buffer.c

elinux jffs初始版本 具体了解JFFS的文件系统！

	unsigned long page;
	struct buffer_head *bh, *tmp;
	struct buffer_head * insert_point;
	int isize;

	if ((size & 511) || (size > PAGE_SIZE)) {
		printk("VFS: grow_buffers: size = %d\n",size);
		return 0;
	}

	isize = BUFSIZE_INDEX(size);

	if (!(page = __get_free_page(pri)))
		return 0;
	bh = create_buffers(page, size);
	if (!bh) {
		free_page(page);
		return 0;
	}

	insert_point = free_list[isize];

	tmp = bh;
	while (1) {
		if (insert_point) {
			tmp->b_next_free = insert_point->b_next_free;
			tmp->b_prev_free = insert_point;
			insert_point->b_next_free->b_prev_free = tmp;
			insert_point->b_next_free = tmp;
		} else {
			tmp->b_prev_free = tmp;
			tmp->b_next_free = tmp;
		}
		insert_point = tmp;
		++nr_buffers;
		if (tmp->b_this_page)
			tmp = tmp->b_this_page;
		else
			break;
	}
	tmp->b_this_page = bh;
	free_list[isize] = bh;
	mem_map[MAP_NR(page)].buffers = bh;
	buffermem += PAGE_SIZE;
	return 1;
}


/* =========== Reduce the buffer memory ============= */

static inline int buffer_waiting(struct buffer_head * bh)
{
	return waitqueue_active(&bh->b_wait);
}

/*
 * try_to_free_buffer() checks if all the buffers on this particular page
 * are unused, and free's the page if so.
 */
int try_to_free_buffer(struct buffer_head * bh, struct buffer_head ** bhp,
		       int priority)
{
	unsigned long page;
	struct buffer_head * tmp, * p;

	*bhp = bh;
	page = (unsigned long) bh->b_data;
	page &= PAGE_MASK;
	tmp = bh;
	do {
		if (!tmp)
			return 0;
		if (tmp->b_count || buffer_protected(tmp) ||
		    buffer_dirty(tmp) || buffer_locked(tmp) ||
		    buffer_waiting(tmp))
			return 0;
		if (priority && buffer_touched(tmp))
			return 0;
		tmp = tmp->b_this_page;
	} while (tmp != bh);
	tmp = bh;
	do {
		p = tmp;
		tmp = tmp->b_this_page;
		nr_buffers--;
		if (p == *bhp)
		  {
		    *bhp = p->b_prev_free;
		    if (p == *bhp) /* Was this the last in the list? */
		      *bhp = NULL;
		  }
		remove_from_queues(p);
		put_unused_buffer_head(p);
	} while (tmp != bh);
	buffermem -= PAGE_SIZE;
	mem_map[MAP_NR(page)].buffers = NULL;
	free_page(page);
	return !mem_map[MAP_NR(page)].count;
}

/* ================== Debugging =================== */

void show_buffers(void)
{
	struct buffer_head * bh;
	int found = 0, locked = 0, dirty = 0, used = 0, lastused = 0;
	int protected = 0;
	int nlist;
	static char *buf_types[NR_LIST] = {"CLEAN","LOCKED","LOCKED1","DIRTY"};

	printk("Buffer memory:   %6dkB\n",buffermem>>10);
	printk("Buffer heads:    %6d\n",nr_buffer_heads);
	printk("Buffer blocks:   %6d\n",nr_buffers);

	for(nlist = 0; nlist < NR_LIST; nlist++) {
	  found = locked = dirty = used = lastused = protected = 0;
	  bh = lru_list[nlist];
	  if(!bh) continue;

	  do {
		found++;
		if (buffer_locked(bh))
			locked++;
		if (buffer_protected(bh))
			protected++;
		if (buffer_dirty(bh))
			dirty++;
		if (bh->b_count)
			used++, lastused = found;
		bh = bh->b_next_free;
	  } while (bh != lru_list[nlist]);
	  printk("%8s: %d buffers, %d used (last=%d), "
		 "%d locked, %d protected, %d dirty\n",
		 buf_types[nlist], found, used, lastused,
		 locked, protected, dirty);
	};
}

/* ===================== Init ======================= */

/*
 * allocate the hash table and init the free list
 */
void buffer_init(void)
{
	hash_table = (struct buffer_head **)vmalloc(NR_HASH*sizeof(struct buffer_head *));
	if (!hash_table)
		panic("Failed to allocate buffer hash table\n");
	memset(hash_table,0,NR_HASH*sizeof(struct buffer_head *));

	lru_list[BUF_CLEAN] = 0;
	grow_buffers(GFP_KERNEL, BLOCK_SIZE);
}


/* ====================== bdflush support =================== */

/* This is a simple kernel daemon, whose job it is to provide a dynamic
 * response to dirty buffers.  Once this process is activated, we write back
 * a limited number of buffers to the disks and then go back to sleep again.
 */
struct wait_queue * bdflush_wait = NULL;
struct wait_queue * bdflush_done = NULL;
struct task_struct *bdflush_tsk = 0;

static void wakeup_bdflush(int wait)
{
	if (current == bdflush_tsk)
		return;
	wake_up(&bdflush_wait);
	if (wait) {
		run_task_queue(&tq_disk);
		sleep_on(&bdflush_done);
		recover_reusable_buffer_heads();
	}
}


/* 
 * Here we attempt to write back old buffers.  We also try to flush inodes 
 * and supers as well, since this function is essentially "update", and 
 * otherwise there would be no way of ensuring that these quantities ever 
 * get written back.  Ideally, we would have a timestamp on the inodes
 * and superblocks so that we could write back only the old ones as well
 */

asmlinkage int sync_old_buffers(void)
{
	int i;
	int ndirty, nwritten;
	int nlist;
	int ncount;
	struct buffer_head * bh, *next;

	sync_supers(0);
	sync_inodes(0);

	ncount = 0;
#ifdef DEBUG
	for(nlist = 0; nlist < NR_LIST; nlist++)
#else
	for(nlist = BUF_DIRTY; nlist <= BUF_DIRTY; nlist++)
#endif
	{
		ndirty = 0;
		nwritten = 0;
	repeat:
		allow_interrupts();

		bh = lru_list[nlist];
		if(bh) 
			 for (i = nr_buffers_type[nlist]; i-- > 0; bh = next) {
				 /* We may have stalled while waiting for I/O to complete. */
				 if(bh->b_list != nlist) goto repeat;
				 next = bh->b_next_free;
				 if(!lru_list[nlist]) {
					 printk("Dirty list empty %d\n", i);
					 break;
				 }
				 
				 /* Clean buffer on dirty list?  Refile it */
				 if (nlist == BUF_DIRTY && !buffer_dirty(bh) && !buffer_locked(bh))
				  {
					  refile_buffer(bh);
					  continue;
				  }
				 
				 if (buffer_locked(bh) || !buffer_dirty(bh))
					  continue;
				 ndirty++;
				 if(bh->b_flushtime > jiffies) continue;
				 nwritten++;
				 next->b_count++;
				 bh->b_count++;
				 bh->b_flushtime = 0;
#ifdef DEBUG
				 if(nlist != BUF_DIRTY) ncount++;
#endif
				 ll_rw_block(WRITE, 1, &bh);
				 bh->b_count--;
				 next->b_count--;
			 }
	}
	run_task_queue(&tq_disk);
#ifdef DEBUG
	if (ncount) printk("sync_old_buffers: %d dirty buffers not on dirty list\n", ncount);
	printk("Wrote %d/%d buffers\n", nwritten, ndirty);
#endif
	
	return 0;
}


/* This is the interface to bdflush.  As we get more sophisticated, we can
 * pass tuning parameters to this "process", to adjust how it behaves. 
 * We would want to verify each parameter, however, to make sure that it 
 * is reasonable. */

asmlinkage int sys_bdflush(int func, long data)
{
	if (!suser())
		return -EPERM;

	if (func == 1)
		 return sync_old_buffers();

	/* Basically func 1 means read param 1, 2 means write param 1, etc */
	if (func >= 2) {
		int i = (func-2) >> 1;
		if (i < 0 || i >= N_PARAM)
			return -EINVAL;
		if((func & 1) == 0) {
			int error = verify_area(VERIFY_WRITE, (int*)data, 4);
			if (!error)
				put_user(bdf_prm.data[i], (int*)data);
			return error;
		}
		if (data < bdflush_min[i] || data > bdflush_max[i])
			return -EINVAL;
		bdf_prm.data[i] = data;
	}

	/* Having func 0 used to launch the actual bdflush and then never
	 * return (unless explicitly killed). We return zero here to 
	 * remain semi-compatible with present update(8) programs.
	 */
	return 0;
}

/* This is the actual bdflush daemon itself. It used to be started from
 * the syscall above, but now we launch it ourselves internally with
 * kernel_thread(...)  directly after the first thread in init/main.c */

/* To prevent deadlocks for a loop device:
 * 1) Do non-blocking writes to loop (avoids deadlock with running
 *	out of request blocks).
 * 2) But do a blocking write if the only dirty buffers are loop buffers
 *	(otherwise we go into an infinite busy-loop).
 * 3) Quit writing loop blocks if a freelist went low (avoids deadlock
 *	with running out of free buffers for loop's "real" device).
*/
int bdflush(void * unused) 
{
	int i;
	int ndirty;
	int nlist;
	int ncount;
	struct buffer_head * bh, *next;
	int major;
	int wrta_cmd = WRITEA;	/* non-blocking write for LOOP */

	/*
	 *	We have a bare-bones task_struct, and really should fill
	 *	in a few more things so "top" and /proc/2/{exe,root,cwd}
	 *	display semi-sane things. Not real crucial though...  
	 */

	current->session = 1;
	current->pgrp = 1;
	sprintf(current->comm, "kflushd");
	bdflush_tsk = current;

	/*
	 *	As a kernel thread we want to tamper with system buffers
	 *	and other internals and thus be subject to the SMP locking
	 *	rules. (On a uniprocessor box this does nothing).
	 */


#ifdef __SMP__
	lock_kernel();
	syscall_count++;
#endif
	for (;;) {
#ifdef DEBUG
		printk("bdflush() activated...");
#endif
		
		ncount = 0;
#ifdef DEBUG
		for(nlist = 0; nlist < NR_LIST; nlist++)
#else
		for(nlist = BUF_DIRTY; nlist <= BUF_DIRTY; nlist++)
#endif
		 {
			 ndirty = 0;
			 refilled = 0;
		 repeat:
			 allow_interrupts();

			 bh = lru_list[nlist];
			 if(bh) 
				  for (i = nr_buffers_type[nlist]; i-- > 0 && ndirty < bdf_prm.b_un.ndirty; 
				       bh = next) {
					  /* We may have stalled while waiting for I/O to complete. */
					  if(bh->b_list != nlist) goto repeat;
					  next = bh->b_next_free;
					  if(!lru_list[nlist]) {
						  printk("Dirty list empty %d\n", i);
						  break;
					  }
					  
					  /* Clean buffer on dirty list?  Refile it */
					  if (nlist == BUF_DIRTY && !buffer_dirty(bh) && !buffer_locked(bh))
					   {
						   refile_buffer(bh);
						   continue;
					   }
					  
					  if (buffer_locked(bh) || !buffer_dirty(bh))
						   continue;
					  major = MAJOR(bh->b_dev);
					  /* Should we write back buffers that are shared or not??
					     currently dirty buffers are not shared, so it does not matter */
					  if (refilled && major == LOOP_MAJOR)
						   continue;
					  next->b_count++;
					  bh->b_count++;
					  ndirty++;
					  bh->b_flushtime = 0;
					  if (major == LOOP_MAJOR) {
						  ll_rw_block(wrta_cmd,1, &bh);
						  wrta_cmd = WRITEA;
						  if (buffer_dirty(bh))
							  --ndirty;
					  }
					  else
					  ll_rw_block(WRITE, 1, &bh);
#ifdef DEBUG
					  if(nlist != BUF_DIRTY) ncount++;
#endif
					  bh->b_count--;
					  next->b_count--;
				  }
		 }
#ifdef DEBUG
		if (ncount) printk("sys_bdflush: %d dirty buffers not on dirty list\n", ncount);
		printk("sleeping again.\n");
#endif
		/* If we didn't write anything, but there are still
		 * dirty buffers, then make the next write to a
		 * loop device to be a blocking write.
		 * This lets us block--which we _must_ do! */
		if (ndirty == 0 && nr_buffers_type[BUF_DIRTY] > 0 && wrta_cmd != WRITE) {
			wrta_cmd = WRITE;
			continue;
		}
		run_task_queue(&tq_disk);
		
		/* If there are still a lot of dirty buffers around, skip the sleep
		   and flush some more */
		if(ndirty == 0 || nr_buffers_type[BUF_DIRTY] <= nr_buffers * bdf_prm.b_un.nfract/100) {
			wake_up(&bdflush_done);
			current->signal = 0;
			interruptible_sleep_on(&bdflush_wait);
		}
	}
}

#ifdef MAGIC_ROM_PTR
int bromptr(kdev_t dev, struct vm_area_struct * vma)
{
        struct inode inode_fake;
        extern struct file_operations * get_blkfops(unsigned int);

        if (get_blkfops(MAJOR(dev))->romptr!=NULL)
        {
                inode_fake.i_rdev=dev;
                return get_blkfops(MAJOR(dev))->romptr(&inode_fake, NULL, vma);
        }
        return -ENOSYS;
}
#endif

/*
 * Overrides for Emacs so that we follow Linus's tabbing style.
 * Emacs will notice this stuff at the end of the file and automatically
 * adjust the settings for this buffer only.  This must remain at the end
 * of the file.
 * ---------------------------------------------------------------------------
 * Local variables:
 * c-indent-level: 8
 * c-brace-imaginary-offset: 0
 * c-brace-offset: -8
 * c-argdecl-indent: 8
 * c-label-offset: -8
 * c-continued-statement-offset: 8
 * c-continued-brace-offset: 0
 * End:
 */