From c7d92071e1dd11c45999457b16554b4abaa73b28 Mon Sep 17 00:00:00 2001
From: salmonik <salmonik@tuta.io>
Date: Sun, 2 Aug 2026 15:21:34 +0200
Subject: v0.5.5: crash reports go to a dedicated CRASHLOG USB stick

The fault handler now writes crash.log to the volume labeled CRASHLOG
(label-selected via fat::crash_vol), falling back to slot 0.  On real
hardware the boot USB may be unwritable, so a second stick labeled
CRASHLOG survives the write; the shell auto-prints the previous crash
report from it at next boot (read_crash_log resolves /disk/<uid>/crash.log
through the FAT path, since Disk nodes hold no cached children).

- fat.rs: volume_label() + crash_vol() (no allocation)
- fs.rs: write_crash_log targets crash_vol(); read_crash_log prefers the
  CRASHLOG disk node; drop now-unused first_disk()
- mkdisk.sh: --label option
- test-fault.sh: boots with a dedicated CRASHLOG stick (mkfs -F 32 -n
  CRASHLOG), verifies crash.log lands there and NOT on the ESP
---
 rsnix/src/interrupts.rs | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'rsnix/src/interrupts.rs')

diff --git a/rsnix/src/interrupts.rs b/rsnix/src/interrupts.rs
index be252df..927e4f1 100644
--- a/rsnix/src/interrupts.rs
+++ b/rsnix/src/interrupts.rs
@@ -393,6 +393,38 @@ pub(crate) struct IntFrame {
     pub(crate) ss: u64,
 }
 
+// ---------------------------------------------------------------------------
+// Fault-dump re-entry guard
+// ---------------------------------------------------------------------------
+
+/// Set when `sched::fault_dump` is running.  Any CPU exception that
+/// fires *while the dump is already in progress* (typically because the
+/// heap is corrupted and the dump path tripped over it) must never
+/// recurse into the dump — that chain (#PF → #DF → #PF) is a triple
+/// fault, which silently resets the machine with no report (black
+/// screen, firmware splash — exactly what real hardware showed).  The
+/// guard short-circuits to a raw heap-free band and a hard halt.
+static mut IN_DUMP: bool = false;
+
+pub fn enter_dump() {
+    unsafe {
+        IN_DUMP = true;
+    }
+}
+
+fn in_dump() -> bool {
+    unsafe { IN_DUMP }
+}
+
+/// Raw, heap-free fallback: a fault fired inside the fault dump.
+fn dump_guard_halt() -> ! {
+    crate::gop::dump_lines(&[
+        "!!! fault inside fault dump",
+        "!!! halting (no triple fault)",
+    ]);
+    halt();
+}
+
 /// Called from the asm common handler — dispatches to the right Rust
 /// handler and returns the frame pointer the asm should switch to (the
 /// next task's, or the same one when no switch happens).
@@ -433,9 +465,15 @@ unsafe extern "C" fn isr_dispatch(frame: &IntFrame) -> usize {
             8 => {
                 // Double fault — dump the frame (we're on the IST stack
                 // so this is safe) and halt.
+                if in_dump() {
+                    dump_guard_halt();
+                }
                 crate::sched::fault_dump("double fault", 0, frame)
             }
             14 => {
+                if in_dump() {
+                    dump_guard_halt();
+                }
                 let cr2: u64;
                 core::arch::asm!("mov {}, cr2", out(reg) cr2,
                     options(nostack, preserves_flags));
@@ -445,6 +483,9 @@ unsafe extern "C" fn isr_dispatch(frame: &IntFrame) -> usize {
             v if v < 32 => {
                 // Any other CPU exception: full dump (screen + serial),
                 // then halt the shell or abort the faulting background task.
+                if in_dump() {
+                    dump_guard_halt();
+                }
                 crate::sched::fault_dump("exception", 0, frame)
             }
             _ => fp,
-- 
cgit v1.2.3