NETGEAR is aware of a growing number of phone and online scams. To learn how to stay safe click here.
Forum Discussion
BUG: KERNEL CRASH in 9.13.1.2, Orbi 970
After being up about 28 hours, one of my 970 satellites did a restart. The bug log reports that the reason was a kernel crash.
It was at about 1:30 AM local time, so little or no action going o...
I assume you have 970 Orbi series? Try these steps and wait to see if it fixes the crashes:
- 9.13.2.1 is the latest version - https://www.netgear.com/support/download/?model=RBE973S&_ga=2.38375275.974127454.1697786862-475167439.1689166105 Update manually or via the router admin web page (Advanced Tab -> Administration-> Firmware Update
- On the router admin web page, Advanced tab, Administration -> Logs: In the section "Include in Logs, turn everything OFF. At the top, click the Clear Log button.
Then let it run and see if the panics continue. If they do, open a support ticket - get the ticket number and post it here, I'll also send that to our engineering contact who may have some ideas.
I also asked ChatGPT with a stacktrace attached, and here's what it said:
That’s a real kernel panic dump — and it gives a lot of clues about what went wrong inside your Orbi 970.
Let’s break it down clearly 👇
---
🧠 Plain-English Summary
Your Orbi 970 crashed because a system process (d2d) tried to write to a null pointer (address 00000000) — meaning it attempted to access memory that doesn’t exist.
This caused the Linux kernel to panic and halt to prevent further damage.
So in short:
> A software component in the router firmware hit a programming bug — likely a memory management or networking issue — causing a system crash.
---
⚙️ Technical Details
From the dump:
Unable to handle kernel NULL pointer dereference at virtual address 00000000
Internal error: Oops: 805 [#1] PREEMPT SMP ARM
Process d2d (pid: 5457)
PC is at skb_queue_tail+0x1c/0x48
Crash function: skb_queue_tail() — this is a Linux kernel function that handles network socket buffers.
Caller: unix_dgram_sendmsg() → part of the inter-process communication (IPC) system using UNIX domain sockets.
Process: d2d — this is almost certainly “Device-to-Device” communication service used by Orbi mesh nodes to talk to each other.
Fault: Null pointer dereference → means some buffer or pointer wasn’t properly initialized or got freed prematurely.
So the D2D (mesh communication) process tried to queue a network packet into a null socket buffer.
That’s a firmware bug, not a hardware failure.
---
🔄 Likely Cause
This is almost always due to:
A firmware bug in the D2D or NSS (Qualcomm networking subsystem) code.
Could be triggered by mesh sync, Wi-Fi backhaul instability, or a corrupted configuration.
The “Tainted: P” line (Tainted: P) means it’s using proprietary Qualcomm/Netgear kernel modules, so standard Linux debugging is limited.