SchOS/kernel/dev/cdev.c

#include "types.h"
#include "defs.h"
#include "param.h"
#include "spinlock.h"
#include "sleeplock.h"
#include "fs.h"
#include "file.h"
#include "x86.h"
#include "errno.h"

extern int consoleread(struct inode*, uint64, char*, int);
extern int consolewrite(struct inode*, uint64, char*, int);
extern int mouseread(struct inode*, uint64, char*, int);

// --- /dev/random and /dev/urandom -------------------------------------------
//
// This was a linear congruential generator seeded with a constant, which means
// **every boot produced the same bytes in the same order**. Not weak: the same.
// A program asking for a key, a nonce, a temporary filename or a hash seed got
// one it shared with every other SchOS machine that had ever run.
//
// What is here now is still not a CSPRNG and does not pretend to be. It is an
// LCG that is *seeded* from something real and re-stirred from the cycle
// counter on every read, which fixes the one property that made the old one
// dangerous rather than merely poor. See "What it does not do" in
// docs/architecture/devices.md.
static uint64 rseed;
static int    rseed_ready;
static void   rseed_init(void);

// RDRAND, if this CPU has it. CPUID leaf 1, ECX bit 30.
//
// Checked rather than assumed: the instruction faults with #UD on a CPU that
// does not implement it, and "the random device is a kernel panic" is a worse
// failure than a weak seed.
static int
rdrand64(uint64 *out)
{
  uint32 a, b, c, d;
  unsigned char ok = 0;
  uint64 v = 0;

  cpuid_leaf(1, &a, &b, &c, &d);
  if (!(c & (1u << 30)))
    return 0;

  // Ten tries, per Intel's own guidance: the instruction is allowed to fail
  // when its entropy pool is momentarily empty, and it says so in CF.
  for (int i = 0; i < 10; i++) {
    asm volatile("rdrand %0; setc %1" : "=r"(v), "=qm"(ok) :: "cc");
    if (ok) { *out = v; return 1; }
  }
  return 0;
}

// Seeded at boot rather than on the first read.
//
// Lazy would work, but it puts the one line that says where the entropy came
// from in the middle of whatever the machine was doing hours later, and it
// makes the first reader pay for the CPUID. Called from main(); the lazy path
// stays as a belt-and-braces for anything that reads before init runs.
void
random_init(void)
{
  if (!rseed_ready)
    rseed_init();
}

static void
rseed_init(void)
{
  uint64 v;

  rseed_ready = 1;
  if (rdrand64(&v)) {
    rseed = v;
    kinfo("random: seeded from RDRAND\n");
    return;
  }

  // No RDRAND. The cycle counter is the only thing here that is different on
  // every boot and not written down anywhere -- it is not entropy in any
  // serious sense, but it is not a constant either, which was the whole
  // problem. Mixed with the wall clock so that two machines starting at the
  // same instant do not agree.
  rseed = rdtsc();
  rseed ^= boot_epoch * 0x9E3779B97F4A7C15ULL;
  rseed ^= (uint64)(uintptr_t)&rseed;
  if (rseed == 0)
    rseed = 0x9E3779B97F4A7C15ULL;
  kinfo("random: no RDRAND; seeded from the cycle counter and the clock\n");
}

int
nullwrite(struct inode *ip, uint64 off, char *dst, int n)
{
  return n;
}

int
nullread(struct inode *ip, uint64 off, char *dst, int n)
{
  return 0;
}

int
zeroread(struct inode *ip, uint64 off, char *dst, int n)
{
  memset(dst, 0, n);
  return n;
}

int
randomread(struct inode *ip, uint64 off, char *dst, int n)
{
  if(!rseed_ready)
    rseed_init();

  for(int i = 0; i < n; i++){
    // Re-stirred from the cycle counter every byte, so two reads a moment
    // apart do not continue one sequence -- and so that a process cannot
    // predict the next caller's bytes from its own.
    rseed ^= rdtsc();
    rseed = rseed * 6364136223846793005ULL + 1442695040888963407ULL;
    dst[i] = (rseed >> 33) & 0xFF;
  }
  return n;
}

// /dev/full — reads as an endless run of zero bytes, every write fails with
// ENOSPC. Programs use it to exercise their out-of-disk-space paths.
int
fullwrite(struct inode *ip, uint64 off, char *dst, int n)
{
  return -ENOSPC;
}

int
mousewrite(struct inode *ip, uint64 off, char *dst, int n)
{
  return n;
}

int
memread(struct inode *ip, uint64 off, char *dst, int n)
{
  switch(ip->minor) {
    case 1: return consoleread(ip, off, dst, n); 
    case 2: return nullread(ip, off, dst, n);    
    case 3: return consoleread(ip, off, dst, n);
    /* 10 = /dev/tty, 11..16 = /dev/tty1..tty6. consoleread resolves the
       minor to a terminal; see vt_for_minor(). */
    case 10: case 11: case 12: case 13: case 14: case 15: case 16:
            return consoleread(ip, off, dst, n);
    case 5: return zeroread(ip, off, dst, n);
    case 7: return zeroread(ip, off, dst, n);   // /dev/full reads as zeros
    case 8: 
    case 9: return randomread(ip, off, dst, n);  
    // Not "operation not permitted", which is what -1 means once it reaches
    // userspace. There is no device on this minor.
    default: return -ENODEV;
  }
}

int
memwrite(struct inode *ip, uint64 off, char *dst, int n)
{
  switch(ip->minor) {
    case 1: return consolewrite(ip, off, dst, n);
    case 10: case 11: case 12: case 13: case 14: case 15: case 16:
            return consolewrite(ip, off, dst, n);
    case 7: return fullwrite(ip, off, dst, n);   // /dev/full: always ENOSPC
    case 2:
    case 5:
    case 8:
    case 9: return nullwrite(ip, off, dst, n); 
    default: return -ENODEV;
  }
}

struct devsw devsw[] = {
  [0] = { 0, 0 },
  [1] = { memread,   memwrite   },
  // /dev/fb0 (major 2) — the framebuffer, kernel/dev/fb.c. This used to be
  // { nullread, nullwrite }, so writing pixels to it succeeded and did
  // nothing.
  // The close hook gives the text console its screen back when whatever was
  // drawing on the framebuffer exits — see fbclose().
  [2] = { fbread,    fbwrite,   0, fbclose },
  [3] = { mouseread, mousewrite },
  [4] = { 0, 0 },
  // /dev/tty (major 5) — alias for the console
  [5] = { memread,   memwrite   },
  // /proc status files (major 6) — see kernel/dev/procfs.c
  [6] = { procread,  procwrite  },
  // /dev/input/eventN (major 7) — raw evdev events, kernel/dev/input.c. The
  // minor is the device index, so event0 is the keyboard and event1 the mouse.
  [7] = { inputread, inputwrite, inputready, inputclose, inputopen },
  // /dev/hdN (major 8) — raw disks, kernel/dev/disk.c. The minor is the IDE
  // device number. No `ready` hook: a disk is always ready, which is what
  // fileread assumes when one is absent.
  [8] = { diskread,  diskwrite  },
  // /dev/pci (major 9) -- PCI devices reachable from userspace, for drivers
  // that do not live in the kernel. Registers arrive through mmap and
  // everything else through ioctl; see include/pciuser.h.
  [9] = { pciuser_read, pciuser_write },
  // /dev/dbg (major 10) -- ask the kernel a question. Write a line, read the
  // answer; see include/dbg.h and docs/architecture/debugging.md.
  [10] = { dbg_read, dbg_write },
  // /dev/netdev (major 11) -- a process, being a network interface. The
  // reverse of major 9: that hands a device to a process, this lets a process
  // be one. See include/netuser.h.
  [11] = { netuser_read, netuser_write, netuser_ready },
  // /dev/dsp (major 12) -- UNIX audio, kernel/dev/audio.c. Write PCM to it.
  // The close hook plays out what is still queued: a program that writes a
  // sound and exits expects to hear the end of it.
  [12] = { dspread,   dspwrite,   0, dspclose },
};