From: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
For the rmap btree to work, we have to fed 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...
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.
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]
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Reviewed-by: Dave Chinner <dchinner@xxxxxxxxxx>
Signed-off-by: Dave Chinner <david@xxxxxxxxxxxxx>
---
fs/xfs/libxfs/xfs_alloc.c | 12 ++++++--
fs/xfs/libxfs/xfs_alloc.h | 4 ++-
fs/xfs/libxfs/xfs_bmap.c | 17 +++++++++--
fs/xfs/libxfs/xfs_bmap.h | 4 ++-
fs/xfs/libxfs/xfs_bmap_btree.c | 6 +++-
fs/xfs/libxfs/xfs_format.h | 65 ++++++++++++++++++++++++++++++++++++++++
fs/xfs/libxfs/xfs_ialloc.c | 7 +++--
fs/xfs/libxfs/xfs_ialloc_btree.c | 7 ++++-
fs/xfs/xfs_bmap_util.c | 3 +-
fs/xfs/xfs_fsops.c | 16 +++++++---
fs/xfs/xfs_log_recover.c | 5 +++-
fs/xfs/xfs_trans.h | 2 +-
fs/xfs/xfs_trans_extfree.c | 5 ++--
13 files changed, 132 insertions(+), 21 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 19b7521..0222e03 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1595,6 +1595,7 @@ xfs_free_ag_extent(
xfs_agnumber_t agno, /* allocation group number */
xfs_agblock_t bno, /* starting block number */
xfs_extlen_t len, /* length of extent */
+ struct xfs_owner_info *oinfo, /* extent owner */
int isfl) /* set if is freelist blocks - no sb acctg */
{
xfs_btree_cur_t *bno_cur; /* cursor for by-block btree */
@@ -2015,13 +2016,15 @@ 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);
@@ -2031,6 +2034,7 @@ 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;
@@ -2684,7 +2688,8 @@ int /* error */
xfs_free_extent(
xfs_trans_t *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 */
{
xfs_alloc_arg_t args;
int error;
@@ -2720,7 +2725,8 @@ xfs_free_extent(
goto error0;
}
- error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
+ error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno,
+ len, oinfo, 0);
if (!error)
xfs_extent_busy_insert(tp, args.agno, args.agbno, len, 0);
error0:
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index d260916..6d0f328 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -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_le(
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7aef8d8..59d4fd1 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -576,7 +576,8 @@ xfs_bmap_add_free(
struct xfs_mount *mp, /* mount point structure */
struct xfs_bmap_free *flist, /* list of extents */
xfs_fsblock_t bno, /* fs block number of extent */
- xfs_filblks_t len) /* length of extent */
+ xfs_filblks_t len, /* length of extent */
+ struct xfs_owner_info *oinfo) /* extent owner */
{
xfs_bmap_free_item_t *cur; /* current (next) element */
xfs_bmap_free_item_t *new; /* new element */
@@ -597,9 +598,14 @@ 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->xbfi_startblock = bno;
new->xbfi_blockcount = (xfs_extlen_t)len;
+ if (oinfo)
+ memcpy(&new->xbfi_oinfo, oinfo, sizeof(struct xfs_owner_info));
+ else
+ memset(&new->xbfi_oinfo, 0, sizeof(struct xfs_owner_info));
for (prev = NULL, cur = flist->xbf_first;
cur != NULL;
prev = cur, cur = cur->xbfi_next) {
@@ -679,6 +685,7 @@ 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);
@@ -702,7 +709,8 @@ 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.flist, cbno, 1);
+ xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
+ xfs_bmap_add_free(mp, cur->bc_private.b.flist, 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);
@@ -783,6 +791,7 @@ 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;
@@ -929,6 +938,7 @@ 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
@@ -4831,6 +4841,7 @@ 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.
@@ -5017,7 +5028,7 @@ xfs_bmap_del_extent(
*/
if (do_fx)
xfs_bmap_add_free(mp, flist, del->br_startblock,
- del->br_blockcount);
+ del->br_blockcount, NULL);
/*
* Adjust inode # blocks in the file.
*/
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e081c76..06dbe08 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -66,6 +66,7 @@ typedef struct xfs_bmap_free_item
{
xfs_fsblock_t xbfi_startblock;/* starting fs block number */
xfs_extlen_t xbfi_blockcount;/* number of blocks in extent */
+ struct xfs_owner_info xbfi_oinfo; /* extent owner */
struct xfs_bmap_free_item *xbfi_next; /* link to next entry */
} xfs_bmap_free_item_t;
@@ -192,7 +193,8 @@ 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_bmap_free *flist,
- xfs_fsblock_t bno, xfs_filblks_t len);
+ xfs_fsblock_t bno, xfs_filblks_t len,
+ struct xfs_owner_info *oinfo);
void xfs_bmap_cancel(struct xfs_bmap_free *flist);
int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index db0c71e..e247b02 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -446,6 +446,8 @@ 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);
@@ -525,8 +527,10 @@ 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.flist, 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.flist, fsbno, 1, &oinfo);
ip->i_d.di_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index ebe0eec..232c145 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1319,6 +1319,71 @@ typedef __be32 xfs_inobt_ptr_t;
*/
#define XFS_RMAP_CRC_MAGIC 0x524d4233 /* 'RMB3' */
+/*
+ * Ownership info for an extent. This is used to create reverse-mapping
+ * entries.
+ */
+#define XFS_RMAP_INO_ATTR_FORK (1)
+#define XFS_RMAP_BMBT_BLOCK (2)
+struct xfs_owner_info {
+ uint64_t oi_owner;
+ xfs_fileoff_t oi_offset;
+ unsigned int oi_flags;
+};
+
+static inline void
+xfs_rmap_ag_owner(
+ struct xfs_owner_info *oi,
+ uint64_t owner)
+{
+ oi->oi_owner = owner;
+ oi->oi_offset = 0;
+ oi->oi_flags = 0;
+}
+
+static inline void
+xfs_rmap_ino_bmbt_owner(
+ struct xfs_owner_info *oi,
+ xfs_ino_t ino,
+ int whichfork)
+{
+ oi->oi_owner = ino;
+ oi->oi_offset = 0;
+ oi->oi_flags = XFS_RMAP_BMBT_BLOCK;
+ if (whichfork == XFS_ATTR_FORK)
+ oi->oi_flags |= XFS_RMAP_INO_ATTR_FORK;
+}
+
+static inline void
+xfs_rmap_ino_owner(
+ struct xfs_owner_info *oi,
+ xfs_ino_t ino,
+ int whichfork,
+ xfs_fileoff_t offset)
+{
+ oi->oi_owner = ino;
+ oi->oi_offset = offset;
+ oi->oi_flags = 0;
+ if (whichfork == XFS_ATTR_FORK)
+ oi->oi_flags |= XFS_RMAP_INO_ATTR_FORK;
+}
+
+/*
+ * Special owner types.
+ *
+ * Seeing as we only support up to 8EB, we have the upper bit of the owner field
+ * to tell us we have a special owner value. We use these for static metadata
+ * allocated at mkfs/growfs time, as well as for freespace management metadata.
+ */
+#define XFS_RMAP_OWN_NULL (-1ULL) /* No owner, for growfs */
+#define XFS_RMAP_OWN_UNKNOWN (-2ULL) /* Unknown owner, for EFI recovery */
+#define XFS_RMAP_OWN_FS (-3ULL) /* static fs metadata */
+#define XFS_RMAP_OWN_LOG (-4ULL) /* static fs metadata */
+#define XFS_RMAP_OWN_AG (-5ULL) /* AG freespace btree blocks */
+#define XFS_RMAP_OWN_INOBT (-6ULL) /* Inode btree blocks */
+#define XFS_RMAP_OWN_INODES (-7ULL) /* Inode chunk */
+#define XFS_RMAP_OWN_MIN (-8ULL) /* guard */
+
#define XFS_RMAP_BLOCK(mp) \
(xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
XFS_FIBT_BLOCK(mp) + 1 : \
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index e3c0af7..aa3d10e 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -614,6 +614,7 @@ xfs_ialloc_ag_alloc(
args.tp = tp;
args.mp = tp->t_mountp;
args.fsbno = NULLFSBLOCK;
+ xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_INODES);
#ifdef DEBUG
/* randomly do sparse inode allocations */
@@ -1824,12 +1825,14 @@ xfs_difree_inode_chunk(
int nextbit;
xfs_agblock_t agbno;
int contigblk;
+ struct xfs_owner_info oinfo;
DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
if (!xfs_inobt_issparse(rec->ir_holemask)) {
/* not sparse, calculate extent info directly */
xfs_bmap_add_free(mp, flist, XFS_AGB_TO_FSB(mp, agno, sagbno),
- mp->m_ialloc_blks);
+ mp->m_ialloc_blks, &oinfo);
return;
}
@@ -1873,7 +1876,7 @@ xfs_difree_inode_chunk(
ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
xfs_bmap_add_free(mp, flist, XFS_AGB_TO_FSB(mp, agno, agbno),
- contigblk);
+ contigblk, &oinfo);
/* reset range to current bit and carry on... */
startidx = endidx = nextbit;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 89c21d7..1a7b016 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -96,6 +96,7 @@ xfs_inobt_alloc_block(
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
+ xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_INOBT);
args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno, sbno);
args.minlen = 1;
args.maxlen = 1;
@@ -125,8 +126,12 @@ xfs_inobt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
+ struct xfs_owner_info oinfo;
+
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
return xfs_free_extent(cur->bc_tp,
- XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1);
+ XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1,
+ &oinfo);
}
STATIC int
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a32c1dc..834639d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -149,7 +149,8 @@ xfs_bmap_finish(
next = free->xbfi_next;
error = xfs_trans_free_extent(*tp, efd, free->xbfi_startblock,
- free->xbfi_blockcount);
+ free->xbfi_blockcount,
+ &free->xbfi_oinfo);
if (error)
return error;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 32e24ec..b4ab22c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -439,6 +439,8 @@ xfs_growfs_data_private(
* There are new blocks in the old last a.g.
*/
if (new) {
+ struct xfs_owner_info oinfo;
+
/*
* Change the agi length.
*/
@@ -466,14 +468,20 @@ xfs_growfs_data_private(
be32_to_cpu(agi->agi_length));
xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
+
/*
* Free the new space.
+ *
+ * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
+ * this doesn't actually exist in the rmap btree.
*/
- error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno,
- be32_to_cpu(agf->agf_length) - new), new);
- if (error) {
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
+ error = xfs_free_extent(tp,
+ XFS_AGB_TO_FSB(mp, agno,
+ be32_to_cpu(agf->agf_length) - new),
+ new, &oinfo);
+ if (error)
goto error0;
- }
}
/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 396565f..7c9bc7c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4179,6 +4179,7 @@ xlog_recover_process_efi(
int error = 0;
xfs_extent_t *extp;
xfs_fsblock_t startblock_fsb;
+ struct xfs_owner_info oinfo;
ASSERT(!test_bit(XFS_EFI_RECOVERED, &efip->efi_flags));
@@ -4211,10 +4212,12 @@ xlog_recover_process_efi(
goto abort_error;
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_UNKNOWN);
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
extp = &(efip->efi_format.efi_extents[i]);
error = xfs_trans_free_extent(tp, efdp, extp->ext_start,
- extp->ext_len);
+ extp->ext_len,
+ &oinfo);
if (error)
goto abort_error;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index e7c49cf..d49dfef 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -221,7 +221,7 @@ struct xfs_efd_log_item *xfs_trans_get_efd(xfs_trans_t *,
uint);
int xfs_trans_free_extent(struct xfs_trans *,
struct xfs_efd_log_item *, xfs_fsblock_t,
- xfs_extlen_t);
+ xfs_extlen_t, struct xfs_owner_info *);
int xfs_trans_commit(struct xfs_trans *);
int __xfs_trans_roll(struct xfs_trans **, struct xfs_inode *, int *);
int xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index a96ae54..d1b8833 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -118,13 +118,14 @@ xfs_trans_free_extent(
struct xfs_trans *tp,
struct xfs_efd_log_item *efdp,
xfs_fsblock_t start_block,
- xfs_extlen_t ext_len)
+ xfs_extlen_t ext_len,
+ struct xfs_owner_info *oinfo)
{
uint next_extent;
struct xfs_extent *extp;
int error;
- error = xfs_free_extent(tp, start_block, ext_len);
+ error = xfs_free_extent(tp, start_block, ext_len, oinfo);
/*
* Mark the transaction dirty, even on error. This ensures the
--
2.7.0
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
