RE: [PATCH v5] eventdev/eth_rx: fix memory leak when token parsing finished

Hi Weiguo, > -Original Message- > From: Weiguo Li > Sent: Friday, February 4, 2022 1:20 PM > To: Jayatheerthan, Jay > Cc: Kundapura, Ganapati ; Naga Harish K, S V > ; > step...@networkplumber.org; dev@dpdk.org > Subject: [PATCH v5] eventdev/eth_rx: fix memory leak when token parsing >

[PATCH v5] eventdev/eth_rx: fix memory leak when token parsing finished

The memory get from strdup should be freed when parameter parsing finished, and also should be freed when error occurs. Fixes: 814d01709328 ("eventdev/eth_rx: support telemetry") Fixes: 9e583185318f ("eventdev/eth_rx: support telemetry") Signed-off-by: Weiguo Li Acked-by: Ganapati Kundapura ---

Re: [PATCH v2] devtools/cocci: update cocci for ethdev namespace

04/02/2022 07:13, Singh, Aman Deep: > Hi Thomas > > On 2/3/2022 2:31 AM, Thomas Monjalon wrote: > > 23/01/2022 18:20, Aman Singh: > >> Added two specific exceptions for ETH_SPEED_10G > >> and ETH_SPEED_25G to avoid there name change. > >> Added check for ETH_TUNNEL_FILTER and ETH_RSS_RETA > > Plea

RE: [PATCH v4] eventdev/eth_rx: fix memory leak when token parsing finished

Hi Weiguo, > -Original Message- > From: Weiguo Li > Sent: Thursday, February 3, 2022 2:20 PM > To: Jayatheerthan, Jay > Cc: Kundapura, Ganapati ; Naga Harish K, S V > ; dev@dpdk.org > Subject: [PATCH v4] eventdev/eth_rx: fix memory leak when token parsing > finished > > The memory get

Re: [PATCH v2] devtools/cocci: update cocci for ethdev namespace

Hi Thomas On 2/3/2022 2:31 AM, Thomas Monjalon wrote: 23/01/2022 18:20, Aman Singh: Added two specific exceptions for ETH_SPEED_10G and ETH_SPEED_25G to avoid there name change. Added check for ETH_TUNNEL_FILTER and ETH_RSS_RETA Please could you explain why? These two macro's ETH_SPEED_10G &

[PATCH] doc: add limitation on MPRQ usage in multi-process app

MPRQ cannot be used in multi-process applications because of externally attached MPRQ buffers. A callback is registered by a primary process to free MPRQ buffers once they are no longer needed. But this information is shared among all the processes. The virtual address of the mlx5_mprq_buf_free_cb

Re: [PATCH 1/1] ci: restrict concurrency

03/02/2022 21:21, Aaron Conole: > Thomas Monjalon writes: > > > Aaron, David, > > Please could you review this patch? > > Thanks > > > > 13/01/2022 13:41, Josh Soref: > >> On Thu, Jan 13, 2022, 6:42 AM Thomas Monjalon wrote: > >> > >> > Hi, > >> > > >> > The explanation should be in the patch,

Re: [dpdk-dev] [PATCH v7 1/4] ethdev: support device reset and recovery events

On Tue, Feb 1, 2022 at 5:20 AM Ferruh Yigit wrote: > > On 2/1/2022 1:09 PM, Kalesh Anakkur Purayil wrote: > > Thank you Ferruh for the review. Please see inline. > > > > On Tue, Feb 1, 2022 at 5:41 PM Ferruh Yigit > > wrote: > > > > On 1/28/2022 12:48 PM, Kalesh

Re: [PATCH 1/1] ci: restrict concurrency

Thomas Monjalon writes: > Aaron, David, > Please could you review this patch? > Thanks > > 13/01/2022 13:41, Josh Soref: >> On Thu, Jan 13, 2022, 6:42 AM Thomas Monjalon wrote: >> >> > Hi, >> > >> > The explanation should be in the patch, not the cover letter. >> > Actually, you don't need a co

Re: [PATCH v15 10/11] app/test: replace .sh script with .py script

O Thu, Feb 03, 2022 at 12:15:19PM +0100, Thomas Monjalon wrote: > 26/01/2022 06:10, Jie Zhou: > > - Add python script to check if system supports hugepages > > - Remove corresponding .sh script > > - Replace calling of .sh with corresponding .py in meson.build > > > > Signed-off-by: Jie Zhou > >

[PATCH v3 3/6] mem: add dirty malloc element support

EAL malloc layer assumed all free elements content is filled with zeros ("clean"), as opposed to uninitialized ("dirty"). This assumption was ensured in two ways: 1. EAL memalloc layer always returned clean memory. 2. Freed memory was cleared before returning into the heap. Clearing the memory can

[PATCH v3 6/6] eal: extend --huge-unlink for hugepage file reuse

Expose Linux EAL ability to reuse existing hugepage files via --huge-unlink=never switch. Default behavior is unchanged, it can also be specified using --huge-unlink=existing for consistency. Old --huge-unlink switch is kept, it is an alias for --huge-unlink=always. Add a test case for the --huge-u

[PATCH v3 5/6] eal/linux: allow hugepage file reuse

Linux EAL ensured that mapped hugepages are clean by always mapping from newly created files: existing hugepage backing files were always removed. In this case, the kernel clears the page to prevent data leaks, because the mapped memory may contain leftover data from the previous process that was u

[PATCH v3 2/6] app/test: add allocator performance benchmark

Memory allocator performance is crucial to applications that deal with large amount of memory or allocate frequently. DPDK allocator performance is affected by EAL options, API used and, at least, allocation size. New autotest is intended to be run with different EAL options. It measures performanc

[PATCH v3 4/6] eal: refactor --huge-unlink storage

In preparation to extend --huge-unlink option semantics refactor how it is stored in the internal configuration. It makes future changes more isolated. Signed-off-by: Dmitry Kozlyuk Acked-by: Thomas Monjalon --- lib/eal/common/eal_common_options.c | 9 + lib/eal/common/eal_internal_cfg.

[PATCH v3 1/6] doc: add hugepage mapping details

Hugepage mapping is a layer of EAL malloc builds upon. There were implicit references to its details, like mentions of segment file descriptors, but no explicit description of its modes and operation. Add an overview of mechanics used on ech supported OS. Convert memory management subsections from

[PATCH v3 0/6] Fast restart with many hugepages

v3: * Improve Linux modes and anonymous mapping doc (Bruce). * Document new "dirty" field of "malloc_elem" structure (David). v2: * Fix hugepage file removal when they are no longer used. Disable removal with --huge-unlink=never as intended. Document this behavior difference. (Bruce)

RE: [EXT] Re: [dpdk-dev] [PATCH v3 2/2] app/testpmd: add queue based pfc CLI options

> -Original Message- > From: Ferruh Yigit > Sent: Thursday, February 3, 2022 9:36 PM > To: Jerin Jacob Kollanukkaran ; dev@dpdk.org; Xiaoyun > Li ; Aman Singh ; > Yuying Zhang > Cc: tho...@monjalon.net; ajit.khapa...@broadcom.com; > abo...@pensando.io; andrew.rybche...@oktetlabs.ru; > b

Re: [dpdk-dev] [PATCH v3 2/2] app/testpmd: add queue based pfc CLI options

On 1/31/2022 6:08 PM, jer...@marvell.com wrote: From: Sunil Kumar Kori Patch adds command line options to configure queue based priority flow control. - Syntax command is given as below: set pfc_queue_ctrl rx\ tx Ahh I see the order is related to the configure struct, wher

[PATCH v3 4/4] crypto: modify return value for asym session create

Rather than the asym session create function returning a session on success, and a NULL value on error, it is modified to now return int values - 0 on success or -EINVAL/-ENOTSUP/-ENOMEM on failure. The session to be used is passed as input. This adds clarity on the failure of the create function,

[PATCH v3 3/4] crypto: add asym session user data API

A user data field is added to the asymmetric session structure. Relevant API added to get/set the field. Signed-off-by: Ciara Power Acked-by: Fan Zhang Acked-by: Anoob Joseph --- v2: Corrected order of version map entries. v3: - Corrected formatting of struct comments. - Added setting user

[PATCH v3 2/4] crypto: hide asym session structure

The rte_cryptodev_asym_session structure is now moved to an internal header. This will no longer be used directly by apps, private session data can be accessed via get API. Signed-off-by: Ciara Power Acked-by: Fan Zhang --- v3: - Removed the incorrect use of void * for asym session in drivers

[PATCH v3 1/4] crypto: use single buffer for asymmetric session

Rather than using a session buffer that contains pointers to private session data elsewhere, have a single session buffer. This session is created for a driver ID, and the mempool element contains space for the max session private data needed for any driver. Signed-off-by: Ciara Power Acked-by: F

[PATCH v3 0/4] crypto: improve asym session usage

This patchset includes improvements for the asymmetric session. The main change is to the session structure, which is now a single buffer, rather than having pointers to private data elsewhere. This session structure is now hidden in an internal header, so the app will never use it directly. Some

Re: [dpdk-dev] [PATCH v3 1/2] ethdev: support queue-based priority flow control

On 1/31/2022 6:08 PM, jer...@marvell.com wrote: From: Jerin Jacob Based on device support and use-case need, there are two different ways to enable PFC. The first case is the port level PFC configuration, in this case, rte_eth_dev_priority_flow_ctrl_set() API shall be used to configure the PFC,

Re: [PATCH] app/testpmd: update raw flow to take hex input

On 1/25/2022 12:42 PM, Ferruh Yigit wrote: On 1/11/2022 5:05 AM, nipun.gu...@nxp.com wrote: From: Nipun Gupta This patch enables method to provide key and mask for raw rules to be provided as hexadecimal values. There is new parameter pattern_mask added to support this. Signed-off-by: Nipun G

Re: [PATCH] app/testpmd: skip stopped queues when forwarding

Hi Dmitry, Thanks for the patch. On 1/13/2022 2:51 PM, Dmitry Kozlyuk wrote: After "port rxq|txq stop" the stopped queue was used in forwarding nonetheless, which may cause undefined behavior in the PMD. Record the configured queue state and account for it when launching forwarding as follow

Re: [PATCH] vhost: fix null pointer dereference

On 1/29/22 20:07, Weiguo Li wrote: Fixes: 155ee3542fb1 ("vhost: improve vhost-user layer logs") Signed-off-by: Weiguo Li --- lib/vhost/vhost_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c index e8297a09eb..d032998

Re: [PATCH v2] vdpa/sfc: fix null dereference

On 1/29/22 19:07, Weiguo Li wrote: Fixes: b11961363b4a ("vdpa/sfc: support device configure and close") Signed-off-by: Weiguo Li --- drivers/vdpa/sfc/sfc_vdpa_ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/vdpa/sfc/sfc_vdpa_ops.c b/drivers/vdpa/sfc/s

Re: [PATCH v2] vhost: add vDPA resource cleanup callback

On 1/27/22 09:45, Xueming Li wrote: This patch adds vDPA device cleanup callback to release resources on vhost user connection close. Signed-off-by: Xueming Li --- lib/vhost/vdpa_driver.h | 3 +++ lib/vhost/vhost_user.c | 6 ++ 2 files changed, 9 insertions(+) diff --git a/lib/vhos

Re: [RFC v3] ethdev: introduce ethdev dump API

On 1/25/2022 1:45 PM, Min Hu (Connor) wrote: Hi, Ferruh, 在 2022/1/25 20:58, Ferruh Yigit 写道: On 1/25/2022 12:56 PM, Ferruh Yigit wrote: On 1/18/2022 3:34 PM, Ajit Khaparde wrote: On Wed, Jan 12, 2022 at 4:06 AM Ray Kinsella wrote: Min Hu (Connor) writes: Added the ethdev dump API which

Re: [PATCH 2/2] app/testpmd: fix stack overflow for EEPROM display

On 2/2/2022 10:00 AM, Singh, Aman Deep wrote: Hi Steve The patch looks ok to me. On 1/20/2022 8:29 AM, Steve Yang wrote: When the size of EEPROM exceeds the default thread stack size(8MB), e.g.: 10Mb size, it will be cashed with stack overflow. Just spelling: 10Mb/10MB, cashed/crashed Can even

RE: [PATCH v4] eventdev/eth_rx: fix memory leak when token parsing finished

Looks good to me. Thank you for catching this. Acked-by: Ganapati Kundapura > -Original Message- > From: Weiguo Li > Sent: 03 February 2022 14:20 > To: Jayatheerthan, Jay > Cc: Kundapura, Ganapati ; Naga Harish K, S > V ; dev@dpdk.org > Subject: [PATCH v4] eventdev/eth_rx: fix memory le

Re: [PATCH v2 1/1] vhost: integrate dmadev in asynchronous datapath

Hi Jiayu, On 1/24/22 17:40, Jiayu Hu wrote: Since dmadev is introduced in 21.11, to avoid the overhead of vhost DMA abstraction layer and simplify application logics, this patch integrates dmadev in asynchronous data path. Signed-off-by: Jiayu Hu Signed-off-by: Sunil Pai G --- doc/guides/pr

Re: [PATCH v6 1/2] net: add functions to calculate UDP/TCP cksum in mbuf

On 1/24/2022 12:28 PM, Xiaoyun Li wrote: Add functions to call rte_raw_cksum_mbuf() to calculate IPv4/6 UDP/TCP checksum in mbuf which can be over multi-segments. Signed-off-by: Xiaoyun Li Acked-by: Aman Singh Acked-by: Ferruh Yigit Tested-by: Sunil Pai G Hi Olivier, I am planning to proceed

Re: [PATCH v1] drivers/net: use internal API to get eth dev from name

On 2/3/2022 8:24 AM, Kumara Parameshwaran wrote: From: Kumara Parameshwaran Make changes in PMDs to use the new function where rte_eth_dev_get_port_by_name is used to get port_id to access rte_eth_devices Signed-off-by: Kumara Parameshwaran --- v1 * Replace rte_eth_get_get_port_by_name in PMDs

Re: [PATCH v1] drivers/net: use internal API to get eth dev from name

On 2/3/2022 8:24 AM, Kumara Parameshwaran wrote: From: Kumara Parameshwaran Make changes in PMDs to use the new function where rte_eth_dev_get_port_by_name is used to get port_id to access rte_eth_devices Signed-off-by: Kumara Parameshwaran --- v1 * Replace rte_eth_get_get_port_by_name in PMDs

Re: [PATCH v1] drivers/net: use internal API to get eth dev from name

On 2/3/2022 8:24 AM, Kumara Parameshwaran wrote: From: Kumara Parameshwaran Make changes in PMDs to use the new function where rte_eth_dev_get_port_by_name is used to get port_id to access rte_eth_devices Signed-off-by: Kumara Parameshwaran --- v1 * Replace rte_eth_get_get_port_by_name in PMD

Re: [PATCH v6 20/50] pdump: remove unneeded header includes

On Thu, Feb 03, 2022 at 01:11:42PM +0100, Morten Brørup wrote: > > From: Bruce Richardson [mailto:bruce.richard...@intel.com] > > Sent: Thursday, 3 February 2022 11.43 > > > > On Wed, Feb 02, 2022 at 07:21:33PM +0100, Morten Brørup wrote: > > > > From: Stephen Hemminger [mailto:step...@networkplum

RE: [PATCH v6 20/50] pdump: remove unneeded header includes

> From: Bruce Richardson [mailto:bruce.richard...@intel.com] > Sent: Thursday, 3 February 2022 11.43 > > On Wed, Feb 02, 2022 at 07:21:33PM +0100, Morten Brørup wrote: > > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > > Sent: Wednesday, 2 February 2022 18.29 > > > > > > On Wed,

Re: [PATCH v1 1/2] net/axgbe: add support for Yellow Carp ethernet device

On 1/31/2022 6:48 AM, Namburu, Chandu-babu wrote: [Public] -Original Message- From: Sebastian, Selwin Sent: Monday, January 31, 2022 11:09 AM To: dev@dpdk.org Cc: Namburu, Chandu-babu ; ferruh.yi...@intel.com Subject: [PATCH v1 1/2] net/axgbe: add support for Yellow Carp ethernet devi

Re: [PATCH 2/2] eal: support systemd service convention for runtime directory

On Wed, Feb 02, 2022 at 10:00:25PM -0800, Stephen Hemminger wrote: > Systemd.exec supports configuring the runtime directory of a service > via RuntimeDirectory=. This creates the directory with the necessary > permissions which actual service may not have if running in container. > > The change t

Re: [PATCH v1] drivers/net: use internal API to get eth dev from name

On 2/3/2022 11:09 AM, kumaraparameshwaran rathinavel wrote: Ferruh, Since in the older patch we had introduced rte_eth_dev_get_by_name patch and had been merged to dpdk-next-net, the current patch failed for the build when I submitted the patch. Is there a way to enforce it to dpdk-next-net ?

[Bug 933] Issue with parsing devargs syntax on Hyper-V platforms with DPDK-21.11

https://bugs.dpdk.org/show_bug.cgi?id=933 Bug ID: 933 Summary: Issue with parsing devargs syntax on Hyper-V platforms with DPDK-21.11 Product: DPDK Version: 21.11 Hardware: x86 OS: Linux Status:

Re: [PATCH] net/enic: adjust memory check and use in proper order

On 2/3/2022 11:11 AM, Thomas Monjalon wrote: 03/02/2022 11:57, Ferruh Yigit: On 2/2/2022 11:50 AM, Thomas Monjalon wrote: Subject: [PATCH] net/enic: adjust memory check and use in proper order Fixes: bb66d562aefc ("net/enic: share flow actions with same signature") Signed-off-by: Weiguo Li

Re: [PATCH v15 10/11] app/test: replace .sh script with .py script

26/01/2022 06:10, Jie Zhou: > - Add python script to check if system supports hugepages > - Remove corresponding .sh script > - Replace calling of .sh with corresponding .py in meson.build > > Signed-off-by: Jie Zhou > Acked-by: Dmitry Kozlyuk > --- > app/test/has-hugepage.sh | 11 --- >

Re: [PATCH] net/enic: adjust memory check and use in proper order

03/02/2022 11:57, Ferruh Yigit: > On 2/2/2022 11:50 AM, Thomas Monjalon wrote: > >>> Subject: [PATCH] net/enic: adjust memory check and use in proper order > >>> > >>> Fixes: bb66d562aefc ("net/enic: share flow actions with same signature") > >>> > >>> Signed-off-by: Weiguo Li > >>> > >>> Reviewed

Re: [PATCH v1] drivers/net: use internal API to get eth dev from name

Ferruh, Since in the older patch we had introduced rte_eth_dev_get_by_name patch and had been merged to dpdk-next-net, the current patch failed for the build when I submitted the patch. Is there a way to enforce it to dpdk-next-net ? On Thu, Feb 3, 2022 at 1:54 PM Kumara Parameshwaran < kumarapar

Re: [PATCH] net/enic: adjust memory check and use in proper order

On 2/2/2022 11:50 AM, Thomas Monjalon wrote: Subject: [PATCH] net/enic: adjust memory check and use in proper order Fixes: bb66d562aefc ("net/enic: share flow actions with same signature") Signed-off-by: Weiguo Li Reviewed-by: John Daley Applied to dpdk-next-net/main, thanks. Please coul

Re: [PATCH v6 20/50] pdump: remove unneeded header includes

On Wed, Feb 02, 2022 at 07:21:33PM +0100, Morten Brørup wrote: > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > Sent: Wednesday, 2 February 2022 18.29 > > > > On Wed, 2 Feb 2022 17:03:44 + > > Bruce Richardson wrote: > > > > > On Wed, Feb 02, 2022 at 05:45:47PM +0100, Mort

Re: [PATCH v2 0/6] Fast restart with many hugepages

On Wed, Feb 2, 2022 at 10:54 PM David Marchand wrote: > I could not check all unit tests with RTE_MALLOC_DEBUG (I passed > -Dc_args=-DRTE_MALLOC_DEBUG to meson). > mbuf_autotest fails but I reproduced the same error before the series > so I'll report and investigate this separately. > Fwiw, the fa

Re: [PATCH] test/mbuf: fix mbuf data content check

On Thu, Feb 03, 2022 at 10:39:12AM +0100, David Marchand wrote: > When allocating a mbuf, its data content is most of the time zero'd but > nothing ensures this. This is especially wrong when building with > RTE_MALLOC_DEBUG, where data is poisoned to 0x6b on free. > > This test reserves MBUF_TEST

[PATCH] test/mbuf: fix mbuf data content check

When allocating a mbuf, its data content is most of the time zero'd but nothing ensures this. This is especially wrong when building with RTE_MALLOC_DEBUG, where data is poisoned to 0x6b on free. This test reserves MBUF_TEST_DATA_LEN2 bytes in the mbuf data segment, and sets this data to 0xcc. Cal

[PATCH] net/iavf: initialize large VF setting at startup

lv_enabled is used to remember if large VF setting is configured, but its value is not initialized at startup. This can lead to a different configuration regarding the initial configuration of the PF. For example, a first start is done with 8 rx and 8 tx queues. Large VF is not needed and reta size

[PATCH v4] eventdev/eth_rx: fix memory leak when token parsing finished

The memory get from strdup should be freed when parameter parsing finished, and also should be freed when error occurs. Fixes: 814d01709328 ("eventdev/eth_rx: support telemetry") Fixes: 9e583185318f ("eventdev/eth_rx: support telemetry") Signed-off-by: Weiguo Li --- v4: * fix compilation issue

[PATCH v2 2/2] net/mlx5: remove unused metadata shift parameter

Due to updated modify field actionimmediate value buffer pattern [1] the implicit shift for the metadata is not needed anymore and should be removed. [1] commit 40c8fb1fd3b3 ("net/mlx5: update modify field action") Signed-off-by: Viacheslav Ovsiienko --- drivers/net/mlx5/mlx5_flow_dv.c | 16 +++

[PATCH v2 1/2] net/mlx5: fix metadata endianness in modify field action

As modify field action immediate source parameter the metadata should follow the CPU endianness (according to SET_META action structure format), and mlx5 PMD wrongly handled the immediate parameter metadata buffer as big-endian, resulting in wrong metadata set action with incorrect endianness. Fix

RE:[PATCH] net/enic: adjust memory check and use in proper order

Hi Monjalon, This fix only moves the memcpy after to null check. so the misplaced of memcpy and null check is reordered. I thought maybe it's too trival a fix to add more explanation. Sorry if it makes any confusion. (last mail is garbled in format) -Weiguo > -Original Message- > From:

[PATCH v1] drivers/net: use internal API to get eth dev from name

From: Kumara Parameshwaran Make changes in PMDs to use the new function where rte_eth_dev_get_port_by_name is used to get port_id to access rte_eth_devices Signed-off-by: Kumara Parameshwaran --- v1 * Replace rte_eth_get_get_port_by_name in PMDs with rte_eth_dev_get_by_name where port_id is u