SchOS/kernel/core/panic.c

// SPDX-License-Identifier: Apache-2.0
//
// PSOGM — the SchOS crash screen.
//
// The name is a nod to the Amiga's "Guru Meditation", but nothing else about
// this is a nod to 1985. Three things it is built around:
//
// *It takes the whole screen.* An earlier version dimmed what was there and
// floated a panel over it, on the argument that a crash screen which wipes the
// display tells you the machine is gone while one that leaves your work visible
// tells you it stopped. That looked good and was wrong: the thing is called a
// Purple Screen, and half a screen of somebody's abandoned work behind the
// report is a distraction at the worst possible moment.
//
// *It is not frightening.* No red, no capitals, no "FATAL". A calm sentence,
// the system's own mark, and then the facts. Whoever is reading this is
// already having a bad time.
//
// *It says considerably more than it needs to.* The screen is the only artefact
// of a kernel panic — there is no core dump and no log to go back to — so
// everything cheap to collect is collected: which CPU, which process, how far
// into the boot, where the kernel is loaded, and a call chain. Anything left
// out here is gone.
//
// Everything is also written to the serial console, in the same order. That is
// what tools/bootcheck.ps1 reads, and it is what you get when the crash happens
// before there is a framebuffer at all.

#include "types.h"
#include "defs.h"
#include "gfx.h"
#include "param.h"
#include "memlayout.h"
#include "mmu.h"
#include "x86.h"
#include "proc.h"
#include "spinlock.h"
// Purple, because the name says so, and white on it because nothing else is
// legible at every brightness a monitor might be set to. The palette lives in
// theme.h with everything else; this file used to keep its own copy under the
// same names but with different values, which meant theme.h described a crash
// screen nobody had ever seen.
#include "theme.h"
#include "logo.h"   /* LOGO_H -- the mark's height, for the layout below */
#include "qr.h"

extern uint ticks;
extern int  panicked;

/* ------------------------------------------------------------------ */
/* Small formatting helpers                                            */
/*                                                                     */
/* cprintf goes to the console, which during a panic is also the screen */
/* being painted over -- so the panel builds its strings itself and     */
/* places them with gfx_text_at.                                        */
/* ------------------------------------------------------------------ */

static char *
put_str(char *p, char *end, const char *s)
{
  while (*s && p < end - 1)
    *p++ = *s++;
  *p = '\0';
  return p;
}

static char *
put_dec(char *p, char *end, uint64 v)
{
  char tmp[24];
  int  i = 0;
  if (v == 0)
    tmp[i++] = '0';
  while (v && i < (int)sizeof(tmp)) { tmp[i++] = '0' + (v % 10); v /= 10; }
  while (i-- && p < end - 1)
    *p++ = tmp[i];
  *p = '\0';
  return p;
}

static char *
put_hex(char *p, char *end, uint64 v, int digits)
{
  const char *d = "0123456789abcdef";
  if (p < end - 2) { *p++ = '0'; *p++ = 'x'; }
  for (int i = digits - 1; i >= 0 && p < end - 1; i--)
    *p++ = d[(v >> (i * 4)) & 0xF];
  *p = '\0';
  return p;
}

/* ------------------------------------------------------------------ */
/* The report                                                          */
/* ------------------------------------------------------------------ */

struct field {
  const char *label;
  char        value[72];
};

#define NFIELD 10

static struct field fields[NFIELD];
static int          nfields;

static struct field *
field(const char *label)
{
  if (nfields >= NFIELD)
    return &fields[NFIELD - 1];
  struct field *f = &fields[nfields++];
  f->label = label;
  f->value[0] = '\0';
  return f;
}

// Collect everything worth knowing while the machine is still in the state
// that produced the fault. Interrupts are already off and no lock is taken:
// a panic that deadlocks trying to report itself tells you nothing at all.
// A short, shoutable name for the failure, derived from the panic message
// rather than declared at every call site.
//
// Windows stop codes are genuinely useful: they are the thing you search for,
// and they stay the same across builds while the prose around them changes.
// Taking the message up to its first colon (or its first few words) gets that
// for free -- "sysrq: crash requested" becomes SYSRQ, "short filewrite" becomes
// SHORT_FILEWRITE -- with no risk of a call site forgetting to supply one.
static void
stop_code(char *out, int cap, const char *reason)
{
  int n = 0;
  for (int i = 0; reason[i] && n < cap - 1; i++) {
    char c = reason[i];
    if (c == ':')
      break;
    if (c == ' ' || c == '\t') {
      if (n == 0 || out[n-1] == '_')
        continue;
      out[n++] = '_';
      continue;
    }
    if (c >= 'a' && c <= 'z') c = c - 'a' + 'A';
    if ((c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_')
      out[n++] = c;
  }
  while (n > 0 && out[n-1] == '_')
    n--;
  if (n == 0)
    { out[n++] = 'P'; out[n++] = 'A'; out[n++] = 'N'; out[n++] = 'I'; out[n++] = 'C'; }
  out[n] = '\0';
}

static void
gather(char *reason, addr_t *pcs, int npcs)
{
  char *e;
  struct field *f;

  nfields = 0;

  f = field("Stop code");
  stop_code(f->value, sizeof(f->value), reason);

  f = field("Reason");
  put_str(f->value, f->value + sizeof(f->value), reason);

  f = field("CPU");
  e = f->value + sizeof(f->value);
  put_dec(f->value, e, mycpu() ? (uint64)mycpu()->id : 0);
  if (!mycpu())
    put_str(f->value, e, "unknown (very early boot)");

  f = field("Process");
  e = f->value + sizeof(f->value);
  if (myproc()) {
    char *p = put_str(f->value, e, myproc()->name);
    p = put_str(p, e, "  pid ");
    put_dec(p, e, (uint64)myproc()->pid);
  } else {
    put_str(f->value, e, "none -- in the kernel, not on anybody's behalf");
  }

  f = field("Uptime");
  e = f->value + sizeof(f->value);
  {
    char *p = put_dec(f->value, e, (uint64)ticks);
    p = put_str(p, e, " ticks (about ");
    p = put_dec(p, e, (uint64)ticks / HZ);
    put_str(p, e, " s)");
  }

  // Every address below is a link-time address. Printing where the kernel
  // actually sits is what lets addr2line resolve them afterwards, and it is
  // the single most useful line here when the trace is all you have.
  f = field("Kernel base");
  e = f->value + sizeof(f->value);
  put_hex(f->value, e, (uint64)KERNBASE, 16);

  f = field("Fault PC");
  e = f->value + sizeof(f->value);
  if (npcs > 0 && pcs[0])
    put_hex(f->value, e, (uint64)pcs[0], 16);
  else
    put_str(f->value, e, "unavailable");
}

/* ------------------------------------------------------------------ */
/* The QR code                                                         */
/*                                                                     */
/* A panic report is only worth what can be carried away from it, and  */
/* at this point there is no network, no log to write to, and often no */
/* second machine on the desk. Photographing the screen works but      */
/* turns a call chain into something that has to be retyped by hand,   */
/* with sixteen hex digits per frame and no way to tell 8 from B.      */
/*                                                                     */
/* A phone camera is a working out-of-band channel that needs no       */
/* driver on our side at all. See kernel/core/qr.c.                    */
/* ------------------------------------------------------------------ */

// Deliberately not a URL. This encodes the report itself, so it goes wherever
// the person holding the phone decides -- and reaches nothing on its own.
//
// Compact because the budget is 134 bytes for the largest symbol this encoder
// builds, and a crash with a deep call chain is exactly when the budget is
// tightest. Two decisions buy most of the room: frames are stored as offsets
// from the kernel base rather than absolute addresses, which halves 16 hex
// digits to 8, and the fields are single letters. The base is included, so
// nothing is lost -- addr2line wants the link-time address and can be given it.
//
// Fields are appended in priority order and the loop simply stops when the
// buffer is full, so a long reason string costs call-chain depth rather than
// producing a report that will not encode.
static int
build_qr_payload(char *buf, int cap, char *reason, addr_t *pcs, int npcs)
{
  char *p = buf, *end = buf + cap;

  // Magic and format version, so whatever reads this later can tell what it is
  // looking at and can change the layout without ambiguity.
  p = put_str(p, end, "SXPSOGM1\n");

  // The reason, not the stop code: the stop code is derived from the reason by
  // stop_code() and carries strictly less, so encoding both would spend bytes
  // on something the reader can recompute.
  //
  // Held back from the end of the buffer so that a long message costs some of
  // the call chain but never all of it. A report with a sentence and no
  // addresses is much harder to act on than one with addresses and a truncated
  // sentence.
  {
    char *reason_end = end - 34;      // three frames and their separators
    if (reason_end > p)
      p = put_str(p, reason_end, reason);
  }

  p = put_str(p, end, "\nc");
  p = put_dec(p, end, mycpu() ? (uint64)mycpu()->id : 0);
  p = put_str(p, end, " p");
  p = put_dec(p, end, myproc() ? (uint64)myproc()->pid : 0);
  p = put_str(p, end, " t");
  p = put_dec(p, end, (uint64)ticks);
  if (myproc()) {
    p = put_str(p, end, " ");
    p = put_str(p, end, myproc()->name);
  }

  p = put_str(p, end, "\nb");
  p = put_hex(p, end, (uint64)KERNBASE, 16);

  p = put_str(p, end, "\n");
  for (int i = 0; i < npcs && pcs[i]; i++) {
    // Nine bytes: eight hex digits and the separator. Stopping here rather than
    // letting put_hex truncate matters -- half an address in a crash report is
    // worse than one fewer address, because it looks like a real one.
    if (end - p < 10)
      break;
    if (i)
      p = put_str(p, end, " ");
    // put_hex prefixes "0x", which is 14 wasted bytes across seven frames.
    {
      const char *d = "0123456789abcdef";
      uint64 off = (uint64)pcs[i] - (uint64)KERNBASE;
      for (int k = 7; k >= 0; k--)
        *p++ = d[(off >> (k * 4)) & 0xF];
      *p = '\0';
    }
  }

  return (int)(p - buf);
}

// One static symbol rather than a local: struct qr is about 3.4 KB and the
// panic path runs on whatever stack the fault left behind, which may not have
// that much room. It is only ever touched here, after everything else has
// stopped.
static struct qr panic_qr;

// Returns the width used, so the text column knows what it may not overlap.
static int
draw_qr_panel(int sw, int sh, int ch, char *reason, addr_t *pcs, int npcs)
{
  char payload[QR_MAX_BYTES];
  int n = build_qr_payload(payload, sizeof(payload), reason, pcs, npcs);

  if (n <= 0 || qr_encode(&panic_qr, (unsigned char *)payload, n) != 0)
    return 0;

  // Four modules of quiet zone, which the standard requires and which decoders
  // genuinely need -- without it many will not find the symbol at all.
  const int quiet = 4;
  int cells = panic_qr.size + 2 * quiet;

  // Scale to about a quarter of the display, then clamp. The lower bound is
  // what a phone can still resolve from a photograph of a monitor; the upper
  // bound stops the thing dominating a screen whose actual job is the text.
  int scale = (sw / 4) / cells;
  if (scale < 3) scale = 3;
  if (scale > 8) scale = 8;

  int card = cells * scale;
  int x0 = sw - card - sw / 24;
  int y0 = sh / 8;

  gfx_fill_rect(x0, y0, card, card, PSOGM_CARD);
  for (int y = 0; y < panic_qr.size; y++)
    for (int x = 0; x < panic_qr.size; x++)
      if (panic_qr.mod[y][x])
        gfx_fill_rect(x0 + (x + quiet) * scale, y0 + (y + quiet) * scale,
                      scale, scale, PSOGM_INK);

  gfx_text_at(x0, y0 + card + ch, "Scan for a text copy", PSOGM_DIM);
  gfx_text_at(x0, y0 + card + ch * 2 + 2, "of this report.", PSOGM_DIM);

  return card + sw / 24;
}

// The frame pointers, one per line, as one string per row.
static void
trace_line(char *buf, int cap, int i, addr_t pc)
{
  char *e = buf + cap;
  char *p = put_str(buf, e, "  #");
  p = put_dec(p, e, (uint64)i);
  p = put_str(p, e, i < 10 ? "   " : "  ");
  p = put_hex(p, e, (uint64)pc, 16);

  // And the name, when the kernel is carrying a symbol table. This is the
  // difference between a crash screen you photograph and then decode against
  // a disassembly, and one you can read. See kernel/core/ksym.c.
  if (ksym_ready()) {
    char name[64];
    if (ksym_lookup((uint64)pc, 0)) {
      ksym_fmt(name, sizeof(name), (uint64)pc);
      p = put_str(p, e, "  ");
      put_str(p, e, name);
    }
  }
}

/* ------------------------------------------------------------------ */

static void
paint(char *reason, addr_t *pcs, int npcs)
{
  int sw, sh;
  gfx_dims(&sw, &sh);

  int ch = gfx_char_h();
  int cw = gfx_char_w();

  // The whole display, one colour. An earlier version dimmed the previous
  // screen and floated a panel over it, which looked good and was wrong: the
  // thing is called a Purple Screen, and half a screen of somebody's abandoned
  // work behind the report is a distraction at the worst possible moment.
  gfx_clear(PSOGM_BG);
  // Glyphs are drawn with their background filled, so the console's cream has
  // to become the background or every line of text arrives in its own box.
  gfx_set_bg(PSOGM_BG);

  // The symbol goes first, because it decides how much width the text has. It
  // is drawn before anything can fail: if the encoder refuses the payload the
  // screen simply has no card and the report is unchanged.
  draw_qr_panel(sw, sh, ch, reason, pcs, npcs);

  int left = sw / 8;
  if (left > 110) left = 110;
  int y = sh / 8;

  // Shift, the system's own mark, from the same include/logo.h the loader
  // splash and the boot console draw. It replaces Guru, a chamfered face that
  // lived only here and was drawn from primitives a few lines up this file.
  //
  // Guru was an *icon*: a pictogram denoting one state, with a face. The
  // argument for it was identity -- ":(" is recognisably Microsoft's, and a
  // crash screen is the single screenshot most likely to leave the machine, so
  // it is the worst place to be wearing somebody else's face. That argument
  // holds. It just does not follow that the answer is a second mark. The logo
  // already signs the system, it is already the thing on the splash the
  // machine started with, and a reader who has seen it twice before the crash
  // recognises it faster than a face they have never seen.
  //
  // A fixed 128 px rather than scaled: the mask is 128x128 and there is no
  // resampler here. The face was scalable and that bought nothing -- it was
  // drawn at one size.
  gfx_draw_logo(left, y, PSOGM_FG, PSOGM_BG);
  y += LOGO_H + ch * 2;

  // Left-aligned, not centred. Centred text reads as a poster; this is a
  // report, and a report is read down the left edge.
  gfx_text_at(left, y, "SchOS ran into a problem and needs to restart.",
              PSOGM_FG);
  y += ch + ch / 2;
  gfx_text_at(left, y, "Nothing on your disks was touched by this.",
              PSOGM_DIM);

  // A rule in the boot splash's accent, the same width as the one under the
  // wordmark there, tying this screen to the one the machine started with.
  //
  // Equal space above and below on purpose: at any less it sits close enough to
  // the line above to read as an underline of that sentence rather than as a
  // divider before the facts.
  y += ch * 2;
  gfx_fill_rect(left, y, 120, 2, SCH_ACCENT);
  y += ch;

  // Facts: quiet labels down the left, bright values in a second column.
  int vx = left + 14 * cw;
  for (int i = 0; i < nfields; i++) {
    gfx_text_at(left, y, fields[i].label, PSOGM_DIM);
    gfx_text_at(vx, y, fields[i].value, PSOGM_FG);
    y += ch + 2;
  }

  y += ch;
  gfx_text_at(left, y, "Call chain", PSOGM_DIM);
  y += ch + 2;

  for (int i = 0; i < npcs && pcs[i]; i++) {
    char line[48];
    trace_line(line, sizeof(line), i, pcs[i]);
    gfx_text_at(vx - 3 * cw, y, line, PSOGM_FG);
    y += ch;
    if (y > sh - ch * 6)
      break;
  }

  // Three closing lines, bottom left. The first used to be an addr2line
  // command, which the call chain above no longer needs -- it prints names.
  //
  // What replaces it is the thing nobody would guess: **this screen is no
  // longer the only copy.** The log survives into the next boot (see
  // include/klog.h), so the right instruction on a crash screen is now
  // "restart and read it" rather than "photograph this".
  //
  // Kept under about 45 characters each: the QR card is on the right, and the
  // 62-character command line this replaces used to run underneath it.
  gfx_text_at(left, sh - ch * 4,
              "This report is in /proc/kmsg after a restart.", PSOGM_DIM);
  gfx_text_at(left, sh - ch * 4 + ch + 4,
              "schdbg, or Ctrl-G on the console, asks more.", PSOGM_DIM);
  gfx_text_at(left, sh - ch * 4 + (ch + 4) * 2,
              "PSOGM  --  Purple Screen of Guru Meditation", PSOGM_DIM);
}

// Same report, down the serial line. This is the copy that survives: it is what
// bootcheck reads, and the only one that exists when the framebuffer does not.
static void
report_serial(char *reason, addr_t *pcs, int npcs)
{
  cprintf("\n");
  cprintf("  :(\n\n");
  cprintf("  SchOS ran into a problem and needs to restart.\n");
  cprintf("  PSOGM -- Purple Screen of Guru Meditation\n\n");

  for (int i = 0; i < nfields; i++) {
    // Pad the label out so the values line up, without a printf width
    // specifier -- cprintf has no such thing.
    int n = 0;
    while (fields[i].label[n]) n++;
    cprintf("    %s", fields[i].label);
    for (int pad = n; pad < 14; pad++)
      cprintf(" ");
    cprintf("%s\n", fields[i].value);
  }

  cprintf("\n    Call chain\n");
  for (int i = 0; i < npcs && pcs[i]; i++) {
    char name[64];
    ksym_fmt(name, sizeof(name), (uint64)pcs[i]);
    cprintf("      #%d  %p  %s\n", i, pcs[i], name);
  }

  if (!ksym_ready())
    cprintf("\n    Resolve with: addr2line -e build/kernel/kernel <address>\n");
  else
    cprintf("\n    For a line number: addr2line -e build/kernel/kernel <address>\n");

  // Where to go next. Worth printing even though the machine is about to stop,
  // because this text is also what ends up in the log -- and the log is the
  // thing being pointed at.
  cprintf("    This report is in /proc/kmsg after a restart.\n");
  cprintf("    Then: schdbg whose <addr> -- who owns a page\n");
  cprintf("          schdbg watch <addr> -- who writes to one\n");
  cprintf("          Ctrl-G on the console -- every view, no shell needed\n");
  cprintf("    Reason: %s\n", reason);
  cprintf("    System halted.\n");
}

__attribute__((noreturn))
void
panic(char *s)
{
  addr_t pcs[10];

  cli();
  // Stop every other path from writing to the console. consputc checks this
  // and spins, which is what keeps another CPU from painting over the report
  // while it is being drawn.
  cons_panic_mode();

  for (int i = 0; i < 10; i++)
    pcs[i] = 0;
  getcallerpcs(&s, pcs);

  gather(s, pcs, 10);
  report_serial(s, pcs, 10);

  if (gfx_ready()) {
    paint(s, pcs, 10);
    // And on every other display the machine has, including the ones the
    // kernel handed to a process. Deliberately after the console's copy: a
    // fault in there must not cost the screen that is already right.
    display_panic_present();
  }

  panicked = 1;
  for (;;)
    hlt();
}