buffer.c

基于组件方式开发操作系统的OSKIT源代码

/*
 *  linux/fs/buffer.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  OSKit support added by the University of Utah, 1997
 */

/*
 *  'buffer.c' implements the buffer-cache functions. Race-conditions have
 * been avoided by NEVER letting an interrupt change a buffer (except for the
 * data, of course), but instead letting the caller do it.
 */

/* Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 */

/* Removed a lot of unnecessary code and simplified things now that
 * the buffer cache isn't our primary cache - Andrew Tridgell 12/96
 */

/* Speed up hash, lru, and free list operations.  Use gfp() for allocating
 * hash table, use SLAB cache for buffer heads. -DaveM
 */

/* Added 32k buffer block sizes - these are required older ARM systems.
 * - RMK
 */

#include <linux/malloc.h>
#include <linux/locks.h>
#include <linux/errno.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/smp_lock.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/sysrq.h>
#include <linux/file.h>
#include <linux/init.h>
#include <linux/quotaops.h>

#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/bitops.h>

#define NR_SIZES 7
static char buffersize_index[65] =
{-1,  0,  1, -1,  2, -1, -1, -1, 3, -1, -1, -1, -1, -1, -1, -1,
  4, -1, -1, -1, -1, -1, -1, -1, -1,-1, -1, -1, -1, -1, -1, -1,
  5, -1, -1, -1, -1, -1, -1, -1, -1,-1, -1, -1, -1, -1, -1, -1,
 -1, -1, -1, -1, -1, -1, -1, -1, -1,-1, -1, -1, -1, -1, -1, -1,
  6};

#define BUFSIZE_INDEX(X) ((int) buffersize_index[(X)>>9])
#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512)
#define NR_RESERVED (2*MAX_BUF_PER_PAGE)
#define MAX_UNUSED_BUFFERS NR_RESERVED+20 /* don't ever have more than this 
					     number of unused buffer heads */

/*
 * Hash table mask..
 */
static unsigned long bh_hash_mask = 0;

static int grow_buffers(int size);

static struct buffer_head ** hash_table;
static struct buffer_head * lru_list[NR_LIST] = {NULL, };
static struct buffer_head * free_list[NR_SIZES] = {NULL, };

static kmem_cache_t *bh_cachep;

static struct buffer_head * unused_list = NULL;
static struct buffer_head * reuse_list = NULL;
static struct wait_queue * buffer_wait = NULL;

static int nr_buffers = 0;
static int nr_buffers_type[NR_LIST] = {0,};
static int nr_buffer_heads = 0;
static int nr_unused_buffer_heads = 0;
static int nr_hashed_buffers = 0;

/* This is used by some architectures to estimate available memory. */
int buffermem = 0;

/* Here is the parameter block for the bdflush process. If you add or
 * remove any of the parameters, make sure to update kernel/sysctl.c.
 */

#define N_PARAM 9

/* The dummy values in this structure are left in there for compatibility
 * with old programs that play with the /proc entries.
 */
union bdflush_param{
	struct {
		int nfract;  /* Percentage of buffer cache dirty to 
				activate bdflush */
		int ndirty;  /* Maximum number of dirty blocks to write out per
				wake-cycle */
		int nrefill; /* Number of clean buffers to try to obtain
				each time we call refill */
		int nref_dirt; /* Dirty buffer threshold for activating bdflush
				  when trying to refill buffers. */
		int interval; /* jiffies delay between kupdate flushes */
		int age_buffer;  /* Time for normal buffer to age before 
				    we flush it */
		int age_super;  /* Time for superblock to age before we 
				   flush it */
		int dummy2;    /* unused */
		int dummy3;    /* unused */
	} b_un;
	unsigned int data[N_PARAM];
} bdf_prm = {{40, 500, 64, 256, 5*HZ, 30*HZ, 5*HZ, 1884, 2}};

/* These are the min and max parameter values that we will allow to be assigned */
int bdflush_min[N_PARAM] = {  0,  10,    5,   25,  0,   1*HZ,   1*HZ, 1, 1};
int bdflush_max[N_PARAM] = {100,5000, 2000, 2000,60*HZ, 600*HZ, 600*HZ, 2047, 5};

void wakeup_bdflush(int);

#ifndef OSKIT
/*
 * Rewrote the wait-routines to use the "new" wait-queue functionality,
 * and getting rid of the cli-sti pairs. The wait-queue routines still
 * need cli-sti, but now it's just a couple of 386 instructions or so.
 *
 * Note that the real wait_on_buffer() is an inline function that checks
 * if 'b_wait' is set before calling this, so that the queues aren't set
 * up unnecessarily.
 */
void __wait_on_buffer(struct buffer_head * bh)
{
	struct task_struct *tsk = current;
	struct wait_queue wait;

	bh->b_count++;
	wait.task = tsk;
	add_wait_queue(&bh->b_wait, &wait);
repeat:
	tsk->state = TASK_UNINTERRUPTIBLE;
	run_task_queue(&tq_disk);
	if (buffer_locked(bh)) {
		schedule();
		goto repeat;
	}
	tsk->state = TASK_RUNNING;
	remove_wait_queue(&bh->b_wait, &wait);
	bh->b_count--;
}
#endif /* OSKIT */

/* Call sync_buffers with wait!=0 to ensure that the call does not
 * return until all buffer writes have completed.  Sync() may return
 * before the writes have finished; fsync() may not.
 */

/* Godamity-damn.  Some buffers (bitmaps for filesystems)
 * spontaneously dirty themselves without ever brelse being called.
 * We will ultimately want to put these in a separate list, but for
 * now we search all of the lists for dirty buffers.
 */
static int sync_buffers(kdev_t dev, int wait)
{
	int i, retry, pass = 0, err = 0;
	struct buffer_head * bh, *next;

	/* One pass for no-wait, three for wait:
	 * 0) write out all dirty, unlocked buffers;
	 * 1) write out all dirty buffers, waiting if locked;
	 * 2) wait for completion by waiting for all buffers to unlock.
	 */
	do {
		retry = 0;
repeat:
		/* We search all lists as a failsafe mechanism, not because we expect
		 * there to be dirty buffers on any of the other lists.
		 */
		bh = lru_list[BUF_DIRTY];
		if (!bh)
			goto repeat2;
		for (i = nr_buffers_type[BUF_DIRTY]*2 ; i-- > 0 ; bh = next) {
			if (bh->b_list != BUF_DIRTY)
				goto repeat;
			next = bh->b_next_free;
			if (!lru_list[BUF_DIRTY])
				break;
			if (dev && bh->b_dev != dev)
				continue;
			if (buffer_locked(bh)) {
				/* Buffer is locked; skip it unless wait is
				 * requested AND pass > 0.
				 */
				if (!wait || !pass) {
					retry = 1;
					continue;
				}
				wait_on_buffer (bh);
				goto repeat;
			}

			/* If an unlocked buffer is not uptodate, there has
			 * been an IO error. Skip it.
			 */
			if (wait && buffer_req(bh) && !buffer_locked(bh) &&
			    !buffer_dirty(bh) && !buffer_uptodate(bh)) {
				err = -EIO;
				continue;
			}

			/* Don't write clean buffers.  Don't write ANY buffers
			 * on the third pass.
			 */
			if (!buffer_dirty(bh) || pass >= 2)
				continue;

			/* Don't bother about locked buffers.
			 *
			 * XXX We checked if it was locked above and there is no
			 * XXX way we could have slept in between. -DaveM
			 */
			if (buffer_locked(bh))
				continue;
			bh->b_count++;
			next->b_count++;
			bh->b_flushtime = 0;
			ll_rw_block(WRITE, 1, &bh);
			bh->b_count--;
			next->b_count--;
			retry = 1;
		}

    repeat2:
		bh = lru_list[BUF_LOCKED];
		if (!bh)
			break;
		for (i = nr_buffers_type[BUF_LOCKED]*2 ; i-- > 0 ; bh = next) {
			if (bh->b_list != BUF_LOCKED)
				goto repeat2;
			next = bh->b_next_free;
			if (!lru_list[BUF_LOCKED])
				break;
			if (dev && bh->b_dev != dev)
				continue;
			if (buffer_locked(bh)) {
				/* Buffer is locked; skip it unless wait is
				 * requested AND pass > 0.
				 */
				if (!wait || !pass) {
					retry = 1;
					continue;
				}
				wait_on_buffer (bh);
				goto repeat2;
			}
		}

		/* If we are waiting for the sync to succeed, and if any dirty
		 * blocks were written, then repeat; on the second pass, only
		 * wait for buffers being written (do not pass to write any
		 * more buffers on the second pass).
		 */
	} while (wait && retry && ++pass<=2);
	return err;
}

void sync_dev(kdev_t dev)
{
	sync_buffers(dev, 0);
	sync_supers(dev);
	sync_inodes(dev);
	sync_buffers(dev, 0);
	DQUOT_SYNC(dev);
	/*
	 * FIXME(eric) we need to sync the physical devices here.
	 * This is because some (scsi) controllers have huge amounts of
	 * cache onboard (hundreds of Mb), and we need to instruct
	 * them to commit all of the dirty memory to disk, and we should
	 * not return until this has happened.
	 *
	 * This would need to get implemented by going through the assorted
	 * layers so that each block major number can be synced, and this
	 * would call down into the upper and mid-layer scsi.
	 */
}

int fsync_dev(kdev_t dev)
{
	sync_buffers(dev, 0);
	sync_supers(dev);
	sync_inodes(dev);
	DQUOT_SYNC(dev);
	return sync_buffers(dev, 1);
}

asmlinkage int sys_sync(void)
{
	lock_kernel();
	fsync_dev(0);
	unlock_kernel();
	return 0;
}

/*
 *	filp may be NULL if called via the msync of a vma.
 */
 
int file_fsync(struct file *filp, struct dentry *dentry)
{
	struct inode * inode = dentry->d_inode;
	struct super_block * sb;
	kdev_t dev;

	/* sync the inode to buffers */
	write_inode_now(inode);

	/* sync the superblock to buffers */
	sb = inode->i_sb;
	wait_on_super(sb);
	if (sb->s_op && sb->s_op->write_super)
		sb->s_op->write_super(sb);

	/* .. finally sync the buffers to disk */
	dev = inode->i_dev;
	return sync_buffers(dev, 1);
}

#ifndef OSKIT
asmlinkage int sys_fsync(unsigned int fd)
{
	struct file * file;
	struct dentry * dentry;
	struct inode * inode;
	int err;

	lock_kernel();
	err = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	dentry = file->f_dentry;
	if (!dentry)
		goto out_putf;

	inode = dentry->d_inode;
	if (!inode)
		goto out_putf;

	err = -EINVAL;
	if (!file->f_op || !file->f_op->fsync)
		goto out_putf;

	/* We need to protect against concurrent writers.. */
	down(&inode->i_sem);
	err = file->f_op->fsync(file, dentry);
	up(&inode->i_sem);

out_putf:
	fput(file);
out:
	unlock_kernel();
	return err;
}

asmlinkage int sys_fdatasync(unsigned int fd)
{
	struct file * file;
	struct dentry * dentry;
	struct inode * inode;
	int err;

	lock_kernel();
	err = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	dentry = file->f_dentry;
	if (!dentry)
		goto out_putf;

	inode = dentry->d_inode;
	if (!inode)
		goto out_putf;

	err = -EINVAL;
	if (!file->f_op || !file->f_op->fsync)
		goto out_putf;

	/* this needs further work, at the moment it is identical to fsync() */
	down(&inode->i_sem);
	err = file->f_op->fsync(file, dentry);
	up(&inode->i_sem);

out_putf:
	fput(file);
out:
	unlock_kernel();
	return err;
}
#endif /* OSKIT */

void invalidate_buffers(kdev_t dev)
{
	int i;
	int nlist;
	struct buffer_head * bh;

	for(nlist = 0; nlist < NR_LIST; nlist++) {
		bh = lru_list[nlist];
		for (i = nr_buffers_type[nlist]*2 ; --i > 0 ; bh = bh->b_next_free) {
			if (bh->b_dev != dev)
				continue;
			wait_on_buffer(bh);
			if (bh->b_dev != dev)
				continue;
			if (bh->b_count)
				continue;
			bh->b_flushtime = 0;
			clear_bit(BH_Protected, &bh->b_state);
			clear_bit(BH_Uptodate, &bh->b_state);
			clear_bit(BH_Dirty, &bh->b_state);
			clear_bit(BH_Req, &bh->b_state);
		}
	}
}

#define _hashfn(dev,block) (((unsigned)(HASHDEV(dev)^block)) & bh_hash_mask)
#define hash(dev,block) hash_table[_hashfn(dev,block)]

static inline void remove_from_hash_queue(struct buffer_head * bh)
{
	struct buffer_head **pprev = bh->b_pprev;
	if (pprev) {
		struct buffer_head * next = bh->b_next;
		if (next) {
			next->b_pprev = pprev;
			bh->b_next = NULL;
		}
		*pprev = next;
		bh->b_pprev = NULL;
	}
	nr_hashed_buffers--;
}

static inline void remove_from_lru_list(struct buffer_head * bh)
{
	if (!(bh->b_prev_free) || !(bh->b_next_free))
		panic("VFS: LRU block list corrupted");
	if (bh->b_dev == B_FREE)
		panic("LRU list corrupted");
	bh->b_prev_free->b_next_free = bh->b_next_free;
	bh->b_next_free->b_prev_free = bh->b_prev_free;

	if (lru_list[bh->b_list] == bh)
		 lru_list[bh->b_list] = bh->b_next_free;
	if (lru_list[bh->b_list] == bh)
		 lru_list[bh->b_list] = NULL;
	bh->b_next_free = bh->b_prev_free = NULL;
}

static inline void remove_from_free_list(struct buffer_head * bh)
{
	int isize = BUFSIZE_INDEX(bh->b_size);
	if (!(bh->b_prev_free) || !(bh->b_next_free))
		panic("VFS: Free block list corrupted");
	if(bh->b_dev != B_FREE)
		panic("Free list corrupted");
	if(!free_list[isize])
		panic("Free list empty");
	if(bh->b_next_free == bh)
		 free_list[isize] = NULL;
	else {