TDA2SX: how to locate the question and find the solution? SYSTEM: IPC: [DSP1] Notify recvfrom failed (Link has been severed, 67) !!!

Hello Cherry,

when App is running, and one gate link(on ipu) is turned on,  the log printed as below:

SYSTEM: IPC: [DSP1] Notify recvfrom failed (Link has been severed, 67) !!!

is that means the ipc link issue？ I had no idea about this error "link has been severed", could you kindly help to tell me where to find the documents to explain the ipc issue? thanks in advance.

environment: TDA2SX, 2G DDR, VSDK, customer made use case;

usecase txt:

Select_xxx_only -> Gate_xxx -> Alg_FrameCopy (A15) -> Dup_xxx(A15) -> Alg_Arcxxx (DSP2) -> Merge_dsp (DSP1)

Dup_xxx(A15) -> Alg_Arcxxx2 (DSP1) -> Merge_dsp (DSP1)

log as below :

Cherry Zhou：

Hi Henry,

We've got your issue and escalated to E2E for more help, the link is as below:

https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1091995/tda2sx-how-to-locate-the-question-and-find-the-solution-system-ipc-dsp1-notify-recvfrom-failed-link-has-been-severed-67

The response might be delayed. Sorry for any inconvenience. 

Thanks.

,

henry o：

Hi Cherry,Thanks for your kindly and intime help, and your warm hearted activity is appreciated.with the progress on development of App software, it is found that OS kernel, driver and base module would influence the app performance, such as memory map, mmu, inter processor communication, etc. and since there are many cores in tda2x Soc platform, systematic thinking method is introduced in problem-solving procedure. i.e. now we take tda2x as a system consists of different cores, such as DSP,IPU,CPU,GPU and they share some common resource and sometimes there are resource conflicts which will influence the performance, and these cores should maintrain a common reference such as memory map, if the memory map which they got is not consistent, the fault would occur. thanks and have a good day.

,

Cherry Zhou：

Got it and please expect the response.

,

henry o：

Hello ,Cherry,Thanks for your kindly help and endeavor to post this question to E2E forum. In these days, I've checked almost all related questions in TI website and forum, and found that many developers have met similar obstacles. and the answer is often that, illegal memory access, such as read NULL pointer, free pointer twice, etc. In this case I've met, the error occurs in some randon mode, sometimes error happens and in other times, the app runs well. so, it seems that it's not a illegal memory access case.

and one developer said that when SR0 memory space is enlarged, the mmu fault issue dispeared. but I don't know whether this solution is suitable for this case and what's the mechanism of it.

if any other answers, pls kindly inform me.

thanks and best rgds.

,

Cherry Zhou：

Hi,

Got it and we will check with our team. 

,

henry o：

Hello, Cherry,

Thanks a lot.

,

Cherry Zhou：

Hi,

The message happens when there is a remoteproc crash and the remoteproc has gone through error recovery. The existing userspace handles that were used for communicating to remote processors is no longer valid after a crash and the handles are marked as errored out, resulting in the above trace.

The remoteproc error recovery mechanism is designed to provide some debug information and perform recovery of the remote processor, but the root-cause of the crash needs to be analyzed and fixed within the firmware. 

The above indicates that there is an MMU fault errors on both DSPs and showing up at addresses 0x50d05000 and 0x50d06e00 respectively. What peripherals have you mapped at these addresses. If this is ISP related region, you need to make sure that the corresponding sub-module is powered ON.

Thanks.

,

henry o：

Hello, Cherry,thanks for your kindly help, I've recieved the reply via email and I'd plan to response this message on another link.have a good day.