[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: Trying to crack the Firefox crashing issue



On 10/5/25 12:46 am, Ken Cunningham wrote:
chatgpt has opinions.

I put in my original run and backtrace from Nov 2023, and chatgpt had the following to say:

The other night I was wonder if AI could assist in tracking down the issue. Given WASM used to work AFAIK, perhaps some AI assisted bisecting is in order.

Thread 1 "firefox" received signal SIGSEGV, Segmentation fault.
i32_load8_u (addr=2014643200, mem=<optimized out>) at rlbox.wasm.c:146

Though I didn't see i32_load8_u come up in my trace it does show up if I single step to the crash.

==========================


The backtrace you've posted shows a **segmentation fault** (`SIGSEGV`) happening in Firefox when running under GDB on a PowerPC64 Linux system. The crash occurs in code generated by RLBox, specifically in `i32_load8_u` within `rlbox.wasm.c`, which appears to be part of a **WebAssembly sandboxed execution environment**. Here's a breakdown:

A breakdown in markdown. :-D



### Key Observations:

* **Faulting function**: `i32_load8_u (addr=2014643200)` — the address accessed is very large and likely invalid. * **Sandbox**: RLBox is being used — this is a sandboxing framework to isolate parts of code, such as XML parsers or other libraries, via WebAssembly.
* **Fault path**:

Interesting it mentions XML here.



  * `w2c_rlbox_getEncodingIndex` → `w2c_rlbox_MOZ_XmlInitEncodingNS_0` → `w2c_rlbox_prologInitProcessor` → eventually called via `nsExpatDriver::ParseChunk`   * This indicates the crash is happening during XML parsing inside the sandbox, possibly parsing a stylesheet (`global.css` is mentioned in the XML).

### Possible Causes:

1. **Invalid pointer dereference** inside the sandbox — RLBox is trying to access memory at an address it shouldn't. 2. **Improper input data or parser state**, especially related to XML or encoding parsing.
3. **Compiler bug or undefined behavior** in sandboxed code generation.
4. **Architecture-specific issue** (PowerPC64) — most testing happens on x86/x86\_64, so bugs may surface on less common platforms.

### What You Can Do:

1. **Check if the address `2014643200` makes sense** in your sandbox — it's very high and likely an invalid offset into the RLBox memory.
2. **Enable RLBox debugging**:

It's exactly an invalid offset. Confirmed by the crash itself. The EA is out of range.



   * Build Firefox with `--enable-debug` and set RLBox-related environment variables like:

     ```bash
     MOZ_RLBOX_SANDBOXED=1
     MOZ_RLBOX_VERBOSE=1
     ```
   * This might produce logs that indicate why the memory is invalid.
3. **Verify XML input**: Try to locate and examine the file or network resource being parsed — malformed or unexpected input could cause faults. 4. **Update Firefox**: Ensure you’re running the latest version of Firefox and all dependencies.
5. **File a bug**:

   * This may be a platform-specific bug. Mozilla tracks RLBox bugs [on Bugzilla](https://bugzilla.mozilla.org/). Include architecture (PowerPC64), the RLBox call path, and the faulty address.

Good luck! GPT :-D



Would you like help inspecting the specific value at `addr=2014643200` or guidance on how to reproduce the crash more minimally?

Yes. Swap it around. :-)


--
My regards,

Damien Stewart.


Reply to: