdk-dev] [PATCH v7 1/6] igb_uio: refactor irq enable/disable into own functions

Interrupt setup code in igb_uio has to deal with multiple types of interrupts and kernel versions. This patch moves the setup and teardown code into own functions, to make it more readable. Signed-off-by: Markus Theil --- lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 112 +-

[dpdk-dev] [PATCH v7 4/6] igb_uio: release in exact reverse order

For better readability throughout the module, the destruction order is changed to the exact inverse construction order. Signed-off-by: Markus Theil --- lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/lib/librte_eal/linuxapp/igb

[dpdk-dev] [PATCH v7 3/6] igb_uio: fix MSI-X IRQ assignment with new IRQ function

The patch which introduced the usage of pci_alloc_irq_vectors came after the patch which switched to non-threaded ISR (f0d1896fa1), but did not use non-threaded ISR, if pci_alloc_irq_vectors is used. Fixes: 99bb58f3adc7 ("igb_uio: switch to new irq function for MSI-X") Cc: nicolas.dich...@6wind.co

Re: [dpdk-dev] [PATCH v3] net/mlx5: support device removal event

Hi Matan, On Tue, Sep 05, 2017 at 10:38:21AM +, Matan Azrad wrote: > Hi Adrien > > > -Original Message- > > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > > Sent: Tuesday, September 5, 2017 12:28 PM > > To: Matan Azrad > > Cc: Nélio Laranjeiro ; dev@dpdk.org > > Subject

[dpdk-dev] [PATCH v5 3/3] test: add tests for reciprocal based division

From: Pavan Bhagavatula This commit provides a set of tests for verifying the correctness and performance of both unsigned 32 and 64bit reciprocal based division. Signed-off-by: Pavan Nikhilesh --- test/test/Makefile| 2 + test/test/test_reciprocal_division.c | 1

[dpdk-dev] [PATCH v5 2/3] eal: add u64 bit variant for reciprocal

From: Pavan Bhagavatula Currently, rte_reciprocal only supports unsigned 32bit divisors. This commit adds support for unsigned 64bit divisors. Rename unsigned 32bit specific functions appropriately and update librte_sched accordingly. Signed-off-by: Pavan Nikhilesh --- lib/librte_eal/bsdapp/e

[dpdk-dev] [PATCH v5 1/3] eal: introduce integer divide through reciprocal

From: Pavan Bhagavatula In some use cases of integer division, denominator remains constant and numerator varies. It is possible to optimize division for such specific scenarios. The librte_sched uses rte_reciprocal to optimize division so, moving it to eal/common would allow other libraries and

Re: [dpdk-dev] [PATCH] examples/l2fwd-crypto: fix uninitialized errno value

> -Original Message- > From: Hemant Agrawal [mailto:hemant.agra...@nxp.com] > Sent: Wednesday, August 23, 2017 1:24 PM > To: dev@dpdk.org > Cc: Doherty, Declan ; De Lara Guarch, Pablo > ; akhil.go...@nxp.com > Subject: [PATCH] examples/l2fwd-crypto: fix uninitialized errno value > > errn

Re: [dpdk-dev] [PATCH v2] app/crypto-perf: fix uninitialized errno value

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Hemant Agrawal > Sent: Tuesday, September 5, 2017 7:17 AM > To: dev@dpdk.org > Cc: Doherty, Declan ; De Lara Guarch, Pablo > ; akhil.go...@nxp.com > Subject: [dpdk-dev] [PATCH v2] app/crypto-perf: fix uninitialize

Re: [dpdk-dev] [PATCH 03/21] vhost: protect virtio_net device struct

On 09/05/2017 12:07 PM, Tiwei Bie wrote: On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote: On 09/05/2017 06:45 AM, Tiwei Bie wrote: On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote: virtio_net device might be accessed while being reallocated in case of NUMA awar

Re: [dpdk-dev] [PATCH 4/4] ethdev: add helpers to move to the new offloads API

Tuesday, September 5, 2017 11:10 AM, Ananyev, Konstantin: > > > > > In fact, right now it is possible to query/change these 3 vlan > > > > > offload flags on the fly (after dev_start) on port basis by > rte_eth_dev_(get|set)_vlan_offload API. Regarding this API from ethdev. So this seems like a

[dpdk-dev] [PATCH v4 3/3] test: add tests for reciprocal based division

From: Pavan Bhagavatula This commit provides a set of tests for verifying the correctness and performance of both unsigned 32 and 64bit reciprocal based division. Signed-off-by: Pavan Nikhilesh --- test/test/Makefile| 2 + test/test/test_reciprocal_division.c | 1

[dpdk-dev] [PATCH v4 2/3] eal: add u64 bit variant for reciprocal

From: Pavan Bhagavatula Currently, rte_reciprocal only supports unsigned 32bit divisors. This commit adds support for unsigned 64bit divisors. Rename unsigned 32bit specific functions appropriately and update librte_sched accordingly. Signed-off-by: Pavan Nikhilesh --- lib/librte_eal/bsdapp/e

[dpdk-dev] [PATCH v4 1/3] eal: introduce integer divide through reciprocal

From: Pavan Bhagavatula In some use cases of integer division, denominator remains constant and numerator varies. It is possible to optimize division for such specific scenarios. The librte_sched uses rte_reciprocal to optimize division so, moving it to eal/common would allow other libraries and

Re: [dpdk-dev] [PATCH v3] net/mlx5: support device removal event

Hi Adrien > -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > Sent: Tuesday, September 5, 2017 12:28 PM > To: Matan Azrad > Cc: Nélio Laranjeiro ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] net/mlx5: support device removal event > > Hi Matan, > > O

[dpdk-dev] [PATCH v2 5/5] doc: remove dpdk iova aware notice

Removed dpdk iova aware ABI deprecation notice, and updated ABI change details in release_17.11.rst. Signed-off-by: Santosh Shukla --- doc/guides/rel_notes/deprecation.rst | 7 --- doc/guides/rel_notes/release_17_11.rst | 27 +++ 2 files changed, 27 insertions(+),

[dpdk-dev] [PATCH v2 3/5] eal/memory: rename memseg member phys to iova addr

Renaming rte_memseg {.phys_addr} to {.iova_addr} Signed-off-by: Santosh Shukla --- v1 --> v2: - includes freebsdp v1 build fixes. lib/librte_eal/bsdapp/eal/eal_memory.c | 4 ++-- lib/librte_eal/common/eal_common_memory.c | 2 +- lib/librte_eal/common/include/rte_memory.h | 4 ++-- lib/libr

[dpdk-dev] [PATCH v2 4/5] eal/memory: rename memory api to iova types

Renamed memory translational api to _iova types. The following api renamed from: rte_mempool_populate_phys() rte_mempool_populate_phys_tab() rte_eal_using_phys_addrs() rte_mem_virt2phy() rte_dump_physmem_layout() rte_eal_get_physmem_layout() rte_eal_get_physmem_size() rte_malloc_virt2phy() rte_mem

[dpdk-dev] [PATCH v2 2/5] eal/memory: rename buf_physaddr to buf_iovaaddr

Signed-off-by: Santosh Shukla --- v1 notes: Since crux of change is at eal/memory area so using that as title. doc/guides/prog_guide/img/mbuf1.svg| 2 +- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h| 2 +- drivers/net/ark/ark_ethdev_rx.c

[dpdk-dev] [PATCH v2 1/5] eal: rename phys_addr_t to iova_addr_t

Renamed data type from phys_addr_t to iova_addr_t. Signed-off-by: Santosh Shukla --- v1 --> v2: - clang build fix for v1 for linuxapp. v1 note: - As changes percolate to all possible dpdk subsystem.. so its difficult to tag subject with one common title, but since, core of changeset is at ea

[dpdk-dev] [PATCH v2 0/5] make dpdk iova aware

v2: Include build fixes reported in patchworks. Changeset based on deprecation notice[1], planned for v17.11 release. Patches are based commit: (c42021fe56 : ethdev: rename map file to match library name) Summary: Renaming memory address translation api/ datatypes and memory struct members to io

  1   2   >