SchOS/kernel/fs/devfs.c

// SPDX-License-Identifier: GPL-2.0-or-later
//
// devtmpfs: /dev, generated rather than stored.
//
// It used to be ~20 mknod() calls in cmd/schinit, which was wrong in two ways
// that are worth separating.
//
// *The cost.* Every node was a real inode on the root filesystem, and SchFS
// commits each mutation as its own transaction group -- a copy-on-write rewrite
// of the path to the root, then an uberblock behind a cache flush. Measured:
// 2600 ms of a first boot spent writing device nodes to a disk, before schinit
// printed its first line. On later boots the nodes already existed and the same
// code took 0 ms, so the cost was invisible unless you built a fresh image --
// which is exactly what anyone working on the system does every time.
//
// *The duplication, which matters more.* Major and minor numbers are the
// kernel's: they are what devsw[] in kernel/dev/cdev.c dispatches on. schinit
// held a second copy of that mapping and nothing checked the two agreed. A new
// character device meant editing a userspace program, and getting a minor wrong
// there produced a node that opened successfully and did nothing.
//
// So the table below sits next to the thing it describes, and /dev is a
// mount rather than a directory somebody populates. `mount("dev", "/dev",
// "devtmpfs", 0, 0)` is the whole of what init does now.
//
// The namespace is all this provides. Reads and writes never reach here --
// fileread/filewrite see T_DEV and dispatch through devsw themselves -- which
// is why there is no read op below that does anything.

#include "core/types.h"
#include "core/defs.h"
#include "core/param.h"
#include "uapi/stat.h"
#include "core/spinlock.h"
#include "core/sleeplock.h"
#include "core/proc.h"
#include "fs/fs.h"
#include "fs/file.h"
#include "uapi/errno.h"
#include "fs/blkdev.h"
#include "dev/pty.h"
#include "core/uaccess.h"

// Inode numbering. Two directories and a flat table of nodes, so the number is
// either a directory id or an index into devnodes[] offset past them.
#define DEVFS_ROOT     1ULL
#define DEVFS_INPUT    2ULL          /* the /dev/input directory */
#define DEVFS_FILE0    16ULL         /* devnodes[0] is inode 16 */
// Disks and partitions the block layer found: /dev/sata0, /dev/sata0p1,
// /dev/usb0p1, named as it named them. Major 8 like hda, minor the block
// device number, and inode DEVFS_BLK0 plus that number. Not in devnodes[],
// because they come and go: a stick plugged in appears, pulled out vanishes.
#define DEVFS_BLK0     4096ULL
// Pseudo-terminals: the /dev/pts directory, its slaves by pair number, and the
// masters, which have inodes so that an open file can hold one but appear in no
// directory -- the only way to one is opening /dev/ptmx.
#define DEVFS_PTS      3ULL
#define DEVFS_PTS0     8192ULL
#define DEVFS_PTM0     12288ULL

// What udev adds to /dev: directories (/dev/input/by-path, /dev/disk/...) and
// symlinks (/dev/fd, /dev/stdin, /dev/char/13:64, /dev/disk/by-id/...). The
// device nodes themselves stay the kernel's; this is a small table of names
// that live only in memory, as they would in a tmpfs, listed after the real
// entries of whichever directory they are in. Nothing here can hold data: a
// regular file in /dev is refused.
#define DEVFS_EXTRA0   32768ULL
#define NEXTRA         192
#define EXTRA_NAME     48
#define EXTRA_TARGET   112

struct extra {
  uchar   used;                 // allocated (an inode exists or is about to)
  uchar   linked;               // has a name in a directory
  short   type;                 // T_DIR or T_SYMLINK
  uint64  parent;               // inum of the directory it is in
  ushort  tlen;
  char    name[EXTRA_NAME];
  char    target[EXTRA_TARGET];
};

static struct {
  struct spinlock lock;
  struct extra e[NEXTRA];
} extras;

static int extras_ready;

static void
extras_init(void)
{
  if (!extras_ready) {
    initlock(&extras.lock, "devfsx");
    extras_ready = 1;
  }
}

static int
extra_of(uint64 inum)
{
  if (inum < DEVFS_EXTRA0)
    return -1;
  uint64 i = inum - DEVFS_EXTRA0;
  return i < NEXTRA ? (int)i : -1;
}

// Which directory a node lives in. Only two exist and a third would want a real
// tree rather than a flag, which is the point at which this file should grow
// one instead of adding DEV_DIR_THIRD.
#define D_ROOT   0
#define D_INPUT  1

struct devnode {
  const char *name;
  short  major;
  short  minor;
  short  dir;
};

// The devices this kernel implements, in the order they appear in a listing.
//
// Minor numbers under major 1 follow Linux's mem-major layout where it costs
// nothing (null=2, zero=5, full=7, random=8, urandom=9), which is worth keeping
// because it is one less arbitrary mapping for anyone reading both.
//
// The majors are devsw[] indices and nothing else; see kernel/dev/cdev.c.
static const struct devnode devnodes[] = {
  { "console", 1, 1,  D_ROOT },
  { "null",    1, 2,  D_ROOT },
  { "keyboard",1, 3,  D_ROOT },
  { "zero",    1, 5,  D_ROOT },
  { "full",    1, 7,  D_ROOT },
  { "random",  1, 8,  D_ROOT },
  { "urandom", 1, 9,  D_ROOT },
  /* /dev/tty is the caller's *controlling* terminal, which is a different
     thing from the console and used to be the same thing only because there
     was one terminal. Minor 10 resolves through proc->ctty; see
     vt_for_minor() in kernel/core/console.c. */
  { "tty",     1, 10, D_ROOT },
  /* The terminal on screen, as on Linux. Xorg opens it to find a free VT and
     switch to it, and without one ran on no VT at all: the console went on
     drawing into the framebuffer over the X screen. Any minor that is not a
     numbered terminal or the controlling one resolves to vt_current(). */
  { "tty0",    1, 0,  D_ROOT },
  { "tty1",    1, 11, D_ROOT },
  { "tty2",    1, 12, D_ROOT },
  { "tty3",    1, 13, D_ROOT },
  { "tty4",    1, 14, D_ROOT },
  { "tty5",    1, 15, D_ROOT },
  { "tty6",    1, 16, D_ROOT },
  { "tty7",    1, 17, D_ROOT },
  { "tty8",    1, 18, D_ROOT },
  { "tty9",    1, 19, D_ROOT },
  { "tty10",   1, 20, D_ROOT },
  { "tty11",   1, 21, D_ROOT },
  { "tty12",   1, 22, D_ROOT },
  { "stdin",   1, 1,  D_ROOT },
  { "stdout",  1, 1,  D_ROOT },
  { "stderr",  1, 1,  D_ROOT },
  { "fb0",     2, 0,  D_ROOT },
  { "pci",     9, 0,  D_ROOT },
  { "dbg",     10, 0, D_ROOT },
  // The same device, answering only the views that read. Minor 1 rather than
  // a flag, because the minor is the one piece of per-open state a character
  // device already sees -- so which one you opened *is* the permission, and
  // nothing has to be remembered between the write and the read. See
  // include/core/dbg.h and cmd/schdbgd.
  { "dbgro",   10, 1, D_ROOT },
  { "netdev",  11, 0, D_ROOT },
  // Audio, spelled the way UNIX spells it. See include/dev/audio.h.
  { "dsp",     12, 0, D_ROOT },
  { "mouse",   3, 1,  D_ROOT },
  // Opening it makes a new pseudo-terminal pair; see kernel/dev/pty.c.
  { "ptmx",    PTMX_MAJOR, 0, D_ROOT },

  // Raw disks. Created whether or not a drive is present: opening one with no
  // disk behind it fails with ENXIO, which is a better answer than a missing
  // path -- and with no node at all, `echo x > /dev/hdb` silently creates an
  // ordinary file of that name and appears to work.
  { "hda",     8, 0,  D_ROOT },
  { "hdb",     8, 1,  D_ROOT },

  // Raw input events, Linux evdev layout. The minor is the device index, so
  // event0 is the keyboard and event1 the mouse.
  { "event0",  7, 0,  D_INPUT },
  { "event1",  7, 1,  D_INPUT },
};

#define NDEVNODES ((int)(sizeof(devnodes) / sizeof(devnodes[0])))

static int
node_of(uint64 inum)
{
  if (inum < DEVFS_FILE0)
    return -1;
  uint64 i = inum - DEVFS_FILE0;
  return i < (uint64)NDEVNODES ? (int)i : -1;
}

static void
devfs_iload(struct inode *ip)
{
  int i = node_of(ip->inum);

  ip->major = ip->minor = 0;
  ip->size  = 0;

  int x = extra_of(ip->inum);
  if (x >= 0) {
    extras_init();
    acquire(&extras.lock);
    if (extras.e[x].used) {
      ip->type  = extras.e[x].type;
      ip->nlink = extras.e[x].type == T_DIR ? 2 : 1;
      ip->size  = extras.e[x].tlen;
      ip->mode  = extras.e[x].type == T_DIR ? 0755 : 0777;
    } else {
      ip->type  = 0;
      ip->nlink = 0;
    }
    release(&extras.lock);
  } else if (ip->inum == DEVFS_ROOT || ip->inum == DEVFS_INPUT ||
      ip->inum == DEVFS_PTS) {
    ip->type  = T_DIR;
    ip->nlink = 2;
  } else if (ip->inum >= DEVFS_PTS0 && ip->inum < DEVFS_PTS0 + NPTY &&
             pty_used((int)(ip->inum - DEVFS_PTS0))) {
    ip->type  = T_DEV;
    ip->nlink = 1;
    ip->major = PTS_MAJOR;
    ip->minor = (short)(ip->inum - DEVFS_PTS0);
    ip->mode  = 0620;
  } else if (ip->inum >= DEVFS_PTM0 && ip->inum < DEVFS_PTM0 + NPTY) {
    ip->type  = T_DEV;
    ip->nlink = 1;
    ip->major = PTM_MAJOR;
    ip->minor = (short)(ip->inum - DEVFS_PTM0);
  } else if (i >= 0) {
    ip->type  = T_DEV;
    ip->nlink = 1;
    ip->major = devnodes[i].major;
    ip->minor = devnodes[i].minor;
  } else if (ip->inum >= DEVFS_BLK0 &&
             blkdev_present((uint)(ip->inum - DEVFS_BLK0))) {
    ip->type  = T_DEV;
    ip->nlink = 1;
    ip->major = 8;
    ip->minor = (short)(ip->inum - DEVFS_BLK0);
  } else {
    ip->type  = 0;                   /* no such node */
    ip->nlink = 0;
  }
  ip->valid = 1;
}

static void devfs_istore(struct inode *ip)               { (void)ip; }
static void
devfs_ifree(struct inode *ip)
{
  int x = extra_of(ip->inum);
  if (x < 0)
    return;
  extras_init();
  acquire(&extras.lock);
  extras.e[x].used = 0;
  release(&extras.lock);
}
static void devfs_truncate(struct inode *ip, uint64 n)   { (void)ip; (void)n; }

// Never reached for a device node: fileread and filewrite see T_DEV and go
// through devsw. Present because fs_ops has the slots, and answering -EIO is
// better than a null pointer if something ever does arrive here.
static int
devfs_read(struct inode *ip, int u, uint64 d, uint64 o, uint n)
{
  int x = extra_of(ip->inum);
  if (x < 0 || ip->type != T_SYMLINK)
    return -1;
  extras_init();
  char buf[EXTRA_TARGET];
  acquire(&extras.lock);
  uint len = extras.e[x].tlen;
  memmove(buf, extras.e[x].target, len);
  release(&extras.lock);
  if (o >= len)
    return 0;
  if (o + n > len)
    n = (uint)(len - o);
  if (u) {
    if (copy_to_user(d, buf + o, n) < 0)
      return -EFAULT;
  } else {
    memmove((char *)d, buf + o, n);
  }
  return (int)n;
}

// Only a symlink's target can be written, once, from offset 0.
static int
devfs_write(struct inode *ip, int u, uint64 s, uint64 o, uint n)
{
  int x = extra_of(ip->inum);
  if (x < 0 || ip->type != T_SYMLINK || o != 0 || n >= EXTRA_TARGET)
    return -1;
  extras_init();
  char buf[EXTRA_TARGET];
  if (u) {
    if (copy_from_user(buf, s, n) < 0)
      return -EFAULT;
  } else {
    memmove(buf, (char *)s, n);
  }
  acquire(&extras.lock);
  memmove(extras.e[x].target, buf, n);
  extras.e[x].tlen = (ushort)n;
  release(&extras.lock);
  ip->size = n;
  return (int)n;
}

static int
streq(const char *a, const char *b)
{
  while (*a && *a == *b) { a++; b++; }
  return *a == *b;
}

static struct inode *
extra_find(uint64 parent, const char *name)
{
  extras_init();
  acquire(&extras.lock);
  for (int i = 0; i < NEXTRA; i++)
    if (extras.e[i].used && extras.e[i].linked && extras.e[i].parent == parent &&
        streq(name, extras.e[i].name)) {
      release(&extras.lock);
      return iget(DEVFS_DEV, DEVFS_EXTRA0 + (uint64)i);
    }
  release(&extras.lock);
  return 0;
}

static struct inode *
devfs_dirlookup(struct inode *dp, char *name, uint *poff)
{
  if (poff)
    *poff = 0;

  int dx = extra_of(dp->inum);
  if (dx >= 0) {
    extras_init();
    if (streq(name, "."))
      return iget(DEVFS_DEV, dp->inum);
    if (streq(name, "..")) {
      acquire(&extras.lock);
      uint64 up = extras.e[dx].parent;
      release(&extras.lock);
      return iget(DEVFS_DEV, up ? up : DEVFS_ROOT);
    }
    return extra_find(dp->inum, name);
  }

  if (streq(name, ".") || (streq(name, "..") && dp->inum == DEVFS_ROOT))
    return iget(DEVFS_DEV, dp->inum);
  if (streq(name, ".."))
    return iget(DEVFS_DEV, DEVFS_ROOT);     /* out of /dev/input */

  if (dp->inum == DEVFS_ROOT && streq(name, "input"))
    return iget(DEVFS_DEV, DEVFS_INPUT);
  if (dp->inum == DEVFS_ROOT && streq(name, "pts"))
    return iget(DEVFS_DEV, DEVFS_PTS);

  // /dev/pts/N: a pair that exists.
  if (dp->inum == DEVFS_PTS) {
    int n = 0;
    const char *s = name;
    if (!*s)
      return 0;
    for (; *s; s++) {
      if (*s < '0' || *s > '9')
        return 0;
      n = n * 10 + (*s - '0');
      if (n >= NPTY)
        return 0;
    }
    return pty_used(n) ? iget(DEVFS_DEV, DEVFS_PTS0 + (uint64)n) : 0;
  }

  // /dev/tty is the caller's controlling terminal. When that is a pty, it is
  // the slave itself -- what a program inside xterm or tmux opens to talk to
  // its terminal must be that terminal, not the console.
  if (dp->inum == DEVFS_ROOT && streq(name, "tty") && myproc() &&
      myproc()->ctty >= PTY_CTTY && myproc()->ctty < PTY_CTTY + NPTY &&
      pty_used(myproc()->ctty - PTY_CTTY))
    return iget(DEVFS_DEV, DEVFS_PTS0 + (uint64)(myproc()->ctty - PTY_CTTY));

  short want = dp->inum == DEVFS_INPUT ? D_INPUT : D_ROOT;
  for (int i = 0; i < NDEVNODES; i++)
    if (devnodes[i].dir == want && streq(name, devnodes[i].name))
      return iget(DEVFS_DEV, DEVFS_FILE0 + (uint64)i);

  if (want == D_ROOT)
    for (int k = 0, b; (b = blkdev_nth(k)) >= 0; k++)
      if (streq(name, blkdev_name((uint)b)))
        return iget(DEVFS_DEV, DEVFS_BLK0 + (uint64)b);

  return extra_find(dp->inum, name);
}

// What can be created here: a directory or a symlink, by ialloc and then
// dirlink -- the order every filesystem is driven in. The device nodes
// themselves are the kernel's: mknod answers EROFS by never getting an inode.
static struct inode *
devfs_ialloc(uint dev, short type)
{
  (void)dev;
  if (type != T_DIR && type != T_SYMLINK)
    return 0;
  extras_init();
  acquire(&extras.lock);
  for (int i = 0; i < NEXTRA; i++)
    if (!extras.e[i].used) {
      memset(&extras.e[i], 0, sizeof(extras.e[i]));
      extras.e[i].used = 1;
      extras.e[i].type = type;
      release(&extras.lock);
      return iget(DEVFS_DEV, DEVFS_EXTRA0 + (uint64)i);
    }
  release(&extras.lock);
  return 0;
}

static int
devfs_dirlink(struct inode *dp, char *name, uint64 inum)
{
  int x = extra_of(inum);
  if (streq(name, ".") || streq(name, ".."))
    return 0;                       /* a new directory's own dots */
  if (x < 0 || strlen(name) >= EXTRA_NAME)
    return -EINVAL;
  extras_init();
  acquire(&extras.lock);
  if (!extras.e[x].used || extras.e[x].linked) {
    release(&extras.lock);
    return -EINVAL;
  }
  extras.e[x].parent = dp->inum;
  extras.e[x].linked = 1;
  memmove(extras.e[x].name, name, strlen(name) + 1);
  release(&extras.lock);
  return 0;
}

static int
devfs_dirempty(struct inode *dp)
{
  if (extra_of(dp->inum) < 0)
    return 0;
  extras_init();
  acquire(&extras.lock);
  for (int i = 0; i < NEXTRA; i++)
    if (extras.e[i].used && extras.e[i].linked && extras.e[i].parent == dp->inum) {
      release(&extras.lock);
      return 0;
    }
  release(&extras.lock);
  return 1;
}

static int
devfs_dirunlink(struct inode *dp, char *name, uint off)
{
  (void)off;
  extras_init();
  acquire(&extras.lock);
  for (int i = 0; i < NEXTRA; i++)
    if (extras.e[i].used && extras.e[i].linked && extras.e[i].parent == dp->inum &&
        streq(name, extras.e[i].name)) {
      extras.e[i].linked = 0;       /* the inode goes when nobody holds it */
      release(&extras.lock);
      return 0;
    }
  release(&extras.lock);
  return -EROFS;                    /* a device node is the kernel's */
}

struct linux_dirent64 {
  uint64 d_ino;
  int64  d_off;
  uint16 d_reclen;
  uchar  d_type;
  char   d_name[];
};

static int
emit(char *out, int cap, int *used, uint64 ino, uchar type, const char *name)
{
  int nl  = (int)strlen(name);
  int rec = (int)((sizeof(struct linux_dirent64) + nl + 1 + 7) & ~7);

  if (*used + rec > cap)
    return -1;                       /* caller stops and resumes next call */

  struct linux_dirent64 *d = (struct linux_dirent64 *)(out + *used);
  d->d_ino    = ino;
  d->d_off    = 0;
  d->d_reclen = (uint16)rec;
  d->d_type   = type;
  memmove(d->d_name, name, nl);
  memset(d->d_name + nl, 0, rec - (int)sizeof(*d) - nl);
  *used += rec;
  return 0;
}

// `off` is an ordinal over the entries of this directory: 0 is ".", 1 is "..",
// and the rest follow. An opaque cookie the way SchFS uses one buys nothing
// here, because the table is fixed and small enough to index directly.
static int
devfs_getdents(struct inode *dp, char *out, int cap, uint64 *poff)
{
  int used = 0;
  uint64 n = *poff;

  int isx = extra_of(dp->inum) >= 0;
  if (dp->inum != DEVFS_ROOT && dp->inum != DEVFS_INPUT &&
      dp->inum != DEVFS_PTS && !isx)
    return -1;

  if (n == 0) {
    if (emit(out, cap, &used, dp->inum, 4 /* DT_DIR */, ".") < 0) return -1;
    n++;
  }
  if (n == 1) {
    uint64 up = dp->inum == DEVFS_ROOT ? DEVFS_ROOT : DEVFS_ROOT;
    if (emit(out, cap, &used, up, 4, "..") < 0) goto out;
    n++;
  }

  // A directory udev made: the dots, then what is in it.
  if (isx) {
    uint64 base = 2;
    extras_init();
    acquire(&extras.lock);
    for (int i = 0; i < NEXTRA; i++) {
      if (!extras.e[i].used || !extras.e[i].linked || extras.e[i].parent != dp->inum)
        continue;
      if (n > base) { base++; continue; }
      if (emit(out, cap, &used, DEVFS_EXTRA0 + (uint64)i,
               extras.e[i].type == T_DIR ? 4 : 10 /* DT_LNK */, extras.e[i].name) < 0)
        break;
      n++;
      base++;
    }
    release(&extras.lock);
    goto out;
  }

  // /dev/pts: the dots, then the pairs that exist. Ordinal 2 + N is pair N,
  // whether or not the ones before it exist, so a pair opened between two
  // calls does not shift the rest.
  if (dp->inum == DEVFS_PTS) {
    for (; n >= 2 && n < 2 + NPTY; n++) {
      int k = (int)(n - 2);
      char nm[4];
      if (!pty_used(k))
        continue;
      nm[0] = k >= 10 ? '0' + k / 10 : '0' + k;
      nm[1] = k >= 10 ? '0' + k % 10 : 0;
      nm[2] = 0;
      if (emit(out, cap, &used, DEVFS_PTS0 + (uint64)k, 2, nm) < 0) goto out;
    }
    goto out;
  }

  // /dev/input and /dev/pts are directory entries of the root, emitted
  // between the dots and the nodes so that their ordinals are stable.
  if (dp->inum == DEVFS_ROOT && n == 2) {
    if (emit(out, cap, &used, DEVFS_INPUT, 4, "input") < 0) goto out;
    n++;
  }
  if (dp->inum == DEVFS_ROOT && n == 3) {
    if (emit(out, cap, &used, DEVFS_PTS, 4, "pts") < 0) goto out;
    n++;
  }

  short want = dp->inum == DEVFS_INPUT ? D_INPUT : D_ROOT;
  uint64 base = dp->inum == DEVFS_ROOT ? 4 : 2;

  for (int i = 0; i < NDEVNODES; i++) {
    if (devnodes[i].dir != want)
      continue;
    if (n > base) { base++; continue; }         /* already emitted */
    if (emit(out, cap, &used, DEVFS_FILE0 + (uint64)i, 2 /* DT_CHR */,
             devnodes[i].name) < 0)
      goto out;
    n++;
    base++;
  }

  if (want == D_ROOT)
    for (int k = 0, b; (b = blkdev_nth(k)) >= 0; k++) {
      if (n > base) { base++; continue; }
      if (emit(out, cap, &used, DEVFS_BLK0 + (uint64)b, 6 /* DT_BLK */,
               blkdev_name((uint)b)) < 0)
        goto out;
      n++;
      base++;
    }

  // What udev added to this directory, after everything the kernel put there.
  extras_init();
  acquire(&extras.lock);
  for (int i = 0; i < NEXTRA; i++) {
    if (!extras.e[i].used || !extras.e[i].linked || extras.e[i].parent != dp->inum)
      continue;
    if (n > base) { base++; continue; }
    if (emit(out, cap, &used, DEVFS_EXTRA0 + (uint64)i,
             extras.e[i].type == T_DIR ? 4 : 10, extras.e[i].name) < 0)
      break;
    n++;
    base++;
  }
  release(&extras.lock);

out:
  *poff = n;
  return used;
}

const struct fs_ops devfs_ops = {
  .name      = "devtmpfs",
  .iload     = devfs_iload,
  .istore    = devfs_istore,
  .ifree     = devfs_ifree,
  .read      = devfs_read,
  .write     = devfs_write,
  .truncate  = devfs_truncate,
  .dirlookup = devfs_dirlookup,
  .dirlink   = devfs_dirlink,
  .dirunlink = devfs_dirunlink,
  .dirempty  = devfs_dirempty,
  .ialloc    = devfs_ialloc,
  .getdents  = devfs_getdents,
};

// Graft it over `target` -- /dev from init, and again wherever a chroot
// wants one. It was always /dev whatever was asked for, so a second mount
// failed as "already mounted" and a chroot had no devices.
int
devfs_mount(const char *target)
{
  struct inode *dp = namei((char *)target);
  int r;

  if (dp == 0)
    return -ENOENT;
  r = mount_add(dp->dev, dp->inum, DEVFS_DEV, DEVFS_ROOT, (char *)target, "dev",
                "devtmpfs");
  iput(dp);
  return r < 0 ? -EBUSY : 0;
}

// The inode of pty master N, for ptmx_open() to hand to the file it opens.
struct inode *
devfs_pty_master(int n)
{
  if (n < 0 || n >= NPTY)
    return 0;
  return iget(DEVFS_DEV, DEVFS_PTM0 + (uint64)n);
}