SchOS/kernel/dev/blkdev.c
Nexoniarz edb560de66 fat: FAT12, FAT16 and FAT32 with long names, read and write
The filesystem every other system can read: a USB stick, an SD card, the
EFI system partition. It is here first for the hardware report, which has
to leave a machine on something that can be read on another one.

  mount -t vfat /dev/usb0p1 /mnt        (msdos and fat work too; -o ro)

Written from Microsoft's specification, and matched to Linux vfat where
the specification leaves a choice: 8.3 names with the NT lowercase bits,
long-name entries otherwise, Linux's alias rule (REPORTS, then BIGNUM~1),
case-insensitive lookup, UTC times, the boot-sector dirty bit, every FAT
copy and FSInfo kept up to date. It uses its own sector cache over the
new blkdev_xfer, since a partition need not be a whole number of 4 KB
blocks, and every operation that changes something reaches the disk
before it returns. Inode numbers come from the entry position, or the
first cluster for a directory, plus a small table for entries that moved.

Around it:
- /dev lists every disk and partition the block layer found (major 8,
  minor = block device), and raw reads and writes on them go by sector.
- The ESP and MBR FAT partitions are registered, typed so the root probe
  passes over them. MBR entries with a bad status byte are skipped, so a
  superfloppy's boot code is not read as a partition table.
- statfs, sync, fsync, umount (EBUSY while in use), shutdown, reboot and
  the power button all know about FAT.
- create undoes and reports a failed ialloc or dirlink (ENOSPC, EINVAL,
  EPERM) instead of panicking; fs_ops gains refuse_types and no_hardlinks.
- filewrite returns a short write instead of panicking on it.
- utimensat is implemented. As a stub returning 0 it made toybox touch
  believe the file existed, so `touch newfile` created nothing on any
  filesystem.

Tested in QEMU against mkfs.vfat images (FAT12 floppy, FAT16 on MBR,
FAT32 superfloppy and GPT ESP) by writing, renaming, deleting, filling to
ENOSPC and truncating there, then checking with fsck.fat -n and mtools on
the host: all clean, contents match.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S1giNvrHTrPMPw7V6x1kQ4
2026-10-23 09:33:35 +02:00

395 lines
10 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
//
// The block device registry, and the partition tables on what is in it.
// See include/blkdev.h.
#include "types.h"
#include "defs.h"
#include "param.h"
#include "spinlock.h"
#include "sleeplock.h"
#include "fs.h"
#include "buf.h"
#include "blkdev.h"
struct blkdev {
int used;
char name[16];
const struct blkdev_ops *ops;
void *priv;
uint64 start; // first sector, in the disk's own sectors
uint64 nsectors;
uint32 secsize;
int parent; // the disk's slot for a partition, -1 for a disk
int schfs; // 1: typed SchFS; -1: typed FAT; 0: anything else
};
static struct blkdev devs[NBLKDEV];
static struct spinlock blklock;
static int blkinit;
static struct blkdev *
lookup(uint dev)
{
if (dev < BLKDEV_FIRST || dev >= BLKDEV_FIRST + NBLKDEV)
return 0;
struct blkdev *d = &devs[dev - BLKDEV_FIRST];
return d->used ? d : 0;
}
static int
add(const char *name, const struct blkdev_ops *ops, void *priv,
uint64 start, uint64 nsectors, uint32 secsize, int parent, int schfs)
{
if (!blkinit) {
initlock(&blklock, "blkdev");
blkinit = 1;
}
acquire(&blklock);
for (int i = 0; i < NBLKDEV; i++) {
if (devs[i].used)
continue;
struct blkdev *d = &devs[i];
safestrcpy(d->name, name, sizeof(d->name));
d->ops = ops;
d->priv = priv;
d->start = start;
d->nsectors = nsectors;
d->secsize = secsize;
d->parent = parent;
d->schfs = schfs;
__sync_synchronize();
d->used = 1;
release(&blklock);
return BLKDEV_FIRST + i;
}
release(&blklock);
cprintf("blkdev: no slot for %s; it will not be usable\n", name);
return -1;
}
// --- partition tables -------------------------------------------------------
static uint32 le32(const uchar *p) { return p[0] | p[1] << 8 | p[2] << 16 | (uint32)p[3] << 24; }
static uint64 le64(const uchar *p) { return le32(p) | (uint64)le32(p + 4) << 32; }
// A GUID as GPT stores it: the first three fields little-endian, the last two
// as bytes. Compared against the printed form, so the constant in blkdev.h is
// the one a person types into sgdisk.
static int
guid_is(const uchar *g, const char *text)
{
static const int order[16] = { 3,2,1,0, 5,4, 7,6, 8,9, 10,11,12,13,14,15 };
uchar want[16];
int n = 0;
for (const char *p = text; *p && n < 32; p++) {
int v;
if (*p == '-')
continue;
if (*p >= '0' && *p <= '9') v = *p - '0';
else if (*p >= 'a' && *p <= 'f') v = *p - 'a' + 10;
else if (*p >= 'A' && *p <= 'F') v = *p - 'A' + 10;
else return 0;
if (n & 1) want[n / 2] |= v; else want[n / 2] = v << 4;
n++;
}
for (int i = 0; i < 16; i++)
if (g[order[i]] != want[i])
return 0;
return 1;
}
static int
guid_zero(const uchar *g)
{
for (int i = 0; i < 16; i++)
if (g[i])
return 0;
return 1;
}
static void
partname(char *out, const char *disk, int n)
{
int i = 0;
for (; disk[i] && i < 12; i++)
out[i] = disk[i];
out[i++] = 'p';
if (n >= 10)
out[i++] = '0' + n / 10;
out[i++] = '0' + n % 10;
out[i] = 0;
}
static int
readsec(struct blkdev *d, uint64 lba, uchar *buf)
{
return d->ops->rw(d->priv, lba, 1, buf, 0);
}
#define ESP_TYPE "C12A7328-F81F-11D2-BA4B-00A0C93EC93B"
// The GUID partition table: the header in sector 1, and its entries wherever
// it says. Only the primary copy is read -- a disk whose primary is damaged
// gets reported as having no partitions rather than half of some.
//
// The EFI system partition is registered like any other, as FAT: the root
// probe passes over it (see blkdev_is_schfs), and kernel/fs/fat mounts it.
static int
scan_gpt(int disk, uchar *sec)
{
struct blkdev *d = &devs[disk];
int found = 0;
if (readsec(d, 1, sec) < 0 || memcmp(sec, "EFI PART", 8) != 0)
return -1;
uint64 elba = le64(sec + 72);
uint32 count = le32(sec + 80);
uint32 esize = le32(sec + 84);
if (esize < 128 || esize > d->secsize || (esize & (esize - 1)) ||
count > 256 || elba < 2 || elba >= d->nsectors) {
cprintf("blkdev: %s: GPT header makes no sense; ignoring it\n", d->name);
return -1;
}
uint32 per = d->secsize / esize;
for (uint32 i = 0; i < count; i++) {
if (i % per == 0 && readsec(d, elba + i / per, sec) < 0)
break;
uchar *e = sec + (i % per) * esize;
if (guid_zero(e))
continue;
uint64 first = le64(e + 32), last = le64(e + 40);
if (first == 0 || last < first || last >= d->nsectors)
continue;
char name[16];
partname(name, d->name, i + 1);
int schfs = guid_is(e, SCHFS_GPT_TYPE) ? 1 : guid_is(e, ESP_TYPE) ? -1 : 0;
if (add(name, d->ops, d->priv, first, last - first + 1, d->secsize,
disk, schfs) >= 0) {
kinfo("blkdev: %s: %d MB%s\n", name,
(int)(((last - first + 1) * d->secsize) >> 20),
schfs > 0 ? ", SchFS" : schfs < 0 ? ", EFI system" : "");
found++;
}
}
return found;
}
// The PC partition table, for disks that have one instead. Primary entries
// only; a protective entry (0xEE) means the disk is GPT and was read above.
//
// A FAT volume with no partition table -- a "superfloppy", which is how a
// good many USB sticks leave the factory -- also ends in 55 AA, and its boot
// code would read as four nonsense entries. Linux tells them apart by the
// status byte, which in a real entry is 0x00 or 0x80 and in boot code is
// whatever the code happens to be.
static int
fat_type(uint32 type)
{
switch (type) {
case 0x01: case 0x04: case 0x06: case 0x0B: case 0x0C: case 0x0E: case 0xEF:
return 1;
}
return 0;
}
static void
scan_mbr(int disk, uchar *sec)
{
struct blkdev *d = &devs[disk];
if (readsec(d, 0, sec) < 0 || sec[510] != 0x55 || sec[511] != 0xAA)
return;
for (int i = 0; i < 4; i++) {
uchar *e = sec + 446 + i * 16;
uint32 type = e[4], first = le32(e + 8), n = le32(e + 12);
// Empty, protective, and extended (which would need its own chain read).
if ((e[0] != 0x00 && e[0] != 0x80) ||
type == 0 || type == 0xEE || type == 0x05 || type == 0x0F ||
n == 0 || first + (uint64)n > d->nsectors)
continue;
char name[16];
partname(name, d->name, i + 1);
if (add(name, d->ops, d->priv, first, n, d->secsize, disk,
fat_type(type) ? -1 : 0) >= 0)
kinfo("blkdev: %s: %d MB, MBR type %x\n", name,
(int)(((uint64)n * d->secsize) >> 20), type);
}
}
int
blkdev_register(const char *name, const struct blkdev_ops *ops, void *priv,
uint64 nsectors, uint32 secsize)
{
if (secsize == 0 || secsize > BSIZE || BSIZE % secsize)
return -1;
int dev = add(name, ops, priv, 0, nsectors, secsize, -1, 0);
if (dev < 0)
return -1;
uchar *sec = (uchar *)kalloc();
if (sec) {
if (scan_gpt(dev - BLKDEV_FIRST, sec) < 0)
scan_mbr(dev - BLKDEV_FIRST, sec);
kfree((char *)sec);
}
return dev;
}
void
blkdev_unregister(int dev)
{
struct blkdev *d = lookup(dev);
if (!d)
return;
int disk = dev - BLKDEV_FIRST;
acquire(&blklock);
for (int i = 0; i < NBLKDEV; i++) {
if (devs[i].used && (i == disk || devs[i].parent == disk)) {
devs[i].used = 0;
kinfo("blkdev: %s removed\n", devs[i].name);
release(&blklock);
binval(BLKDEV_FIRST + i);
acquire(&blklock);
}
}
release(&blklock);
}
// --- I/O ---------------------------------------------------------------------
int
blkdev_present(uint dev)
{
return lookup(dev) != 0;
}
// Same contract as iderw(): fill b->data and set B_VALID on a read, write it
// out and clear B_DIRTY on a write. A failed transfer panics, for the reason
// usb_storage_rw() gives: bread() has no way to report one, and a buffer that
// silently holds the wrong bytes is how a filesystem is corrupted.
void
blkdev_rw(struct buf *b)
{
struct blkdev *d = lookup(b->dev);
int write = (b->flags & B_DIRTY) != 0;
if (!holdingsleep(&b->lock))
panic("blkdev_rw: buf not locked");
if (!d)
panic("blkdev_rw: no such device");
uint32 per = BSIZE / d->secsize;
uint64 lba = b->blockno * per;
if (lba + per > d->nsectors)
panic("blkdev_rw: block out of range");
if (d->ops->rw(d->priv, d->start + lba, per, b->data, write) < 0) {
cprintf("blkdev: %s: %s of block %d failed\n", d->name,
write ? "write" : "read", (int)b->blockno);
panic("blkdev_rw: transfer failed");
}
b->flags |= B_VALID;
b->flags &= ~B_DIRTY;
}
int
blkdev_xfer(uint dev, uint64 lba, uint32 count, void *buf, int write)
{
struct blkdev *d = lookup(dev);
if (!d || count == 0 || (uint64)count * d->secsize > BSIZE ||
lba + count > d->nsectors || lba + count < lba)
return -1;
return d->ops->rw(d->priv, d->start + lba, count, buf, write) < 0 ? -1 : 0;
}
uint64
blkdev_sectors(uint dev, uint32 *secsize)
{
struct blkdev *d = lookup(dev);
if (!d)
return 0;
if (secsize)
*secsize = d->secsize;
return d->nsectors;
}
int
blkdev_flush(uint dev)
{
struct blkdev *d = lookup(dev);
if (!d || !d->ops->flush)
return 0;
return d->ops->flush(d->priv);
}
int
blkdev_nth(int i)
{
for (int s = 0; s < NBLKDEV; s++)
if (devs[s].used && i-- == 0)
return BLKDEV_FIRST + s;
return -1;
}
const char *
blkdev_name(uint dev)
{
struct blkdev *d = lookup(dev);
return d ? d->name : "?";
}
int
blkdev_is_schfs(uint dev)
{
struct blkdev *d = lookup(dev);
return d ? d->schfs : 0;
}
// --- /proc/partitions --------------------------------------------------------
static int
put(char *buf, int cap, int off, const char *s)
{
while (*s && off < cap)
buf[off++] = *s++;
return off;
}
static int
putu(char *buf, int cap, int off, uint64 v)
{
char t[24];
int n = 0;
do { t[n++] = '0' + v % 10; v /= 10; } while (v);
while (n && off < cap)
buf[off++] = t[--n];
return off;
}
int
blkdev_info(char *buf, int cap)
{
int off = put(buf, cap, 0, "dev name MB type\n");
for (int s = 0; s < NBLKDEV; s++) {
struct blkdev *d = &devs[s];
if (!d->used)
continue;
off = putu(buf, cap, off, BLKDEV_FIRST + s);
off = put(buf, cap, off, " ");
off = put(buf, cap, off, d->name);
for (int pad = 12 - strlen(d->name); pad > 0; pad--)
off = put(buf, cap, off, " ");
off = putu(buf, cap, off, (d->nsectors * d->secsize) >> 20);
off = put(buf, cap, off, d->parent < 0 ? " disk" :
d->schfs > 0 ? " schfs" :
d->schfs < 0 ? " fat" : " part");
off = put(buf, cap, off, "\n");
}
return off;
}