SchOS/kernel/dev/bio.c
Nexoniarz 527e6eac42 Raise the disk ceiling: 64-bit blocks, no FSSIZE panic, LBA48
SchFS is a 64-bit format addressing 64 ZB. The stack under it was not,
and the lowest limit was three orders of magnitude below the one anybody
would have guessed:

  ide.c   panicked on any block >= FSSIZE -- 150000 blocks, 614 MB
  ide.c   computed the sector in an int, and addressed it with LBA28
  bio.c   took a 32-bit block number, capping any device at 16 TB
  schfs   refused blocks past 0xffffffff, mirroring the cache

The FSSIZE check is the one that mattered. FSSIZE describes the size of a
v1 filesystem *image*; it had no business bounding a physical device, and
it meant a disk larger than half a gigabyte panicked the kernel rather
than being read.

struct buf's blockno is uint64 now, and so is bread's. idestart computes
the sector in 64 bits and picks LBA48 when it does not fit in 28 -- per
request, so everything that fits stays on the LBA28 path every existing
image has been read through. The 48-bit registers are written high half
first, because each is a two-deep FIFO and the other order leaves the
drive addressing whatever the low bytes alone describe.

Verified with a 2 GB disk carrying a marker at 1 GiB -- block 262144,
well past the old panic at 150000. The guest reads it back:
"MARKER-PAST-THE-OLD-LIMIT". schfs-check passes including the round-trip;
bootcheck 108 [ok].

Two limits deliberately left, both noted rather than guessed at: raw
/dev/hdN access still goes through devsw's 32-bit offset, so a raw device
is addressable to 4 GB; and usb_storage computes a 32-bit LBA, which is
what SCSI READ(10) carries -- READ(16) is a different command, not a
wider variable.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-10 18:50:31 +02:00

160 lines
3.8 KiB
C

// Buffer cache.
//
// The buffer cache is a linked list of buf structures holding
// cached copies of disk block contents. Caching disk blocks
// in memory reduces the number of disk reads and also provides
// a synchronization point for disk blocks used by multiple processes.
//
// Interface:
// * To get a buffer for a particular disk block, call bread.
// * After changing buffer data, call bwrite to write it to disk.
// * When done with the buffer, call brelse.
// * Do not use the buffer after calling brelse.
// * Only one process at a time can use a buffer,
// so do not keep them longer than necessary.
//
// The implementation uses two state flags internally:
// * B_VALID: the buffer data has been read from the disk.
// * B_DIRTY: the buffer data has been modified
// and needs to be written to disk.
#include "types.h"
#include "defs.h"
#include "param.h"
#include "spinlock.h"
#include "sleeplock.h"
#include "fs.h"
#include "buf.h"
struct {
struct spinlock lock;
struct buf buf[NBUF];
// Linked list of all buffers, through prev/next.
// head.next is most recently used.
struct buf head;
} bcache;
void
binit(void)
{
struct buf *b;
initlock(&bcache.lock, "bcache");
//PAGEBREAK!
// Create linked list of buffers
bcache.head.prev = &bcache.head;
bcache.head.next = &bcache.head;
for(b = bcache.buf; b < bcache.buf+NBUF; b++){
b->next = bcache.head.next;
b->prev = &bcache.head;
initsleeplock(&b->lock, "buffer");
bcache.head.next->prev = b;
bcache.head.next = b;
}
}
// Route a request to the driver that owns b->dev. Everything above this line
// is device-agnostic; everything below picks a backend. RAMDISK_DEV is served
// out of memory (kernel/dev/ramdisk.c), USBDISK_DEV by bulk transfers to a
// USB stick, everything else by the IDE driver.
static void
bdevrw(struct buf *b)
{
if(b->dev == RAMDISK_DEV){
ramdiskrw(b);
return;
}
if(b->dev == USBDISK_DEV){
usb_storage_rw(b);
return;
}
iderw(b);
}
// Look through buffer cache for block on device dev.
// If not found, allocate a buffer.
// In either case, return locked buffer.
static struct buf*
bget(uint dev, uint64 blockno)
{
struct buf *b;
acquire(&bcache.lock);
// Is the block already cached?
for(b = bcache.head.next; b != &bcache.head; b = b->next){
if(b->dev == dev && b->blockno == blockno){
b->refcnt++;
release(&bcache.lock);
acquiresleep(&b->lock);
return b;
}
}
// Not cached; recycle some unused buffer and clean buffer
// "clean" because B_DIRTY and not locked means log.c
// hasn't yet committed the changes to the buffer.
for(b = bcache.head.prev; b != &bcache.head; b = b->prev){
if(b->refcnt == 0 && (b->flags & B_DIRTY) == 0) {
b->dev = dev;
b->blockno = blockno;
b->flags = 0;
b->refcnt = 1;
release(&bcache.lock);
acquiresleep(&b->lock);
return b;
}
}
panic("bget: no buffers");
}
// Return a locked buf with the contents of the indicated block.
struct buf*
bread(uint dev, uint64 blockno)
{
struct buf *b;
b = bget(dev, blockno);
if(!(b->flags & B_VALID)) {
bdevrw(b);
}
return b;
}
// Write b's contents to disk. Must be locked.
void
bwrite(struct buf *b)
{
if(!holdingsleep(&b->lock))
panic("bwrite");
b->flags |= B_DIRTY;
bdevrw(b);
}
// Release a locked buffer.
// Move to the head of the MRU list.
void
brelse(struct buf *b)
{
if(!holdingsleep(&b->lock))
panic("brelse");
releasesleep(&b->lock);
acquire(&bcache.lock);
b->refcnt--;
if (b->refcnt == 0) {
// no one is waiting for it.
b->next->prev = b->prev;
b->prev->next = b->next;
b->next = bcache.head.next;
b->prev = &bcache.head;
bcache.head.next->prev = b;
bcache.head.next = b;
}
release(&bcache.lock);
}
//PAGEBREAK!