Public Access
Safe Mode, crash reports, and a watched main loop
Every build now records at boot which version runs and, after a crash restart, which one crashed (even across a Rollback). The core dump summary (task, PC, reason, backtrace) is printed and raised as a Notification; `crash` shows it later. After 3 crash restarts in a row the firmware starts in Safe Mode: clock, Wi-Fi, Update Service and Debug Console only (SafeMode, 2 host tests). A normal restart or a minute up resets the count. The main loop is now on the task watchdog (enableLoopWDT): Arduino only watched core 0's idle task, so a stuck loop hung the device for good. The Update Service restarts into an installed update by itself if the main loop hasn't after 90 s. Debug Builds: `coredump get` and `reset` are answered by the console's own task; rdbg.py crash decodes the backtrace and rdbg.py coredump runs esp-coredump, against ELFs archived by version and digest in .pio/elves. The StorageService mutex is now made in the constructor: Safe Mode never starts that Service, and `info` crashed on the null mutex, 29 times in a row before the fix was pushed into Safe Mode over Wi-Fi. Verified on the device: crash report and full core dump decoded over Wi-Fi; Safe Mode at exactly 3 crashes, left by `reboot`; a hung loop caught by the watchdog in 5 s; `reset` from the console task. ADR 0005. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EhqxQ49eCju4CzKYNjZzwT
This commit is contained in:
@@ -4,6 +4,10 @@
|
||||
|
||||
#include <WiFi.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <esp_core_dump.h>
|
||||
#include <esp_flash.h>
|
||||
|
||||
#include "platform/console.h"
|
||||
#include "version.h"
|
||||
|
||||
@@ -43,6 +47,24 @@ bool readLine(NetworkClient& c, std::string& line, uint32_t timeoutMs) {
|
||||
return false;
|
||||
}
|
||||
|
||||
// The raw core dump partition contents, as esp-coredump reads them ("-t raw").
|
||||
void sendCoreDump(NetworkClient& client) {
|
||||
size_t addr = 0, size = 0;
|
||||
if (esp_core_dump_image_check() != ESP_OK || esp_core_dump_image_get(&addr, &size) != ESP_OK) {
|
||||
client.print("coredump: none\n");
|
||||
return;
|
||||
}
|
||||
client.printf("coredump: data %u\n", (unsigned)size);
|
||||
uint8_t buf[1024];
|
||||
for (size_t off = 0; off < size;) {
|
||||
size_t n = std::min(sizeof buf, size - off);
|
||||
if (esp_flash_read(nullptr, buf, addr + off, n) != ESP_OK) break; // the host sees a short file
|
||||
if (client.write(buf, n) != n) return;
|
||||
off += n;
|
||||
}
|
||||
client.print("coredump: end\n");
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
DebugConsole::DebugConsole(WifiService& wifi) : wifi_(wifi), lock_(xSemaphoreCreateMutex()) {}
|
||||
@@ -125,6 +147,17 @@ void DebugConsole::serve(NetworkClient& client) {
|
||||
client.stop();
|
||||
break;
|
||||
}
|
||||
if (line == "reset") { // answered here: works even when the main loop is stuck
|
||||
client.print("debug: restarting now\n");
|
||||
client.flush();
|
||||
delay(200);
|
||||
esp_restart();
|
||||
}
|
||||
if (line == "coredump get") { // binary: answered here, not by the main loop
|
||||
sendCoreDump(client);
|
||||
line.clear();
|
||||
continue;
|
||||
}
|
||||
xSemaphoreTake(lock_, portMAX_DELAY);
|
||||
bool full = commands_.size() >= kMaxQueued;
|
||||
if (!full && !line.empty()) commands_.push_back(line);
|
||||
|
||||
Reference in New Issue
Block a user