SchOS/kernel/core/ksym.c

// SPDX-License-Identifier: Apache-2.0
//
// Naming an address.
//
// docs/architecture/debugging.md milestone D0. It is the least clever thing on that
// plan and the one everything else is worth more with: a call chain of six
// hex numbers has to be resolved by hand against a disassembly that may not
// be the build that was running, and the resolving is done at exactly the
// moment when you least want a second task.
//
// The table is built by tools/ksyms.pl from the *first* of two link passes and
// linked into the second. kernel/kernel.ld puts .ksym after .text and .rodata,
// so carrying the table cannot move the addresses recorded in it; the Makefile
// checks that rather than trusting it, by listing the text symbols of both
// passes and refusing to build if they differ.

#include "types.h"
#include "defs.h"

// Weak, and the reason is worth stating: the first link pass has no table --
// it is the input to the program that writes one. An undefined weak symbol
// links as zero, so that pass resolves these to nothing and still links. The
// same property means a kernel built with the generator removed boots fine and
// simply cannot name anything, which is a much better failure than a build
// that stops.
extern const uint32 ksym_count      __attribute__((weak));
extern const uint64 ksym_base       __attribute__((weak));
extern const uint64 ksym_textend    __attribute__((weak));
extern const uint32 ksym_addr[]     __attribute__((weak));
extern const uint32 ksym_nameoff[]  __attribute__((weak));
extern const char   ksym_names[]    __attribute__((weak));

int
ksym_ready(void)
{
  return &ksym_count != 0 && ksym_count > 0;
}

// The greatest symbol at or below addr.
//
// Returns 0 for anything outside the kernel's text, which includes every
// userspace address -- naming a user rip with a kernel symbol would be worse
// than printing the number, because it would look like an answer.
const char *
ksym_lookup(uint64 addr, uint64 *off)
{
  if (!ksym_ready())
    return 0;
  if (addr < ksym_base || addr >= ksym_textend)
    return 0;

  uint32 want = (uint32)(addr - ksym_base);

  // Binary search for the last entry <= want, in the half-open form so the
  // indices stay unsigned and nothing has to go below zero. ksym_addr[0] is 0
  // by construction -- the base *is* the first symbol -- so the invariant
  // "ksym_addr[lo] <= want" holds on entry and there is no empty case.
  uint32 lo = 0, hi = ksym_count;
  while (hi - lo > 1) {
    uint32 mid = lo + (hi - lo) / 2;
    if (ksym_addr[mid] <= want)
      lo = mid;
    else
      hi = mid;
  }

  if (off)
    *off = want - ksym_addr[lo];
  return &ksym_names[ksym_nameoff[lo]];
}

static int
put(char *buf, int cap, int n, const char *s)
{
  while (*s && n < cap - 1)
    buf[n++] = *s++;
  return n;
}

static int
puthex(char *buf, int cap, int n, uint64 v)
{
  static const char h[] = "0123456789abcdef";
  char tmp[17];
  int  i = 0;

  if (v == 0)
    return put(buf, cap, n, "0");
  while (v && i < 16) { tmp[i++] = h[v & 0xF]; v >>= 4; }
  while (i-- > 0 && n < cap - 1)
    buf[n++] = tmp[i];
  return n;
}

// "sched+0x2a", or the bare address when there is nothing to say.
//
// Writes into a caller's buffer rather than printing, because both callers
// that matter are in panic context: one is building a line for the crash
// screen and the other is building the QR payload. Neither can call cprintf.
int
ksym_fmt(char *buf, int cap, uint64 addr)
{
  uint64 off = 0;
  const char *name;
  int n = 0;

  if (cap <= 1) {
    if (cap == 1)
      buf[0] = 0;
    return 0;
  }

  name = ksym_lookup(addr, &off);
  if (!name) {
    n = put(buf, cap, n, "0x");
    n = puthex(buf, cap, n, addr);
    buf[n] = 0;
    return n;
  }

  n = put(buf, cap, n, name);
  if (off) {
    n = put(buf, cap, n, "+0x");
    n = puthex(buf, cap, n, off);
  }
  buf[n] = 0;
  return n;
}