/*
* Allocation group level functions.
*/
+static inline int
+xfs_ialloc_cluster_alignment(
+ xfs_alloc_arg_t *args)
+{
+ if (xfs_sb_version_hasalign(&args->mp->m_sb) &&
+ args->mp->m_sb.sb_inoalignmt >=
+ XFS_B_TO_FSBT(args->mp, XFS_INODE_CLUSTER_SIZE(args->mp)))
+ return args->mp->m_sb.sb_inoalignmt;
+ return 1;
+}
+
+/*
+ * Lookup the record equal to ino in the btree given by cur.
+ */
+STATIC int /* error */
+xfs_inobt_lookup_eq(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agino_t ino, /* starting inode of chunk */
+ __int32_t fcnt, /* free inode count */
+ xfs_inofree_t free, /* free inode mask */
+ int *stat) /* success/failure */
+{
+ cur->bc_rec.i.ir_startino = ino;
+ cur->bc_rec.i.ir_freecount = fcnt;
+ cur->bc_rec.i.ir_free = free;
+ return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
+/*
+ * Lookup the first record greater than or equal to ino
+ * in the btree given by cur.
+ */
+int /* error */
+xfs_inobt_lookup_ge(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agino_t ino, /* starting inode of chunk */
+ __int32_t fcnt, /* free inode count */
+ xfs_inofree_t free, /* free inode mask */
+ int *stat) /* success/failure */
+{
+ cur->bc_rec.i.ir_startino = ino;
+ cur->bc_rec.i.ir_freecount = fcnt;
+ cur->bc_rec.i.ir_free = free;
+ return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
+}
+
+/*
+ * Lookup the first record less than or equal to ino
+ * in the btree given by cur.
+ */
+int /* error */
+xfs_inobt_lookup_le(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agino_t ino, /* starting inode of chunk */
+ __int32_t fcnt, /* free inode count */
+ xfs_inofree_t free, /* free inode mask */
+ int *stat) /* success/failure */
+{
+ cur->bc_rec.i.ir_startino = ino;
+ cur->bc_rec.i.ir_freecount = fcnt;
+ cur->bc_rec.i.ir_free = free;
+ return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
+}
+
+/*
+ * Update the record referred to by cur to the value given
+ * by [ino, fcnt, free].
+ * This either works (return 0) or gets an EFSCORRUPTED error.
+ */
+STATIC int /* error */
+xfs_inobt_update(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agino_t ino, /* starting inode of chunk */
+ __int32_t fcnt, /* free inode count */
+ xfs_inofree_t free) /* free inode mask */
+{
+ union xfs_btree_rec rec;
+
+ rec.inobt.ir_startino = cpu_to_be32(ino);
+ rec.inobt.ir_freecount = cpu_to_be32(fcnt);
+ rec.inobt.ir_free = cpu_to_be64(free);
+ return xfs_btree_update(cur, &rec);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int /* error */
+xfs_inobt_get_rec(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agino_t *ino, /* output: starting inode of chunk */
+ __int32_t *fcnt, /* output: number of free inodes */
+ xfs_inofree_t *free, /* output: free inode mask */
+ int *stat) /* output: success/failure */
+{
+ union xfs_btree_rec *rec;
+ int error;
+
+ error = xfs_btree_get_rec(cur, &rec, stat);
+ if (!error && *stat == 1) {
+ *ino = be32_to_cpu(rec->inobt.ir_startino);
+ *fcnt = be32_to_cpu(rec->inobt.ir_freecount);
+ *free = be64_to_cpu(rec->inobt.ir_free);
+ }
+ return error;
+}
/*
* Allocate new inodes in the allocation group specified by agbp.
int version; /* inode version number to use */
int isaligned = 0; /* inode allocation at stripe unit */
/* boundary */
+ unsigned int gen;
args.tp = tp;
args.mp = tp->t_mountp;
args.mod = args.total = args.wasdel = args.isfl =
args.userdata = args.minalignslop = 0;
args.prod = 1;
- args.alignment = 1;
+
/*
- * Allow space for the inode btree to split.
+ * We need to take into account alignment here to ensure that
+ * we don't modify the free list if we fail to have an exact
+ * block. If we don't have an exact match, and every oher
+ * attempt allocation attempt fails, we'll end up cancelling
+ * a dirty transaction and shutting down.
+ *
+ * For an exact allocation, alignment must be 1,
+ * however we need to take cluster alignment into account when
+ * fixing up the freelist. Use the minalignslop field to
+ * indicate that extra blocks might be required for alignment,
+ * but not to use them in the actual exact allocation.
*/
+ args.alignment = 1;
+ args.minalignslop = xfs_ialloc_cluster_alignment(&args) - 1;
+
+ /* Allow space for the inode btree to split. */
args.minleft = XFS_IN_MAXLEVELS(args.mp) - 1;
if ((error = xfs_alloc_vextent(&args)))
return error;
ASSERT(!(args.mp->m_flags & XFS_MOUNT_NOALIGN));
args.alignment = args.mp->m_dalign;
isaligned = 1;
- } else if (XFS_SB_VERSION_HASALIGN(&args.mp->m_sb) &&
- args.mp->m_sb.sb_inoalignmt >=
- XFS_B_TO_FSBT(args.mp,
- XFS_INODE_CLUSTER_SIZE(args.mp)))
- args.alignment = args.mp->m_sb.sb_inoalignmt;
- else
- args.alignment = 1;
+ } else
+ args.alignment = xfs_ialloc_cluster_alignment(&args);
/*
* Need to figure out where to allocate the inode blocks.
* Ideally they should be spaced out through the a.g.
args.agbno = be32_to_cpu(agi->agi_root);
args.fsbno = XFS_AGB_TO_FSB(args.mp,
be32_to_cpu(agi->agi_seqno), args.agbno);
- if (XFS_SB_VERSION_HASALIGN(&args.mp->m_sb) &&
- args.mp->m_sb.sb_inoalignmt >=
- XFS_B_TO_FSBT(args.mp, XFS_INODE_CLUSTER_SIZE(args.mp)))
- args.alignment = args.mp->m_sb.sb_inoalignmt;
- else
- args.alignment = 1;
+ args.alignment = xfs_ialloc_cluster_alignment(&args);
if ((error = xfs_alloc_vextent(&args)))
return error;
}
* use the old version so that old kernels will continue to be
* able to use the file system.
*/
- if (XFS_SB_VERSION_HASNLINK(&args.mp->m_sb))
+ if (xfs_sb_version_hasnlink(&args.mp->m_sb))
version = XFS_DINODE_VERSION_2;
else
version = XFS_DINODE_VERSION_1;
+ /*
+ * Seed the new inode cluster with a random generation number. This
+ * prevents short-term reuse of generation numbers if a chunk is
+ * freed and then immediately reallocated. We use random numbers
+ * rather than a linear progression to prevent the next generation
+ * number from being easily guessable.
+ */
+ gen = random32();
for (j = 0; j < nbufs; j++) {
/*
* Get the block.
free = XFS_MAKE_IPTR(args.mp, fbuf, i);
free->di_core.di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
free->di_core.di_version = version;
+ free->di_core.di_gen = cpu_to_be32(gen);
free->di_next_unlinked = cpu_to_be32(NULLAGINO);
xfs_ialloc_log_di(tp, fbuf, i,
XFS_DI_CORE_BITS | XFS_DI_NEXT_UNLINKED);
}
xfs_trans_inode_alloc_buf(tp, fbuf);
}
- be32_add(&agi->agi_count, newlen);
- be32_add(&agi->agi_freecount, newlen);
+ be32_add_cpu(&agi->agi_count, newlen);
+ be32_add_cpu(&agi->agi_freecount, newlen);
agno = be32_to_cpu(agi->agi_seqno);
down_read(&args.mp->m_peraglock);
args.mp->m_perag[agno].pagi_freecount += newlen;
/*
* Insert records describing the new inode chunk into the btree.
*/
- cur = xfs_btree_init_cursor(args.mp, tp, agbp, agno,
- XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
+ cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
for (thisino = newino;
thisino < newino + newlen;
thisino += XFS_INODES_PER_CHUNK) {
return error;
}
ASSERT(i == 0);
- if ((error = xfs_inobt_insert(cur, &i))) {
+ if ((error = xfs_btree_insert(cur, &i))) {
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
*/
agno = tagno;
*IO_agbp = NULL;
- cur = xfs_btree_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno),
- XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
freecount += rec.ir_freecount;
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error0;
} while (i == 1);
/*
* Search left with tcur, back up 1 record.
*/
- if ((error = xfs_inobt_decrement(tcur, 0, &i)))
+ if ((error = xfs_btree_decrement(tcur, 0, &i)))
goto error1;
doneleft = !i;
if (!doneleft) {
/*
* Search right with cur, go forward 1 record.
*/
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error1;
doneright = !i;
if (!doneright) {
* further left.
*/
if (useleft) {
- if ((error = xfs_inobt_decrement(tcur, 0,
+ if ((error = xfs_btree_decrement(tcur, 0,
&i)))
goto error1;
doneleft = !i;
* further right.
*/
else {
- if ((error = xfs_inobt_increment(cur, 0,
+ if ((error = xfs_btree_increment(cur, 0,
&i)))
goto error1;
doneright = !i;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0)
break;
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
}
if ((error = xfs_inobt_update(cur, rec.ir_startino, rec.ir_freecount,
rec.ir_free)))
goto error0;
- be32_add(&agi->agi_freecount, -1);
+ be32_add_cpu(&agi->agi_freecount, -1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
down_read(&mp->m_peraglock);
mp->m_perag[tagno].pagi_freecount--;
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
freecount += rec.ir_freecount;
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error0;
} while (i == 1);
ASSERT(freecount == be32_to_cpu(agi->agi_freecount) ||
/*
* Initialize the cursor.
*/
- cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO,
- (xfs_inode_t *)0, 0);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
#ifdef DEBUG
if (cur->bc_nlevels == 1) {
int freecount = 0;
goto error0;
if (i) {
freecount += rec.ir_freecount;
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error0;
}
} while (i == 1);
/*
* When an inode cluster is free, it becomes eligible for removal
*/
- if ((mp->m_flags & XFS_MOUNT_IDELETE) &&
+ if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
(rec.ir_freecount == XFS_IALLOC_INODES(mp))) {
*delete = 1;
* to be freed when the transaction is committed.
*/
ilen = XFS_IALLOC_INODES(mp);
- be32_add(&agi->agi_count, -ilen);
- be32_add(&agi->agi_freecount, -(ilen - 1));
+ be32_add_cpu(&agi->agi_count, -ilen);
+ be32_add_cpu(&agi->agi_freecount, -(ilen - 1));
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
down_read(&mp->m_peraglock);
mp->m_perag[agno].pagi_freecount -= ilen - 1;
xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));
- if ((error = xfs_inobt_delete(cur, &i))) {
- cmn_err(CE_WARN, "xfs_difree: xfs_inobt_delete returned an error %d on %s.\n",
+ if ((error = xfs_btree_delete(cur, &i))) {
+ cmn_err(CE_WARN, "xfs_difree: xfs_btree_delete returned an error %d on %s.\n",
error, mp->m_fsname);
goto error0;
}
/*
* Change the inode free counts and log the ag/sb changes.
*/
- be32_add(&agi->agi_freecount, 1);
+ be32_add_cpu(&agi->agi_freecount, 1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
down_read(&mp->m_peraglock);
mp->m_perag[agno].pagi_freecount++;
goto error0;
if (i) {
freecount += rec.ir_freecount;
- if ((error = xfs_inobt_increment(cur, 0, &i)))
+ if ((error = xfs_btree_increment(cur, 0, &i)))
goto error0;
}
} while (i == 1);
#endif /* DEBUG */
return error;
}
- cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO,
- (xfs_inode_t *)0, 0);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
if ((error = xfs_inobt_lookup_le(cur, agino, 0, 0, &i))) {
#ifdef DEBUG
xfs_fs_cmn_err(CE_ALERT, mp, "xfs_dilocate: "
xfs_trans_log_buf(tp, bp, first, last);
}
+#ifdef DEBUG
+STATIC void
+xfs_check_agi_unlinked(
+ struct xfs_agi *agi)
+{
+ int i;
+
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
+ ASSERT(agi->agi_unlinked[i]);
+}
+#else
+#define xfs_check_agi_unlinked(agi)
+#endif
+
/*
* Read in the allocation group header (inode allocation section)
*/
int
-xfs_ialloc_read_agi(
- xfs_mount_t *mp, /* file system mount structure */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- xfs_buf_t **bpp) /* allocation group hdr buf */
+xfs_read_agi(
+ struct xfs_mount *mp, /* file system mount structure */
+ struct xfs_trans *tp, /* transaction pointer */
+ xfs_agnumber_t agno, /* allocation group number */
+ struct xfs_buf **bpp) /* allocation group hdr buf */
{
- xfs_agi_t *agi; /* allocation group header */
- int agi_ok; /* agi is consistent */
- xfs_buf_t *bp; /* allocation group hdr buf */
- xfs_perag_t *pag; /* per allocation group data */
- int error;
+ struct xfs_agi *agi; /* allocation group header */
+ int agi_ok; /* agi is consistent */
+ int error;
ASSERT(agno != NULLAGNUMBER);
- error = xfs_trans_read_buf(
- mp, tp, mp->m_ddev_targp,
+
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &bp);
+ XFS_FSS_TO_BB(mp, 1), 0, bpp);
if (error)
return error;
- ASSERT(bp && !XFS_BUF_GETERROR(bp));
+
+ ASSERT(*bpp && !XFS_BUF_GETERROR(*bpp));
+ agi = XFS_BUF_TO_AGI(*bpp);
/*
* Validate the magic number of the agi block.
*/
- agi = XFS_BUF_TO_AGI(bp);
- agi_ok =
- be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
- XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
+ agi_ok = be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
+ XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)) &&
+ be32_to_cpu(agi->agi_seqno) == agno;
if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
XFS_RANDOM_IALLOC_READ_AGI))) {
- XFS_CORRUPTION_ERROR("xfs_ialloc_read_agi", XFS_ERRLEVEL_LOW,
+ XFS_CORRUPTION_ERROR("xfs_read_agi", XFS_ERRLEVEL_LOW,
mp, agi);
- xfs_trans_brelse(tp, bp);
+ xfs_trans_brelse(tp, *bpp);
return XFS_ERROR(EFSCORRUPTED);
}
+
+ XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_AGI, XFS_AGI_REF);
+
+ xfs_check_agi_unlinked(agi);
+ return 0;
+}
+
+int
+xfs_ialloc_read_agi(
+ struct xfs_mount *mp, /* file system mount structure */
+ struct xfs_trans *tp, /* transaction pointer */
+ xfs_agnumber_t agno, /* allocation group number */
+ struct xfs_buf **bpp) /* allocation group hdr buf */
+{
+ struct xfs_agi *agi; /* allocation group header */
+ struct xfs_perag *pag; /* per allocation group data */
+ int error;
+
+ error = xfs_read_agi(mp, tp, agno, bpp);
+ if (error)
+ return error;
+
+ agi = XFS_BUF_TO_AGI(*bpp);
pag = &mp->m_perag[agno];
+
if (!pag->pagi_init) {
pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
pag->pagi_count = be32_to_cpu(agi->agi_count);
pag->pagi_init = 1;
- } else {
- /*
- * It's possible for these to be out of sync if
- * we are in the middle of a forced shutdown.
- */
- ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
- XFS_FORCED_SHUTDOWN(mp));
}
-#ifdef DEBUG
- {
- int i;
-
- for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
- ASSERT(agi->agi_unlinked[i]);
- }
-#endif
-
- XFS_BUF_SET_VTYPE_REF(bp, B_FS_AGI, XFS_AGI_REF);
- *bpp = bp;
+ /*
+ * It's possible for these to be out of sync if
+ * we are in the middle of a forced shutdown.
+ */
+ ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
+ XFS_FORCED_SHUTDOWN(mp));
return 0;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff