[PATCH] event/dsw: optimize serving port logic

2024-01-14 Thread Mattias Rönnblom
To reduce flow migration overhead, replace the array-based representation of which set of ports are bound to a particular queue by a bitmask-based one. The maximum number of DSW event ports remains 64, but after this change can no longer easily be increased by modifying DSW_MAX_PORTS and recompile

Re: [PATCH v3 0/7] fix race-condition of proactive error handling mode

2024-01-14 Thread fengchengwen
Kindly ping. On 2023/12/5 10:30, fengchengwen wrote: > Hi Ferruh, > > I notice this patchset was delegated to you, so could you take a view? > > Thanks. > > On 2023/11/6 21:11, Chengwen Feng wrote: >> This patch fixes race-condition of proactive error handling mode, the >> discussion thread [1]

[PATCH 0/8] optimize the firmware loading process

2024-01-14 Thread Chaoyong He
This patch series aims to speedup the DPDK application start by optimize the firmware loading process in sereval places. We also simplify the port name in multiple PF firmware case to make the customer happy. Peng Zhang (8): net/nfp: add the interface for getting the firmware name net/nfp: spe

[PATCH 1/8] net/nfp: add the interface for getting the firmware name

2024-01-14 Thread Chaoyong He
From: Peng Zhang Add the interfce for getting the suitable firmware name. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/nfp/nfp_ethdev.c | 79 ++-- 1 file changed, 48 insertions(+), 31 deletions(-) diff --git a/driver

[PATCH 2/8] net/nfp: speed up the firmware loading process

2024-01-14 Thread Chaoyong He
From: Peng Zhang The previous design spent too much time checking whether the port was alive, now optimize this process and speed up the firmware loading process. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/nfp/nfp_ethdev.c | 29 +--

[PATCH 3/8] net/nfp: optimize loading the firmware process

2024-01-14 Thread Chaoyong He
From: Peng Zhang Add the skip loading firmware flag, when any other port is alive, this flag will be true. Also make sure the order of starting the keepalive is earlier than getting the firmware status. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/n

[PATCH 4/8] net/nfp: enlarge the range of skipping loading the firmware

2024-01-14 Thread Chaoyong He
From: Peng Zhang Enlarge the range of skip loading firmware by add the condition there is no port with the condition of abnormal. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/nfp/nfp_ethdev.c | 30 -- 1 file changed, 24 i

[PATCH 5/8] net/nfp: add the step of clearing the beat time

2024-01-14 Thread Chaoyong He
From: Peng Zhang Add the step of clearing the beat time of specific port when DPDK exit. Add the step of clearing the beat time of other ports when reload firmware. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/nfp/nfp_ethdev.c | 25 +

[PATCH 6/8] net/nfp: add the elf module

2024-01-14 Thread Chaoyong He
From: Peng Zhang Add the elf module, which can get mip information from the firmware ELF file. Signed-off-by: Peng Zhang Reviewed-by: Chaoyong He Reviewed-by: Long Wu --- drivers/net/nfp/meson.build |1 + drivers/net/nfp/nfpcore/nfp_elf.c | 1078 + drive

[PATCH 7/8] net/nfp: reload the firmware only when firmware changed

2024-01-14 Thread Chaoyong He
From: Peng Zhang Add the interfaces of getting firmware build time from BSP and ELF file, only reloading the firmware when the build time is different, which means the firmware has changed. This will accelerate the average startup time for both multi-PF and single-PF firmware. Signed-off-by: Pe

[PATCH 8/8] net/nfp: simplify the port name for multiple PFs

2024-01-14 Thread Chaoyong He
From: Peng Zhang For the firmware which does not support multiple PF feature, there are multiple PFs corresponding to a single PCI BDF address, so we have to distinguish them by using a '_port*' postfix for the device name. For the firmware which supports multiple PFs feature, there is only one

Re: [PATCH v2 00/16] verify strdup return value

2024-01-14 Thread fengchengwen
Friendly ping. On 2023/11/10 18:01, Chengwen Feng wrote: > This patchset mainly fix the return value of strdup not checked which > may lead to segment fault. It also include two commits which fix memory > leak of strdup. > > Chengwen Feng (16): > eal: verify strdup return value > bus/dpaa: ve

RE: [EXT] [PATCH] app/test-crypto-perf: add missed resubmission fix

2024-01-14 Thread Suanming Mou
> -Original Message- > From: Anoob Joseph > Sent: Wednesday, January 10, 2024 10:47 PM > To: Suanming Mou > Cc: dev@dpdk.org; sta...@dpdk.org; ciara.po...@intel.com > Subject: RE: [EXT] [PATCH] app/test-crypto-perf: add missed resubmission fix > > Hi Suanming, > > Please see inline.

RE: 21.11.6 patches review and test

2024-01-14 Thread Xu, HailinX
> -Original Message- > From: Kevin Traynor > Sent: Wednesday, December 20, 2023 9:23 PM > To: sta...@dpdk.org > Cc: dev@dpdk.org; Abhishek Marathe ; > Ali Alnubani ; benjamin.wal...@intel.com; David > Christensen ; Hemant Agrawal > ; Stokes, Ian ; Jerin Jacob > ; Mcnamara, John ; Ju- > Hyo