xfs_inode.c

linux 内核源代码

 * at least do it for regular files.
 */
#ifdef DEBUG
void
xfs_isize_check(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	xfs_fsize_t	isize)
{
	xfs_fileoff_t	map_first;
	int		nimaps;
	xfs_bmbt_irec_t	imaps[2];

	if ((ip->i_d.di_mode & S_IFMT) != S_IFREG)
		return;

	if (ip->i_d.di_flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_EXTSIZE))
		return;

	nimaps = 2;
	map_first = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
	/*
	 * The filesystem could be shutting down, so bmapi may return
	 * an error.
	 */
	if (xfs_bmapi(NULL, ip, map_first,
			 (XFS_B_TO_FSB(mp,
				       (xfs_ufsize_t)XFS_MAXIOFFSET(mp)) -
			  map_first),
			 XFS_BMAPI_ENTIRE, NULL, 0, imaps, &nimaps,
			 NULL, NULL))
	    return;
	ASSERT(nimaps == 1);
	ASSERT(imaps[0].br_startblock == HOLESTARTBLOCK);
}
#endif	/* DEBUG */

/*
 * Calculate the last possible buffered byte in a file.  This must
 * include data that was buffered beyond the EOF by the write code.
 * This also needs to deal with overflowing the xfs_fsize_t type
 * which can happen for sizes near the limit.
 *
 * We also need to take into account any blocks beyond the EOF.  It
 * may be the case that they were buffered by a write which failed.
 * In that case the pages will still be in memory, but the inode size
 * will never have been updated.
 */
xfs_fsize_t
xfs_file_last_byte(
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp;
	xfs_fsize_t	last_byte;
	xfs_fileoff_t	last_block;
	xfs_fileoff_t	size_last_block;
	int		error;

	ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE | MR_ACCESS));

	mp = ip->i_mount;
	/*
	 * Only check for blocks beyond the EOF if the extents have
	 * been read in.  This eliminates the need for the inode lock,
	 * and it also saves us from looking when it really isn't
	 * necessary.
	 */
	if (ip->i_df.if_flags & XFS_IFEXTENTS) {
		error = xfs_bmap_last_offset(NULL, ip, &last_block,
			XFS_DATA_FORK);
		if (error) {
			last_block = 0;
		}
	} else {
		last_block = 0;
	}
	size_last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)ip->i_size);
	last_block = XFS_FILEOFF_MAX(last_block, size_last_block);

	last_byte = XFS_FSB_TO_B(mp, last_block);
	if (last_byte < 0) {
		return XFS_MAXIOFFSET(mp);
	}
	last_byte += (1 << mp->m_writeio_log);
	if (last_byte < 0) {
		return XFS_MAXIOFFSET(mp);
	}
	return last_byte;
}

#if defined(XFS_RW_TRACE)
STATIC void
xfs_itrunc_trace(
	int		tag,
	xfs_inode_t	*ip,
	int		flag,
	xfs_fsize_t	new_size,
	xfs_off_t	toss_start,
	xfs_off_t	toss_finish)
{
	if (ip->i_rwtrace == NULL) {
		return;
	}

	ktrace_enter(ip->i_rwtrace,
		     (void*)((long)tag),
		     (void*)ip,
		     (void*)(unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff),
		     (void*)(unsigned long)(ip->i_d.di_size & 0xffffffff),
		     (void*)((long)flag),
		     (void*)(unsigned long)((new_size >> 32) & 0xffffffff),
		     (void*)(unsigned long)(new_size & 0xffffffff),
		     (void*)(unsigned long)((toss_start >> 32) & 0xffffffff),
		     (void*)(unsigned long)(toss_start & 0xffffffff),
		     (void*)(unsigned long)((toss_finish >> 32) & 0xffffffff),
		     (void*)(unsigned long)(toss_finish & 0xffffffff),
		     (void*)(unsigned long)current_cpu(),
		     (void*)(unsigned long)current_pid(),
		     (void*)NULL,
		     (void*)NULL,
		     (void*)NULL);
}
#else
#define	xfs_itrunc_trace(tag, ip, flag, new_size, toss_start, toss_finish)
#endif

/*
 * Start the truncation of the file to new_size.  The new size
 * must be smaller than the current size.  This routine will
 * clear the buffer and page caches of file data in the removed
 * range, and xfs_itruncate_finish() will remove the underlying
 * disk blocks.
 *
 * The inode must have its I/O lock locked EXCLUSIVELY, and it
 * must NOT have the inode lock held at all.  This is because we're
 * calling into the buffer/page cache code and we can't hold the
 * inode lock when we do so.
 *
 * We need to wait for any direct I/Os in flight to complete before we
 * proceed with the truncate. This is needed to prevent the extents
 * being read or written by the direct I/Os from being removed while the
 * I/O is in flight as there is no other method of synchronising
 * direct I/O with the truncate operation.  Also, because we hold
 * the IOLOCK in exclusive mode, we prevent new direct I/Os from being
 * started until the truncate completes and drops the lock. Essentially,
 * the vn_iowait() call forms an I/O barrier that provides strict ordering
 * between direct I/Os and the truncate operation.
 *
 * The flags parameter can have either the value XFS_ITRUNC_DEFINITE
 * or XFS_ITRUNC_MAYBE.  The XFS_ITRUNC_MAYBE value should be used
 * in the case that the caller is locking things out of order and
 * may not be able to call xfs_itruncate_finish() with the inode lock
 * held without dropping the I/O lock.  If the caller must drop the
 * I/O lock before calling xfs_itruncate_finish(), then xfs_itruncate_start()
 * must be called again with all the same restrictions as the initial
 * call.
 */
int
xfs_itruncate_start(
	xfs_inode_t	*ip,
	uint		flags,
	xfs_fsize_t	new_size)
{
	xfs_fsize_t	last_byte;
	xfs_off_t	toss_start;
	xfs_mount_t	*mp;
	bhv_vnode_t	*vp;
	int		error = 0;

	ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
	ASSERT((new_size == 0) || (new_size <= ip->i_size));
	ASSERT((flags == XFS_ITRUNC_DEFINITE) ||
	       (flags == XFS_ITRUNC_MAYBE));

	mp = ip->i_mount;
	vp = XFS_ITOV(ip);

	/* wait for the completion of any pending DIOs */
	if (new_size < ip->i_size)
		vn_iowait(ip);

	/*
	 * Call toss_pages or flushinval_pages to get rid of pages
	 * overlapping the region being removed.  We have to use
	 * the less efficient flushinval_pages in the case that the
	 * caller may not be able to finish the truncate without
	 * dropping the inode's I/O lock.  Make sure
	 * to catch any pages brought in by buffers overlapping
	 * the EOF by searching out beyond the isize by our
	 * block size. We round new_size up to a block boundary
	 * so that we don't toss things on the same block as
	 * new_size but before it.
	 *
	 * Before calling toss_page or flushinval_pages, make sure to
	 * call remapf() over the same region if the file is mapped.
	 * This frees up mapped file references to the pages in the
	 * given range and for the flushinval_pages case it ensures
	 * that we get the latest mapped changes flushed out.
	 */
	toss_start = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
	toss_start = XFS_FSB_TO_B(mp, toss_start);
	if (toss_start < 0) {
		/*
		 * The place to start tossing is beyond our maximum
		 * file size, so there is no way that the data extended
		 * out there.
		 */
		return 0;
	}
	last_byte = xfs_file_last_byte(ip);
	xfs_itrunc_trace(XFS_ITRUNC_START, ip, flags, new_size, toss_start,
			 last_byte);
	if (last_byte > toss_start) {
		if (flags & XFS_ITRUNC_DEFINITE) {
			xfs_tosspages(ip, toss_start,
					-1, FI_REMAPF_LOCKED);
		} else {
			error = xfs_flushinval_pages(ip, toss_start,
					-1, FI_REMAPF_LOCKED);
		}
	}

#ifdef DEBUG
	if (new_size == 0) {
		ASSERT(VN_CACHED(vp) == 0);
	}
#endif
	return error;
}

/*
 * Shrink the file to the given new_size.  The new
 * size must be smaller than the current size.
 * This will free up the underlying blocks
 * in the removed range after a call to xfs_itruncate_start()
 * or xfs_atruncate_start().
 *
 * The transaction passed to this routine must have made
 * a permanent log reservation of at least XFS_ITRUNCATE_LOG_RES.
 * This routine may commit the given transaction and
 * start new ones, so make sure everything involved in
 * the transaction is tidy before calling here.
 * Some transaction will be returned to the caller to be
 * committed.  The incoming transaction must already include
 * the inode, and both inode locks must be held exclusively.
 * The inode must also be "held" within the transaction.  On
 * return the inode will be "held" within the returned transaction.
 * This routine does NOT require any disk space to be reserved
 * for it within the transaction.
 *
 * The fork parameter must be either xfs_attr_fork or xfs_data_fork,
 * and it indicates the fork which is to be truncated.  For the
 * attribute fork we only support truncation to size 0.
 *
 * We use the sync parameter to indicate whether or not the first
 * transaction we perform might have to be synchronous.  For the attr fork,
 * it needs to be so if the unlink of the inode is not yet known to be
 * permanent in the log.  This keeps us from freeing and reusing the
 * blocks of the attribute fork before the unlink of the inode becomes
 * permanent.
 *
 * For the data fork, we normally have to run synchronously if we're
 * being called out of the inactive path or we're being called
 * out of the create path where we're truncating an existing file.
 * Either way, the truncate needs to be sync so blocks don't reappear
 * in the file with altered data in case of a crash.  wsync filesystems
 * can run the first case async because anything that shrinks the inode
 * has to run sync so by the time we're called here from inactive, the
 * inode size is permanently set to 0.
 *
 * Calls from the truncate path always need to be sync unless we're
 * in a wsync filesystem and the file has already been unlinked.
 *
 * The caller is responsible for correctly setting the sync parameter.
 * It gets too hard for us to guess here which path we're being called
 * out of just based on inode state.
 */
int
xfs_itruncate_finish(
	xfs_trans_t	**tp,
	xfs_inode_t	*ip,
	xfs_fsize_t	new_size,
	int		fork,
	int		sync)
{
	xfs_fsblock_t	first_block;
	xfs_fileoff_t	first_unmap_block;
	xfs_fileoff_t	last_block;
	xfs_filblks_t	unmap_len=0;
	xfs_mount_t	*mp;
	xfs_trans_t	*ntp;
	int		done;
	int		committed;
	xfs_bmap_free_t	free_list;
	int		error;

	ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);
	ASSERT((new_size == 0) || (new_size <= ip->i_size));
	ASSERT(*tp != NULL);
	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
	ASSERT(ip->i_transp == *tp);
	ASSERT(ip->i_itemp != NULL);
	ASSERT(ip->i_itemp->ili_flags & XFS_ILI_HOLD);


	ntp = *tp;
	mp = (ntp)->t_mountp;
	ASSERT(! XFS_NOT_DQATTACHED(mp, ip));

	/*
	 * We only support truncating the entire attribute fork.
	 */
	if (fork == XFS_ATTR_FORK) {
		new_size = 0LL;
	}
	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
	xfs_itrunc_trace(XFS_ITRUNC_FINISH1, ip, 0, new_size, 0, 0);
	/*
	 * The first thing we do is set the size to new_size permanently
	 * on disk.  This way we don't have to worry about anyone ever
	 * being able to look at the data being freed even in the face
	 * of a crash.  What we're getting around here is the case where
	 * we free a block, it is allocated to another file, it is written
	 * to, and then we crash.  If the new data gets written to the
	 * file but the log buffers containing the free and reallocation
	 * don't, then we'd end up with garbage in the blocks being freed.
	 * As long as we make the new_size permanent before actually
	 * freeing any blocks it doesn't matter if they get writtten to.
	 *
	 * The callers must signal into us whether or not the size
	 * setting here must be synchronous.  There are a few cases
	 * where it doesn't have to be synchronous.  Those cases
	 * occur if the file is unlinked and we know the unlink is
	 * permanent or if the blocks being truncated are guaranteed
	 * to be beyond the inode eof (regardless of the link count)
	 * and the eof value is permanent.  Both of these cases occur
	 * only on wsync-mounted filesystems.  In those cases, we're
	 * guaranteed that no user will ever see the data in the blocks
	 * that are being truncated so the truncate can run async.
	 * In the free beyond eof case, the file may wind up with
	 * more blocks allocated to it than it needs if we crash
	 * and that won't get fixed until the next time the file
	 * is re-opened and closed but that's ok as that shouldn't
	 * be too many blocks.
	 *
	 * However, we can't just make all wsync xactions run async
	 * because there's one call out of the create path that needs
	 * to run sync where it's truncating an existing file to size
	 * 0 whose size is > 0.
	 *
	 * It's probably possible to come up with a test in this
	 * routine that would correctly distinguish all the above
	 * cases from the values of the function parameters and the
	 * inode state but for sanity's sake, I've decided to let the
	 * layers above just tell us.  It's simpler to correctly figure
	 * out in the layer above exactly under what conditions we
	 * can run async and I think it's easier for others read and
	 * follow the logic in case something has to be changed.
	 * cscope is your friend -- rcc.
	 *
	 * The attribute fork is much simpler.
	 *
	 * For the attribute fork we allow the caller to tell us whether
	 * the unlink of the inode that led to this call is yet permanent
	 * in the on disk log.  If it is not and we will be freeing extents
	 * in this inode then we make the first transaction synchronous
	 * to make sure that the unlink is permanent by the time we free
	 * the blocks.
	 */
	if (fork == XFS_DATA_FORK) {
		if (ip->i_d.di_nextents > 0) {
			/*
			 * If we are not changing the file size then do
			 * not update the on-disk file size - we may be
			 * called from xfs_inactive_free_eofblocks().  If we
			 * update the on-disk file size and then the system
			 * crashes before the contents of the file are
			 * flushed to disk then the files may be full of
			 * holes (ie NULL files bug).
			 */
			if (ip->i_size != new_size) {
				ip->i_d.di_size = new_size;
				ip->i_size = new_size;
				xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
			}
		}
	} else if (sync) {
		ASSERT(!(mp->m_flags & XFS_MOUNT_WSYNC));
		if (ip->i_d.di_anextents > 0)
			xfs_trans_set_sync(ntp);
	}
	ASSERT(fork == XFS_DATA_FORK ||
		(fork == XFS_ATTR_FORK &&
			((sync && !(mp->m_flags & XFS_MOUNT_WSYNC)) ||
			 (sync == 0 && (mp->m_flags & XFS_MOUNT_WSYNC)))));

	/*
	 * Since it is possible for space to become allocated beyond
	 * the end of the file (in a crash where the space is allocated
	 * but the inode size is not yet updated), simply remove any
	 * blocks which show up between the new EOF and the maximum
	 * possible file size.  If the first block to be removed is
	 * beyond the maximum file size (ie it is the same as last_block),
	 * then there is nothing to do.
	 */
	last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
	ASSERT(first_unmap_block <= last_block);
	done = 0;
	if (last_block == first_unmap_block) {
		done = 1;
	} else {
		unmap_len = last_block - first_unmap_block + 1;
	}
	while (!done) {
		/*
		 * Free up up to XFS_ITRUNC_MAX_EXTENTS.  xfs_bunmapi()
		 * will tell us whether it freed the entire range or
		 * not.  If this is a synchronous mount (wsync),
		 * then we can tell bunmapi to keep all the
		 * transactions asynchronous since the unlink
		 * transaction that made this inode inactive has
		 * already hit the disk.  There's no danger of
		 * the freed blocks being reused, there being a
		 * crash, and the reused blocks suddenly reappearing
		 * in this file with garbage in them once recovery
		 * runs.
		 */