void *obj,
int startoff)
{
+ struct xfs_dinode *dip = obj;
xfs_dir2_sf_t *sf;
ASSERT(bitoffs(startoff) == 0);
- sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(obj);
+ sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(dip);
return sf->hdr.i8count == 0;
}
void *obj,
int startoff)
{
+ struct xfs_dinode *dip = obj;
xfs_dir2_sf_t *sf;
ASSERT(bitoffs(startoff) == 0);
- sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(obj);
+ sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(dip);
return sf->hdr.i8count != 0;
}
int startoff,
int idx)
{
+ struct xfs_dinode *dip = obj;
xfs_dir2_sf_t *sf;
ASSERT(bitoffs(startoff) == 0);
ASSERT(idx == 0);
- sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(obj);
+ sf = (xfs_dir2_sf_t *)XFS_DFORK_DPTR(dip);
return bitize(sf->hdr.i8count ?
(uint)sizeof(xfs_dir2_ino8_t) :
(uint)sizeof(xfs_dir2_ino4_t));
#define XFS_BLF_AGF_BUF (1<<6)
#define XFS_BLF_AGFL_BUF (1<<7)
#define XFS_BLF_AGI_BUF (1<<8)
+#define XFS_BLF_DINO_BUF (1<<9)
#define XFS_BLF_TYPE_MASK \
(XFS_BLF_UDQUOT_BUF | \
XFS_BLF_BTREE_BUF | \
XFS_BLF_AGF_BUF | \
XFS_BLF_AGFL_BUF | \
- XFS_BLF_AGI_BUF)
+ XFS_BLF_AGI_BUF | \
+ XFS_BLF_DINO_BUF)
#define XFS_BLF_CHUNK 128
#define XFS_BLF_SHIFT 7
#define __XFS_DINODE_H__
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v) (((v) == 1 || (v) == 2))
+#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3)
typedef struct xfs_timestamp {
__be32 t_sec; /* timestamp seconds */
/* di_next_unlinked is the only non-core field in the old dinode */
__be32 di_next_unlinked;/* agi unlinked list ptr */
-} __attribute__((packed)) xfs_dinode_t;
+
+ /* start of the extended dinode, writable fields */
+ __le32 di_crc; /* CRC of the inode */
+ __be64 di_changecount; /* number of attribute changes */
+ __be64 di_lsn; /* flush sequence */
+ __be64 di_flags2; /* more random flags */
+ __u8 di_pad2[16]; /* more padding for future expansion */
+
+ /* fields only written to during inode creation */
+ xfs_timestamp_t di_crtime; /* time created */
+ __be64 di_ino; /* inode number */
+ uuid_t di_uuid; /* UUID of the filesystem */
+
+ /* structure must be padded to 64 bit alignment */
+} xfs_dinode_t;
#define DI_MAX_FLUSH 0xffff
+/*
+ * Size of the core inode on disk. Version 1 and 2 inodes have
+ * the same size, but version 3 has grown a few additional fields.
+ */
+static inline uint xfs_dinode_size(int version)
+{
+ if (version == 3)
+ return sizeof(struct xfs_dinode);
+ return offsetof(struct xfs_dinode, di_crc);
+}
+
/*
* The 32 bit link count in the inode theoretically maxes out at UINT_MAX.
* Since the pathconf interface is signed, we use 2^31 - 1 instead.
* Inode size for given fs.
*/
#define XFS_LITINO(mp, version) \
- ((int)(((mp)->m_sb.sb_inodesize) - sizeof(struct xfs_dinode)))
+ ((int)(((mp)->m_sb.sb_inodesize) - xfs_dinode_size(version)))
#define XFS_BROOT_SIZE_ADJ(ip) \
(XFS_BMBT_BLOCK_LEN((ip)->i_mount) - sizeof(xfs_bmdr_block_t))
* Return pointers to the data or attribute forks.
*/
#define XFS_DFORK_DPTR(dip) \
- ((char *)(dip) + sizeof(struct xfs_dinode))
+ ((char *)dip + xfs_dinode_size(dip->di_version))
#define XFS_DFORK_APTR(dip) \
(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
#define XFS_DFORK_PTR(dip,w) \
__uint16_t di_dmstate; /* DMIG state info */
__uint16_t di_flags; /* random flags, XFS_DIFLAG_... */
__uint32_t di_gen; /* generation number */
+
+ /* di_next_unlinked is the only non-core field in the old dinode */
+ __be32 di_next_unlinked;/* agi unlinked list ptr */
+
+ /* start of the extended dinode, writable fields */
+ __uint32_t di_crc; /* CRC of the inode */
+ __uint64_t di_changecount; /* number of attribute changes */
+ xfs_lsn_t di_lsn; /* flush sequence */
+ __uint64_t di_flags2; /* more random flags */
+ __uint8_t di_pad2[16]; /* more padding for future expansion */
+
+ /* fields only written to during inode creation */
+ xfs_ictimestamp_t di_crtime; /* time created */
+ xfs_ino_t di_ino; /* inode number */
+ uuid_t di_uuid; /* UUID of the filesystem */
+
+ /* structure must be padded to 64 bit alignment */
} xfs_icdinode_t;
+static inline uint xfs_icdinode_size(struct xfs_icdinode *dicp)
+{
+ if (dicp->di_version == 3)
+ return sizeof(struct xfs_icdinode);
+ return offsetof(struct xfs_icdinode, di_next_unlinked);
+}
+
/*
* Flags for xfs_ichgtime().
*/
#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
+#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
/*
* Per-fork incore inode flags.
struct xfs_buf **, uint, uint);
int xfs_iread(struct xfs_mount *, struct xfs_trans *,
struct xfs_inode *, uint);
+void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
void xfs_dinode_to_disk(struct xfs_dinode *,
struct xfs_icdinode *);
void xfs_idestroy_fork(struct xfs_inode *, int);
ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLF_DINO_BUF);
}
/*
ip->i_d.di_ctime.t_sec = (__int32_t)tv.tv_sec;
ip->i_d.di_ctime.t_nsec = (__int32_t)tv.tv_nsec;
}
+ if (flags & XFS_ICHGTIME_CREATE) {
+ ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
+ ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
+ }
}
/*
xfs_inode_t *ip;
uint flags;
int error;
+ int times;
/*
* Call the space management code to pick
ip->i_d.di_gid = cr->cr_gid;
xfs_set_projid(&ip->i_d, pip ? 0 : fsx->fsx_projid);
memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
+ xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD);
/*
* If the superblock version is up to where we support new format
ip->i_d.di_size = 0;
ip->i_d.di_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
- xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG|XFS_ICHGTIME_MOD);
/*
* di_gen will have been taken care of in xfs_iread.
*/
ip->i_d.di_dmevmask = 0;
ip->i_d.di_dmstate = 0;
ip->i_d.di_flags = pip ? 0 : fsx->fsx_xflags;
+
+ if (ip->i_d.di_version == 3) {
+ ASSERT(ip->i_d.di_ino == ino);
+ ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid));
+ ip->i_d.di_crc = 0;
+ ip->i_d.di_changecount = 1;
+ ip->i_d.di_lsn = 0;
+ ip->i_d.di_flags2 = 0;
+ memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
+ ip->i_d.di_crtime = ip->i_d.di_mtime;
+ }
+
flags = XFS_ILOG_CORE;
switch (mode & S_IFMT) {
case S_IFIFO:
ASSERT(ip->i_d.di_nextents+ip->i_d.di_anextents <= ip->i_d.di_nblocks);
ASSERT(ip->i_d.di_forkoff <= mp->m_sb.sb_inodesize);
+ /* bump the change count on v3 inodes */
+ if (ip->i_d.di_version == 3)
+ ip->i_d.di_changecount++;
+
/*
* Copy the dirty parts of the inode into the on-disk
* inode. We always copy out the core of the inode,
if (XFS_IFORK_Q(ip))
xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
+ /* update the lsn in the on disk inode if required */
+ if (ip->i_d.di_version == 3)
+ dip->di_lsn = cpu_to_be64(iip->ili_item.li_lsn);
+
+ /* generate the checksum. */
+ xfs_dinode_calc_crc(mp, dip);
+
return 0;
}
int version;
int i, j;
xfs_daddr_t d;
+ xfs_ino_t ino = 0;
/*
* Loop over the new block(s), filling in the inodes.
* the new inode format, then use the new inode version. Otherwise
* use the old version so that old kernels will continue to be
* able to use the file system.
+ *
+ * For v3 inodes, we also need to write the inode number into the inode,
+ * so calculate the first inode number of the chunk here as
+ * XFS_OFFBNO_TO_AGINO() only works on filesystem block boundaries, not
+ * cluster boundaries and so cannot be used in the cluster buffer loop
+ * below.
*/
- if (xfs_sb_version_hasnlink(&mp->m_sb))
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ version = 3;
+ ino = XFS_AGINO_TO_INO(mp, agno,
+ XFS_OFFBNO_TO_AGINO(mp, agbno, 0));
+ } else if (xfs_sb_version_hasnlink(&mp->m_sb))
version = 2;
else
version = 1;
xfs_buf_zero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog);
for (i = 0; i < ninodes; i++) {
int ioffset = i << mp->m_sb.sb_inodelog;
- uint isize = sizeof(struct xfs_dinode);
+ uint isize = xfs_dinode_size(version);
free = xfs_make_iptr(mp, fbuf, i);
free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
free->di_version = version;
free->di_gen = cpu_to_be32(gen);
free->di_next_unlinked = cpu_to_be32(NULLAGINO);
+
+ if (version == 3) {
+ free->di_ino = cpu_to_be64(ino);
+ ino++;
+ uuid_copy(&free->di_uuid, &mp->m_sb.sb_uuid);
+ xfs_dinode_calc_crc(mp, free);
+ }
+
xfs_trans_log_buf(tp, fbuf, ioffset, ioffset + isize - 1);
}
xfs_trans_inode_alloc_buf(tp, fbuf);
to->di_dmstate = be16_to_cpu(from->di_dmstate);
to->di_flags = be16_to_cpu(from->di_flags);
to->di_gen = be32_to_cpu(from->di_gen);
+
+ if (to->di_version == 3) {
+ to->di_changecount = be64_to_cpu(from->di_changecount);
+ to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
+ to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
+ to->di_flags2 = be64_to_cpu(from->di_flags2);
+ to->di_ino = be64_to_cpu(from->di_ino);
+ to->di_lsn = be64_to_cpu(from->di_lsn);
+ memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+ platform_uuid_copy(&to->di_uuid, &from->di_uuid);
+ }
}
void
to->di_dmstate = cpu_to_be16(from->di_dmstate);
to->di_flags = cpu_to_be16(from->di_flags);
to->di_gen = cpu_to_be32(from->di_gen);
+
+ if (from->di_version == 3) {
+ to->di_changecount = cpu_to_be64(from->di_changecount);
+ to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
+ to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
+ to->di_flags2 = cpu_to_be64(from->di_flags2);
+ to->di_ino = cpu_to_be64(from->di_ino);
+ to->di_lsn = cpu_to_be64(from->di_lsn);
+ memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+ platform_uuid_copy(&to->di_uuid, &from->di_uuid);
+ }
+}
+
+static bool
+xfs_dinode_verify(
+ struct xfs_mount *mp,
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip)
+{
+ if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
+ return false;
+
+ /* only version 3 or greater inodes are extensively verified here */
+ if (dip->di_version < 3)
+ return true;
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+ if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ offsetof(struct xfs_dinode, di_crc)))
+ return false;
+ if (be64_to_cpu(dip->di_ino) != ip->i_ino)
+ return false;
+ if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ return true;
+}
+
+void
+xfs_dinode_calc_crc(
+ struct xfs_mount *mp,
+ struct xfs_dinode *dip)
+{
+ __uint32_t crc;
+
+ if (dip->di_version < 3)
+ return;
+
+ ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
+ crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ offsetof(struct xfs_dinode, di_crc));
+ dip->di_crc = xfs_end_cksum(crc);
}
/*
if (error)
return error;
- /*
- * If we got something that isn't an inode it means someone
- * (nfs or dmi) has a stale handle.
- */
- if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC)) {
-#ifdef DEBUG
- xfs_alert(mp,
- "%s: dip->di_magic (0x%x) != XFS_DINODE_MAGIC (0x%x)",
- __func__, be16_to_cpu(dip->di_magic), XFS_DINODE_MAGIC);
-#endif /* DEBUG */
- error = XFS_ERROR(EINVAL);
+ /* even unallocated inodes are verified */
+ if (!xfs_dinode_verify(mp, ip, dip)) {
+ xfs_alert(mp, "%s: validation failed for inode %lld failed",
+ __func__, ip->i_ino);
+
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
+ error = XFS_ERROR(EFSCORRUPTED);
goto out_brelse;
}
goto out_brelse;
}
} else {
+ /*
+ * Partial initialisation of the in-core inode. Just the bits
+ * that xfs_ialloc won't overwrite or relies on being correct.
+ */
ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
ip->i_d.di_version = dip->di_version;
ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
+
+ if (dip->di_version == 3) {
+ ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
+ uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
+ }
+
/*
* Make sure to pull in the mode here as well in
* case the inode is released without being used.
mode = dino.di_mode & S_IFMT;
size = (int)dino.di_size;
xlog_print_trans_inode_core(&dino);
- *ptr += sizeof(xfs_icdinode_t);
+ *ptr += xfs_icdinode_size(&dino);
if (*i == num_ops-1 && f->ilf_size == 3) {
return 1;
f->ilf_dsize);
/* core inode comes 2nd */
- ASSERT(item->ri_buf[1].i_len == sizeof(xfs_icdinode_t));
+ ASSERT(item->ri_buf[1].i_len == xfs_icdinode_size((xfs_icdinode_t *)
+ item->ri_buf[1].i_addr));
xlog_recover_print_inode_core((xfs_icdinode_t *)
item->ri_buf[1].i_addr);
xfs_bmap_free_t flist;
xfs_dfiloff_t bno;
xfs_bmbt_irec_t map[XFS_BMAP_MAX_NMAP];
+ int vers;
+ int times;
/*
* first set up inode
error);
}
- memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+ vers = xfs_sb_version_hascrc(&mp->m_sb) ? 3 : 1;
+ ip->i_d.di_version = vers;
+ memset(&ip->i_d, 0, xfs_icdinode_size(&ip->i_d));
ip->i_d.di_magic = XFS_DINODE_MAGIC;
ip->i_d.di_mode = S_IFREG;
- ip->i_d.di_version = 1;
+ ip->i_d.di_version = vers;
ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_nlink = 1; /* account for sb ptr */
+ times = XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD;
+ if (ip->i_d.di_version == 3) {
+ ip->i_d.di_crc = 0;
+ ip->i_d.di_changecount = 1;
+ ip->i_d.di_lsn = 0;
+ ip->i_d.di_flags2 = 0;
+ ip->i_d.di_ino = mp->m_sb.sb_rbmino;
+ memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
+ platform_uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
+ times |= XFS_ICHGTIME_CREATE;
+ }
+ libxfs_trans_ichgtime(tp, ip, times);
+
/*
* now the ifork
*/
xfs_bmap_free_t flist;
xfs_dfiloff_t bno;
xfs_bmbt_irec_t map[XFS_BMAP_MAX_NMAP];
+ int vers;
+ int times;
/*
* first set up inode
error);
}
- memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+ vers = xfs_sb_version_hascrc(&mp->m_sb) ? 3 : 1;
+ ip->i_d.di_version = vers;
+ memset(&ip->i_d, 0, xfs_icdinode_size(&ip->i_d));
ip->i_d.di_magic = XFS_DINODE_MAGIC;
ip->i_d.di_mode = S_IFREG;
- ip->i_d.di_version = 1;
+ ip->i_d.di_version = vers;
ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_nlink = 1; /* account for sb ptr */
+ times = XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD;
+ if (ip->i_d.di_version == 3) {
+ ip->i_d.di_crc = 0;
+ ip->i_d.di_changecount = 1;
+ ip->i_d.di_lsn = 0;
+ ip->i_d.di_flags2 = 0;
+ ip->i_d.di_ino = mp->m_sb.sb_rsumino;
+ memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
+ platform_uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
+ times |= XFS_ICHGTIME_CREATE;
+ }
+ libxfs_trans_ichgtime(tp, ip, times);
+
/*
* now the ifork
*/
int error;
const mode_t mode = 0755;
ino_tree_node_t *irec;
+ int vers;
+ int times;
ASSERT(xfs_sb_version_hasdirv2(&mp->m_sb));
/*
* take care of the core -- initialization from xfs_ialloc()
*/
- memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+ vers = xfs_sb_version_hascrc(&mp->m_sb) ? 3 : 1;
+ ip->i_d.di_version = vers;
+ memset(&ip->i_d, 0, xfs_icdinode_size(&ip->i_d));
ip->i_d.di_magic = XFS_DINODE_MAGIC;
ip->i_d.di_mode = (__uint16_t) mode|S_IFDIR;
- ip->i_d.di_version = 1;
+ ip->i_d.di_version = vers;
ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_nlink = 1; /* account for . */
+ times = XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD;
+ if (ip->i_d.di_version == 3) {
+ ip->i_d.di_crc = 0;
+ ip->i_d.di_changecount = 1;
+ ip->i_d.di_lsn = 0;
+ ip->i_d.di_flags2 = 0;
+ ip->i_d.di_ino = mp->m_sb.sb_rootino;
+ memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
+ platform_uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
+ times |= XFS_ICHGTIME_CREATE;
+ }
+ libxfs_trans_ichgtime(tp, ip, times);
+
libxfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*