[dpdk-dev] [Bug 9] qays

https://dpdk.org/tracker/show_bug.cgi?id=9 Thomas Monjalon (ad...@dpdk.org) changed: What|Removed |Added Status|CONFIRMED |RESOLVED CC|

Re: [dpdk-dev] [RFC] P4 enablement in DPDK

Hi, I want to express support for this proposal and adding P4 capabilities in DPDK. For example, I personally see a lot of demand for a production-quality P4-programmable software switch. A few comments on this: 1) I see a lot of similarities between the proposed PDEV table runtime API and th

[dpdk-dev] [PATCH v2 19/22] net/softnic: add cli for ttl action

Add cli commands for ttl action in softnic pipeline objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 23 +++ drivers/net/softnic/rte_eth_softnic_internals.h | 8 +++ drivers/net/softnic/rte_eth_softnic_thread.c

[dpdk-dev] [PATCH v2 22/22] app/testpmd: rework softnic forward mode

Modied the testpmd softnic forwarding mode as per the changes in softnic PMD. To run testpmd application with softnic fwd mode, following command is used; $ ./testpmd -c 0xc -n 4 --vdev 'net_softnic0,firware=script.cli' -- -i --forward-mode=softnic Signed-off-by: Jasvinder Singh Signed-off-by

[dpdk-dev] [PATCH v2 21/22] net/softnic: start and stop function

Implements softnic start and stop function. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c | 38 ++--- drivers/net/softnic/rte_eth_softnic_internals.h | 6 drivers/net/softnic/rte_eth_softnic_pipeli

[dpdk-dev] [PATCH v2 20/22] net/softnic: receive and transmit queue setup

Implements softnic receive and transmit queues setup using swq object. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c | 62 ++- 1 file changed, 32 insertions(+), 30 deletions(-) diff --git a/drivers/ne

[dpdk-dev] [PATCH v2 16/22] net/softnic: add cli for pipeline table entries

Add cli commands for table entries in softnic pipeline objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 2177 --- drivers/net/softnic/rte_eth_softnic_internals.h | 35 + drivers/net/softnic/rte

[dpdk-dev] [PATCH v2 18/22] net/softnic: add cli for meter action

Add cli commands for meter action in softnic pipeline objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 418 drivers/net/softnic/rte_eth_softnic_internals.h | 29 ++ drivers/net/softnic/rte_

[dpdk-dev] [PATCH v2 17/22] net/softnic: add cli to read pipeline port and table stats

Add cli commands to read port and table stats of softnic pipeline objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 285 drivers/net/softnic/rte_eth_softnic_internals.h | 29 +++ drivers/net/sof

[dpdk-dev] [PATCH v2 15/22] net/softnic: add cli to enable and disable pipeline

Add cli commands to enable and disable pipelines on specific threads in softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 103 drivers/net/softnic/rte_eth_softnic_internals.h | 10 + drivers/net/softnic/rte

[dpdk-dev] [PATCH v2 10/22] net/softnic: add thread

Add thread data structure and init function to run softnic pipelines objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 1 + drivers/net/softnic/rte_eth_softnic.c | 8 +++ drivers/net/softnic/rte_eth_softn

[dpdk-dev] [PATCH v2 12/22] net/softnic: add cli interface

Add interface for softnic cli commands. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 2 + drivers/net/softnic/parser.c| 687 drivers/net/softnic/parser.h

[dpdk-dev] [PATCH v2 14/22] net/softnic: add cli to create softnic objects

Add cli commands to create softnic objects such as mempool, swq, pipeline, etc. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic_cli.c | 1634 ++- drivers/net/softnic/rte_eth_softnic_internals.h | 85 ++ driver

[dpdk-dev] [PATCH v2 13/22] net/softnic: add connection agent

Add connection agent to enable connectivity with external agen (e.g. telnet, netcat, Python script, etc). Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile | 1 + drivers/net/softnic/conn.c | 332 ++

[dpdk-dev] [PATCH v2 11/22] net/softnic: add softnic run API

Implements softnic API function to run pipeline objects. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c| 13 -- drivers/net/softnic/rte_eth_softnic_thread.c | 195 +++ 2 files changed, 195 insertions(+

[dpdk-dev] [PATCH v2 09/22] net/softnic: add pipeline object

Add pipeline object implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 3 +- drivers/net/softnic/rte_eth_softnic.c | 2 + drivers/net/softnic/rte_eth_softnic_internals.h | 196 +

[dpdk-dev] [PATCH v2 08/22] net/softnic: add table action profile

Add pipeline's table action profile implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c | 2 + drivers/net/softnic/rte_eth_softnic_action.c| 227 drivers/net/softnic/r

[dpdk-dev] [PATCH v2 07/22] net/softnic: add port action profile

Add pipeline's port action profile implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 3 + drivers/net/softnic/hash_func.h | 359 drivers/net/softnic/ha

[dpdk-dev] [PATCH v2 06/22] net/softnic: add trafic manager object

Add traffic manager(tmgr) object to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c | 2 ++ drivers/net/softnic/rte_eth_softnic_internals.h | 25 ++-- drivers/net/softnic/rte_eth_softnic_tm.c

[dpdk-dev] [PATCH v2 02/22] net/softnic: add software queue object

Add swq object implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 1 + drivers/net/softnic/rte_eth_softnic.c | 7 ++ drivers/net/softnic/rte_eth_softnic_internals.h | 39 ++ d

[dpdk-dev] [PATCH v2 03/22] net/softnic: add link object

Add link object implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 1 + drivers/net/softnic/rte_eth_softnic.c | 4 + drivers/net/softnic/rte_eth_softnic_internals.h | 37 ++ d

[dpdk-dev] [PATCH v2 05/22] net/softnic: add tap object

Add tap object implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 1 + drivers/net/softnic/rte_eth_softnic.c | 2 + drivers/net/softnic/rte_eth_softnic_internals.h | 29 ++ dri

[dpdk-dev] [PATCH v2 04/22] net/softnic: add mempool object

Add mempool object implementation to the softnic. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/Makefile| 1 + drivers/net/softnic/rte_eth_softnic.c | 2 + drivers/net/softnic/rte_eth_softnic_internals.h | 38 +++

[dpdk-dev] [PATCH v2 00/22] net/softnic: refactoring

This patch set modifies the Soft NIC device driver to use the Packet Framework, which makes it much more modular, flexible and extensible with new functionality. � The Soft NIC allows building custom NIC pipelines in SW. The Soft NIC pipeline is DIY and reconfigurable through �firmware� (DPDK Pa

[dpdk-dev] [PATCH v2 01/22] net/softnic: restructuring

Rework the softnic implementation to have flexiblity in enabling more features to its receive and transmit data path. Signed-off-by: Cristian Dumitrescu Signed-off-by: Jasvinder Singh --- drivers/net/softnic/rte_eth_softnic.c | 607 drivers/net/softnic/rte_eth

[dpdk-dev] [dpdk-announce] DPDK 17.11.3 (LTS) released

Hi all, Here is a new LTS release: http://fast.dpdk.org/rel/dpdk-17.11.3.tar.xz The git tree is at: http://dpdk.org/browse/dpdk-stable/?h=17.11 Note: a source file of the Broadcom NetXtreme PMD, which was mistakenly marked as licensed under the GPL-2, has been fixed and marked as

Re: [dpdk-dev] [PATCH 05/22] ethdev: introduce device lock

On Thu, 7 Jun 2018 20:38:32 +0800 Qi Zhang wrote: > +/** > + * Lock an Ethernet Device directly or register a callback function > + * for condition check at runtime, this help application to prevent > + * a device be detached unexpectly. > + * NOTE: Lock a device mutliple times with same parmete

Re: [dpdk-dev] [PATCH] vhost: fix missing increment of log cache count

On 15.06.2018 16:48, Maxime Coquelin wrote: > The log_cache_nb_elem was never incremented, resulting > in all dirty pages to be missed during live migration. > > Fixes: c16915b87109 ("vhost: improve dirty pages logging performance") > Cc: sta...@dpdk.org > > Reported-by: Peng He > Cc: Ilya Maxim

Re: [dpdk-dev] [PATCH 04/22] ethdev: enable hotplug on multi-process

On 07-Jun-18 1:38 PM, Qi Zhang wrote: The patch introduce the solution to handle different hotplug cases in multi-process situation, it include below scenario: 1. Attach a share device from primary 2. Detach a share device from primary 3. Attach a share device from secondary 4. Detach a share de

Re: [dpdk-dev] [PATCH 05/22] ethdev: introduce device lock

On 07-Jun-18 1:38 PM, Qi Zhang wrote: Introduce API rte_eth_dev_lock and rte_eth_dev_unlock to let application lock or unlock on specific ethdev, a locked device can't be detached, this help applicaiton to prevent unexpected device detaching, especially in multi-process envrionment. Aslo the new

Re: [dpdk-dev] [PATCH] examples/ip_pipeline: add link show to the cli

Hi Kevin, If you only need access to this linked list for iterating through it, you can add a new function: struct link *link_next(struct link *) that gets you the next element in the list (for first element, invoke with link = NULL; at and of list, it returns NULL). Makes sense? Are there oth

Re: [dpdk-dev] [PATCH 00/22] enable hotplug on multi-process

Hi Qi, I haven't read the code yet, and i'll be the first to admit that i'm not too well versed on how shared/private device data works, so my apologies in advance if all of below comments are addressed by implementation details or are way off base! On 07-Jun-18 1:38 PM, Qi Zhang wrote:

[dpdk-dev] [PATCH v2] memory: make eal_get_virtual_area() aware of base-virtaddr alignment

From: Dariusz Stojaczyk Whenever a calculated base-virtaddr offset had to be manually aligned to requested page_sz, we did not take account of that alignment in incrementing the base-virtaddr offset further. The next requested virtual area could print a warning "hint [...] not respected!" and let

Re: [dpdk-dev] [dpdk-stable] [PATCH v1] mbuf: fix RTE_ETH_IS_IPV6_HDR comment typo

On 6/14/2018 5:45 PM, Ferruh Yigit wrote: > On 6/14/2018 4:09 AM, Haiyue Wang wrote: >> It should be IPv6, not IPv4. >> Fixes: f295a00a2b44 ("mbuf: add definitions of unified packet types") >> Cc: sta...@dpdk.org >> >> Signed-off-by: Haiyue Wang > > Reviewed-by: Ferruh Yigit Applied to dpdk-n

Re: [dpdk-dev] [PATCH] examples/ip_pipeline: add link show to the cli

Hi Cristian, > > + > > + link_list = links_get(); > > We don't need this function, the lined list of links is a global public > object, > please access it directly. link_list is declared as a static struct in link.c so it is not accessible from cli.c I can either leave this function in to p

Re: [dpdk-dev] [PATCH v3] net/i40e: illagel pactket checking

> -Original Message- > From: Wu, Yanglong > Sent: Friday, June 15, 2018 2:19 PM > To: dev@dpdk.org > Cc: Zhang, Qi Z ; Ananyev, Konstantin > ; Wu, Yanglong > Subject: [PATCH v3] net/i40e: illagel pactket checking > illagel pactket --> illegal packet > Some illegal packets will lead t

[dpdk-dev] [dpdk-announce] DPDK 18.02.2 released

Hi all, Here is a new stable release: https://fast.dpdk.org/rel/dpdk-18.02.2.tar.xz The git tree is at: https://dpdk.org/browse/dpdk-stable/?h=18_02 Note: a source file of the Broadcom NetXtreme PMD, which was mistakenly marked as licensed under the GPL-2, has been fixed and mark

[dpdk-dev] [PATCH 8/8] ipc: remove main IPC thread

Previously, to handle requests from peer(s), or replies for a request (sync or async) by itself, a dedicated IPC thread was set up. Now that every other piece of the puzzle is in place, we can get rid of the IPC thread, and move waiting for IPC messages entirely into the interrupt thread. Signed-

[dpdk-dev] [PATCH 6/8] eal/bsdapp: add interrupt thread

Add interrupt thread to FreeBSD. It is largely a copy-paste from Linuxapp interrupt thread, except for a few key differences: * Use kevent instead of epoll * Do not recreate the event queue on adding/removing interrupt sources, add/remove them to/from the queue on the fly instead * No support fo

[dpdk-dev] [PATCH 7/8] eal/bsdapp: add alarm support

Implement EAL alarm API support for FreeBSD. The implementation is largely identical to that of Linux version, with one key difference. The alarm API is a little Linux-centric in that it is expecting the alarm API to manage alarm timeouts without involvement of the interrupt thread. This works on

[dpdk-dev] [PATCH 1/8] eal/linux: use glibc malloc in alarm

From: Jianfeng Tan IPC is used by memory subsystem, and when we merge IPC threads with interrupt threads, asynchronous IPC requests will have to use alarm API. However, currently, alarm API uses rte_malloc to allocate memory, which will create a circular dependency between alarm API and memory su

[dpdk-dev] [PATCH 4/8] eal: bring forward init of interrupt handling

From: Jianfeng Tan IPC will reply on interrupt handling, so we move forward the init of interrupt handling. Signed-off-by: Jianfeng Tan Signed-off-by: Anatoly Burakov --- lib/librte_eal/bsdapp/eal/eal.c | 10 +- lib/librte_eal/linuxapp/eal/eal.c | 10 +- 2 files changed, 10

[dpdk-dev] [PATCH 5/8] eal: add IPC type for interrupt thread

From: Jianfeng Tan We are going to merge IPC into interrupt thread. This patch adds IPC type for interrupt thread. Signed-off-by: Jianfeng Tan Signed-off-by: Anatoly Burakov --- Notes: RFC->RFCv2: - Fixed typo in test app .../common/include/rte_eal_interrupts.h | 1 + lib/lib

[dpdk-dev] [PATCH 3/8] ipc: remove IPC thread for async requests

Previously, we were using two IPC threads - one to handle messages and synchronous requests, and another to handle asynchronous requests. To handle replies for an async request, rte_mp_handle woke up the rte_mp_handle_async thread to process through pthread_cond variable. Change it to handle async

[dpdk-dev] [PATCH 2/8] eal/linux: use glibc malloc in interrupt handling

From: Jianfeng Tan IPC is used by memory subsystem, and thus it should not use rte_malloc to avoid circular dependency. Switch to using regular glibc malloc in interrupts API. Signed-off-by: Jianfeng Tan Signed-off-by: Anatoly Burakov --- lib/librte_eal/linuxapp/eal/eal_interrupts.c | 14

[dpdk-dev] [PATCH 0/8] Remove IPC threads

As previously discussed [1], IPC threads need to be removed and their workload moved to interrupt thread. FreeBSD did not have an interrupt thread, nor did it support alarm API. This patchset adds support for both on FreeBSD. FreeBSD interrupt thread is based on kevent, FreeBSD's native event mult

Re: [dpdk-dev] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment

On 15-Jun-18 1:24 PM, Dariusz Stojaczyk wrote: From: Dariusz Stojaczyk Whenever a calculated base-virtaddr offset had to be manually aligned to requested page_sz, we did not take account of that alignment in incrementing the base-virtaddr offset further. The next requested virtual area could pr

Re: [dpdk-dev] [PATCH v10 6/6] devtools: expand meson cross compiling test coverage

On Fri, Jun 15, 2018 at 06:21:43PM +0800, Gavin Hu wrote: > The default test script covers only default host cc compiler, either gcc or > clang, the fix is to cover both, gcc and clang. And also the build dirs are > changed to *-host-$c, indicating the difference of cc used. > > Fixes: a55277a788

Re: [dpdk-dev] [PATCH v3] net/i40e: workaround for Fortville performance

> -Original Message- > From: Wang, Haiyue > Sent: Wednesday, June 13, 2018 1:53 PM > To: dev@dpdk.org > Cc: Wang, Haiyue ; Zhang, Qi Z > ; Wu, Jingjing ; Yang, Qiming > ; sta...@dpdk.org > Subject: [PATCH v3] net/i40e: workaround for Fortville performance > > The GL_SWR_PM_UP_THR value

Re: [dpdk-dev] [PATCH] i40evf: don't reset device_info data

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Damjan Marion > Sent: Thursday, June 7, 2018 4:31 AM > To: dev@dpdk.org > Cc: Damjan Marion > Subject: [dpdk-dev] [PATCH] i40evf: don't reset device_info data > > At this point valid data is already set by rte_

Re: [dpdk-dev] [PATCH 0/2] net/i40e: print real global changes

> -Original Message- > From: Xing, Beilei > Sent: Thursday, June 7, 2018 10:40 AM > To: Zhang, Qi Z > Cc: dev@dpdk.org > Subject: [PATCH 0/2] net/i40e: print real global changes > > Only real changes should be logged, so only the first detected change will be > logged. Log should be li

[dpdk-dev] [PATCH] vhost: fix missing increment of log cache count

The log_cache_nb_elem was never incremented, resulting in all dirty pages to be missed during live migration. Fixes: c16915b87109 ("vhost: improve dirty pages logging performance") Cc: sta...@dpdk.org Reported-by: Peng He Cc: Ilya Maximets Signed-off-by: Maxime Coquelin --- lib/librte_vhost/v

Re: [dpdk-dev] [PATCH v10 4/6] devtools: fix the missing ninja command error

On Fri, Jun 15, 2018 at 06:21:41PM +0800, Gavin Hu wrote: > On some linux distributions, eg: CentOS, the ninja executable has a > different name: ninja-build, this patch is to check and adapt to it > accordingly. > > ./devtools/test-meson-builds.sh: line 24: ninja: command not found > > Fixes: a5

Re: [dpdk-dev] Missing an increment on vq->log_cache_nb_elem ?

Hi, Maxime, My name is Peng He. Thanks. > 在 2018年6月15日，下午9:24，Maxime Coquelin 写道： > > Hi, > > On 06/15/2018 02:32 PM, Ilya Maximets wrote: >>> Hi, >>> >>> >>> In the latest dpdk master branch, in the function *vhost_log_cache_page*: >>> >>> >>> static __rte_always_inline void >>> vh

Re: [dpdk-dev] [PATCH] drivers/bonding: fix bond mac address reset

On 6/14/2018 9:38 PM, Chas Williams wrote: > > > On Thu, Jun 14, 2018 at 12:49 PM Ferruh Yigit > wrote: > > On 5/23/2018 10:11 AM, Kiran Kumar wrote: > > Currently when resetting bond mac address, we are getting the > > persisted mac address from slave

Re: [dpdk-dev] Missing an increment on vq->log_cache_nb_elem ?

Hi, On 06/15/2018 02:32 PM, Ilya Maximets wrote: Hi, In the latest dpdk master branch, in the function *vhost_log_cache_page*: static __rte_always_inline void vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq, uint64_t page) { uint32_t bi

Re: [dpdk-dev] [PATCH v2] net/pcap: rx_iface_in stream type support

On 6/14/2018 9:44 PM, Ido Goshen wrote: > I think we are starting to mix two things > One is how to configure pcap eth dev with multiple queues and I totally agree > it would have been nicer to just say something like "max_tx_queues =N" > instead of needing to write "tx_iface" N times, but as it

Re: [dpdk-dev] Missing an increment on vq->log_cache_nb_elem ?

> Hi, > > > In the latest dpdk master branch, in the function *vhost_log_cache_page*: > > > static __rte_always_inline void > vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq, > uint64_t page) > { > uint32_t bit_nr = page % (sizeof(unsigned lo

[dpdk-dev] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment

From: Dariusz Stojaczyk Whenever a calculated base-virtaddr offset had to be manually aligned to requested page_sz, we did not take account of that alignment in incrementing the base-virtaddr offset further. The next requested virtual area could print a warning "hint [...] not respected!" and let

Re: [dpdk-dev] [PATCH 2/2] app/testpmd: add NVGRE encap/decap support

Hi Bernard, On Fri, Jun 15, 2018 at 09:32:02AM +, Iremonger, Bernard wrote: > Hi Nelio, > >[...] > > @@ -14927,6 +14930,81 @@ cmdline_parse_inst_t cmd_set_vxlan = { > > }, > > }; > > > > +/** Set VXLAN encapsulation details */ > > VXLAN should be NVGRE. >[...] Right, > > b/app/test-p

[dpdk-dev] [Bug 62] Rawdev autotest fails

https://dpdk.org/tracker/show_bug.cgi?id=62 Bug ID: 62 Summary: Rawdev autotest fails Product: DPDK Version: 18.05 Hardware: All OS: All Status: CONFIRMED Severity: normal Priority: Normal

Re: [dpdk-dev] [PATCH v1 2/6] compress/zlib: add device setup PMD ops

Hi Shally, Comments inline. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shally Verma > Sent: Tuesday, May 15, 2018 11:32 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; dev@dpdk.org; > pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subj

Re: [dpdk-dev] [PATCH v1 6/6] doc: add ZLIB PMD documentation

Hi, Comments inline. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shally Verma > Sent: Tuesday, May 15, 2018 11:32 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; dev@dpdk.org; > pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subject: [dp

Re: [dpdk-dev] [PATCH v1 4/6] compress/zlib: add enq deq apis

Comments inline. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shally Verma > Sent: Tuesday, May 15, 2018 11:32 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; dev@dpdk.org; > pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subject: [dpdk-d

Re: [dpdk-dev] [PATCH v1 3/6] compress/zlib: add xform and stream create support

Comment Inline. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shally Verma > Sent: Tuesday, May 15, 2018 11:32 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; dev@dpdk.org; > pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subject: [dpdk-de

Re: [dpdk-dev] [PATCH v1 1/6] compress/zlib: add ZLIB PMD support

Hi, thanks for the work, reviewed the PMD see comments below. > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shally Verma > Sent: Tuesday, May 15, 2018 11:32 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; dev@dpdk.org; > pathr...@caviumnetworks.com; Suni

Re: [dpdk-dev] 18.02.2 patches review and test

On Fri, 2018-06-08 at 10:16 +0100, Luca Boccassi wrote: > On Mon, 2018-06-04 at 09:58 +0100, Luca Boccassi wrote: > > Hi all, > > > > Here is a list of patches targeted for stable release 18.02.2. > > Please > > help review and test. The planned date for the final release is > > Thursday, > > the

[dpdk-dev] [PATCH] crypto/null: add dynamic logging to null driver

1.added new logtype for null driver. 2.registered new logtype. 3.NULL_CRYPTO_LOG_ERR, RTE_LOG_ERR and CDEV_LOG_ERR are replaced with new logtype name NULL_PMD_LOG. Signed-off-by: Pallantla Poornima Reviewed-by: Reshma Pattan --- drivers/crypto/null/null_crypto_pmd.c | 15 ++

Re: [dpdk-dev] [PATCH v6 7/7] devtools: expand meson cross compiling coverage

Thanks Bruce, I submitted v10 patch set fixing the whitespace issues. > -Original Message- > From: Bruce Richardson > Sent: Thursday, June 14, 2018 6:45 PM > To: Gavin Hu > Cc: dev@dpdk.org; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v6 7/7] devtools: expand meson cross > compiling

[dpdk-dev] [PATCH v10 6/6] devtools: expand meson cross compiling test coverage

The default test script covers only default host cc compiler, either gcc or clang, the fix is to cover both, gcc and clang. And also the build dirs are changed to *-host-$c, indicating the difference of cc used. Fixes: a55277a788 ("devtools: add test script for meson builds") Cc: sta...@dpdk.org

[dpdk-dev] [PATCH v10 5/6] build: fix the meson cross compile error

The following error hits if host cc compiler is clang(default one in most linux distributions) and the cross compiler is gcc. The root cause is: the hybride compilers add the warning options to the meson project as project arguments, which apply for both host compiling and cross compiling. But som

[dpdk-dev] [PATCH v10 3/6] build: fix the meson build warning

This is to fix the unnecessary warning output, it is not consistent with the configurations of other platforms. WARNING: Cross file does not specify strip binary, result will not be stripped. Fixes: e53a5299d2 ("build: support vendor specific ARM cross builds") Cc: sta...@dpdk.org Signed-off-by:

[dpdk-dev] [PATCH v10 2/6] doc: add a guide doc for cross compiling from x86

From: gavin hu This is the guide for cross compiling ARM64 DPDK from X86 hosts. Signed-off-by: Gavin Hu Reviewed-by: Steve Capper Reviewed-by: Honnappa Nagarahalli Acked-by: Marko Kovacevic --- .../linux_gsg/cross_build_dpdk_for_arm64.rst | 137 + doc/guides/linux_

[dpdk-dev] [PATCH v10 4/6] devtools: fix the missing ninja command error

On some linux distributions, eg: CentOS, the ninja executable has a different name: ninja-build, this patch is to check and adapt to it accordingly. ./devtools/test-meson-builds.sh: line 24: ninja: command not found Fixes: a55277a788 ("devtools: add test script for meson builds") Cc: sta...@dpdk.

[dpdk-dev] [PATCH v10 1/6] mk: fix makefile based cross build errors

From: gavin hu The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was enabled when the cross compiler gcc is greater than 7.0, but for the host side buildtools/pmdinfogen, if the native gcc is older than 7.0, or the host cc compiler is clang, it should not be enabled. The fix

[dpdk-dev] [PATCH v10 0/6] Fix the cross compiling errors

1. Pre-v5 of this patch set(two patches) is to fix the GNU Makefile based cross compiling errors and add a guiding doc for this. 2. v6 add 5 more new patches to cover meson cross fixes 3. v7 Some minor changes to address the comments: a) trim the commit message b) at the start of the scri

Re: [dpdk-dev] [PATCH v9 6/6] devtools: expand meson cross compiling test coverage

On Fri, Jun 15, 2018 at 05:26:05PM +0800, Gavin Hu wrote: > The default test script covers only default host cc compiler, either gcc or > clang, the fix is to cover both, gcc and clang. And also the build dirs are > changed to *-host-$c, indicating the difference of cc used. > > Fixes: a55277a788

Re: [dpdk-dev] [PATCH v9 4/6] devtools: fix the missing ninja command error

On Fri, Jun 15, 2018 at 05:26:03PM +0800, Gavin Hu wrote: > On some linux distributions, eg: CentOS, the ninja executable has a > different name: ninja-build, this patch is to check and adapt to it > accordingly. > > ./devtools/test-meson-builds.sh: line 24: ninja: command not found > > Fixes: a5

Re: [dpdk-dev] [PATCH v8 6/6] devtools: expand meson cross compiling coverage

Hi Bruce, Thanks for your review, new v9 patch set was submitted. Any more comments are welcome! Best Regards, Gavin > -Original Message- > From: Bruce Richardson > Sent: Friday, June 15, 2018 4:28 PM > To: Gavin Hu > Cc: dev@dpdk.org; nd ; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PA

Re: [dpdk-dev] [PATCH 2/2] app/testpmd: add NVGRE encap/decap support

Hi Nelio, > -Original Message- > From: Nelio Laranjeiro [mailto:nelio.laranje...@6wind.com] > Sent: Thursday, June 14, 2018 4:09 PM > To: dev@dpdk.org; Adrien Mazarguil ; Lu, > Wenzhuo ; Wu, Jingjing ; > Iremonger, Bernard > Cc: Awal, Mohammad Abdul > Subject: [PATCH 2/2] app/testpmd: ad

[dpdk-dev] [PATCH v9 5/6] build: fix the meson cross compile error

The following error hits if host cc compiler is clang(default one in most linux distributions) and the cross compiler is gcc. The root cause is: the hybride compilers add the warning options to the meson project as project arguments, which apply for both host compiling and cross compiling. But som

[dpdk-dev] [PATCH v9 6/6] devtools: expand meson cross compiling test coverage

The default test script covers only default host cc compiler, either gcc or clang, the fix is to cover both, gcc and clang. And also the build dirs are changed to *-host-$c, indicating the difference of cc used. Fixes: a55277a788 ("devtools: add test script for meson builds") Cc: sta...@dpdk.org

[dpdk-dev] [PATCH v9 4/6] devtools: fix the missing ninja command error

On some linux distributions, eg: CentOS, the ninja executable has a different name: ninja-build, this patch is to check and adapt to it accordingly. ./devtools/test-meson-builds.sh: line 24: ninja: command not found Fixes: a55277a788 ("devtools: add test script for meson builds") Cc: sta...@dpdk.

[dpdk-dev] [PATCH v9 1/6] mk: fix makefile based cross build errors

From: gavin hu The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was enabled when the cross compiler gcc is greater than 7.0, but for the host side buildtools/pmdinfogen, if the native gcc is older than 7.0, or the host cc compiler is clang, it should not be enabled. The fix

[dpdk-dev] [PATCH v9 2/6] doc: add a guide doc for cross compiling from x86

From: gavin hu This is the guide for cross compiling ARM64 DPDK from X86 hosts. Signed-off-by: Gavin Hu Reviewed-by: Steve Capper Reviewed-by: Honnappa Nagarahalli Acked-by: Marko Kovacevic --- .../linux_gsg/cross_build_dpdk_for_arm64.rst | 137 + doc/guides/linux_

[dpdk-dev] [PATCH v9 0/6] Fix the cross compiling errors

1. Pre-v5 of this patch set(two patches) is to fix the GNU Makefile based cross compiling errors and add a guiding doc for this. 2. v6 add 5 more new patches to cover meson cross fixes 3. v7 Some minor changes to address the comments: a) trim the commit message b) at the start of the scri

[dpdk-dev] [PATCH v9 3/6] build: fix the meson build warning

This is to fix the unnecessary warning output, it is not consistent with the configurations of other platforms. WARNING: Cross file does not specify strip binary, result will not be stripped. Fixes: e53a5299d2 ("build: support vendor specific ARM cross builds") Cc: sta...@dpdk.org Signed-off-by:

Re: [dpdk-dev] [PATCH v3 2/6] lib/cryptodev: add asym op support in cryptodev

> -Original Message- > From: Shally Verma [mailto:shally.ve...@caviumnetworks.com] > Sent: Wednesday, May 16, 2018 7:05 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; akhil.go...@nxp.com; > dev@dpdk.org; pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subject: [PATCH

Re: [dpdk-dev] [PATCH] vhost: use SMP memory barrier before kicking guest

On 06/07/2018 04:38 PM, Maxime Coquelin wrote: vhost_vring_call() used rte_mb(), which translates into mfence instruction on x86. This patch changes to use rte_smp_mb(), which changed recently to translate into a locked ADD instruction for performance reason. The measured gain is up to 3% wi

Re: [dpdk-dev] [PATCH v3 1/6] lib/cryptodev: add asymmetric algos in cryptodev

Hi Shally, > -Original Message- > From: Shally Verma [mailto:shally.ve...@caviumnetworks.com] > Sent: Wednesday, May 16, 2018 7:05 AM > To: De Lara Guarch, Pablo > Cc: Trahe, Fiona ; akhil.go...@nxp.com; > dev@dpdk.org; pathr...@caviumnetworks.com; Sunila Sahu > ; Ashish Gupta > > Subjec

Re: [dpdk-dev] [PATCH V21 4/4] app/testpmd: show example to handle hot unplug

On 6/14/2018 8:59 PM, Iremonger, Bernard wrote: Hi Jeff, -Original Message- From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jeff Guo Sent: Thursday, May 3, 2018 11:49 AM To: step...@networkplumber.org; Richardson, Bruce ; Yigit, Ferruh ; Ananyev, Konstantin ; gaetan.ri...@6wind.

Re: [dpdk-dev] [RFC] hot plug failure handle mechanism

On 6/15/2018 5:37 AM, Thomas Monjalon wrote: Hi, I am sorry, it is very hard to be sure we understand correctly your thougths. I like the proposal, but I want to be sure my understanding was not biased by what I would like to read :) So I try to reword below. Please confirm it matches your in

Re: [dpdk-dev] [PATCH v8 6/6] devtools: expand meson cross compiling coverage

On Fri, Jun 15, 2018 at 04:01:20PM +0800, Gavin Hu wrote: > The default test script covers only default host cc compiler, either gcc or > clang, the fix is to cover both, gcc and clang. And also the build dirs are > changed to *-host-$c, indicating the difference of cc used. > > Fixes: a55277a788

Re: [dpdk-dev] [PATCH v8 4/6] devtools: fix the missing ninja command error on CentOS

On Fri, Jun 15, 2018 at 04:01:18PM +0800, Gavin Hu wrote: > On CentOS, the ninja executable has a different name: > ninja-build, this patch is to fix the missing command error > on CentOS as follows: > ./devtools/test-meson-builds.sh: line 24: ninja: command not found > > Fixes: a55277a788 ("devto

Re: [dpdk-dev] [PATCH v6 7/7] devtools: expand meson cross compiling coverage

> -Original Message- > From: Bruce Richardson > Sent: Thursday, June 14, 2018 6:45 PM > To: Gavin Hu > Cc: dev@dpdk.org; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v6 7/7] devtools: expand meson cross > compiling coverage > > On Thu, Jun 14, 2018 at 05:51:27PM +0800, Gavin Hu wro

Re: [dpdk-dev] [PATCH v6 5/7] devtools: fix the missing ninja command error on CentOS

> -Original Message- > From: Bruce Richardson > Sent: Thursday, June 14, 2018 6:41 PM > To: Gavin Hu > Cc: dev@dpdk.org; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v6 5/7] devtools: fix the missing ninja > command error on CentOS > > On Thu, Jun 14, 2018 at 05:51:25PM +0800, Gavi

Re: [dpdk-dev] [PATCH v6 3/7] devtools: fix the Exec format error

Hi Bruce, This patch was dropped, thanks for your review. Best Regards, Gavin > -Original Message- > From: Bruce Richardson > Sent: Thursday, June 14, 2018 6:34 PM > To: Gavin Hu > Cc: dev@dpdk.org; sta...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v6 3/7] devtools: fix the Exec format

Re: [dpdk-dev] [PATCH v3 6/6] doc: add asym crypto in cryptodev programmer guide

Thanks for reviewing. Acked to all feedback Thanks Shally >-Original Message- >From: Kovacevic, Marko [mailto:marko.kovace...@intel.com] >Sent: 14 June 2018 16:13 >To: Verma, Shally ; De Lara Guarch, Pablo > >Cc: Trahe, Fiona ; akhil.go...@nxp.com; dev@dpdk.org; >Athreya, Narayana Prasad

[dpdk-dev] [PATCH v8 3/6] build: fix the meson build warning

This is to fix the unnecessary warning output, it is not consistent with the configurations of other platforms. WARNING: Cross file does not specify strip binary, result will not be stripped. Fixes: e53a5299d2 ("build: support vendor specific ARM cross builds") Cc: sta...@dpdk.org Signed-off-by:

Re: [dpdk-dev] [PATCH] vhost: refine the vhost_new_device

On 06/08/2018 11:18 AM, xiangxia.m@gmail.com wrote: From: Tonghao Zhang Make sure find avalid device id before allocating virtio_net, if not, return directly. It may avoid allocating and freeing virtio_net when there is not valid device id. Signed-off-by: Tonghao Zhang --- lib/librte_v

  1   2   >