[dpdk-dev] [PATCH 5/6] rwlock not released when the key exists

Consisntly use a single exit path in the code, have the various return values set 'ret' then use the single exit path. Signed-off-by: mstolarchuk --- lib/librte_hash/rte_cuckoo_hash.c | 22 +++--- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/lib/librte_hash/rte

[dpdk-dev] [PATCH 6/6] static variable whouldn't be used to compute recursion level

the 'static nr_pushes' variable creates a single instance of the value across multiple invocations of the same procedure. In the case of a numa machine, this variable is then associated with one specifci numa node, degrading performance. but the more troublesome issue iw when two unrelated threa

[dpdk-dev] [PATCH 2/7] rwlock not released when the key exists

Consisntly use a single exit path in the code, have th various return values set then call the exit path. --- lib/librte_hash/rte_cuckoo_hash.c | 22 +++--- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuc

[dpdk-dev] [PATCH 1/7] Use an accessor for rte_hash_key

Improves consistency, allows identifcation of use-sites Signed-off-by: mstolarchuk --- lib/librte_hash/rte_cuckoo_hash.c | 64 +++ 1 file changed, 31 insertions(+), 33 deletions(-) diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_h

Re: [dpdk-dev] DPDK qos support for 40G port

> -Original Message- > From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Friday, August 18, 2017 6:22 PM > To: Dumitrescu, Cristian > Cc: Kevin Yan ; dev@dpdk.org > Subject: Re: [dpdk-dev] DPDK qos support for 40G port > > On Fri, 18 Aug 2017 11:24:12 + > "Dumitres

Re: [dpdk-dev] [dpdk-stable] 16.11.3 (LTS) patches review and test

On 08/18/2017 11:45 AM, Yuanhan Liu wrote: > Hi all, > > Here is a list of patches targeted for LTS release 16.11.3. Please > help review and test. The planned date for the final release is 30th, > Aug. Before that, please let me know if anyone has objections with > these patches being applied. >

Re: [dpdk-dev] DPDK qos support for 40G port

On Fri, 18 Aug 2017 11:24:12 + "Dumitrescu, Cristian" wrote: > Hi Kevin, > > > Hi Cristian, > > Sorry to bother again, could you give suggestions/hints of code change to > > support single 40G port? Because in our setup, we will use single 40G port > > (Intel XL710) as the network interfac

Re: [dpdk-dev] [PATCH v3 1/2] net/i40e: new API to add VF MAC address from PF

On 8/18/2017 1:32 AM, Stephen Hemminger wrote: > On Fri, 18 Aug 2017 02:33:42 +0800 > Wenzhuo Lu wrote: > >> Currently, rte_eth_dev_mac_addr_add is used by a >> testpmd CLI to add a MAC address for VF. But the >> parameter 'pool' of this API means the VMDq pool, >> not VF. >> So, it's wrong to us

Re: [dpdk-dev] [PATCH] nfp: handle packets with length 0 as usual ones

On Fri, Aug 18, 2017 at 4:10 PM, Ferruh Yigit wrote: > On 8/11/2017 11:05 AM, Alejandro Lucero wrote: > > A DPDK app could, whatever the reason, send packets with size 0. > > The PMD is not sending those packets, which does make sense, > > but the problem is the mbuf is not released either. That

Re: [dpdk-dev] [dpdk-stable] [PATCH v3] net/i40e: fix PF notify issue when VF is not up

On 8/15/2017 10:06 AM, Xing, Beilei wrote: > > >> -Original Message- >> From: Li, Xiaoyun >> Sent: Tuesday, August 15, 2017 3:40 PM >> To: Xing, Beilei >> Cc: Wu, Jingjing ; dev@dpdk.org; Li, Xiaoyun >> ; sta...@dpdk.org >> Subject: [PATCH v3] net/i40e: fix PF notify issue when VF is not

Re: [dpdk-dev] [PATCH] app/testpmd: wrong usage of fseek & ftell to determine filesize

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Daniel Mrzyglod > Sent: Friday, August 18, 2017 10:18 PM > To: Xing, Beilei > Cc: dev@dpdk.org; Mrzyglod, DanielX T > Subject: [dpdk-dev] [PATCH] app/testpmd: wrong usage of fseek & ftell to > determine filesize

Re: [dpdk-dev] [PATCH] kni: fix build on SLE12 SP3

Hi Nirmoy, On 8/15/2017 10:58 AM, Nirmoy Das wrote: > compilation error: > build/lib/librte_eal/linuxapp/kni/kni_net.c:215:5: error: ‘struct net_device’ > has no member named ‘trans_start’ Commit log is too long, can you please break this line. > dev->trans_start = jiffies; > > Signed-off-by

Re: [dpdk-dev] [PATCH] test/crypto: rename GCM test code

> -Original Message- > From: De Lara Guarch, Pablo > Sent: Friday, August 18, 2017 9:07 AM > To: Doherty, Declan > Cc: dev@dpdk.org; De Lara Guarch, Pablo > > Subject: [PATCH] test/crypto: rename GCM test code > > Before adding AES-CCM tests, some test code used for AES-GCM can be > re

[dpdk-dev] [PATCH 4/4] crypto/openssl: add AES-CCM support

Add support to AES-CCM, for 128, 192 and 256-bit keys. Signed-off-by: Pablo de Lara --- doc/guides/cryptodevs/features/default.ini | 3 + doc/guides/cryptodevs/features/openssl.ini | 3 + doc/guides/cryptodevs/openssl.rst| 1 + doc/guides/rel_notes/release_17_11.rst |

[dpdk-dev] [PATCH 3/4] test/crypto: rename GCM test code

Before adding AES-CCM tests, some test code used for AES-GCM can be renamed, so it can be reused for AES-CCM, as both need similar parameters. Signed-off-by: Pablo de Lara --- test/test/test_cryptodev.c | 245 +++-- ...ectors.h => test_cryptodev_aead_test_

[dpdk-dev] [PATCH 2/4] crypto/openssl: init GCM key at session creation

When creating a session for AES-GCM, since the key is going to be constant, the OpenSSL context can initialize the key at that moment, leaving the setting of the IV for the operation handling. Signed-off-by: Pablo de Lara --- drivers/crypto/openssl/rte_openssl_pmd.c | 208 +++

[dpdk-dev] [PATCH] test/crypto: rename GCM test code

Before adding AES-CCM tests, some test code used for AES-GCM can be renamed, so it can be reused for AES-CCM, as both need similar parameters. Signed-off-by: Pablo de Lara --- test/test/test_cryptodev.c | 245 +++-- ...ectors.h => test_cryptodev_aead_test_

[dpdk-dev] [PATCH 1/4] crypto/openssl: fix AEAD parameters

When using AES-GCM with OpenSSL, cipher direction and authentication operation were being set incorrectly, as the PMD was looking at the cipher and authentication transform, instead of the new AEAD. Fixes: b79e4c00af0e ("cryptodev: use AES-GCM/CCM as AEAD algorithms") Cc: sta...@dpdk.org Signed-o

[dpdk-dev] [PATCH 0/4] Add support for AES-CCM

AES-CCM support is added in the OpenSSL PMD. The PMD and the test code have been reworked, to avoid duplications with AES-GCM code, as both algorithms are quite similar (both are AEAD algorithms). Also, an optimization for AES-GCM (and AES-CCM after the last patch) has been introduced, initializin

[dpdk-dev] [PATCH 6/6] app/crypto-perf: use single mempool

In order to improve memory utilization, a single mempool is created, containing the crypto operation and mbufs (one if operation is in-place, two if out-of-place). This way, a single object is allocated and freed per operation, reducing the amount of memory in cache, which improves scalability. Si

[dpdk-dev] [PATCH 5/6] app/crypto-perf: do not populate the mbufs at init

For throughput and latency tests, it is not required to populate the mbufs with any test vector. For verify test, there is already a function that rewrites the mbufs every time they are going to be used with crypto operations. Signed-off-by: Pablo de Lara --- app/test-crypto-perf/cperf_test_late

[dpdk-dev] [PATCH 4/6] app/crypto-perf: overwrite mbuf when verifying

When running the verify test, mbufs in the pool were populated with the test vector loaded from a file. To avoid limiting the number of operations to the pool size, mbufs will be rewritten with the test vector, before linking them to the crypto operations. Signed-off-by: Pablo de Lara --- app/te

[dpdk-dev] [PATCH 3/6] app/crypto-perf: parse segment size

Instead of parsing number of segments, from the command line, parse segment size, as it is a more usual case to have the segment size fixed and then different packet sizes will require different number of segments. Signed-off-by: Pablo de Lara --- app/test-crypto-perf/cperf_ops.c | 2

[dpdk-dev] [PATCH 1/6] app/crypto-perf: set AAD after the crypto operation

Instead of prepending the AAD (Additional Authenticated Data) in the mbuf, it is easier to set after the crypto operation, as it is a read-only value, like the IV, and then it is not restricted to the size of the mbuf headroom. Signed-off-by: Pablo de Lara --- app/test-crypto-perf/cperf_ops.c

[dpdk-dev] [PATCH 2/6] app/crypto-perf: parse AEAD data from vectors

Since DPDK 17.08, there is specific parameters for AEAD algorithm, like AES-GCM. When verifying crypto operations with test vectors, the parser was not reading AEAD data (such as IV or key). Fixes: 8a5b494a7f99 ("app/test-crypto-perf: add AEAD parameters") Cc: sta...@dpdk.org Signed-off-by: Pablo

[dpdk-dev] [PATCH 0/6] Crypto-perf app improvements

This patchset includes some improvements in the Crypto performance application. The last patch, in particular, introduces performance improvements. Currently, crypto operations are allocated in a mempool and mbufs in a different one. Since crypto operations and mbufs are mapped 1:1, the can share

Re: [dpdk-dev] [PATCH] kni: fix SLE version detection

On 8/11/2017 5:33 PM, Nirmoy Das wrote: > detect SLE version reverse chronologically as ">=" is being used. > > Signed-off-by: Nirmoy Das Fixes: 2972254ce163 ("kni: fix build on Suse 12 SP3") Acked-by: Ferruh Yigit

Re: [dpdk-dev] [PATCH] nfp: support new medatada api

On 8/11/2017 3:30 PM, Alejandro Lucero wrote: > We need to support how metadata was handled and the new api, which will > allow to work with different metadata types and data dynamically. What is the API mentioned? > > Although this patch just supports one type handled by the PMD. Future uses >

Re: [dpdk-dev] [dpdk-stable] [PATCH] nfp: fix rss

On 8/11/2017 2:43 PM, Alejandro Lucero wrote: > Redirection table was not being updated properly. > There is also a problem when configuring RSS. > > Fixes: 934e4c60fbff ("nfp: add RSS") Cc: sta...@dpdk.org > > Signed-off-by: Alejandro Lucero Applied to dpdk-next-net/master, thanks.

[dpdk-dev] [PATCH 8/8] test/crypto: do not allocate extra memory for digest

Now that PMDs do not need extra space in the mbuf to store temporarily the digest when verifying an authentication tag, it is not required to allocate more memory in the mbufs passed to cryptodev. Signed-off-by: Pablo de Lara --- test/test/test_cryptodev_blockcipher.c | 29 ++

[dpdk-dev] [PATCH 6/8] crypto/zuc: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 7/8] crypto/aesni_mb: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 4/8] crypto/kasumi: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 5/8] crypto/snow3g: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 3/8] crypto/openssl: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 2/8] crypto/armv8: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

[dpdk-dev] [PATCH 1/8] crypto/aesni_gcm: do not append digest

When performing an authentication verification, the PMD was using memory at the end of the input buffer, to store temporarily the digest. This operation requires the buffer to have enough tailroom unnecessarily. Instead, memory is allocated for each queue pair, to store temporarily the digest gener

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

When performing authentication verification, some crypto PMDs require extra memory where the generated digest can be placed. Currently, these PMDs are getting the memory from the end of the source mbuf, which might fail if there is not enough tailroom. To avoid this situation, some memory is alloc

Re: [dpdk-dev] [dpdk-stable] [PATCH] nfp: write mac address to configuration bar

On 8/11/2017 11:25 AM, Alejandro Lucero wrote: > If not a valid mac present in configuration bar, PMD creates a random > one. It needs to be passed to the NIC. > > Signed-off-by: Alejandro Lucero Applied to dpdk-next-net/master, thanks.

Re: [dpdk-dev] [PATCH] nfp: handle packets with length 0 as usual ones

On 8/11/2017 11:05 AM, Alejandro Lucero wrote: > A DPDK app could, whatever the reason, send packets with size 0. > The PMD is not sending those packets, which does make sense, > but the problem is the mbuf is not released either. That leads > to mbufs not being available, because the app trusts th

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/i40e: fix flow control watermark mismatch

On 8/15/2017 6:40 PM, Kevin Traynor wrote: > On 08/13/2017 01:05 AM, Zhang, Qi Z wrote: >> Hi Kevin: >> >>> -Original Message- >>> From: Kevin Traynor [mailto:ktray...@redhat.com] >>> Sent: Thursday, August 10, 2017 11:16 PM >>> To: Zhang, Qi Z ; Wu, Jingjing >>> Cc: dev@dpdk.org; sta...@d

Re: [dpdk-dev] [PATCH] net/i40e: fix return code not checked

On 8/18/2017 3:23 PM, Ferruh Yigit wrote: > On 8/10/2017 10:12 AM, Daniel Mrzyglod wrote: >> Calling i40e_vsi_delete_mac without checking return >> value (as is done elsewhere 5 out of 6 times) >> >> Coverity issue: 140735 >> Fixes: 43c89d5a4fde ("net/i40e: set VF MAC from PF") >> >> Signed-off-by:

Re: [dpdk-dev] [PATCH] net/i40e: fix return code not checked

On 8/10/2017 10:12 AM, Daniel Mrzyglod wrote: > Calling i40e_vsi_delete_mac without checking return > value (as is done elsewhere 5 out of 6 times) > > Coverity issue: 140735 > Fixes: 43c89d5a4fde ("net/i40e: set VF MAC from PF") > > Signed-off-by: Daniel Mrzyglod Reviewed-by: Ferruh Yigit

Re: [dpdk-dev] [PATCH] net/ixgbe: fix MAC VLAN filter fail problem

On 8/8/2017 7:19 AM, wei zhao wrote: > Add a mode type check for MAC VLAN mode, if fdir is > in this mode, it do not need to do Sanity check for x550. > Fixes: dc0c16105d2d ("ixgbe: fix X550 flow director check") Cc: sta...@dpdk.org > > Signed-off-by: Wei Zhao Applied to dpdk-next-net/master, t

[dpdk-dev] [PATCH] app/testpmd: wrong usage of fseek & ftell to determine filesize

This issue was about passing unsigned argument where should be signed number. In reality this is about wrong usage of fseek and ftell to determine filesize. This patch is compliant to suggestions from FIO19-C: "Do not use fseek() and ftell() to compute the size of a regular file" Coverity issue: 1

[dpdk-dev] [PATCH] crypto/aesni_mb: add DES support

The Multi-buffer library now supports DES-CBC and DES-DOCSISBPI algorithms, so this commit extends adds support for them in the PMD. Signed-off-by: Pablo de Lara --- doc/guides/cryptodevs/aesni_mb.rst | 2 + doc/guides/cryptodevs/features/aesni_mb.ini | 3 ++ doc/guides/rel_notes/rele

Re: [dpdk-dev] [PATCH v3] net/af_packet: support Tx scattered mbuf input

On 8/7/2017 10:45 AM, Wenfeng Liu wrote: > Signed-off-by: Wenfeng Liu Reviewed-by: Ferruh Yigit

Re: [dpdk-dev] [PATCH] net/ark: remove empty header file

On 8/4/2017 9:53 PM, Ed Czeck wrote: > > On Thu, Aug 3, 2017 at 1:38 PM, Ferruh Yigit > wrote: >> >> Signed-off-by: Ferruh Yigit > Acked-by: Ed Czeck Applied to dpdk-next-net/master, thanks.

Re: [dpdk-dev] [PATCH v1 00/21] net/mlx5: cleanup for isolated mode

On 8/2/2017 3:10 PM, Nelio Laranjeiro wrote: > This series cleanups the control plane part and the way it uses the different > kind of objects (DPDK queues, Verbs Queues, ...). It has three goals: > > 1. Reduce the memory usage by sharing all possible objects. > > 2. Leave the configuration to

Re: [dpdk-dev] [PATCH v1 04/48] net/mlx4: remove useless compilation checks

On 8/1/2017 5:53 PM, Adrien Mazarguil wrote: > Verbs support for RSS, inline receive and extended device query calls has > not been optional for a while. Their absence is untested and is therefore > unsupported. > > Remove the related compilation checks and assume Mellanox OFED is up to > date, as

Re: [dpdk-dev] [PATCH v1 00/48] net/mlx4: trim and refactor entire PMD

On 8/1/2017 5:53 PM, Adrien Mazarguil wrote: > The main purpose of this large series is to relieve the mlx4 PMD from its > dependency on Mellanox OFED to instead rely on the standard rdma-core > package provided by Linux distributions. > > While compatibility with Mellanox OFED is preserved, all n

[dpdk-dev] eth_fm10k_dev_init failed as there is no Glort update

Hi Cheng, I am working on a system which uses fm10k driver. In my system, I am hitting an error in eth_fm10k_dev_init(). We are waiting for VF to get GLoRT update message once update_lport_state(hw, hw->mac.dglort_map, 1, 1); is done. Check goes something like this. if (hw->mac.type == fm10k_

Re: [dpdk-dev] eth_fm10k_dev_init failed as there is no Glort update

We are having kernel fm10k PF + fm10k VF driver. We are getting the update(glort updated) in all the cases in most of the times. But randomly, we are seeing this issue in one of VF initialisation. The frequency of issue is, say 1 in 20 times. On Thu, Aug 17, 2017 at 2:44 PM, Chen, Jing D wrote:

Re: [dpdk-dev] eth_fm10k_dev_init failed as there is no Glort update

Hi Everyone, Can anyone help me on this? Regards, Krishna Sharma On Wed, Aug 16, 2017 at 7:24 PM, Krishna S wrote: > Hi Cheng, > > I am working on a system which uses fm10k driver. > > In my system, I am hitting an error in eth_fm10k_dev_init(). > > We are waiting for VF to get GLoRT update mes

[dpdk-dev] [PATCH 6/6] bus/fslmc: refactor scan and probe functions

Scan now searches for devices through sysfs interface and adds them to a list for later initialization. During probe, each device is initialized accroding to its property. Signed-off-by: Shreyansh Jain --- drivers/bus/fslmc/fslmc_bus.c| 185 - drivers/bus/fslmc/fslmc_vfio

[dpdk-dev] [PATCH 4/6] crypto/dpaa2_sec: update driver type field

Signed-off-by: Shreyansh Jain --- drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c index e0f6cfc..95c3951 100644 --- a/drivers/crypto/dpaa2_sec

[dpdk-dev] [PATCH 5/6] drivers: refactor DPAA2 object definition

Initially, DPAA2 objects (except ETH and CRYPTO) were defined from VFIO layer. This patch moves that into Bus definition. This patch also realigns the object types with the new device types. Signed-off-by: Shreyansh Jain --- drivers/bus/fslmc/fslmc_vfio.c | 11 +- drivers/bus/f

[dpdk-dev] [PATCH 3/6] net/dpaa2: update driver type field

Shifting from existing device identifier to driver type field. Signed-off-by: Shreyansh Jain --- drivers/net/dpaa2/dpaa2_ethdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 429b3a0..360109e 100644

[dpdk-dev] [PATCH 2/6] bus/fslmc: introduce new device type enumerator

Existing devices and drivers depended on device ID rather than type. A new enumerator for all DPAA2 devices is introduced in this patch. At this point, the probe would not be able to link DPAA2 devices with the driver and I/O would not work. Subsequent patches will fix this. Signed-off-by: Shreya

[dpdk-dev] [PATCH 1/6] bus/fslmc: support only single group and container

Currently DPAA2 code doesn't support multiple groups and containers. Remove such provision in code to simplify code. Signed-off-by: Shreyansh Jain --- drivers/bus/fslmc/fslmc_vfio.c | 70 +++--- drivers/bus/fslmc/fslmc_vfio.h | 3 +- 2 files changed, 26 inser

[dpdk-dev] [PATCH 0/6] NXP DPAA2: Refactor bus scan/probe code

In [1], during the IOVA Mapping patch set [2] discussion, it was observed that DPAA2 scan was actually doing work meant for probing. This patchset demarcates the roles of FSLMC bus scan and probe functions much more clearly than before: 1. scan now only add devices into a list unlike previously,

Re: [dpdk-dev] [RFC PATCH 1/4] rte_security: API definitions

On 8/18/2017 2:46 PM, Thomas Monjalon wrote: Hi, 16/08/2017 17:40, Hemant Agrawal: Hi Thomas, Can we get a next-security tree to do development around this proposal? Also, we can discuss about this proposal in general in next techboard meeting. First question to ask: Why not create a

Re: [dpdk-dev] DPDK qos support for 40G port

Hi Kevin, > Hi Cristian, > Sorry to bother again, could you give suggestions/hints of code change to > support single 40G port? Because in our setup, we will use single 40G port > (Intel XL710) as the network interface. > > Or is there any workaround to bypass the limitation?(we are not willing

Re: [dpdk-dev] [PATCH] doc/failsafe: fix typos in nics guide

On Fri, Aug 18, 2017 at 06:57:48AM -0400, Yong Wang wrote: > Signed-off-by: Yong Wang Acked-by: Gaetan Rivet > --- > doc/guides/nics/fail_safe.rst | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > > diff --git a/doc/guides/nics/fail_safe.rst b/doc/guides/nics/fail_safe.rst > index

[dpdk-dev] [PATCH] doc/failsafe: fix typos in nics guide

Signed-off-by: Yong Wang --- doc/guides/nics/fail_safe.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/guides/nics/fail_safe.rst b/doc/guides/nics/fail_safe.rst index 34ecae2..c4e3d2e 100644 --- a/doc/guides/nics/fail_safe.rst +++ b/doc/guides/nics/fail_safe.rst @@

[dpdk-dev] [PATCH v6 6/6] mk: set -ISCDIR before -IRTE_OUT/include in CFLAGS

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 v6 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 v6 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 v6 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 v6 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 v6 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

[dpdk-dev] [PATCH v6 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] 16.11.3 (LTS) patches review and test

Hi all, Here is a list of patches targeted for LTS release 16.11.3. Please help review and test. The planned date for the final release is 30th, Aug. Before that, please let me know if anyone has objections with these patches being applied. These patches are located at branch 16.11 of dpdk-stable

Re: [dpdk-dev] [PATCH] ethdev: fix device state on close

On Thu, Aug 17, 2017 at 06:04:27AM +, Shahaf Shuler wrote: > Wednesday, August 16, 2017 6:26 PM, Gaëtan Rivet: > > > Even though it is reasonable for driver to call the > > rte_eth_dev_port_release, I still think the ethdev layer should protect from > > such bad behavior from the application si

Re: [dpdk-dev] [RFCv2 00/40] Building DPDK with meson and ninja

On Fri, 2017-08-18 at 09:35 +0100, Bruce Richardson wrote: > On Thu, Aug 17, 2017 at 04:25:36PM +0100, Luca Boccassi wrote: > > On Thu, 2017-08-17 at 16:10 +0200, Marco Varlese wrote: > > > Hi Bruce, > > > > > > On Mon, 2017-08-14 at 10:51 +0100, Bruce Richardson wrote: > > > > Following on from p

Re: [dpdk-dev] [RFCv2 00/40] Building DPDK with meson and ninja

On Fri, 2017-08-18 at 10:52 +0200, Marco Varlese wrote: > On Fri, 2017-08-18 at 09:35 +0100, Bruce Richardson wrote: > > > > On Thu, Aug 17, 2017 at 04:25:36PM +0100, Luca Boccassi wrote: > > > > > > > > > On Thu, 2017-08-17 at 16:10 +0200, Marco Varlese wrote: > > > > > > > > > > > > Hi Bruce

Re: [dpdk-dev] [RFC PATCH 1/4] rte_security: API definitions

Hi, 16/08/2017 17:40, Hemant Agrawal: > Hi Thomas, > Can we get a next-security tree to do development around this proposal? > > Also, we can discuss about this proposal in general in next techboard meeting. First question to ask: Why not create a repository elsewhere for your trials? The

Re: [dpdk-dev] [PATCH] net/failsafe: fix parameters parsing

On Thu, Aug 17, 2017 at 06:52:48PM +, Matan Azrad wrote: > Hi Gaetan > > > -Original Message- > > From: Gaëtan Rivet [mailto:gaetan.ri...@6wind.com] > > Sent: Thursday, August 17, 2017 7:25 PM > > To: Matan Azrad > > Cc: dev@dpdk.org; Ori Kam ; sta...@dpdk.org > > Subject: Re: [PATCH]

Re: [dpdk-dev] [RFCv2 00/40] Building DPDK with meson and ninja

On Fri, 2017-08-18 at 09:35 +0100, Bruce Richardson wrote: > On Thu, Aug 17, 2017 at 04:25:36PM +0100, Luca Boccassi wrote: > > > > On Thu, 2017-08-17 at 16:10 +0200, Marco Varlese wrote: > > > > > > Hi Bruce, > > > > > > On Mon, 2017-08-14 at 10:51 +0100, Bruce Richardson wrote: > > > > > > >

Re: [dpdk-dev] eth_fm10k_dev_init failed as there is no Glort update

> -Original Message- > From: Krishna S [mailto:k.shar...@gmail.com] > Sent: Thursday, August 17, 2017 6:33 PM > To: Chen, Jing D > Cc: dev@dpdk.org; Wang, Xiao W > Subject: Re: eth_fm10k_dev_init failed as there is no Glort update > > We are having kernel fm10k PF + fm10k VF driver. We

Re: [dpdk-dev] [RFCv2 00/40] Building DPDK with meson and ninja

On Thu, Aug 17, 2017 at 04:25:36PM +0100, Luca Boccassi wrote: > On Thu, 2017-08-17 at 16:10 +0200, Marco Varlese wrote: > > Hi Bruce, > > > > On Mon, 2017-08-14 at 10:51 +0100, Bruce Richardson wrote: > > > Following on from previous RFC [http://dpdk.org/dev/patchwork/patch > > > /25104/] > > > h

Re: [dpdk-dev] [RFCv2 00/40] Building DPDK with meson and ninja

Hi Luca, On Thu, 2017-08-17 at 16:24 +0100, Luca Boccassi wrote: > On Thu, 2017-08-17 at 16:10 +0200, Marco Varlese wrote: > > > > Hi Bruce, > > > > On Mon, 2017-08-14 at 10:51 +0100, Bruce Richardson wrote: > > > > > > Following on from previous RFC [http://dpdk.org/dev/patchwork/patch > > > /

Re: [dpdk-dev] [PATCH] net/failsafe: safer subdev iterator

On Thu, Aug 17, 2017 at 05:39:29PM -0700, Stephen Hemminger wrote: > On Thu, 17 Aug 2017 17:52:09 +0200 > Gaetan Rivet wrote: > > > The sub_device iterator macro should follow the general gist of the > > tailq API for an easier understanding and safer use. > > > > Once the loop has finished, the