Re: [PATCH 34/63] xfs: support removing extents from CoW fork

[Brian Foster <bfoster@redhat.com>]

On Thu, Sep 29, 2016 at 08:09:21PM -0700, Darrick J. Wong wrote:
> Create a helper method to remove extents from the CoW fork without
> any of the side effects (rmapbt/bmbt updates) of the regular extent
> deletion routine.  We'll eventually use this to clear out the CoW fork
> during ioend processing.
> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
> v2: Use bmapi_read to iterate and trim the CoW extents instead of
> reading them raw via the iext code.
> ---
>  fs/xfs/libxfs/xfs_bmap.c |  176 ++++++++++++++++++++++++++++++++++++++++++++++
>  fs/xfs/libxfs/xfs_bmap.h |    1 
>  2 files changed, 177 insertions(+)
> 
> 
> diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
> index 85a0c86..451f3e4 100644
> --- a/fs/xfs/libxfs/xfs_bmap.c
> +++ b/fs/xfs/libxfs/xfs_bmap.c
> @@ -4906,6 +4906,7 @@ xfs_bmap_del_extent(
>  		/*
>  		 * Matches the whole extent.  Delete the entry.
>  		 */
> +		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
>  		xfs_iext_remove(ip, *idx, 1,
>  				whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0);
>  		--*idx;
> @@ -5123,6 +5124,181 @@ xfs_bmap_del_extent(
>  }
>  
>  /*
> + * xfs_bunmapi_cow() -- Remove the relevant parts of the CoW fork.
> + *			See xfs_bmap_del_extent.
> + * @ip: XFS inode.
> + * @idx: Extent number to delete.
> + * @del: Extent to remove.
> + */
> +int
> +xfs_bunmapi_cow(
> +	xfs_inode_t		*ip,
> +	xfs_bmbt_irec_t		*del)
> +{
> +	xfs_filblks_t		da_new;	/* new delay-alloc indirect blocks */
> +	xfs_filblks_t		da_old;	/* old delay-alloc indirect blocks */
> +	xfs_fsblock_t		del_endblock = 0;/* first block past del */
> +	xfs_fileoff_t		del_endoff;	/* first offset past del */
> +	int			delay;	/* current block is delayed allocated */
> +	xfs_bmbt_rec_host_t	*ep;	/* current extent entry pointer */
> +	int			error;	/* error return value */
> +	xfs_bmbt_irec_t		got;	/* current extent entry */
> +	xfs_fileoff_t		got_endoff;	/* first offset past got */
> +	xfs_ifork_t		*ifp;	/* inode fork pointer */
> +	xfs_mount_t		*mp;	/* mount structure */
> +	xfs_filblks_t		nblks;	/* quota/sb block count */
> +	xfs_bmbt_irec_t		new;	/* new record to be inserted */
> +	/* REFERENCED */
> +	uint			qfield;	/* quota field to update */
> +	xfs_filblks_t		temp;	/* for indirect length calculations */
> +	xfs_filblks_t		temp2;	/* for indirect length calculations */
> +	int			state = BMAP_COWFORK;
> +	int			eof;
> +	xfs_extnum_t		eidx;
> +
> +	mp = ip->i_mount;
> +	XFS_STATS_INC(mp, xs_del_exlist);
> +
> +	ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
> +			&eidx, &got, &new);
> +
> +	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
> +	ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
> +		(uint)sizeof(xfs_bmbt_rec_t)));

The alignment above is a little wonky. E.g.:

	ASSERT((eidx >= 0) &&
	       (eidx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));

... but it sounds like hch plans to clean this up and rework it in the
near future.

> +	ASSERT(del->br_blockcount > 0);
> +	ASSERT(got.br_startoff <= del->br_startoff);
> +	del_endoff = del->br_startoff + del->br_blockcount;
> +	got_endoff = got.br_startoff + got.br_blockcount;
> +	ASSERT(got_endoff >= del_endoff);
> +	delay = isnullstartblock(got.br_startblock);
> +	ASSERT(isnullstartblock(del->br_startblock) == delay);
> +	qfield = 0;
> +	error = 0;
> +	/*
> +	 * If deleting a real allocation, must free up the disk space.
> +	 */
> +	if (!delay) {
> +		nblks = del->br_blockcount;
> +		qfield = XFS_TRANS_DQ_BCOUNT;
> +		/*
> +		 * Set up del_endblock and cur for later.
> +		 */
> +		del_endblock = del->br_startblock + del->br_blockcount;
> +		da_old = da_new = 0;
> +	} else {
> +		da_old = startblockval(got.br_startblock);
> +		da_new = 0;
> +		nblks = 0;
> +	}
> +	qfield = qfield;
> +	nblks = nblks;
> +
> +	/*
> +	 * Set flag value to use in switch statement.
> +	 * Left-contig is 2, right-contig is 1.
> +	 */
> +	switch (((got.br_startoff == del->br_startoff) << 1) |
> +		(got_endoff == del_endoff)) {
> +	case 3:
> +		/*
> +		 * Matches the whole extent.  Delete the entry.
> +		 */
> +		xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
> +		--eidx;
> +		break;
> +
> +	case 2:
> +		/*
> +		 * Deleting the first part of the extent.
> +		 */
> +		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
> +		xfs_bmbt_set_startoff(ep, del_endoff);
> +		temp = got.br_blockcount - del->br_blockcount;
> +		xfs_bmbt_set_blockcount(ep, temp);
> +		if (delay) {
> +			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
> +				da_old);
> +			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
> +			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
> +			da_new = temp;
> +			break;
> +		}
> +		xfs_bmbt_set_startblock(ep, del_endblock);
> +		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
> +		break;
> +
> +	case 1:
> +		/*
> +		 * Deleting the last part of the extent.
> +		 */
> +		temp = got.br_blockcount - del->br_blockcount;
> +		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
> +		xfs_bmbt_set_blockcount(ep, temp);
> +		if (delay) {
> +			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
> +				da_old);
> +			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
> +			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
> +			da_new = temp;
> +			break;
> +		}
> +		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
> +		break;
> +
> +	case 0:
> +		/*
> +		 * Deleting the middle of the extent.
> +		 */
> +		temp = del->br_startoff - got.br_startoff;
> +		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
> +		xfs_bmbt_set_blockcount(ep, temp);
> +		new.br_startoff = del_endoff;
> +		temp2 = got_endoff - del_endoff;
> +		new.br_blockcount = temp2;
> +		new.br_state = got.br_state;
> +		if (!delay) {
> +			new.br_startblock = del_endblock;
> +		} else {
> +			temp = xfs_bmap_worst_indlen(ip, temp);
> +			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
> +			temp2 = xfs_bmap_worst_indlen(ip, temp2);
> +			new.br_startblock = nullstartblock((int)temp2);
> +			da_new = temp + temp2;
> +			while (da_new > da_old) {
> +				if (temp) {
> +					temp--;
> +					da_new--;
> +					xfs_bmbt_set_startblock(ep,
> +						nullstartblock((int)temp));
> +				}
> +				if (da_new == da_old)
> +					break;
> +				if (temp2) {
> +					temp2--;
> +					da_new--;
> +					new.br_startblock =
> +						nullstartblock((int)temp2);
> +				}
> +			}

xfs_bmap_split_indlen() ?

Brian

> +		}
> +		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
> +		xfs_iext_insert(ip, eidx + 1, 1, &new, state);
> +		++eidx;
> +		break;
> +	}
> +
> +	/*
> +	 * Account for change in delayed indirect blocks.
> +	 * Nothing to do for disk quota accounting here.
> +	 */
> +	ASSERT(da_old >= da_new);
> +	if (da_old > da_new)
> +		xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
> +
> +	return error;
> +}
> +
> +/*
>   * Unmap (remove) blocks from a file.
>   * If nexts is nonzero then the number of extents to remove is limited to
>   * that value.  If not all extents in the block range can be removed then
> diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
> index 75b1a1f..7c4ad01 100644
> --- a/fs/xfs/libxfs/xfs_bmap.h
> +++ b/fs/xfs/libxfs/xfs_bmap.h
> @@ -221,6 +221,7 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
>  		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
>  		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
>  		struct xfs_defer_ops *dfops, int *done);
> +int	xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
>  int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
>  		xfs_extnum_t num);
>  uint	xfs_default_attroffset(struct xfs_inode *ip);
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html