Commit 340785cc authored by Darrick J. Wong's avatar Darrick J. Wong Committed by Dave Chinner
Browse files

xfs: add owner field to extent allocation and freeing 



For the rmap btree to work, we have to feed the extent owner
information to the the allocation and freeing functions. This
information is what will end up in the rmap btree that tracks
allocated extents. While we technically don't need the owner
information when freeing extents, passing it allows us to validate
that the extent we are removing from the rmap btree actually
belonged to the owner we expected it to belong to.

We also define a special set of owner values for internal metadata
that would otherwise have no owner. This allows us to tell the
difference between metadata owned by different per-ag btrees, as
well as static fs metadata (e.g. AG headers) and internal journal
blocks.

There are also a couple of special cases we need to take care of -
during EFI recovery, we don't actually know who the original owner
was, so we need to pass a wildcard to indicate that we aren't
checking the owner for validity. We also need special handling in
growfs, as we "free" the space in the last AG when extending it, but
because it's new space it has no actual owner...

While touching the xfs_bmap_add_free() function, re-order the
parameters to put the struct xfs_mount first.

Extend the owner field to include both the owner type and some sort
of index within the owner.  The index field will be used to support
reverse mappings when reflink is enabled.

When we're freeing extents from an EFI, we don't have the owner
information available (rmap updates have their own redo items).
xfs_free_extent therefore doesn't need to do an rmap update. Make
sure that the log replay code signals this correctly.

This is based upon a patch originally from Dave Chinner. It has been
extended to add more owner information with the intent of helping
recovery operations when things go wrong (e.g. offset of user data
block in a file).

[dchinner: de-shout the xfs_rmap_*_owner helpers]
[darrick: minor style fixes suggested by Christoph Hellwig]

Signed-off-by: default avatarDave Chinner <dchinner@redhat.com>
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: default avatarDave Chinner <dchinner@redhat.com>
Signed-off-by: default avatarDave Chinner <david@fromorbit.com>
parent 8018026e

fs/xfs/libxfs/xfs_alloc.c

+16 −10
Original line number Diff line number Diff line
@@ -36,6 +36,7 @@ 
#include "xfs_trans.h"

#include "xfs_buf_item.h"

#include "xfs_log.h"

#include "xfs_rmap.h"



struct workqueue_struct *xfs_alloc_wq;
@@ -1589,14 +1590,15 @@ error0: 
/*

 * Free the extent starting at agno/bno for length.

 */

STATIC int			/* error */

STATIC int

xfs_free_ag_extent(

	xfs_trans_t	*tp,	/* transaction pointer */

	xfs_buf_t	*agbp,	/* buffer for a.g. freelist header */

	xfs_agnumber_t	agno,	/* allocation group number */

	xfs_agblock_t	bno,	/* starting block number */

	xfs_extlen_t	len,	/* length of extent */

	int		isfl)	/* set if is freelist blocks - no sb acctg */

	xfs_trans_t		*tp,

	xfs_buf_t		*agbp,

	xfs_agnumber_t		agno,

	xfs_agblock_t		bno,

	xfs_extlen_t		len,

	struct xfs_owner_info	*oinfo,

	int			isfl)

{

	xfs_btree_cur_t	*bno_cur;	/* cursor for by-block btree */

	xfs_btree_cur_t	*cnt_cur;	/* cursor for by-size btree */
@@ -2005,13 +2007,15 @@ xfs_alloc_fix_freelist( 
	 * back on the free list? Maybe we should only do this when space is

	 * getting low or the AGFL is more than half full?

	 */

	xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);

	while (pag->pagf_flcount > need) {

		struct xfs_buf	*bp;



		error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);

		if (error)

			goto out_agbp_relse;

		error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1, 1);

		error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1,

					   &targs.oinfo, 1);

		if (error)

			goto out_agbp_relse;

		bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
@@ -2021,6 +2025,7 @@ xfs_alloc_fix_freelist( 
	memset(&targs, 0, sizeof(targs));

	targs.tp = tp;

	targs.mp = mp;

	xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);

	targs.agbp = agbp;

	targs.agno = args->agno;

	targs.alignment = targs.minlen = targs.prod = targs.isfl = 1;
@@ -2709,7 +2714,8 @@ int /* error */ 
xfs_free_extent(

	struct xfs_trans	*tp,	/* transaction pointer */

	xfs_fsblock_t		bno,	/* starting block number of extent */

	xfs_extlen_t		len)	/* length of extent */

	xfs_extlen_t		len,	/* length of extent */

	struct xfs_owner_info	*oinfo)	/* extent owner */

{

	struct xfs_mount	*mp = tp->t_mountp;

	struct xfs_buf		*agbp;
@@ -2737,7 +2743,7 @@ xfs_free_extent( 
		agbno + len <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_length),

				err);



	error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, 0);

	error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, oinfo, 0);

	if (error)

		goto err;

fs/xfs/libxfs/xfs_alloc.h

+5 −3
Original line number Diff line number Diff line
@@ -123,6 +123,7 @@ typedef struct xfs_alloc_arg { 
	char		isfl;		/* set if is freelist blocks - !acctg */

	char		userdata;	/* mask defining userdata treatment */

	xfs_fsblock_t	firstblock;	/* io first block allocated */

	struct xfs_owner_info	oinfo;	/* owner of blocks being allocated */

} xfs_alloc_arg_t;



/*
@@ -210,7 +211,8 @@ int /* error */ 
xfs_free_extent(

	struct xfs_trans	*tp,	/* transaction pointer */

	xfs_fsblock_t		bno,	/* starting block number of extent */

	xfs_extlen_t	len);	/* length of extent */

	xfs_extlen_t		len,	/* length of extent */

	struct xfs_owner_info	*oinfo);/* extent owner */



int				/* error */

xfs_alloc_lookup_ge(

fs/xfs/libxfs/xfs_bmap.c

+19 −6
Original line number Diff line number Diff line
@@ -46,6 +46,7 @@ 
#include "xfs_symlink.h"

#include "xfs_attr_leaf.h"

#include "xfs_filestream.h"

#include "xfs_rmap.h"





kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -571,10 +572,11 @@ xfs_bmap_validate_ret( 
 */

void

xfs_bmap_add_free(

	struct xfs_mount	*mp,		/* mount point structure */

	struct xfs_defer_ops	*dfops,		/* list of extents */

	xfs_fsblock_t		bno,		/* fs block number of extent */

	xfs_filblks_t		len)		/* length of extent */

	struct xfs_mount		*mp,

	struct xfs_defer_ops		*dfops,

	xfs_fsblock_t			bno,

	xfs_filblks_t			len,

	struct xfs_owner_info		*oinfo)

{

	struct xfs_extent_free_item	*new;		/* new element */

#ifdef DEBUG
@@ -593,9 +595,14 @@ xfs_bmap_add_free( 
	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);

#endif

	ASSERT(xfs_bmap_free_item_zone != NULL);



	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);

	new->xefi_startblock = bno;

	new->xefi_blockcount = (xfs_extlen_t)len;

	if (oinfo)

		new->xefi_oinfo = *oinfo;

	else

		xfs_rmap_skip_owner_update(&new->xefi_oinfo);

	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,

			XFS_FSB_TO_AGBNO(mp, bno), len);

	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
@@ -628,6 +635,7 @@ xfs_bmap_btree_to_extents( 
	xfs_mount_t		*mp;	/* mount point structure */

	__be64			*pp;	/* ptr to block address */

	struct xfs_btree_block	*rblock;/* root btree block */

	struct xfs_owner_info	oinfo;



	mp = ip->i_mount;

	ifp = XFS_IFORK_PTR(ip, whichfork);
@@ -651,7 +659,8 @@ xfs_bmap_btree_to_extents( 
	cblock = XFS_BUF_TO_BLOCK(cbp);

	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))

		return error;

	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1);

	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);

	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo);

	ip->i_d.di_nblocks--;

	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);

	xfs_trans_binval(tp, cbp);
@@ -732,6 +741,7 @@ xfs_bmap_extents_to_btree( 
	memset(&args, 0, sizeof(args));

	args.tp = tp;

	args.mp = mp;

	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);

	args.firstblock = *firstblock;

	if (*firstblock == NULLFSBLOCK) {

		args.type = XFS_ALLOCTYPE_START_BNO;
@@ -878,6 +888,7 @@ xfs_bmap_local_to_extents( 
	memset(&args, 0, sizeof(args));

	args.tp = tp;

	args.mp = ip->i_mount;

	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);

	args.firstblock = *firstblock;

	/*

	 * Allocate a block.  We know we need only one, since the
@@ -3660,6 +3671,7 @@ xfs_bmap_btalloc( 
	args.tp = ap->tp;

	args.mp = mp;

	args.fsbno = ap->blkno;

	xfs_rmap_skip_owner_update(&args.oinfo);



	/* Trim the allocation back to the maximum an AG can fit. */

	args.maxlen = MIN(ap->length, XFS_ALLOC_AG_MAX_USABLE(mp));
@@ -4839,6 +4851,7 @@ xfs_bmap_del_extent( 
		nblks = 0;

		do_fx = 0;

	}



	/*

	 * Set flag value to use in switch statement.

	 * Left-contig is 2, right-contig is 1.
@@ -5026,7 +5039,7 @@ xfs_bmap_del_extent( 
	 */

	if (do_fx)

		xfs_bmap_add_free(mp, dfops, del->br_startblock,

			del->br_blockcount);

				del->br_blockcount, NULL);

	/*

	 * Adjust inode # blocks in the file.

	 */

fs/xfs/libxfs/xfs_bmap.h

+3 −1
Original line number Diff line number Diff line
@@ -67,6 +67,7 @@ struct xfs_extent_free_item 
	xfs_fsblock_t		xefi_startblock;/* starting fs block number */

	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */

	struct list_head	xefi_list;

	struct xfs_owner_info	xefi_oinfo;	/* extent owner */

};



#define	XFS_BMAP_MAX_NMAP	4
@@ -165,7 +166,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, 
int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);

void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);

void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,

			  xfs_fsblock_t bno, xfs_filblks_t len);

			  xfs_fsblock_t bno, xfs_filblks_t len,

			  struct xfs_owner_info *oinfo);

void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);

int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,

		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);

fs/xfs/libxfs/xfs_bmap_btree.c

+6 −1
Original line number Diff line number Diff line
@@ -35,6 +35,7 @@ 
#include "xfs_quota.h"

#include "xfs_trace.h"

#include "xfs_cksum.h"

#include "xfs_rmap.h"



/*

 * Determine the extent state.
@@ -447,6 +448,8 @@ xfs_bmbt_alloc_block( 
	args.mp = cur->bc_mp;

	args.fsbno = cur->bc_private.b.firstblock;

	args.firstblock = args.fsbno;

	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,

			cur->bc_private.b.whichfork);



	if (args.fsbno == NULLFSBLOCK) {

		args.fsbno = be64_to_cpu(start->l);
@@ -526,8 +529,10 @@ xfs_bmbt_free_block( 
	struct xfs_inode	*ip = cur->bc_private.b.ip;

	struct xfs_trans	*tp = cur->bc_tp;

	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));

	struct xfs_owner_info	oinfo;



	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1);

	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);

	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);

	ip->i_d.di_nblocks--;



	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

CRA Git | Maintained and supported by SUSTech CRA and CCSE