bitmap.c

来自「linux 内核源代码」· C语言 代码 · 共 1,568 行 · 第 1/3 页

/*
 * bitmap.c two-level bitmap (C) Peter T. Breuer ([e-mail]) 2003
 *
 * bitmap_create  - sets up the bitmap structure
 * bitmap_destroy - destroys the bitmap structure
 *
 * additions, Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.:
 * - added disk storage for bitmap
 * - changes to allow various bitmap chunk sizes
 */

/*
 * Still to do:
 *
 * flush after percent set rather than just time based. (maybe both).
 * wait if count gets too high, wake when it drops to half.
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/sched.h>
#include <linux/list.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/buffer_head.h>
#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>

/* debug macros */

#define DEBUG 0

#if DEBUG
/* these are for debugging purposes only! */

/* define one and only one of these */
#define INJECT_FAULTS_1 0 /* cause bitmap_alloc_page to fail always */
#define INJECT_FAULTS_2 0 /* cause bitmap file to be kicked when first bit set*/
#define INJECT_FAULTS_3 0 /* treat bitmap file as kicked at init time */
#define INJECT_FAULTS_4 0 /* undef */
#define INJECT_FAULTS_5 0 /* undef */
#define INJECT_FAULTS_6 0

/* if these are defined, the driver will fail! debug only */
#define INJECT_FATAL_FAULT_1 0 /* fail kmalloc, causing bitmap_create to fail */
#define INJECT_FATAL_FAULT_2 0 /* undef */
#define INJECT_FATAL_FAULT_3 0 /* undef */
#endif

//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */
#define DPRINTK(x...) do { } while(0)

#ifndef PRINTK
#  if DEBUG > 0
#    define PRINTK(x...) printk(KERN_DEBUG x)
#  else
#    define PRINTK(x...)
#  endif
#endif

static inline char * bmname(struct bitmap *bitmap)
{
	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
}


/*
 * just a placeholder - calls kmalloc for bitmap pages
 */
static unsigned char *bitmap_alloc_page(struct bitmap *bitmap)
{
	unsigned char *page;

#ifdef INJECT_FAULTS_1
	page = NULL;
#else
	page = kmalloc(PAGE_SIZE, GFP_NOIO);
#endif
	if (!page)
		printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
	else
		PRINTK("%s: bitmap_alloc_page: allocated page at %p\n",
			bmname(bitmap), page);
	return page;
}

/*
 * for now just a placeholder -- just calls kfree for bitmap pages
 */
static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
{
	PRINTK("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page);
	kfree(page);
}

/*
 * check a page and, if necessary, allocate it (or hijack it if the alloc fails)
 *
 * 1) check to see if this page is allocated, if it's not then try to alloc
 * 2) if the alloc fails, set the page's hijacked flag so we'll use the
 *    page pointer directly as a counter
 *
 * if we find our page, we increment the page's refcount so that it stays
 * allocated while we're using it
 */
static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
{
	unsigned char *mappage;

	if (page >= bitmap->pages) {
		printk(KERN_ALERT
			"%s: invalid bitmap page request: %lu (> %lu)\n",
			bmname(bitmap), page, bitmap->pages-1);
		return -EINVAL;
	}


	if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
		return 0;

	if (bitmap->bp[page].map) /* page is already allocated, just return */
		return 0;

	if (!create)
		return -ENOENT;

	spin_unlock_irq(&bitmap->lock);

	/* this page has not been allocated yet */

	if ((mappage = bitmap_alloc_page(bitmap)) == NULL) {
		PRINTK("%s: bitmap map page allocation failed, hijacking\n",
			bmname(bitmap));
		/* failed - set the hijacked flag so that we can use the
		 * pointer as a counter */
		spin_lock_irq(&bitmap->lock);
		if (!bitmap->bp[page].map)
			bitmap->bp[page].hijacked = 1;
		goto out;
	}

	/* got a page */

	spin_lock_irq(&bitmap->lock);

	/* recheck the page */

	if (bitmap->bp[page].map || bitmap->bp[page].hijacked) {
		/* somebody beat us to getting the page */
		bitmap_free_page(bitmap, mappage);
		return 0;
	}

	/* no page was in place and we have one, so install it */

	memset(mappage, 0, PAGE_SIZE);
	bitmap->bp[page].map = mappage;
	bitmap->missing_pages--;
out:
	return 0;
}


/* if page is completely empty, put it back on the free list, or dealloc it */
/* if page was hijacked, unmark the flag so it might get alloced next time */
/* Note: lock should be held when calling this */
static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
{
	char *ptr;

	if (bitmap->bp[page].count) /* page is still busy */
		return;

	/* page is no longer in use, it can be released */

	if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */
		bitmap->bp[page].hijacked = 0;
		bitmap->bp[page].map = NULL;
		return;
	}

	/* normal case, free the page */

#if 0
/* actually ... let's not.  We will probably need the page again exactly when
 * memory is tight and we are flusing to disk
 */
	return;
#else
	ptr = bitmap->bp[page].map;
	bitmap->bp[page].map = NULL;
	bitmap->missing_pages++;
	bitmap_free_page(bitmap, ptr);
	return;
#endif
}


/*
 * bitmap file handling - read and write the bitmap file and its superblock
 */

/* copy the pathname of a file to a buffer */
char *file_path(struct file *file, char *buf, int count)
{
	struct dentry *d;
	struct vfsmount *v;

	if (!buf)
		return NULL;

	d = file->f_path.dentry;
	v = file->f_path.mnt;

	buf = d_path(d, v, buf, count);

	return IS_ERR(buf) ? NULL : buf;
}

/*
 * basic page I/O operations
 */

/* IO operations when bitmap is stored near all superblocks */
static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long index)
{
	/* choose a good rdev and read the page from there */

	mdk_rdev_t *rdev;
	struct list_head *tmp;
	struct page *page = alloc_page(GFP_KERNEL);
	sector_t target;

	if (!page)
		return ERR_PTR(-ENOMEM);

	ITERATE_RDEV(mddev, rdev, tmp) {
		if (! test_bit(In_sync, &rdev->flags)
		    || test_bit(Faulty, &rdev->flags))
			continue;

		target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);

		if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
			page->index = index;
			attach_page_buffers(page, NULL); /* so that free_buffer will
							  * quietly no-op */
			return page;
		}
	}
	return ERR_PTR(-EIO);

}

static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
{
	mdk_rdev_t *rdev;
	struct list_head *tmp;
	mddev_t *mddev = bitmap->mddev;

	ITERATE_RDEV(mddev, rdev, tmp)
		if (test_bit(In_sync, &rdev->flags)
		    && !test_bit(Faulty, &rdev->flags)) {
			int size = PAGE_SIZE;
			if (page->index == bitmap->file_pages-1)
				size = roundup(bitmap->last_page_size,
					       bdev_hardsect_size(rdev->bdev));
			/* Just make sure we aren't corrupting data or
			 * metadata
			 */
			if (bitmap->offset < 0) {
				/* DATA  BITMAP METADATA  */
				if (bitmap->offset
				    + (long)(page->index * (PAGE_SIZE/512))
				    + size/512 > 0)
					/* bitmap runs in to metadata */
					return -EINVAL;
				if (rdev->data_offset + mddev->size*2
				    > rdev->sb_offset*2 + bitmap->offset)
					/* data runs in to bitmap */
					return -EINVAL;
			} else if (rdev->sb_offset*2 < rdev->data_offset) {
				/* METADATA BITMAP DATA */
				if (rdev->sb_offset*2
				    + bitmap->offset
				    + page->index*(PAGE_SIZE/512) + size/512
				    > rdev->data_offset)
					/* bitmap runs in to data */
					return -EINVAL;
			} else {
				/* DATA METADATA BITMAP - no problems */
			}
			md_super_write(mddev, rdev,
				       (rdev->sb_offset<<1) + bitmap->offset
				       + page->index * (PAGE_SIZE/512),
				       size,
				       page);
		}

	if (wait)
		md_super_wait(mddev);
	return 0;
}

static void bitmap_file_kick(struct bitmap *bitmap);
/*
 * write out a page to a file
 */
static void write_page(struct bitmap *bitmap, struct page *page, int wait)
{
	struct buffer_head *bh;

	if (bitmap->file == NULL) {
		switch (write_sb_page(bitmap, page, wait)) {
		case -EINVAL:
			bitmap->flags |= BITMAP_WRITE_ERROR;
		}
	} else {

		bh = page_buffers(page);

		while (bh && bh->b_blocknr) {
			atomic_inc(&bitmap->pending_writes);
			set_buffer_locked(bh);
			set_buffer_mapped(bh);
			submit_bh(WRITE, bh);
			bh = bh->b_this_page;
		}

		if (wait) {
			wait_event(bitmap->write_wait,
				   atomic_read(&bitmap->pending_writes)==0);
		}
	}
	if (bitmap->flags & BITMAP_WRITE_ERROR)
		bitmap_file_kick(bitmap);
}

static void end_bitmap_write(struct buffer_head *bh, int uptodate)
{
	struct bitmap *bitmap = bh->b_private;
	unsigned long flags;

	if (!uptodate) {
		spin_lock_irqsave(&bitmap->lock, flags);
		bitmap->flags |= BITMAP_WRITE_ERROR;
		spin_unlock_irqrestore(&bitmap->lock, flags);
	}
	if (atomic_dec_and_test(&bitmap->pending_writes))
		wake_up(&bitmap->write_wait);
}

/* copied from buffer.c */
static void
__clear_page_buffers(struct page *page)
{
	ClearPagePrivate(page);
	set_page_private(page, 0);
	page_cache_release(page);
}
static void free_buffers(struct page *page)
{
	struct buffer_head *bh = page_buffers(page);

	while (bh) {
		struct buffer_head *next = bh->b_this_page;
		free_buffer_head(bh);
		bh = next;
	}
	__clear_page_buffers(page);
	put_page(page);
}

/* read a page from a file.
 * We both read the page, and attach buffers to the page to record the
 * address of each block (using bmap).  These addresses will be used
 * to write the block later, completely bypassing the filesystem.
 * This usage is similar to how swap files are handled, and allows us
 * to write to a file with no concerns of memory allocation failing.
 */
static struct page *read_page(struct file *file, unsigned long index,
			      struct bitmap *bitmap,
			      unsigned long count)
{
	struct page *page = NULL;
	struct inode *inode = file->f_path.dentry->d_inode;
	struct buffer_head *bh;
	sector_t block;

	PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
			(unsigned long long)index << PAGE_SHIFT);

	page = alloc_page(GFP_KERNEL);
	if (!page)
		page = ERR_PTR(-ENOMEM);
	if (IS_ERR(page))
		goto out;

	bh = alloc_page_buffers(page, 1<<inode->i_blkbits, 0);
	if (!bh) {
		put_page(page);
		page = ERR_PTR(-ENOMEM);
		goto out;
	}
	attach_page_buffers(page, bh);
	block = index << (PAGE_SHIFT - inode->i_blkbits);
	while (bh) {
		if (count == 0)
			bh->b_blocknr = 0;
		else {
			bh->b_blocknr = bmap(inode, block);
			if (bh->b_blocknr == 0) {
				/* Cannot use this file! */
				free_buffers(page);
				page = ERR_PTR(-EINVAL);
				goto out;
			}
			bh->b_bdev = inode->i_sb->s_bdev;
			if (count < (1<<inode->i_blkbits))
				count = 0;
			else
				count -= (1<<inode->i_blkbits);

			bh->b_end_io = end_bitmap_write;
			bh->b_private = bitmap;
			atomic_inc(&bitmap->pending_writes);
			set_buffer_locked(bh);
			set_buffer_mapped(bh);
			submit_bh(READ, bh);
		}
		block++;
		bh = bh->b_this_page;
	}
	page->index = index;

	wait_event(bitmap->write_wait,
		   atomic_read(&bitmap->pending_writes)==0);
	if (bitmap->flags & BITMAP_WRITE_ERROR) {
		free_buffers(page);
		page = ERR_PTR(-EIO);
	}
out:
	if (IS_ERR(page))
		printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
			(int)PAGE_SIZE,
			(unsigned long long)index << PAGE_SHIFT,
			PTR_ERR(page));
	return page;
}

/*
 * bitmap file superblock operations
 */

/* update the event counter and sync the superblock to disk */
void bitmap_update_sb(struct bitmap *bitmap)
{
	bitmap_super_t *sb;
	unsigned long flags;

	if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
		return;
	spin_lock_irqsave(&bitmap->lock, flags);
	if (!bitmap->sb_page) { /* no superblock */
		spin_unlock_irqrestore(&bitmap->lock, flags);
		return;
	}
	spin_unlock_irqrestore(&bitmap->lock, flags);
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	sb->events = cpu_to_le64(bitmap->mddev->events);
	if (!bitmap->mddev->degraded)
		sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
	kunmap_atomic(sb, KM_USER0);
	write_page(bitmap, bitmap->sb_page, 1);
}

/* print out the bitmap file superblock */
void bitmap_print_sb(struct bitmap *bitmap)
{
	bitmap_super_t *sb;

	if (!bitmap || !bitmap->sb_page)
		return;
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
	printk(KERN_DEBUG "          uuid: %08x.%08x.%08x.%08x\n",
					*(__u32 *)(sb->uuid+0),
					*(__u32 *)(sb->uuid+4),
					*(__u32 *)(sb->uuid+8),
					*(__u32 *)(sb->uuid+12));
	printk(KERN_DEBUG "        events: %llu\n",
			(unsigned long long) le64_to_cpu(sb->events));
	printk(KERN_DEBUG "events cleared: %llu\n",
			(unsigned long long) le64_to_cpu(sb->events_cleared));
	printk(KERN_DEBUG "         state: %08x\n", le32_to_cpu(sb->state));
	printk(KERN_DEBUG "     chunksize: %d B\n", le32_to_cpu(sb->chunksize));
	printk(KERN_DEBUG "  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
	printk(KERN_DEBUG "     sync size: %llu KB\n",
			(unsigned long long)le64_to_cpu(sb->sync_size)/2);
	printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));
	kunmap_atomic(sb, KM_USER0);
}

/* read the superblock from the bitmap file and initialize some bitmap fields */
static int bitmap_read_sb(struct bitmap *bitmap)
{
	char *reason = NULL;
	bitmap_super_t *sb;
	unsigned long chunksize, daemon_sleep, write_behind;
	unsigned long long events;
	int err = -EINVAL;

	/* page 0 is the superblock, read it... */
	if (bitmap->file) {
		loff_t isize = i_size_read(bitmap->file->f_mapping->host);
		int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;

		bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);