diff options
Diffstat (limited to 'fs/xfs')
48 files changed, 1131 insertions, 775 deletions
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 444626ddbd1b..d9b42425291e 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -118,8 +118,6 @@ xfs_allocbt_free_block( xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); - - xfs_trans_binval(cur->bc_tp, bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h index 919756e3ba53..90928bbe693c 100644 --- a/fs/xfs/libxfs/xfs_attr_sf.h +++ b/fs/xfs/libxfs/xfs_attr_sf.h @@ -24,22 +24,6 @@ * Small attribute lists are packed as tightly as possible so as * to fit into the literal area of the inode. */ - -/* - * Entries are packed toward the top as tight as possible. - */ -typedef struct xfs_attr_shortform { - struct xfs_attr_sf_hdr { /* constant-structure header block */ - __be16 totsize; /* total bytes in shortform list */ - __u8 count; /* count of active entries */ - } hdr; - struct xfs_attr_sf_entry { - __uint8_t namelen; /* actual length of name (no NULL) */ - __uint8_t valuelen; /* actual length of value (no NULL) */ - __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ - __uint8_t nameval[1]; /* name & value bytes concatenated */ - } list[1]; /* variable sized array */ -} xfs_attr_shortform_t; typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t; typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index ef00156f4f96..6a051662d8f9 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -912,7 +912,7 @@ xfs_bmap_local_to_extents( * We don't want to deal with the case of keeping inode data inline yet. * So sending the data fork of a regular inode is invalid. */ - ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK)); + ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK)); ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); @@ -1079,7 +1079,7 @@ xfs_bmap_add_attrfork_local( if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip)) return 0; - if (S_ISDIR(ip->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip)->i_mode)) { memset(&dargs, 0, sizeof(dargs)); dargs.geo = ip->i_mount->m_dir_geo; dargs.dp = ip; @@ -1091,7 +1091,7 @@ xfs_bmap_add_attrfork_local( return xfs_dir2_sf_to_block(&dargs); } - if (S_ISLNK(ip->i_d.di_mode)) + if (S_ISLNK(VFS_I(ip)->i_mode)) return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags, XFS_DATA_FORK, xfs_symlink_local_to_remote); diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 1637c37bfbaa..e37508ae589b 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -531,7 +531,6 @@ xfs_bmbt_free_block( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); - xfs_trans_binval(tp, bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index a0eb18ce3ad3..1f88e1ce770f 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -294,6 +294,21 @@ xfs_btree_sblock_verify_crc( return true; } +static int +xfs_btree_free_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + int error; + + error = cur->bc_ops->free_block(cur, bp); + if (!error) { + xfs_trans_binval(cur->bc_tp, bp); + XFS_BTREE_STATS_INC(cur, free); + } + return error; +} + /* * Delete the btree cursor. */ @@ -3209,6 +3224,7 @@ xfs_btree_kill_iroot( int level; int index; int numrecs; + int error; #ifdef DEBUG union xfs_btree_ptr ptr; int i; @@ -3272,8 +3288,6 @@ xfs_btree_kill_iroot( cpp = xfs_btree_ptr_addr(cur, 1, cblock); #ifdef DEBUG for (i = 0; i < numrecs; i++) { - int error; - error = xfs_btree_check_ptr(cur, cpp, i, level - 1); if (error) { XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); @@ -3283,8 +3297,11 @@ xfs_btree_kill_iroot( #endif xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); - cur->bc_ops->free_block(cur, cbp); - XFS_BTREE_STATS_INC(cur, free); + error = xfs_btree_free_block(cur, cbp); + if (error) { + XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); + return error; + } cur->bc_bufs[level - 1] = NULL; be16_add_cpu(&block->bb_level, -1); @@ -3317,14 +3334,12 @@ xfs_btree_kill_root( */ cur->bc_ops->set_root(cur, newroot, -1); - error = cur->bc_ops->free_block(cur, bp); + error = xfs_btree_free_block(cur, bp); if (error) { XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); return error; } - XFS_BTREE_STATS_INC(cur, free); - cur->bc_bufs[level] = NULL; cur->bc_ra[level] = 0; cur->bc_nlevels--; @@ -3830,10 +3845,9 @@ xfs_btree_delrec( } /* Free the deleted block. */ - error = cur->bc_ops->free_block(cur, rbp); + error = xfs_btree_free_block(cur, rbp); if (error) goto error0; - XFS_BTREE_STATS_INC(cur, free); /* * If we joined with the left neighbor, set the buffer in the diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index b14bbd6bb05f..8d4d8bce41bf 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -641,6 +641,22 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp) */ #define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */ +/* + * Entries are packed toward the top as tight as possible. + */ +typedef struct xfs_attr_shortform { + struct xfs_attr_sf_hdr { /* constant-structure header block */ + __be16 totsize; /* total bytes in shortform list */ + __u8 count; /* count of active entries */ + } hdr; + struct xfs_attr_sf_entry { + __uint8_t namelen; /* actual length of name (no NULL) */ + __uint8_t valuelen; /* actual length of value (no NULL) */ + __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ + __uint8_t nameval[1]; /* name & value bytes concatenated */ + } list[1]; /* variable sized array */ +} xfs_attr_shortform_t; + typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */ __be16 base; /* base of free region */ __be16 size; /* length of free region */ diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 2fb53a5c0a74..af0f9d171f8a 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -176,7 +176,7 @@ xfs_dir_isempty( { xfs_dir2_sf_hdr_t *sfp; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_d.di_size == 0) /* might happen during shutdown. */ return 1; if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp)) @@ -231,7 +231,7 @@ xfs_dir_init( struct xfs_da_args *args; int error; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino); if (error) return error; @@ -266,7 +266,7 @@ xfs_dir_createname( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (inum) { rval = xfs_dir_ino_validate(tp->t_mountp, inum); if (rval) @@ -364,7 +364,7 @@ xfs_dir_lookup( int v; /* type-checking value */ int lock_mode; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_lookup); /* @@ -443,7 +443,7 @@ xfs_dir_removename( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_remove); args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS); @@ -505,7 +505,7 @@ xfs_dir_replace( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); rval = xfs_dir_ino_validate(tp->t_mountp, inum); if (rval) diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index c679f3c05b63..89c21d771e35 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -125,16 +125,8 @@ xfs_inobt_free_block( struct xfs_btree_cur *cur, struct xfs_buf *bp) { - xfs_fsblock_t fsbno; - int error; - - fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)); - error = xfs_free_extent(cur->bc_tp, fsbno, 1); - if (error) - return error; - - xfs_trans_binval(cur->bc_tp, bp); - return error; + return xfs_free_extent(cur->bc_tp, + XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1); } STATIC int diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 1aabfda669b0..9d9559eb2835 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -195,28 +195,50 @@ xfs_imap_to_bp( } void -xfs_dinode_from_disk( - xfs_icdinode_t *to, - xfs_dinode_t *from) +xfs_inode_from_disk( + struct xfs_inode *ip, + struct xfs_dinode *from) { - to->di_magic = be16_to_cpu(from->di_magic); - to->di_mode = be16_to_cpu(from->di_mode); - to->di_version = from ->di_version; + struct xfs_icdinode *to = &ip->i_d; + struct inode *inode = VFS_I(ip); + + + /* + * Convert v1 inodes immediately to v2 inode format as this is the + * minimum inode version format we support in the rest of the code. + */ + to->di_version = from->di_version; + if (to->di_version == 1) { + set_nlink(inode, be16_to_cpu(from->di_onlink)); + to->di_projid_lo = 0; + to->di_projid_hi = 0; + to->di_version = 2; + } else { + set_nlink(inode, be32_to_cpu(from->di_nlink)); + to->di_projid_lo = be16_to_cpu(from->di_projid_lo); + to->di_projid_hi = be16_to_cpu(from->di_projid_hi); + } + to->di_format = from->di_format; - to->di_onlink = be16_to_cpu(from->di_onlink); to->di_uid = be32_to_cpu(from->di_uid); to->di_gid = be32_to_cpu(from->di_gid); - to->di_nlink = be32_to_cpu(from->di_nlink); - to->di_projid_lo = be16_to_cpu(from->di_projid_lo); - to->di_projid_hi = be16_to_cpu(from->di_projid_hi); - memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); to->di_flushiter = be16_to_cpu(from->di_flushiter); - to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec); - to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec); - to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec); - to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec); - to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec); - to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec); + + /* + * Time is signed, so need to convert to signed 32 bit before + * storing in inode timestamp which may be 64 bit. Otherwise + * a time before epoch is converted to a time long after epoch + * on 64 bit systems. + */ + inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec); + inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec); + inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec); + inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec); + inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec); + inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec); + inode->i_generation = be32_to_cpu(from->di_gen); + inode->i_mode = be16_to_cpu(from->di_mode); + to->di_size = be64_to_cpu(from->di_size); to->di_nblocks = be64_to_cpu(from->di_nblocks); to->di_extsize = be32_to_cpu(from->di_extsize); @@ -227,42 +249,96 @@ xfs_dinode_from_disk( to->di_dmevmask = be32_to_cpu(from->di_dmevmask); 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); + inode->i_version = 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)); - uuid_copy(&to->di_uuid, &from->di_uuid); } } void -xfs_dinode_to_disk( - xfs_dinode_t *to, - xfs_icdinode_t *from) +xfs_inode_to_disk( + struct xfs_inode *ip, + struct xfs_dinode *to, + xfs_lsn_t lsn) +{ + struct xfs_icdinode *from = &ip->i_d; + struct inode *inode = VFS_I(ip); + + to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC); + to->di_onlink = 0; + + to->di_version = from->di_version; + to->di_format = from->di_format; + to->di_uid = cpu_to_be32(from->di_uid); + to->di_gid = cpu_to_be32(from->di_gid); + to->di_projid_lo = cpu_to_be16(from->di_projid_lo); + to->di_projid_hi = cpu_to_be16(from->di_projid_hi); + + memset(to->di_pad, 0, sizeof(to->di_pad)); + to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec); + to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec); + to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec); + to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec); + to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec); + to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec); + to->di_nlink = cpu_to_be32(inode->i_nlink); + to->di_gen = cpu_to_be32(inode->i_generation); + to->di_mode = cpu_to_be16(inode->i_mode); + + to->di_size = cpu_to_be64(from->di_size); + to->di_nblocks = cpu_to_be64(from->di_nblocks); + to->di_extsize = cpu_to_be32(from->di_extsize); + to->di_nextents = cpu_to_be32(from->di_nextents); + to->di_anextents = cpu_to_be16(from->di_anextents); + to->di_forkoff = from->di_forkoff; + to->di_aformat = from->di_aformat; + to->di_dmevmask = cpu_to_be32(from->di_dmevmask); + to->di_dmstate = cpu_to_be16(from->di_dmstate); + to->di_flags = cpu_to_be16(from->di_flags); + + if (from->di_version == 3) { + to->di_changecount = cpu_to_be64(inode->i_version); + 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(ip->i_ino); + to->di_lsn = cpu_to_be64(lsn); + memset(to->di_pad2, 0, sizeof(to->di_pad2)); + uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid); + to->di_flushiter = 0; + } else { + to->di_flushiter = cpu_to_be16(from->di_flushiter); + } +} + +void +xfs_log_dinode_to_disk( + struct xfs_log_dinode *from, + struct xfs_dinode *to) { to->di_magic = cpu_to_be16(from->di_magic); to->di_mode = cpu_to_be16(from->di_mode); - to->di_version = from ->di_version; + to->di_version = from->di_version; to->di_format = from->di_format; - to->di_onlink = cpu_to_be16(from->di_onlink); + to->di_onlink = 0; to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); to->di_nlink = cpu_to_be32(from->di_nlink); to->di_projid_lo = cpu_to_be16(from->di_projid_lo); to->di_projid_hi = cpu_to_be16(from->di_projid_hi); memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); + to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec); to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec); to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec); to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec); to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec); to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec); + to->di_size = cpu_to_be64(from->di_size); to->di_nblocks = cpu_to_be64(from->di_nblocks); to->di_extsize = cpu_to_be32(from->di_extsize); @@ -367,13 +443,10 @@ xfs_iread( !(mp->m_flags & XFS_MOUNT_IKEEP)) { /* initialise the on-disk inode core */ memset(&ip->i_d, 0, sizeof(ip->i_d)); - ip->i_d.di_magic = XFS_DINODE_MAGIC; - ip->i_d.di_gen = prandom_u32(); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + VFS_I(ip)->i_generation = prandom_u32(); + if (xfs_sb_version_hascrc(&mp->m_sb)) ip->i_d.di_version = 3; - ip->i_d.di_ino = ip->i_ino; - uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid); - } else + else ip->i_d.di_version = 2; return 0; } @@ -403,7 +476,7 @@ xfs_iread( * Otherwise, just get the truly permanent information. */ if (dip->di_mode) { - xfs_dinode_from_disk(&ip->i_d, dip); + xfs_inode_from_disk(ip, dip); error = xfs_iformat_fork(ip, dip); if (error) { #ifdef DEBUG @@ -417,16 +490,10 @@ xfs_iread( * 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); + VFS_I(ip)->i_generation = 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. @@ -434,25 +501,10 @@ xfs_iread( * the inode is already free and not try to mess * with the uninitialized part of it. */ - ip->i_d.di_mode = 0; - } - - /* - * Automatically convert version 1 inode formats in memory to version 2 - * inode format. If the inode is modified, it will get logged and - * rewritten as a version 2 inode. We can do this because we set the - * superblock feature bit for v2 inodes unconditionally during mount - * and it means the reast of the code can assume the inode version is 2 - * or higher. - */ - if (ip->i_d.di_version == 1) { - ip->i_d.di_version = 2; - memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); - ip->i_d.di_nlink = ip->i_d.di_onlink; - ip->i_d.di_onlink = 0; - xfs_set_projid(ip, 0); + VFS_I(ip)->i_mode = 0; } + ASSERT(ip->i_d.di_version >= 2); ip->i_delayed_blks = 0; /* diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 9308c47f2a52..7c4dd321b215 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -20,7 +20,36 @@ struct xfs_inode; struct xfs_dinode; -struct xfs_icdinode; + +/* + * In memory representation of the XFS inode. This is held in the in-core struct + * xfs_inode and represents the current on disk values but the structure is not + * in on-disk format. That is, this structure is always translated to on-disk + * format specific structures at the appropriate time. + */ +struct xfs_icdinode { + __int8_t di_version; /* inode version */ + __int8_t di_format; /* format of di_c data */ + __uint16_t di_flushiter; /* incremented on flush */ + __uint32_t di_uid; /* owner's user id */ + __uint32_t di_gid; /* owner's group id */ + __uint16_t di_projid_lo; /* lower part of owner's project id */ + __uint16_t di_projid_hi; /* higher part of owner's project id */ + xfs_fsize_t di_size; /* number of bytes in file */ + xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ + xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ + xfs_extnum_t di_nextents; /* number of extents in data fork */ + xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/ + __uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ + __int8_t di_aformat; /* format of attr fork's data */ + __uint32_t di_dmevmask; /* DMIG event mask */ + __uint16_t di_dmstate; /* DMIG state info */ + __uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ + + __uint64_t di_flags2; /* more random flags */ + + xfs_ictimestamp_t di_crtime; /* time created */ +}; /* * Inode location information. Stored in the inode and passed to @@ -38,8 +67,11 @@ int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *, 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 *to, struct xfs_icdinode *from); -void xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from); +void xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to, + xfs_lsn_t lsn); +void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); +void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, + struct xfs_dinode *to); #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 0defbd02f62d..11faf7df14c8 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -31,6 +31,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_attr_sf.h" +#include "xfs_da_format.h" kmem_zone_t *xfs_ifork_zone; @@ -120,7 +121,7 @@ xfs_iformat_fork( return -EFSCORRUPTED; } - switch (ip->i_d.di_mode & S_IFMT) { + switch (VFS_I(ip)->i_mode & S_IFMT) { case S_IFIFO: case S_IFCHR: case S_IFBLK: diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 265314690415..d54a8018b079 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -290,6 +290,7 @@ typedef struct xfs_inode_log_format_64 { __int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_64_t; + /* * Flags for xfs_trans_log_inode flags field. */ @@ -360,15 +361,15 @@ typedef struct xfs_ictimestamp { } xfs_ictimestamp_t; /* - * NOTE: This structure must be kept identical to struct xfs_dinode - * except for the endianness annotations. + * Define the format of the inode core that is logged. This structure must be + * kept identical to struct xfs_dinode except for the endianness annotations. */ -typedef struct xfs_icdinode { +struct xfs_log_dinode { __uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */ __uint16_t di_mode; /* mode and type of file */ __int8_t di_version; /* inode version */ __int8_t di_format; /* format of di_c data */ - __uint16_t di_onlink; /* old number of links to file */ + __uint8_t di_pad3[2]; /* unused in v2/3 inodes */ __uint32_t di_uid; /* owner's user id */ __uint32_t di_gid; /* owner's group id */ __uint32_t di_nlink; /* number of links to file */ @@ -407,13 +408,13 @@ typedef struct xfs_icdinode { 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(int version) +static inline uint xfs_log_dinode_size(int version) { if (version == 3) - return sizeof(struct xfs_icdinode); - return offsetof(struct xfs_icdinode, di_next_unlinked); + return sizeof(struct xfs_log_dinode); + return offsetof(struct xfs_log_dinode, di_next_unlinked); } /* @@ -495,6 +496,8 @@ enum xfs_blft { XFS_BLFT_ATTR_LEAF_BUF, XFS_BLFT_ATTR_RMT_BUF, XFS_BLFT_SB_BUF, + XFS_BLFT_RTBITMAP_BUF, + XFS_BLFT_RTSUMMARY_BUF, XFS_BLFT_MAX_BUF = (1 << XFS_BLFT_BITS), }; diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index f51078f1e92a..8eed51275bb3 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -37,7 +37,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_DQ_PROJ 0x0002 /* project quota */ #define XFS_DQ_GROUP 0x0004 /* a group quota */ #define XFS_DQ_DIRTY 0x0008 /* dquot is dirty */ -#define XFS_DQ_FREEING 0x0010 /* dquot is beeing torn down */ +#define XFS_DQ_FREEING 0x0010 /* dquot is being torn down */ #define XFS_DQ_ALLTYPES (XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP) @@ -116,6 +116,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_QMOPT_DQREPAIR 0x0001000 /* repair dquot if damaged */ #define XFS_QMOPT_GQUOTA 0x0002000 /* group dquot requested */ #define XFS_QMOPT_ENOSPC 0x0004000 /* enospc instead of edquot (prj) */ +#define XFS_QMOPT_DQNEXT 0x0008000 /* return next dquot >= this ID */ /* * flags to xfs_trans_mod_dquot to indicate which field needs to be diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 9b59ffa1fc19..951c044e24e4 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -42,6 +42,31 @@ */ /* + * Real time buffers need verifiers to avoid runtime warnings during IO. + * We don't have anything to verify, however, so these are just dummy + * operations. + */ +static void +xfs_rtbuf_verify_read( + struct xfs_buf *bp) +{ + return; +} + +static void +xfs_rtbuf_verify_write( + struct xfs_buf *bp) +{ + return; +} + +const struct xfs_buf_ops xfs_rtbuf_ops = { + .name = "rtbuf", + .verify_read = xfs_rtbuf_verify_read, + .verify_write = xfs_rtbuf_verify_write, +}; + +/* * Get a buffer for the bitmap or summary file block specified. * The buffer is returned read and locked. */ @@ -68,9 +93,12 @@ xfs_rtbuf_get( ASSERT(map.br_startblock != NULLFSBLOCK); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map.br_startblock), - mp->m_bsize, 0, &bp, NULL); + mp->m_bsize, 0, &bp, &xfs_rtbuf_ops); if (error) return error; + + xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF + : XFS_BLFT_RTBITMAP_BUF); *bpp = bp; return 0; } @@ -983,7 +1011,7 @@ xfs_rtfree_extent( mp->m_sb.sb_rextents) { if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM; - *(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0; + *(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); } return 0; diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index b25bb9a343f3..961e6475a309 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -27,7 +27,6 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t, extern void xfs_perag_put(struct xfs_perag *pag); extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t); -extern void xfs_sb_calc_crc(struct xfs_buf *bp); extern void xfs_log_sb(struct xfs_trans *tp); extern int xfs_sync_sb(struct xfs_mount *mp, bool wait); extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 15c3ceb845b9..81ac870834da 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -53,6 +53,7 @@ extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; +extern const struct xfs_buf_ops xfs_rtbuf_ops; /* * Transaction types. Used to distinguish types of buffers. These never reach diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index b125f9019145..75a39a8257ee 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -36,6 +36,10 @@ #include <linux/pagevec.h> #include <linux/writeback.h> +/* flags for direct write completions */ +#define XFS_DIO_FLAG_UNWRITTEN (1 << 0) +#define XFS_DIO_FLAG_APPEND (1 << 1) + /* * structure owned by writepages passed to individual writepage calls */ @@ -225,10 +229,12 @@ xfs_end_io( struct xfs_inode *ip = XFS_I(ioend->io_inode); int error = 0; - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { + /* + * Set an error if the mount has shut down and proceed with end I/O + * processing so it can perform whatever cleanups are necessary. + */ + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) ioend->io_error = -EIO; - goto done; - } /* * For unwritten extents we need to issue transactions to convert a @@ -1039,27 +1045,8 @@ xfs_vm_releasepage( } /* - * When we map a DIO buffer, we may need to attach an ioend that describes the - * type of write IO we are doing. This passes to the completion function the - * operations it needs to perform. If the mapping is for an overwrite wholly - * within the EOF then we don't need an ioend and so we don't allocate one. - * This avoids the unnecessary overhead of allocating and freeing ioends for - * workloads that don't require transactions on IO completion. - * - * If we get multiple mappings in a single IO, we might be mapping different - * types. But because the direct IO can only have a single private pointer, we - * need to ensure that: - * - * a) i) the ioend spans the entire region of unwritten mappings; or - * ii) the ioend spans all the mappings that cross or are beyond EOF; and - * b) if it contains unwritten extents, it is *permanently* marked as such - * - * We could do this by chaining ioends like buffered IO does, but we only - * actually get one IO completion callback from the direct IO, and that spans - * the entire IO regardless of how many mappings and IOs are needed to complete - * the DIO. There is only going to be one reference to the ioend and its life - * cycle is constrained by the DIO completion code. hence we don't need - * reference counting here. + * When we map a DIO buffer, we may need to pass flags to + * xfs_end_io_direct_write to tell it what kind of write IO we are doing. * * Note that for DIO, an IO to the highest supported file block offset (i.e. * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64 @@ -1067,68 +1054,26 @@ xfs_vm_releasepage( * extending the file size. We won't know for sure until IO completion is run * and the actual max write offset is communicated to the IO completion * routine. - * - * For DAX page faults, we are preparing to never see unwritten extents here, - * nor should we ever extend the inode size. Hence we will soon have nothing to - * do here for this case, ensuring we don't have to provide an IO completion - * callback to free an ioend that we don't actually need for a fault into the - * page at offset (2^63 - 1FSB) bytes. */ - static void xfs_map_direct( struct inode *inode, struct buffer_head *bh_result, struct xfs_bmbt_irec *imap, - xfs_off_t offset, - bool dax_fault) + xfs_off_t offset) { - struct xfs_ioend *ioend; + uintptr_t *flags = (uintptr_t *)&bh_result->b_private; xfs_off_t size = bh_result->b_size; - int type; - - if (ISUNWRITTEN(imap)) - type = XFS_IO_UNWRITTEN; - else - type = XFS_IO_OVERWRITE; - trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap); - - if (dax_fault) { - ASSERT(type == XFS_IO_OVERWRITE); - trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type, - imap); - return; - } + trace_xfs_get_blocks_map_direct(XFS_I(inode), offset, size, + ISUNWRITTEN(imap) ? XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, imap); - if (bh_result->b_private) { - ioend = bh_result->b_private; - ASSERT(ioend->io_size > 0); - ASSERT(offset >= ioend->io_offset); - if (offset + size > ioend->io_offset + ioend->io_size) - ioend->io_size = offset - ioend->io_offset + size; - - if (type == XFS_IO_UNWRITTEN && type != ioend->io_type) - ioend->io_type = XFS_IO_UNWRITTEN; - - trace_xfs_gbmap_direct_update(XFS_I(inode), ioend->io_offset, - ioend->io_size, ioend->io_type, - imap); - } else if (type == XFS_IO_UNWRITTEN || - offset + size > i_size_read(inode) || - offset + size < 0) { - ioend = xfs_alloc_ioend(inode, type); - ioend->io_offset = offset; - ioend->io_size = size; - - bh_result->b_private = ioend; + if (ISUNWRITTEN(imap)) { + *flags |= XFS_DIO_FLAG_UNWRITTEN; + set_buffer_defer_completion(bh_result); + } else if (offset + size > i_size_read(inode) || offset + size < 0) { + *flags |= XFS_DIO_FLAG_APPEND; set_buffer_defer_completion(bh_result); - - trace_xfs_gbmap_direct_new(XFS_I(inode), offset, size, type, - imap); - } else { - trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type, - imap); } } @@ -1299,9 +1244,12 @@ __xfs_get_blocks( if (ISUNWRITTEN(&imap)) set_buffer_unwritten(bh_result); /* direct IO needs special help */ - if (create && direct) - xfs_map_direct(inode, bh_result, &imap, offset, - dax_fault); + if (create && direct) { + if (dax_fault) + ASSERT(!ISUNWRITTEN(&imap)); + else + xfs_map_direct(inode, bh_result, &imap, offset); + } } /* @@ -1371,42 +1319,50 @@ xfs_get_blocks_dax_fault( return __xfs_get_blocks(inode, iblock, bh_result, create, true, true); } -static void -__xfs_end_io_direct_write( - struct inode *inode, - struct xfs_ioend *ioend, +/* + * Complete a direct I/O write request. + * + * xfs_map_direct passes us some flags in the private data to tell us what to + * do. If no flags are set, then the write IO is an overwrite wholly within + * the existing allocated file size and so there is nothing for us to do. + * + * Note that in this case the completion can be called in interrupt context, + * whereas if we have flags set we will always be called in task context + * (i.e. from a workqueue). + */ +STATIC int +xfs_end_io_direct_write( + struct kiocb *iocb, loff_t offset, - ssize_t size) + ssize_t size, + void *private) { - struct xfs_mount *mp = XFS_I(inode)->i_mount; + struct inode *inode = file_inode(iocb->ki_filp); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + uintptr_t flags = (uintptr_t)private; + int error = 0; - if (XFS_FORCED_SHUTDOWN(mp) || ioend->io_error) - goto out_end_io; + trace_xfs_end_io_direct_write(ip, offset, size); - /* - * dio completion end_io functions are only called on writes if more - * than 0 bytes was written. - */ - ASSERT(size > 0); + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; - /* - * The ioend only maps whole blocks, while the IO may be sector aligned. - * Hence the ioend offset/size may not match the IO offset/size exactly. - * Because we don't map overwrites within EOF into the ioend, the offset - * may not match, but only if the endio spans EOF. Either way, write - * the IO sizes into the ioend so that completion processing does the - * right thing. - */ - ASSERT(offset + size <= ioend->io_offset + ioend->io_size); - ioend->io_size = size; - ioend->io_offset = offset; + if (size <= 0) + return size; /* - * The ioend tells us whether we are doing unwritten extent conversion + * The flags tell us whether we are doing unwritten extent conversions * or an append transaction that updates the on-disk file size. These * cases are the only cases where we should *potentially* be needing * to update the VFS inode size. - * + */ + if (flags == 0) { + ASSERT(offset + size <= i_size_read(inode)); + return 0; + } + + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We * have no other method of updating EOF for AIO, so always do it here @@ -1417,91 +1373,56 @@ __xfs_end_io_direct_write( * here can result in EOF moving backwards and Bad Things Happen when * that occurs. */ - spin_lock(&XFS_I(inode)->i_flags_lock); + spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) i_size_write(inode, offset + size); - spin_unlock(&XFS_I(inode)->i_flags_lock); - - /* - * If we are doing an append IO that needs to update the EOF on disk, - * do the transaction reserve now so we can use common end io - * processing. Stashing the error (if there is one) in the ioend will - * result in the ioend processing passing on the error if it is - * possible as we can't return it from here. - */ - if (ioend->io_type == XFS_IO_OVERWRITE) - ioend->io_error = xfs_setfilesize_trans_alloc(ioend); + spin_unlock(&ip->i_flags_lock); -out_end_io: - xfs_end_io(&ioend->io_work); - return; -} + if (flags & XFS_DIO_FLAG_UNWRITTEN) { + trace_xfs_end_io_direct_write_unwritten(ip, offset, size); -/* - * Complete a direct I/O write request. - * - * The ioend structure is passed from __xfs_get_blocks() to tell us what to do. - * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite - * wholly within the EOF and so there is nothing for us to do. Note that in this - * case the completion can be called in interrupt context, whereas if we have an - * ioend we will always be called in task context (i.e. from a workqueue). - */ -STATIC void -xfs_end_io_direct_write( - struct kiocb *iocb, - loff_t offset, - ssize_t size, - void *private) -{ - struct inode *inode = file_inode(iocb->ki_filp); - struct xfs_ioend *ioend = private; + error = xfs_iomap_write_unwritten(ip, offset, size); + } else if (flags & XFS_DIO_FLAG_APPEND) { + struct xfs_trans *tp; - trace_xfs_gbmap_direct_endio(XFS_I(inode), offset, size, - ioend ? ioend->io_type : 0, NULL); + trace_xfs_end_io_direct_write_append(ip, offset, size); - if (!ioend) { - ASSERT(offset + size <= i_size_read(inode)); - return; + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0); + if (error) { + xfs_trans_cancel(tp); + return error; + } + error = xfs_setfilesize(ip, tp, offset, size); } - __xfs_end_io_direct_write(inode, ioend, offset, size); + return error; } -static inline ssize_t -xfs_vm_do_dio( - struct inode *inode, +STATIC ssize_t +xfs_vm_direct_IO( struct kiocb *iocb, struct iov_iter *iter, - loff_t offset, - void (*endio)(struct kiocb *iocb, - loff_t offset, - ssize_t size, - void *private), - int flags) + loff_t offset) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + dio_iodone_t *endio = NULL; + int flags = 0; struct block_device *bdev; - if (IS_DAX(inode)) + if (iov_iter_rw(iter) == WRITE) { + endio = xfs_end_io_direct_write; + flags = DIO_ASYNC_EXTEND; + } + + if (IS_DAX(inode)) { return dax_do_io(iocb, inode, iter, offset, xfs_get_blocks_direct, endio, 0); + } bdev = xfs_find_bdev_for_inode(inode); return __blockdev_direct_IO(iocb, inode, bdev, iter, offset, - xfs_get_blocks_direct, endio, NULL, flags); -} - -STATIC ssize_t -xfs_vm_direct_IO( - struct kiocb *iocb, - struct iov_iter *iter, - loff_t offset) -{ - struct inode *inode = iocb->ki_filp->f_mapping->host; - - if (iov_iter_rw(iter) == WRITE) - return xfs_vm_do_dio(inode, iocb, iter, offset, - xfs_end_io_direct_write, DIO_ASYNC_EXTEND); - return xfs_vm_do_dio(inode, iocb, iter, offset, NULL, 0); + xfs_get_blocks_direct, endio, NULL, flags); } /* @@ -1584,14 +1505,22 @@ xfs_vm_write_failed( if (block_start >= to) break; - if (!buffer_delay(bh)) + /* + * Process delalloc and unwritten buffers beyond EOF. We can + * encounter unwritten buffers in the event that a file has + * post-EOF unwritten extents and an extending write happens to + * fail (e.g., an unaligned write that also involves a delalloc + * to the same page). + */ + if (!buffer_delay(bh) && !buffer_unwritten(bh)) continue; if (!buffer_new(bh) && block_offset < i_size_read(inode)) continue; - xfs_vm_kill_delalloc_range(inode, block_offset, - block_offset + bh->b_size); + if (buffer_delay(bh)) + xfs_vm_kill_delalloc_range(inode, block_offset, + block_offset + bh->b_size); /* * This buffer does not contain data anymore. make sure anyone @@ -1602,6 +1531,7 @@ xfs_vm_write_failed( clear_buffer_mapped(bh); clear_buffer_new(bh); clear_buffer_dirty(bh); + clear_buffer_unwritten(bh); } } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 45ec9e40150c..fd7f51c39b3f 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -202,10 +202,12 @@ xfs_bmap_rtalloc( ralen = MAXEXTLEN / mp->m_sb.sb_rextsize; /* - * Lock out other modifications to the RT bitmap inode. + * Lock out modifications to both the RT bitmap and summary inodes */ xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL); xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL); + xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL); /* * If it's an allocation to an empty file at offset 0, @@ -821,7 +823,7 @@ bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force) { /* prealloc/delalloc exists only on regular files */ - if (!S_ISREG(ip->i_d.di_mode)) + if (!S_ISREG(VFS_I(ip)->i_mode)) return false; /* @@ -1726,7 +1728,7 @@ xfs_swap_extents( xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL); /* Verify that both files have the same format */ - if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) { + if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) { error = -EINVAL; goto out_unlock; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 435c7de42e5f..9a2191b91137 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -650,7 +650,7 @@ xfs_buf_read_map( if (bp) { trace_xfs_buf_read(bp, flags, _RET_IP_); - if (!XFS_BUF_ISDONE(bp)) { + if (!(bp->b_flags & XBF_DONE)) { XFS_STATS_INC(target->bt_mount, xb_get_read); bp->b_ops = ops; _xfs_buf_read(bp, flags); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index c75721acd867..4eb89bd4ee73 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -302,6 +302,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, /* Buffer Utility Routines */ extern void *xfs_buf_offset(struct xfs_buf *, size_t); +extern void xfs_buf_stale(struct xfs_buf *bp); /* Delayed Write Buffer Routines */ extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); @@ -312,31 +313,6 @@ extern int xfs_buf_delwri_submit_nowait(struct list_head *); extern int xfs_buf_init(void); extern void xfs_buf_terminate(void); -#define XFS_BUF_ZEROFLAGS(bp) \ - ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \ - XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \ - XBF_WRITE_FAIL)) - -void xfs_buf_stale(struct xfs_buf *bp); -#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE) -#define XFS_BUF_ISSTALE(bp) ((bp)->b_flags & XBF_STALE) - -#define XFS_BUF_DONE(bp) ((bp)->b_flags |= XBF_DONE) -#define XFS_BUF_UNDONE(bp) ((bp)->b_flags &= ~XBF_DONE) -#define XFS_BUF_ISDONE(bp) ((bp)->b_flags & XBF_DONE) - -#define XFS_BUF_ASYNC(bp) ((bp)->b_flags |= XBF_ASYNC) -#define XFS_BUF_UNASYNC(bp) ((bp)->b_flags &= ~XBF_ASYNC) -#define XFS_BUF_ISASYNC(bp) ((bp)->b_flags & XBF_ASYNC) - -#define XFS_BUF_READ(bp) ((bp)->b_flags |= XBF_READ) -#define XFS_BUF_UNREAD(bp) ((bp)->b_flags &= ~XBF_READ) -#define XFS_BUF_ISREAD(bp) ((bp)->b_flags & XBF_READ) - -#define XFS_BUF_WRITE(bp) ((bp)->b_flags |= XBF_WRITE) -#define XFS_BUF_UNWRITE(bp) ((bp)->b_flags &= ~XBF_WRITE) -#define XFS_BUF_ISWRITE(bp) ((bp)->b_flags & XBF_WRITE) - /* * These macros use the IO block map rather than b_bn. b_bn is now really * just for the buffer cache index for cached buffers. As IO does not use b_bn diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 7e986da34f6c..99e91a0e554e 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -431,7 +431,7 @@ xfs_buf_item_unpin( if (freed && stale) { ASSERT(bip->bli_flags & XFS_BLI_STALE); ASSERT(xfs_buf_islocked(bp)); - ASSERT(XFS_BUF_ISSTALE(bp)); + ASSERT(bp->b_flags & XBF_STALE); ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); trace_xfs_buf_item_unpin_stale(bip); @@ -493,7 +493,7 @@ xfs_buf_item_unpin( xfs_buf_hold(bp); bp->b_flags |= XBF_ASYNC; xfs_buf_ioerror(bp, -EIO); - XFS_BUF_UNDONE(bp); + bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); xfs_buf_ioend(bp); } @@ -1067,7 +1067,7 @@ xfs_buf_iodone_callbacks( */ if (XFS_FORCED_SHUTDOWN(mp)) { xfs_buf_stale(bp); - XFS_BUF_DONE(bp); + bp->b_flags |= XBF_DONE; trace_xfs_buf_item_iodone(bp, _RET_IP_); goto do_callbacks; } @@ -1090,7 +1090,7 @@ xfs_buf_iodone_callbacks( * errors tend to affect the whole device and a failing log write * will make us give up. But we really ought to do better here. */ - if (XFS_BUF_ISASYNC(bp)) { + if (bp->b_flags & XBF_ASYNC) { ASSERT(bp->b_iodone != NULL); trace_xfs_buf_item_iodone_async(bp, _RET_IP_); @@ -1113,7 +1113,7 @@ xfs_buf_iodone_callbacks( * sure to return the error to the caller of xfs_bwrite(). */ xfs_buf_stale(bp); - XFS_BUF_DONE(bp); + bp->b_flags |= XBF_DONE; trace_xfs_buf_error_relse(bp, _RET_IP_); diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 642d55d10075..93b3ab0c5435 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -665,7 +665,7 @@ xfs_readdir( if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_getdents); args.dp = dp; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 9c44d38dcd1f..316b2a1bdba5 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -92,26 +92,28 @@ xfs_qm_adjust_dqlimits( { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_disk_dquot *d = &dq->q_core; + struct xfs_def_quota *defq; int prealloc = 0; ASSERT(d->d_id); + defq = xfs_get_defquota(dq, q); - if (q->qi_bsoftlimit && !d->d_blk_softlimit) { - d->d_blk_softlimit = cpu_to_be64(q->qi_bsoftlimit); + if (defq->bsoftlimit && !d->d_blk_softlimit) { + d->d_blk_softlimit = cpu_to_be64(defq->bsoftlimit); prealloc = 1; } - if (q->qi_bhardlimit && !d->d_blk_hardlimit) { - d->d_blk_hardlimit = cpu_to_be64(q->qi_bhardlimit); + if (defq->bhardlimit && !d->d_blk_hardlimit) { + d->d_blk_hardlimit = cpu_to_be64(defq->bhardlimit); prealloc = 1; } - if (q->qi_isoftlimit && !d->d_ino_softlimit) - d->d_ino_softlimit = cpu_to_be64(q->qi_isoftlimit); - if (q->qi_ihardlimit && !d->d_ino_hardlimit) - d->d_ino_hardlimit = cpu_to_be64(q->qi_ihardlimit); - if (q->qi_rtbsoftlimit && !d->d_rtb_softlimit) - d->d_rtb_softlimit = cpu_to_be64(q->qi_rtbsoftlimit); - if (q->qi_rtbhardlimit && !d->d_rtb_hardlimit) - d->d_rtb_hardlimit = cpu_to_be64(q->qi_rtbhardlimit); + if (defq->isoftlimit && !d->d_ino_softlimit) + d->d_ino_softlimit = cpu_to_be64(defq->isoftlimit); + if (defq->ihardlimit && !d->d_ino_hardlimit) + d->d_ino_hardlimit = cpu_to_be64(defq->ihardlimit); + if (defq->rtbsoftlimit && !d->d_rtb_softlimit) + d->d_rtb_softlimit = cpu_to_be64(defq->rtbsoftlimit); + if (defq->rtbhardlimit && !d->d_rtb_hardlimit) + d->d_rtb_hardlimit = cpu_to_be64(defq->rtbhardlimit); if (prealloc) xfs_dquot_set_prealloc_limits(dq); @@ -232,7 +234,8 @@ xfs_qm_init_dquot_blk( { struct xfs_quotainfo *q = mp->m_quotainfo; xfs_dqblk_t *d; - int curid, i; + xfs_dqid_t curid; + int i; ASSERT(tp); ASSERT(xfs_buf_islocked(bp)); @@ -243,7 +246,6 @@ xfs_qm_init_dquot_blk( * ID of the first dquot in the block - id's are zero based. */ curid = id - (id % q->qi_dqperchunk); - ASSERT(curid >= 0); memset(d, 0, BBTOB(q->qi_dqchunklen)); for (i = 0; i < q->qi_dqperchunk; i++, d++, curid++) { d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC); @@ -464,12 +466,13 @@ xfs_qm_dqtobp( struct xfs_bmbt_irec map; int nmaps = 1, error; struct xfs_buf *bp; - struct xfs_inode *quotip = xfs_dq_to_quota_inode(dqp); + struct xfs_inode *quotip; struct xfs_mount *mp = dqp->q_mount; xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id); struct xfs_trans *tp = (tpp ? *tpp : NULL); uint lock_mode; + quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags); dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk; lock_mode = xfs_ilock_data_map_shared(quotip); @@ -685,6 +688,56 @@ error0: } /* + * Advance to the next id in the current chunk, or if at the + * end of the chunk, skip ahead to first id in next allocated chunk + * using the SEEK_DATA interface. + */ +int +xfs_dq_get_next_id( + xfs_mount_t *mp, + uint type, + xfs_dqid_t *id, + loff_t eof) +{ + struct xfs_inode *quotip; + xfs_fsblock_t start; + loff_t offset; + uint lock; + xfs_dqid_t next_id; + int error = 0; + + /* Simple advance */ + next_id = *id + 1; + + /* If new ID is within the current chunk, advancing it sufficed */ + if (next_id % mp->m_quotainfo->qi_dqperchunk) { + *id = next_id; + return 0; + } + + /* Nope, next_id is now past the current chunk, so find the next one */ + start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk; + + quotip = xfs_quota_inode(mp, type); + lock = xfs_ilock_data_map_shared(quotip); + + offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start), + eof, SEEK_DATA); + if (offset < 0) + error = offset; + + xfs_iunlock(quotip, lock); + + /* -ENXIO is essentially "no more data" */ + if (error) + return (error == -ENXIO ? -ENOENT: error); + + /* Convert next data offset back to a quota id */ + *id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk; + return 0; +} + +/* * Given the file system, inode OR id, and type (UDQUOT/GDQUOT), return a * a locked dquot, doing an allocation (if requested) as needed. * When both an inode and an id are given, the inode's id takes precedence. @@ -704,6 +757,7 @@ xfs_qm_dqget( struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = xfs_dquot_tree(qi, type); struct xfs_dquot *dqp; + loff_t eof = 0; int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -731,6 +785,21 @@ xfs_qm_dqget( } #endif + /* Get the end of the quota file if we need it */ + if (flags & XFS_QMOPT_DQNEXT) { + struct xfs_inode *quotip; + xfs_fileoff_t last; + uint lock_mode; + + quotip = xfs_quota_inode(mp, type); + lock_mode = xfs_ilock_data_map_shared(quotip); + error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK); + xfs_iunlock(quotip, lock_mode); + if (error) + return error; + eof = XFS_FSB_TO_B(mp, last); + } + restart: mutex_lock(&qi->qi_tree_lock); dqp = radix_tree_lookup(tree, id); @@ -744,6 +813,18 @@ restart: goto restart; } + /* uninit / unused quota found in radix tree, keep looking */ + if (flags & XFS_QMOPT_DQNEXT) { + if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { + xfs_dqunlock(dqp); + mutex_unlock(&qi->qi_tree_lock); + error = xfs_dq_get_next_id(mp, type, &id, eof); + if (error) + return error; + goto restart; + } + } + dqp->q_nrefs++; mutex_unlock(&qi->qi_tree_lock); @@ -770,6 +851,13 @@ restart: if (ip) xfs_ilock(ip, XFS_ILOCK_EXCL); + /* If we are asked to find next active id, keep looking */ + if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) { + error = xfs_dq_get_next_id(mp, type, &id, eof); + if (!error) + goto restart; + } + if (error) return error; @@ -820,6 +908,17 @@ restart: qi->qi_dquots++; mutex_unlock(&qi->qi_tree_lock); + /* If we are asked to find next active id, keep looking */ + if (flags & XFS_QMOPT_DQNEXT) { + if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { + xfs_qm_dqput(dqp); + error = xfs_dq_get_next_id(mp, type, &id, eof); + if (error) + return error; + goto restart; + } + } + dqret: ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL)); trace_xfs_dqget_miss(dqp); diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index 652cd3c5b58c..2816d42507bc 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -152,7 +152,7 @@ xfs_nfs_get_inode( return ERR_PTR(error); } - if (ip->i_d.di_gen != generation) { + if (VFS_I(ip)->i_generation != generation) { IRELE(ip); return ERR_PTR(-ESTALE); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 52883ac3cf84..ac0fd32de31e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -156,9 +156,9 @@ xfs_update_prealloc_flags( xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); if (!(flags & XFS_PREALLOC_INVISIBLE)) { - ip->i_d.di_mode &= ~S_ISUID; - if (ip->i_d.di_mode & S_IXGRP) - ip->i_d.di_mode &= ~S_ISGID; + VFS_I(ip)->i_mode &= ~S_ISUID; + if (VFS_I(ip)->i_mode & S_IXGRP) + VFS_I(ip)->i_mode &= ~S_ISGID; xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); } @@ -1337,31 +1337,31 @@ out: return found; } -STATIC loff_t -xfs_seek_hole_data( - struct file *file, +/* + * caller must lock inode with xfs_ilock_data_map_shared, + * can we craft an appropriate ASSERT? + * + * end is because the VFS-level lseek interface is defined such that any + * offset past i_size shall return -ENXIO, but we use this for quota code + * which does not maintain i_size, and we want to SEEK_DATA past i_size. + */ +loff_t +__xfs_seek_hole_data( + struct inode *inode, loff_t start, + loff_t end, int whence) { - struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; loff_t uninitialized_var(offset); - xfs_fsize_t isize; xfs_fileoff_t fsbno; - xfs_filblks_t end; - uint lock; + xfs_filblks_t lastbno; int error; - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - lock = xfs_ilock_data_map_shared(ip); - - isize = i_size_read(inode); - if (start >= isize) { + if (start >= end) { error = -ENXIO; - goto out_unlock; + goto out_error; } /* @@ -1369,22 +1369,22 @@ xfs_seek_hole_data( * by fsbno to the end block of the file. */ fsbno = XFS_B_TO_FSBT(mp, start); - end = XFS_B_TO_FSB(mp, isize); + lastbno = XFS_B_TO_FSB(mp, end); for (;;) { struct xfs_bmbt_irec map[2]; int nmap = 2; unsigned int i; - error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap, + error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap, XFS_BMAPI_ENTIRE); if (error) - goto out_unlock; + goto out_error; /* No extents at given offset, must be beyond EOF */ if (nmap == 0) { error = -ENXIO; - goto out_unlock; + goto out_error; } for (i = 0; i < nmap; i++) { @@ -1426,7 +1426,7 @@ xfs_seek_hole_data( * hole at the end of any file). */ if (whence == SEEK_HOLE) { - offset = isize; + offset = end; break; } /* @@ -1434,7 +1434,7 @@ xfs_seek_hole_data( */ ASSERT(whence == SEEK_DATA); error = -ENXIO; - goto out_unlock; + goto out_error; } ASSERT(i > 1); @@ -1445,14 +1445,14 @@ xfs_seek_hole_data( */ fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount; start = XFS_FSB_TO_B(mp, fsbno); - if (start >= isize) { + if (start >= end) { if (whence == SEEK_HOLE) { - offset = isize; + offset = end; break; } ASSERT(whence == SEEK_DATA); error = -ENXIO; - goto out_unlock; + goto out_error; } } @@ -1464,7 +1464,39 @@ out: * situation in particular. */ if (whence == SEEK_HOLE) - offset = min_t(loff_t, offset, isize); + offset = min_t(loff_t, offset, end); + + return offset; + +out_error: + return error; +} + +STATIC loff_t +xfs_seek_hole_data( + struct file *file, + loff_t start, + int whence) +{ + struct inode *inode = file->f_mapping->host; + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + uint lock; + loff_t offset, end; + int error = 0; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + lock = xfs_ilock_data_map_shared(ip); + + end = i_size_read(inode); + offset = __xfs_seek_hole_data(inode, start, end, whence); + if (offset < 0) { + error = offset; + goto out_unlock; + } + offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes); out_unlock: diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index c4c130f9bfb6..a51353a1f87f 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -151,7 +151,7 @@ xfs_filestream_pick_ag( xfs_agnumber_t ag, max_ag = NULLAGNUMBER; int err, trylock, nscan; - ASSERT(S_ISDIR(ip->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(ip)->i_mode)); /* 2% of an AG's blocks must be free for it to be chosen. */ minfree = mp->m_sb.sb_agblocks / 50; @@ -319,7 +319,7 @@ xfs_filestream_lookup_ag( xfs_agnumber_t startag, ag = NULLAGNUMBER; struct xfs_mru_cache_elem *mru; - ASSERT(S_ISREG(ip->i_d.di_mode)); + ASSERT(S_ISREG(VFS_I(ip)->i_mode)); pip = xfs_filestream_get_parent(ip); if (!pip) diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index 1b6a98b66886..f32713f14f9a 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -25,6 +25,5 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval, xfs_fsop_resblks_t *outval); extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags); -extern int xfs_fs_log_dummy(struct xfs_mount *mp); #endif /* __XFS_FSOPS_H__ */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index d7a490f24ead..bf2d60749278 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -63,6 +63,9 @@ xfs_inode_alloc( return NULL; } + /* VFS doesn't initialise i_mode! */ + VFS_I(ip)->i_mode = 0; + XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!spin_is_locked(&ip->i_flags_lock)); @@ -79,7 +82,7 @@ xfs_inode_alloc( memset(&ip->i_df, 0, sizeof(xfs_ifork_t)); ip->i_flags = 0; ip->i_delayed_blks = 0; - memset(&ip->i_d, 0, sizeof(xfs_icdinode_t)); + memset(&ip->i_d, 0, sizeof(ip->i_d)); return ip; } @@ -98,7 +101,7 @@ void xfs_inode_free( struct xfs_inode *ip) { - switch (ip->i_d.di_mode & S_IFMT) { + switch (VFS_I(ip)->i_mode & S_IFMT) { case S_IFREG: case S_IFDIR: case S_IFLNK: @@ -135,6 +138,34 @@ xfs_inode_free( } /* + * When we recycle a reclaimable inode, we need to re-initialise the VFS inode + * part of the structure. This is made more complex by the fact we store + * information about the on-disk values in the VFS inode and so we can't just + * overwrite the values unconditionally. Hence we save the parameters we + * need to retain across reinitialisation, and rewrite them into the VFS inode + * after reinitialisation even if it fails. + */ +static int +xfs_reinit_inode( + struct xfs_mount *mp, + struct inode *inode) +{ + int error; + uint32_t nlink = inode->i_nlink; + uint32_t generation = inode->i_generation; + uint64_t version = inode->i_version; + umode_t mode = inode->i_mode; + + error = inode_init_always(mp->m_super, inode); + + set_nlink(inode, nlink); + inode->i_generation = generation; + inode->i_version = version; + inode->i_mode = mode; + return error; +} + +/* * Check the validity of the inode we just found it the cache */ static int @@ -185,7 +216,7 @@ xfs_iget_cache_hit( /* * If lookup is racing with unlink return an error immediately. */ - if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) { + if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) { error = -ENOENT; goto out_error; } @@ -208,7 +239,7 @@ xfs_iget_cache_hit( spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); - error = inode_init_always(mp->m_super, inode); + error = xfs_reinit_inode(mp, inode); if (error) { /* * Re-initializing the inode failed, and we are in deep @@ -295,7 +326,7 @@ xfs_iget_cache_miss( trace_xfs_iget_miss(ip); - if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) { + if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) { error = -ENOENT; goto out_destroy; } @@ -444,7 +475,7 @@ again: * If we have a real type for an on-disk inode, we can setup the inode * now. If it's a new inode being created, xfs_ialloc will handle it. */ - if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0) + if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0) xfs_setup_existing_inode(ip); return 0; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ceba1a83cacc..96f606deee31 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -57,9 +57,9 @@ kmem_zone_t *xfs_inode_zone; */ #define XFS_ITRUNC_MAX_EXTENTS 2 -STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *); - -STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *); +STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *); +STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *); +STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *); /* * helper function to extract extent size hint from inode @@ -766,6 +766,7 @@ xfs_ialloc( uint flags; int error; struct timespec tv; + struct inode *inode; /* * Call the space management code to pick @@ -791,6 +792,7 @@ xfs_ialloc( if (error) return error; ASSERT(ip != NULL); + inode = VFS_I(ip); /* * We always convert v1 inodes to v2 now - we only support filesystems @@ -800,20 +802,16 @@ xfs_ialloc( if (ip->i_d.di_version == 1) ip->i_d.di_version = 2; - ip->i_d.di_mode = mode; - ip->i_d.di_onlink = 0; - ip->i_d.di_nlink = nlink; - ASSERT(ip->i_d.di_nlink == nlink); + inode->i_mode = mode; + set_nlink(inode, nlink); ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid()); ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid()); xfs_set_projid(ip, prid); - memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); if (pip && XFS_INHERIT_GID(pip)) { ip->i_d.di_gid = pip->i_d.di_gid; - if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) { - ip->i_d.di_mode |= S_ISGID; - } + if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) + inode->i_mode |= S_ISGID; } /* @@ -822,38 +820,29 @@ xfs_ialloc( * (and only if the irix_sgid_inherit compatibility variable is set). */ if ((irix_sgid_inherit) && - (ip->i_d.di_mode & S_ISGID) && - (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) { - ip->i_d.di_mode &= ~S_ISGID; - } + (inode->i_mode & S_ISGID) && + (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) + inode->i_mode &= ~S_ISGID; ip->i_d.di_size = 0; ip->i_d.di_nextents = 0; ASSERT(ip->i_d.di_nblocks == 0); tv = current_fs_time(mp->m_super); - ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec; - ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec; - ip->i_d.di_atime = ip->i_d.di_mtime; - ip->i_d.di_ctime = ip->i_d.di_mtime; + inode->i_mtime = tv; + inode->i_atime = tv; + inode->i_ctime = tv; - /* - * di_gen will have been taken care of in xfs_iread. - */ ip->i_d.di_extsize = 0; ip->i_d.di_dmevmask = 0; ip->i_d.di_dmstate = 0; ip->i_d.di_flags = 0; 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_meta_uuid)); - ip->i_d.di_crc = 0; - ip->i_d.di_changecount = 1; - ip->i_d.di_lsn = 0; + inode->i_version = 1; 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; + ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec; + ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec; } @@ -1092,35 +1081,24 @@ xfs_dir_ialloc( } /* - * Decrement the link count on an inode & log the change. - * If this causes the link count to go to zero, initiate the - * logging activity required to truncate a file. + * Decrement the link count on an inode & log the change. If this causes the + * link count to go to zero, move the inode to AGI unlinked list so that it can + * be freed when the last active reference goes away via xfs_inactive(). */ int /* error */ xfs_droplink( xfs_trans_t *tp, xfs_inode_t *ip) { - int error; - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); - ASSERT (ip->i_d.di_nlink > 0); - ip->i_d.di_nlink--; drop_nlink(VFS_I(ip)); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - error = 0; - if (ip->i_d.di_nlink == 0) { - /* - * We're dropping the last link to this file. - * Move the on-disk inode to the AGI unlinked list. - * From xfs_inactive() we will pull the inode from - * the list and free it. - */ - error = xfs_iunlink(tp, ip); - } - return error; + if (VFS_I(ip)->i_nlink) + return 0; + + return xfs_iunlink(tp, ip); } /* @@ -1134,8 +1112,6 @@ xfs_bumplink( xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); ASSERT(ip->i_d.di_version > 1); - ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE)); - ip->i_d.di_nlink++; inc_nlink(VFS_I(ip)); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); return 0; @@ -1393,7 +1369,6 @@ xfs_create_tmpfile( */ xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); - ip->i_d.di_nlink--; error = xfs_iunlink(tp, ip); if (error) goto out_trans_cancel; @@ -1444,7 +1419,7 @@ xfs_link( trace_xfs_link(tdp, target_name); - ASSERT(!S_ISDIR(sip->i_d.di_mode)); + ASSERT(!S_ISDIR(VFS_I(sip)->i_mode)); if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; @@ -1492,7 +1467,10 @@ xfs_link( xfs_bmap_init(&free_list, &first_block); - if (sip->i_d.di_nlink == 0) { + /* + * Handle initial link state of O_TMPFILE inode + */ + if (VFS_I(sip)->i_nlink == 0) { error = xfs_iunlink_remove(tp, sip); if (error) goto error_return; @@ -1648,7 +1626,7 @@ xfs_release( xfs_mount_t *mp = ip->i_mount; int error; - if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0)) + if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0)) return 0; /* If this is a read-only mount, don't do this (would generate I/O) */ @@ -1679,7 +1657,7 @@ xfs_release( } } - if (ip->i_d.di_nlink == 0) + if (VFS_I(ip)->i_nlink == 0) return 0; if (xfs_can_free_eofblocks(ip, false)) { @@ -1883,7 +1861,7 @@ xfs_inactive( * If the inode is already free, then there can be nothing * to clean up here. */ - if (ip->i_d.di_mode == 0) { + if (VFS_I(ip)->i_mode == 0) { ASSERT(ip->i_df.if_real_bytes == 0); ASSERT(ip->i_df.if_broot_bytes == 0); return; @@ -1895,7 +1873,7 @@ xfs_inactive( if (mp->m_flags & XFS_MOUNT_RDONLY) return; - if (ip->i_d.di_nlink != 0) { + if (VFS_I(ip)->i_nlink != 0) { /* * force is true because we are evicting an inode from the * cache. Post-eof blocks must be freed, lest we end up with @@ -1907,7 +1885,7 @@ xfs_inactive( return; } - if (S_ISREG(ip->i_d.di_mode) && + if (S_ISREG(VFS_I(ip)->i_mode) && (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 || ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0)) truncate = 1; @@ -1916,7 +1894,7 @@ xfs_inactive( if (error) return; - if (S_ISLNK(ip->i_d.di_mode)) + if (S_ISLNK(VFS_I(ip)->i_mode)) error = xfs_inactive_symlink(ip); else if (truncate) error = xfs_inactive_truncate(ip); @@ -1952,16 +1930,21 @@ xfs_inactive( } /* - * This is called when the inode's link count goes to 0. - * We place the on-disk inode on a list in the AGI. It - * will be pulled from this list when the inode is freed. + * This is called when the inode's link count goes to 0 or we are creating a + * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be + * set to true as the link count is dropped to zero by the VFS after we've + * created the file successfully, so we have to add it to the unlinked list + * while the link count is non-zero. + * + * We place the on-disk inode on a list in the AGI. It will be pulled from this + * list when the inode is freed. */ -int +STATIC int xfs_iunlink( - xfs_trans_t *tp, - xfs_inode_t *ip) + struct xfs_trans *tp, + struct xfs_inode *ip) { - xfs_mount_t *mp; + xfs_mount_t *mp = tp->t_mountp; xfs_agi_t *agi; xfs_dinode_t *dip; xfs_buf_t *agibp; @@ -1971,10 +1954,7 @@ xfs_iunlink( int offset; int error; - ASSERT(ip->i_d.di_nlink == 0); - ASSERT(ip->i_d.di_mode != 0); - - mp = tp->t_mountp; + ASSERT(VFS_I(ip)->i_mode != 0); /* * Get the agi buffer first. It ensures lock ordering @@ -2412,10 +2392,10 @@ xfs_ifree( struct xfs_icluster xic = { 0 }; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(ip->i_d.di_nlink == 0); + ASSERT(VFS_I(ip)->i_nlink == 0); ASSERT(ip->i_d.di_nextents == 0); ASSERT(ip->i_d.di_anextents == 0); - ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode)); + ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode)); ASSERT(ip->i_d.di_nblocks == 0); /* @@ -2429,7 +2409,7 @@ xfs_ifree( if (error) return error; - ip->i_d.di_mode = 0; /* mark incore inode as free */ + VFS_I(ip)->i_mode = 0; /* mark incore inode as free */ ip->i_d.di_flags = 0; ip->i_d.di_dmevmask = 0; ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */ @@ -2439,7 +2419,7 @@ xfs_ifree( * Bump the generation count so no one will be confused * by reincarnations of this inode. */ - ip->i_d.di_gen++; + VFS_I(ip)->i_generation++; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); if (xic.deleted) @@ -2526,7 +2506,7 @@ xfs_remove( { xfs_mount_t *mp = dp->i_mount; xfs_trans_t *tp = NULL; - int is_dir = S_ISDIR(ip->i_d.di_mode); + int is_dir = S_ISDIR(VFS_I(ip)->i_mode); int error = 0; xfs_bmap_free_t free_list; xfs_fsblock_t first_block; @@ -2580,8 +2560,8 @@ xfs_remove( * If we're removing a directory perform some additional validation. */ if (is_dir) { - ASSERT(ip->i_d.di_nlink >= 2); - if (ip->i_d.di_nlink != 2) { + ASSERT(VFS_I(ip)->i_nlink >= 2); + if (VFS_I(ip)->i_nlink != 2) { error = -ENOTEMPTY; goto out_trans_cancel; } @@ -2771,7 +2751,7 @@ xfs_cross_rename( if (dp1 != dp2) { dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; - if (S_ISDIR(ip2->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip2)->i_mode)) { error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot, dp1->i_ino, first_block, free_list, spaceres); @@ -2779,7 +2759,7 @@ xfs_cross_rename( goto out_trans_abort; /* transfer ip2 ".." reference to dp1 */ - if (!S_ISDIR(ip1->i_d.di_mode)) { + if (!S_ISDIR(VFS_I(ip1)->i_mode)) { error = xfs_droplink(tp, dp2); if (error) goto out_trans_abort; @@ -2798,7 +2778,7 @@ xfs_cross_rename( ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; } - if (S_ISDIR(ip1->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip1)->i_mode)) { error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot, dp2->i_ino, first_block, free_list, spaceres); @@ -2806,7 +2786,7 @@ xfs_cross_rename( goto out_trans_abort; /* transfer ip1 ".." reference to dp2 */ - if (!S_ISDIR(ip2->i_d.di_mode)) { + if (!S_ISDIR(VFS_I(ip2)->i_mode)) { error = xfs_droplink(tp, dp1); if (error) goto out_trans_abort; @@ -2903,7 +2883,7 @@ xfs_rename( struct xfs_inode *inodes[__XFS_SORT_INODES]; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); - bool src_is_directory = S_ISDIR(src_ip->i_d.di_mode); + bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); int spaceres; int error; @@ -3032,12 +3012,12 @@ xfs_rename( * target and source are directories and that target can be * destroyed, or that neither is a directory. */ - if (S_ISDIR(target_ip->i_d.di_mode)) { + if (S_ISDIR(VFS_I(target_ip)->i_mode)) { /* * Make sure target dir is empty. */ if (!(xfs_dir_isempty(target_ip)) || - (target_ip->i_d.di_nlink > 2)) { + (VFS_I(target_ip)->i_nlink > 2)) { error = -EEXIST; goto out_trans_cancel; } @@ -3144,7 +3124,7 @@ xfs_rename( * intermediate state on disk. */ if (wip) { - ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0); + ASSERT(VFS_I(wip)->i_nlink == 0); error = xfs_bumplink(tp, wip); if (error) goto out_bmap_cancel; @@ -3313,7 +3293,7 @@ cluster_corrupt_out: * mark it as stale and brelse. */ if (bp->b_iodone) { - XFS_BUF_UNDONE(bp); + bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); xfs_buf_ioerror(bp, -EIO); xfs_buf_ioend(bp); @@ -3462,14 +3442,7 @@ xfs_iflush_int( __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto corrupt_out; } - if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC, - mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: Bad inode %Lu, ptr 0x%p, magic number 0x%x", - __func__, ip->i_ino, ip, ip->i_d.di_magic); - goto corrupt_out; - } - if (S_ISREG(ip->i_d.di_mode)) { + if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && (ip->i_d.di_format != XFS_DINODE_FMT_BTREE), @@ -3479,7 +3452,7 @@ xfs_iflush_int( __func__, ip->i_ino, ip); goto corrupt_out; } - } else if (S_ISDIR(ip->i_d.di_mode)) { + } else if (S_ISDIR(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) && @@ -3523,12 +3496,11 @@ xfs_iflush_int( ip->i_d.di_flushiter++; /* - * Copy the dirty parts of the inode into the on-disk - * inode. We always copy out the core of the inode, - * because if the inode is dirty at all the core must - * be. + * Copy the dirty parts of the inode into the on-disk inode. We always + * copy out the core of the inode, because if the inode is dirty at all + * the core must be. */ - xfs_dinode_to_disk(dip, &ip->i_d); + xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn); /* Wrap, we never let the log put out DI_MAX_FLUSH */ if (ip->i_d.di_flushiter == DI_MAX_FLUSH) @@ -3580,10 +3552,6 @@ xfs_iflush_int( */ xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item); - /* 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); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index ca9e11989cbd..43e1d51b15eb 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -63,7 +63,7 @@ typedef struct xfs_inode { unsigned long i_flags; /* see defined flags below */ unsigned int i_delayed_blks; /* count of delay alloc blks */ - xfs_icdinode_t i_d; /* most of ondisk inode */ + struct xfs_icdinode i_d; /* most of ondisk inode */ /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ @@ -88,7 +88,7 @@ static inline struct inode *VFS_I(struct xfs_inode *ip) */ static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip) { - if (S_ISREG(ip->i_d.di_mode)) + if (S_ISREG(VFS_I(ip)->i_mode)) return i_size_read(VFS_I(ip)); return ip->i_d.di_size; } @@ -369,7 +369,7 @@ static inline int xfs_isiflocked(struct xfs_inode *ip) */ #define XFS_INHERIT_GID(pip) \ (((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \ - ((pip)->i_d.di_mode & S_ISGID)) + (VFS_I(pip)->i_mode & S_ISGID)) int xfs_release(struct xfs_inode *ip); void xfs_inactive(struct xfs_inode *ip); @@ -405,8 +405,6 @@ int xfs_ifree(struct xfs_trans *, xfs_inode_t *, struct xfs_bmap_free *); int xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t); -int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); - void xfs_iext_realloc(xfs_inode_t *, int, int); void xfs_iunpin_wait(xfs_inode_t *); @@ -437,6 +435,8 @@ int xfs_update_prealloc_flags(struct xfs_inode *ip, int xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset, xfs_fsize_t isize, bool *did_zeroing); int xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count); +loff_t __xfs_seek_hole_data(struct inode *inode, loff_t start, + loff_t eof, int whence); /* from xfs_iops.c */ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index d14b12b8cfef..c48b5b18d771 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -135,7 +135,7 @@ xfs_inode_item_size( *nvecs += 2; *nbytes += sizeof(struct xfs_inode_log_format) + - xfs_icdinode_size(ip->i_d.di_version); + xfs_log_dinode_size(ip->i_d.di_version); xfs_inode_item_data_fork_size(iip, nvecs, nbytes); if (XFS_IFORK_Q(ip)) @@ -322,6 +322,81 @@ xfs_inode_item_format_attr_fork( } } +static void +xfs_inode_to_log_dinode( + struct xfs_inode *ip, + struct xfs_log_dinode *to, + xfs_lsn_t lsn) +{ + struct xfs_icdinode *from = &ip->i_d; + struct inode *inode = VFS_I(ip); + + to->di_magic = XFS_DINODE_MAGIC; + + to->di_version = from->di_version; + to->di_format = from->di_format; + to->di_uid = from->di_uid; + to->di_gid = from->di_gid; + to->di_projid_lo = from->di_projid_lo; + to->di_projid_hi = from->di_projid_hi; + + memset(to->di_pad, 0, sizeof(to->di_pad)); + memset(to->di_pad3, 0, sizeof(to->di_pad3)); + to->di_atime.t_sec = inode->i_atime.tv_sec; + to->di_atime.t_nsec = inode->i_atime.tv_nsec; + to->di_mtime.t_sec = inode->i_mtime.tv_sec; + to->di_mtime.t_nsec = inode->i_mtime.tv_nsec; + to->di_ctime.t_sec = inode->i_ctime.tv_sec; + to->di_ctime.t_nsec = inode->i_ctime.tv_nsec; + to->di_nlink = inode->i_nlink; + to->di_gen = inode->i_generation; + to->di_mode = inode->i_mode; + + to->di_size = from->di_size; + to->di_nblocks = from->di_nblocks; + to->di_extsize = from->di_extsize; + to->di_nextents = from->di_nextents; + to->di_anextents = from->di_anextents; + to->di_forkoff = from->di_forkoff; + to->di_aformat = from->di_aformat; + to->di_dmevmask = from->di_dmevmask; + to->di_dmstate = from->di_dmstate; + to->di_flags = from->di_flags; + + if (from->di_version == 3) { + to->di_changecount = inode->i_version; + to->di_crtime.t_sec = from->di_crtime.t_sec; + to->di_crtime.t_nsec = from->di_crtime.t_nsec; + to->di_flags2 = from->di_flags2; + + to->di_ino = ip->i_ino; + to->di_lsn = lsn; + memset(to->di_pad2, 0, sizeof(to->di_pad2)); + uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid); + to->di_flushiter = 0; + } else { + to->di_flushiter = from->di_flushiter; + } +} + +/* + * Format the inode core. Current timestamp data is only in the VFS inode + * fields, so we need to grab them from there. Hence rather than just copying + * the XFS inode core structure, format the fields directly into the iovec. + */ +static void +xfs_inode_item_format_core( + struct xfs_inode *ip, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) +{ + struct xfs_log_dinode *dic; + + dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE); + xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn); + xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_d.di_version)); +} + /* * This is called to fill in the vector of log iovecs for the given inode * log item. It fills the first item with an inode log format structure, @@ -351,10 +426,7 @@ xfs_inode_item_format( ilf->ilf_size = 2; /* format + core */ xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); - xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE, - &ip->i_d, - xfs_icdinode_size(ip->i_d.di_version)); - + xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); if (XFS_IFORK_Q(ip)) { xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 478d04e07f95..81d6d6218803 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -114,7 +114,7 @@ xfs_find_handle( handle.ha_fid.fid_len = sizeof(xfs_fid_t) - sizeof(handle.ha_fid.fid_len); handle.ha_fid.fid_pad = 0; - handle.ha_fid.fid_gen = ip->i_d.di_gen; + handle.ha_fid.fid_gen = inode->i_generation; handle.ha_fid.fid_ino = ip->i_ino; hsize = XFS_HSIZE(handle); @@ -963,7 +963,7 @@ xfs_set_diflags( di_flags |= XFS_DIFLAG_NODEFRAG; if (xflags & FS_XFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; - if (S_ISDIR(ip->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip)->i_mode)) { if (xflags & FS_XFLAG_RTINHERIT) di_flags |= XFS_DIFLAG_RTINHERIT; if (xflags & FS_XFLAG_NOSYMLINKS) @@ -972,7 +972,7 @@ xfs_set_diflags( di_flags |= XFS_DIFLAG_EXTSZINHERIT; if (xflags & FS_XFLAG_PROJINHERIT) di_flags |= XFS_DIFLAG_PROJINHERIT; - } else if (S_ISREG(ip->i_d.di_mode)) { + } else if (S_ISREG(VFS_I(ip)->i_mode)) { if (xflags & FS_XFLAG_REALTIME) di_flags |= XFS_DIFLAG_REALTIME; if (xflags & FS_XFLAG_EXTSIZE) @@ -1128,14 +1128,14 @@ xfs_ioctl_setattr_check_extsize( { struct xfs_mount *mp = ip->i_mount; - if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode)) + if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && - !S_ISDIR(ip->i_d.di_mode)) + !S_ISDIR(VFS_I(ip)->i_mode)) return -EINVAL; - if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents && + if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents && ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) return -EINVAL; @@ -1256,9 +1256,9 @@ xfs_ioctl_setattr( * successful return from chown() */ - if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && + if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) && !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) - ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); + VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ if (xfs_get_projid(ip) != fa->fsx_projid) { diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 76b71a1c6c32..0d38b1d2c420 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -459,8 +459,8 @@ xfs_vn_getattr( stat->size = XFS_ISIZE(ip); stat->dev = inode->i_sb->s_dev; - stat->mode = ip->i_d.di_mode; - stat->nlink = ip->i_d.di_nlink; + stat->mode = inode->i_mode; + stat->nlink = inode->i_nlink; stat->uid = inode->i_uid; stat->gid = inode->i_gid; stat->ino = ip->i_ino; @@ -506,9 +506,6 @@ xfs_setattr_mode( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ip->i_d.di_mode &= S_IFMT; - ip->i_d.di_mode |= mode & ~S_IFMT; - inode->i_mode &= S_IFMT; inode->i_mode |= mode & ~S_IFMT; } @@ -522,21 +519,12 @@ xfs_setattr_time( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - if (iattr->ia_valid & ATTR_ATIME) { + if (iattr->ia_valid & ATTR_ATIME) inode->i_atime = iattr->ia_atime; - ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; - ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; - } - if (iattr->ia_valid & ATTR_CTIME) { + if (iattr->ia_valid & ATTR_CTIME) inode->i_ctime = iattr->ia_ctime; - ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; - ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; - } - if (iattr->ia_valid & ATTR_MTIME) { + if (iattr->ia_valid & ATTR_MTIME) inode->i_mtime = iattr->ia_mtime; - ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; - ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; - } } int @@ -661,9 +649,9 @@ xfs_setattr_nonsize( * The set-user-ID and set-group-ID bits of a file will be * cleared upon successful return from chown() */ - if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && + if ((inode->i_mode & (S_ISUID|S_ISGID)) && !capable(CAP_FSETID)) - ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); + inode->i_mode &= ~(S_ISUID|S_ISGID); /* * Change the ownerships and register quota modifications @@ -773,7 +761,7 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); - ASSERT(S_ISREG(ip->i_d.di_mode)); + ASSERT(S_ISREG(inode->i_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); @@ -991,21 +979,13 @@ xfs_vn_update_time( } xfs_ilock(ip, XFS_ILOCK_EXCL); - if (flags & S_CTIME) { + if (flags & S_CTIME) inode->i_ctime = *now; - ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec; - ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec; - } - if (flags & S_MTIME) { + if (flags & S_MTIME) inode->i_mtime = *now; - ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec; - ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec; - } - if (flags & S_ATIME) { + if (flags & S_ATIME) inode->i_atime = *now; - ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec; - ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec; - } + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP); return xfs_trans_commit(tp); @@ -1232,8 +1212,6 @@ xfs_setup_inode( /* make the inode look hashed for the writeback code */ hlist_add_fake(&inode->i_hash); - inode->i_mode = ip->i_d.di_mode; - set_nlink(inode, ip->i_d.di_nlink); inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid); inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid); @@ -1249,14 +1227,7 @@ xfs_setup_inode( break; } - inode->i_generation = ip->i_d.di_gen; i_size_write(inode, ip->i_d.di_size); - inode->i_atime.tv_sec = ip->i_d.di_atime.t_sec; - inode->i_atime.tv_nsec = ip->i_d.di_atime.t_nsec; - inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec; - inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec; - inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec; - inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec; xfs_diflags_to_iflags(inode, ip); ip->d_ops = ip->i_mount->m_nondir_inode_ops; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 930ebd86beba..ce73eb34620d 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -57,6 +57,7 @@ xfs_bulkstat_one_int( { struct xfs_icdinode *dic; /* dinode core info pointer */ struct xfs_inode *ip; /* incore inode pointer */ + struct inode *inode; struct xfs_bstat *buf; /* return buffer */ int error = 0; /* error value */ @@ -77,30 +78,33 @@ xfs_bulkstat_one_int( ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); + inode = VFS_I(ip); dic = &ip->i_d; /* xfs_iget returns the following without needing * further change. */ - buf->bs_nlink = dic->di_nlink; buf->bs_projid_lo = dic->di_projid_lo; buf->bs_projid_hi = dic->di_projid_hi; buf->bs_ino = ino; - buf->bs_mode = dic->di_mode; buf->bs_uid = dic->di_uid; buf->bs_gid = dic->di_gid; buf->bs_size = dic->di_size; - buf->bs_atime.tv_sec = dic->di_atime.t_sec; - buf->bs_atime.tv_nsec = dic->di_atime.t_nsec; - buf->bs_mtime.tv_sec = dic->di_mtime.t_sec; - buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec; - buf->bs_ctime.tv_sec = dic->di_ctime.t_sec; - buf->bs_ctime.tv_nsec = dic->di_ctime.t_nsec; + + buf->bs_nlink = inode->i_nlink; + buf->bs_atime.tv_sec = inode->i_atime.tv_sec; + buf->bs_atime.tv_nsec = inode->i_atime.tv_nsec; + buf->bs_mtime.tv_sec = inode->i_mtime.tv_sec; + buf->bs_mtime.tv_nsec = inode->i_mtime.tv_nsec; + buf->bs_ctime.tv_sec = inode->i_ctime.tv_sec; + buf->bs_ctime.tv_nsec = inode->i_ctime.tv_nsec; + buf->bs_gen = inode->i_generation; + buf->bs_mode = inode->i_mode; + buf->bs_xflags = xfs_ip2xflags(ip); buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog; buf->bs_extents = dic->di_nextents; - buf->bs_gen = dic->di_gen; memset(buf->bs_pad, 0, sizeof(buf->bs_pad)); buf->bs_dmevmask = dic->di_dmevmask; buf->bs_dmstate = dic->di_dmstate; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 9c9a1c9bcc7f..40b700d3f426 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1212,7 +1212,7 @@ xlog_iodone(xfs_buf_t *bp) } /* log I/O is always issued ASYNC */ - ASSERT(XFS_BUF_ISASYNC(bp)); + ASSERT(bp->b_flags & XBF_ASYNC); xlog_state_done_syncing(iclog, aborted); /* @@ -1864,9 +1864,8 @@ xlog_sync( bp->b_io_length = BTOBB(count); bp->b_fspriv = iclog; - XFS_BUF_ZEROFLAGS(bp); - XFS_BUF_ASYNC(bp); - bp->b_flags |= XBF_SYNCIO; + bp->b_flags &= ~(XBF_FUA | XBF_FLUSH); + bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE); if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) { bp->b_flags |= XBF_FUA; @@ -1893,12 +1892,11 @@ xlog_sync( /* account for log which doesn't start at block #0 */ XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart); + /* * Don't call xfs_bwrite here. We do log-syncs even when the filesystem * is shutting down. */ - XFS_BUF_WRITE(bp); - error = xlog_bdstrat(bp); if (error) { xfs_buf_ioerror_alert(bp, "xlog_sync"); @@ -1910,9 +1908,8 @@ xlog_sync( xfs_buf_associate_memory(bp, (char *)&iclog->ic_header + count, split); bp->b_fspriv = iclog; - XFS_BUF_ZEROFLAGS(bp); - XFS_BUF_ASYNC(bp); - bp->b_flags |= XBF_SYNCIO; + bp->b_flags &= ~(XBF_FUA | XBF_FLUSH); + bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE); if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) bp->b_flags |= XBF_FUA; @@ -1921,7 +1918,6 @@ xlog_sync( /* account for internal log which doesn't start at block #0 */ XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart); - XFS_BUF_WRITE(bp); error = xlog_bdstrat(bp); if (error) { xfs_buf_ioerror_alert(bp, "xlog_sync (split)"); @@ -3979,7 +3975,7 @@ xfs_log_force_umount( log->l_flags & XLOG_ACTIVE_RECOVERY) { mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN; if (mp->m_sb_bp) - XFS_BUF_DONE(mp->m_sb_bp); + mp->m_sb_bp->b_flags |= XBF_DONE; return 0; } @@ -4009,7 +4005,7 @@ xfs_log_force_umount( spin_lock(&log->l_icloglock); mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN; if (mp->m_sb_bp) - XFS_BUF_DONE(mp->m_sb_bp); + mp->m_sb_bp->b_flags |= XBF_DONE; /* * Mark the log and the iclogs with IO error flags to prevent any diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index da37beb76f6e..9347bf1bdc00 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -190,7 +190,7 @@ xlog_bread_noalign( ASSERT(nbblks <= bp->b_length); XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); - XFS_BUF_READ(bp); + bp->b_flags |= XBF_READ; bp->b_io_length = nbblks; bp->b_error = 0; @@ -275,7 +275,6 @@ xlog_bwrite( ASSERT(nbblks <= bp->b_length); XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); - XFS_BUF_ZEROFLAGS(bp); xfs_buf_hold(bp); xfs_buf_lock(bp); bp->b_io_length = nbblks; @@ -1109,27 +1108,10 @@ xlog_verify_head( bool tmp_wrapped; /* - * Search backwards through the log looking for the log record header - * block. This wraps all the way back around to the head so something is - * seriously wrong if we can't find it. - */ - found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk, - rhead, wrapped); - if (found < 0) - return found; - if (!found) { - xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); - return -EIO; - } - - *tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn)); - - /* - * Now that we have a tail block, check the head of the log for torn - * writes. Search again until we hit the tail or the maximum number of - * log record I/Os that could have been in flight at one time. Use a - * temporary buffer so we don't trash the rhead/bp pointer from the - * call above. + * Check the head of the log for torn writes. Search backwards from the + * head until we hit the tail or the maximum number of log record I/Os + * that could have been in flight at one time. Use a temporary buffer so + * we don't trash the rhead/bp pointers from the caller. */ tmp_bp = xlog_get_bp(log, 1); if (!tmp_bp) @@ -1216,6 +1198,115 @@ xlog_verify_head( } /* + * Check whether the head of the log points to an unmount record. In other + * words, determine whether the log is clean. If so, update the in-core state + * appropriately. + */ +static int +xlog_check_unmount_rec( + struct xlog *log, + xfs_daddr_t *head_blk, + xfs_daddr_t *tail_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + struct xfs_buf *bp, + bool *clean) +{ + struct xlog_op_header *op_head; + xfs_daddr_t umount_data_blk; + xfs_daddr_t after_umount_blk; + int hblks; + int error; + char *offset; + + *clean = false; + + /* + * Look for unmount record. If we find it, then we know there was a + * clean unmount. Since 'i' could be the last block in the physical + * log, we convert to a log block before comparing to the head_blk. + * + * Save the current tail lsn to use to pass to xlog_clear_stale_blocks() + * below. We won't want to clear the unmount record if there is one, so + * we pass the lsn of the unmount record rather than the block after it. + */ + if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { + int h_size = be32_to_cpu(rhead->h_size); + int h_version = be32_to_cpu(rhead->h_version); + + if ((h_version & XLOG_VERSION_2) && + (h_size > XLOG_HEADER_CYCLE_SIZE)) { + hblks = h_size / XLOG_HEADER_CYCLE_SIZE; + if (h_size % XLOG_HEADER_CYCLE_SIZE) + hblks++; + } else { + hblks = 1; + } + } else { + hblks = 1; + } + after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); + after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); + if (*head_blk == after_umount_blk && + be32_to_cpu(rhead->h_num_logops) == 1) { + umount_data_blk = rhead_blk + hblks; + umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); + error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + if (error) + return error; + + op_head = (struct xlog_op_header *)offset; + if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { + /* + * Set tail and last sync so that newly written log + * records will point recovery to after the current + * unmount record. + */ + xlog_assign_atomic_lsn(&log->l_tail_lsn, + log->l_curr_cycle, after_umount_blk); + xlog_assign_atomic_lsn(&log->l_last_sync_lsn, + log->l_curr_cycle, after_umount_blk); + *tail_blk = after_umount_blk; + + *clean = true; + } + } + + return 0; +} + +static void +xlog_set_state( + struct xlog *log, + xfs_daddr_t head_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + bool bump_cycle) +{ + /* + * Reset log values according to the state of the log when we + * crashed. In the case where head_blk == 0, we bump curr_cycle + * one because the next write starts a new cycle rather than + * continuing the cycle of the last good log record. At this + * point we have guaranteed that all partial log records have been + * accounted for. Therefore, we know that the last good log record + * written was complete and ended exactly on the end boundary + * of the physical log. + */ + log->l_prev_block = rhead_blk; + log->l_curr_block = (int)head_blk; + log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); + if (bump_cycle) + log->l_curr_cycle++; + atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); + atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); + xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); + xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); +} + +/* * Find the sync block number or the tail of the log. * * This will be the block number of the last record to have its @@ -1238,22 +1329,20 @@ xlog_find_tail( xfs_daddr_t *tail_blk) { xlog_rec_header_t *rhead; - xlog_op_header_t *op_head; char *offset = NULL; xfs_buf_t *bp; int error; - xfs_daddr_t umount_data_blk; - xfs_daddr_t after_umount_blk; xfs_daddr_t rhead_blk; xfs_lsn_t tail_lsn; - int hblks; bool wrapped = false; + bool clean = false; /* * Find previous log record */ if ((error = xlog_find_head(log, head_blk))) return error; + ASSERT(*head_blk < INT_MAX); bp = xlog_get_bp(log, 1); if (!bp) @@ -1271,100 +1360,75 @@ xlog_find_tail( } /* - * Trim the head block back to skip over torn records. We can have - * multiple log I/Os in flight at any time, so we assume CRC failures - * back through the previous several records are torn writes and skip - * them. + * Search backwards through the log looking for the log record header + * block. This wraps all the way back around to the head so something is + * seriously wrong if we can't find it. */ - ASSERT(*head_blk < INT_MAX); - error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk, - &rhead, &wrapped); - if (error) - goto done; + error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, + &rhead_blk, &rhead, &wrapped); + if (error < 0) + return error; + if (!error) { + xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); + return -EIO; + } + *tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn)); /* - * Reset log values according to the state of the log when we - * crashed. In the case where head_blk == 0, we bump curr_cycle - * one because the next write starts a new cycle rather than - * continuing the cycle of the last good log record. At this - * point we have guaranteed that all partial log records have been - * accounted for. Therefore, we know that the last good log record - * written was complete and ended exactly on the end boundary - * of the physical log. + * Set the log state based on the current head record. */ - log->l_prev_block = rhead_blk; - log->l_curr_block = (int)*head_blk; - log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); - if (wrapped) - log->l_curr_cycle++; - atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); - atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); - xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); - xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); + xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); /* - * Look for unmount record. If we find it, then we know there - * was a clean unmount. Since 'i' could be the last block in - * the physical log, we convert to a log block before comparing - * to the head_blk. + * Look for an unmount record at the head of the log. This sets the log + * state to determine whether recovery is necessary. + */ + error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead, + rhead_blk, bp, &clean); + if (error) + goto done; + + /* + * Verify the log head if the log is not clean (e.g., we have anything + * but an unmount record at the head). This uses CRC verification to + * detect and trim torn writes. If discovered, CRC failures are + * considered torn writes and the log head is trimmed accordingly. * - * Save the current tail lsn to use to pass to - * xlog_clear_stale_blocks() below. We won't want to clear the - * unmount record if there is one, so we pass the lsn of the - * unmount record rather than the block after it. + * Note that we can only run CRC verification when the log is dirty + * because there's no guarantee that the log data behind an unmount + * record is compatible with the current architecture. */ - if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { - int h_size = be32_to_cpu(rhead->h_size); - int h_version = be32_to_cpu(rhead->h_version); + if (!clean) { + xfs_daddr_t orig_head = *head_blk; - if ((h_version & XLOG_VERSION_2) && - (h_size > XLOG_HEADER_CYCLE_SIZE)) { - hblks = h_size / XLOG_HEADER_CYCLE_SIZE; - if (h_size % XLOG_HEADER_CYCLE_SIZE) - hblks++; - } else { - hblks = 1; - } - } else { - hblks = 1; - } - after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); - after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); - tail_lsn = atomic64_read(&log->l_tail_lsn); - if (*head_blk == after_umount_blk && - be32_to_cpu(rhead->h_num_logops) == 1) { - umount_data_blk = rhead_blk + hblks; - umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); - error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + error = xlog_verify_head(log, head_blk, tail_blk, bp, + &rhead_blk, &rhead, &wrapped); if (error) goto done; - op_head = (xlog_op_header_t *)offset; - if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { - /* - * Set tail and last sync so that newly written - * log records will point recovery to after the - * current unmount record. - */ - xlog_assign_atomic_lsn(&log->l_tail_lsn, - log->l_curr_cycle, after_umount_blk); - xlog_assign_atomic_lsn(&log->l_last_sync_lsn, - log->l_curr_cycle, after_umount_blk); - *tail_blk = after_umount_blk; - - /* - * Note that the unmount was clean. If the unmount - * was not clean, we need to know this to rebuild the - * superblock counters from the perag headers if we - * have a filesystem using non-persistent counters. - */ - log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + /* update in-core state again if the head changed */ + if (*head_blk != orig_head) { + xlog_set_state(log, *head_blk, rhead, rhead_blk, + wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); + error = xlog_check_unmount_rec(log, head_blk, tail_blk, + rhead, rhead_blk, bp, + &clean); + if (error) + goto done; } } /* + * Note that the unmount was clean. If the unmount was not clean, we + * need to know this to rebuild the superblock counters from the perag + * headers if we have a filesystem using non-persistent counters. + */ + if (clean) + log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + + /* * Make sure that there are no blocks in front of the head * with the same cycle number as the head. This can happen * because we allow multiple outstanding log writes concurrently, @@ -2473,6 +2537,13 @@ xlog_recover_validate_buf_type( } bp->b_ops = &xfs_sb_buf_ops; break; +#ifdef CONFIG_XFS_RT + case XFS_BLFT_RTBITMAP_BUF: + case XFS_BLFT_RTSUMMARY_BUF: + /* no magic numbers for verification of RT buffers */ + bp->b_ops = &xfs_rtbuf_ops; + break; +#endif /* CONFIG_XFS_RT */ default: xfs_warn(mp, "Unknown buffer type %d!", xfs_blft_from_flags(buf_f)); @@ -2793,7 +2864,7 @@ xfs_recover_inode_owner_change( return -ENOMEM; /* instantiate the inode */ - xfs_dinode_from_disk(&ip->i_d, dip); + xfs_inode_from_disk(ip, dip); ASSERT(ip->i_d.di_version >= 3); error = xfs_iformat_fork(ip, dip); @@ -2839,7 +2910,7 @@ xlog_recover_inode_pass2( int error; int attr_index; uint fields; - xfs_icdinode_t *dicp; + struct xfs_log_dinode *ldip; uint isize; int need_free = 0; @@ -2892,8 +2963,8 @@ xlog_recover_inode_pass2( error = -EFSCORRUPTED; goto out_release; } - dicp = item->ri_buf[1].i_addr; - if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) { + ldip = item->ri_buf[1].i_addr; + if (unlikely(ldip->di_magic != XFS_DINODE_MAGIC)) { xfs_alert(mp, "%s: Bad inode log record, rec ptr 0x%p, ino %Ld", __func__, item, in_f->ilf_ino); @@ -2929,13 +3000,13 @@ xlog_recover_inode_pass2( * to skip replay when the on disk inode is newer than the log one */ if (!xfs_sb_version_hascrc(&mp->m_sb) && - dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) { + ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { /* * Deal with the wrap case, DI_MAX_FLUSH is less * than smaller numbers */ if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && - dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) { + ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { /* do nothing */ } else { trace_xfs_log_recover_inode_skip(log, in_f); @@ -2945,13 +3016,13 @@ xlog_recover_inode_pass2( } /* Take the opportunity to reset the flush iteration count */ - dicp->di_flushiter = 0; + ldip->di_flushiter = 0; - if (unlikely(S_ISREG(dicp->di_mode))) { - if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) && - (dicp->di_format != XFS_DINODE_FMT_BTREE)) { + if (unlikely(S_ISREG(ldip->di_mode))) { + if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && + (ldip->di_format != XFS_DINODE_FMT_BTREE)) { XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)", - XFS_ERRLEVEL_LOW, mp, dicp); + XFS_ERRLEVEL_LOW, mp, ldip); xfs_alert(mp, "%s: Bad regular inode log record, rec ptr 0x%p, " "ino ptr = 0x%p, ino bp = 0x%p, ino %Ld", @@ -2959,12 +3030,12 @@ xlog_recover_inode_pass2( error = -EFSCORRUPTED; goto out_release; } - } else if (unlikely(S_ISDIR(dicp->di_mode))) { - if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) && - (dicp->di_format != XFS_DINODE_FMT_BTREE) && - (dicp->di_format != XFS_DINODE_FMT_LOCAL)) { + } else if (unlikely(S_ISDIR(ldip->di_mode))) { + if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && + (ldip->di_format != XFS_DINODE_FMT_BTREE) && + (ldip->di_format != XFS_DINODE_FMT_LOCAL)) { XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)", - XFS_ERRLEVEL_LOW, mp, dicp); + XFS_ERRLEVEL_LOW, mp, ldip); xfs_alert(mp, "%s: Bad dir inode log record, rec ptr 0x%p, " "ino ptr = 0x%p, ino bp = 0x%p, ino %Ld", @@ -2973,32 +3044,32 @@ xlog_recover_inode_pass2( goto out_release; } } - if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){ + if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){ XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)", - XFS_ERRLEVEL_LOW, mp, dicp); + XFS_ERRLEVEL_LOW, mp, ldip); xfs_alert(mp, "%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, " "dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld", __func__, item, dip, bp, in_f->ilf_ino, - dicp->di_nextents + dicp->di_anextents, - dicp->di_nblocks); + ldip->di_nextents + ldip->di_anextents, + ldip->di_nblocks); error = -EFSCORRUPTED; goto out_release; } - if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) { + if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) { XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)", - XFS_ERRLEVEL_LOW, mp, dicp); + XFS_ERRLEVEL_LOW, mp, ldip); xfs_alert(mp, "%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, " "dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__, - item, dip, bp, in_f->ilf_ino, dicp->di_forkoff); + item, dip, bp, in_f->ilf_ino, ldip->di_forkoff); error = -EFSCORRUPTED; goto out_release; } - isize = xfs_icdinode_size(dicp->di_version); + isize = xfs_log_dinode_size(ldip->di_version); if (unlikely(item->ri_buf[1].i_len > isize)) { XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)", - XFS_ERRLEVEL_LOW, mp, dicp); + XFS_ERRLEVEL_LOW, mp, ldip); xfs_alert(mp, "%s: Bad inode log record length %d, rec ptr 0x%p", __func__, item->ri_buf[1].i_len, item); @@ -3006,8 +3077,8 @@ xlog_recover_inode_pass2( goto out_release; } - /* The core is in in-core format */ - xfs_dinode_to_disk(dip, dicp); + /* recover the log dinode inode into the on disk inode */ + xfs_log_dinode_to_disk(ldip, dip); /* the rest is in on-disk format */ if (item->ri_buf[1].i_len > isize) { @@ -4337,8 +4408,8 @@ xlog_recover_process_one_iunlink( if (error) goto fail_iput; - ASSERT(ip->i_d.di_nlink == 0); - ASSERT(ip->i_d.di_mode != 0); + ASSERT(VFS_I(ip)->i_nlink == 0); + ASSERT(VFS_I(ip)->i_mode != 0); /* setup for the next pass */ agino = be32_to_cpu(dip->di_next_unlinked); @@ -4491,7 +4562,7 @@ xlog_recover_process( * know precisely what failed. */ if (pass == XLOG_RECOVER_CRCPASS) { - if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc)) + if (rhead->h_crc && crc != rhead->h_crc) return -EFSBADCRC; return 0; } @@ -4502,7 +4573,7 @@ xlog_recover_process( * zero CRC check prevents warnings from being emitted when upgrading * the kernel from one that does not add CRCs by default. */ - if (crc != le32_to_cpu(rhead->h_crc)) { + if (crc != rhead->h_crc) { if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) { xfs_alert(log->l_mp, "log record CRC mismatch: found 0x%x, expected 0x%x.", @@ -4926,10 +4997,9 @@ xlog_do_recover( * updates, re-read in the superblock and reverify it. */ bp = xfs_getsb(log->l_mp, 0); - XFS_BUF_UNDONE(bp); - ASSERT(!(XFS_BUF_ISWRITE(bp))); - XFS_BUF_READ(bp); - XFS_BUF_UNASYNC(bp); + bp->b_flags &= ~(XBF_DONE | XBF_ASYNC); + ASSERT(!(bp->b_flags & XBF_WRITE)); + bp->b_flags |= XBF_READ; bp->b_ops = &xfs_sb_buf_ops; error = xfs_buf_submit_wait(bp); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index bb753b359bee..986290c4b7ab 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -865,7 +865,7 @@ xfs_mountfs( ASSERT(rip != NULL); - if (unlikely(!S_ISDIR(rip->i_d.di_mode))) { + if (unlikely(!S_ISDIR(VFS_I(rip)->i_mode))) { xfs_warn(mp, "corrupted root inode %llu: not a directory", (unsigned long long)rip->i_ino); xfs_iunlock(rip, XFS_ILOCK_EXCL); @@ -1284,7 +1284,7 @@ xfs_getsb( } xfs_buf_hold(bp); - ASSERT(XFS_BUF_ISDONE(bp)); + ASSERT(bp->b_flags & XBF_DONE); return bp; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index b57098481c10..a4e03ab50342 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -327,7 +327,6 @@ extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta, bool reserved); extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta); -extern int xfs_mount_log_sb(xfs_mount_t *); extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 532ab79d38fe..be125e1758c1 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -560,6 +560,37 @@ xfs_qm_shrink_count( return list_lru_shrink_count(&qi->qi_lru, sc); } +STATIC void +xfs_qm_set_defquota( + xfs_mount_t *mp, + uint type, + xfs_quotainfo_t *qinf) +{ + xfs_dquot_t *dqp; + struct xfs_def_quota *defq; + int error; + + error = xfs_qm_dqread(mp, 0, type, XFS_QMOPT_DOWARN, &dqp); + + if (!error) { + xfs_disk_dquot_t *ddqp = &dqp->q_core; + + defq = xfs_get_defquota(dqp, qinf); + + /* + * Timers and warnings have been already set, let's just set the + * default limits for this quota type + */ + defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit); + defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit); + defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit); + defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit); + defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit); + defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit); + xfs_qm_dqdestroy(dqp); + } +} + /* * This initializes all the quota information that's kept in the * mount structure @@ -606,19 +637,19 @@ xfs_qm_init_quotainfo( * We try to get the limits from the superuser's limits fields. * This is quite hacky, but it is standard quota practice. * - * We look at the USR dquot with id == 0 first, but if user quotas - * are not enabled we goto the GRP dquot with id == 0. - * We don't really care to keep separate default limits for user - * and group quotas, at least not at this point. - * * Since we may not have done a quotacheck by this point, just read * the dquot without attaching it to any hashtables or lists. + * + * Timers and warnings are globally set by the first timer found in + * user/group/proj quota types, otherwise a default value is used. + * This should be split into different fields per quota type. */ error = xfs_qm_dqread(mp, 0, XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER : (XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP : XFS_DQ_PROJ), XFS_QMOPT_DOWARN, &dqp); + if (!error) { xfs_disk_dquot_t *ddqp = &dqp->q_core; @@ -639,13 +670,6 @@ xfs_qm_init_quotainfo( be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT; qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ? be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT; - qinf->qi_bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit); - qinf->qi_bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit); - qinf->qi_ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit); - qinf->qi_isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit); - qinf->qi_rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit); - qinf->qi_rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit); - xfs_qm_dqdestroy(dqp); } else { qinf->qi_btimelimit = XFS_QM_BTIMELIMIT; @@ -656,6 +680,13 @@ xfs_qm_init_quotainfo( qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT; } + if (XFS_IS_UQUOTA_RUNNING(mp)) + xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf); + if (XFS_IS_GQUOTA_RUNNING(mp)) + xfs_qm_set_defquota(mp, XFS_DQ_GROUP, qinf); + if (XFS_IS_PQUOTA_RUNNING(mp)) + xfs_qm_set_defquota(mp, XFS_DQ_PROJ, qinf); + qinf->qi_shrinker.count_objects = xfs_qm_shrink_count; qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan; qinf->qi_shrinker.seeks = DEFAULT_SEEKS; diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 996a04064894..2975a822e9f0 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -53,6 +53,15 @@ extern struct kmem_zone *xfs_qm_dqtrxzone; */ #define XFS_DQUOT_CLUSTER_SIZE_FSB (xfs_filblks_t)1 +struct xfs_def_quota { + xfs_qcnt_t bhardlimit; /* default data blk hard limit */ + xfs_qcnt_t bsoftlimit; /* default data blk soft limit */ + xfs_qcnt_t ihardlimit; /* default inode count hard limit */ + xfs_qcnt_t isoftlimit; /* default inode count soft limit */ + xfs_qcnt_t rtbhardlimit; /* default realtime blk hard limit */ + xfs_qcnt_t rtbsoftlimit; /* default realtime blk soft limit */ +}; + /* * Various quota information for individual filesystems. * The mount structure keeps a pointer to this. @@ -76,12 +85,9 @@ typedef struct xfs_quotainfo { struct mutex qi_quotaofflock;/* to serialize quotaoff */ xfs_filblks_t qi_dqchunklen; /* # BBs in a chunk of dqs */ uint qi_dqperchunk; /* # ondisk dqs in above chunk */ - xfs_qcnt_t qi_bhardlimit; /* default data blk hard limit */ - xfs_qcnt_t qi_bsoftlimit; /* default data blk soft limit */ - xfs_qcnt_t qi_ihardlimit; /* default inode count hard limit */ - xfs_qcnt_t qi_isoftlimit; /* default inode count soft limit */ - xfs_qcnt_t qi_rtbhardlimit;/* default realtime blk hard limit */ - xfs_qcnt_t qi_rtbsoftlimit;/* default realtime blk soft limit */ + struct xfs_def_quota qi_usr_default; + struct xfs_def_quota qi_grp_default; + struct xfs_def_quota qi_prj_default; struct shrinker qi_shrinker; } xfs_quotainfo_t; @@ -104,15 +110,15 @@ xfs_dquot_tree( } static inline struct xfs_inode * -xfs_dq_to_quota_inode(struct xfs_dquot *dqp) +xfs_quota_inode(xfs_mount_t *mp, uint dq_flags) { - switch (dqp->dq_flags & XFS_DQ_ALLTYPES) { + switch (dq_flags & XFS_DQ_ALLTYPES) { case XFS_DQ_USER: - return dqp->q_mount->m_quotainfo->qi_uquotaip; + return mp->m_quotainfo->qi_uquotaip; case XFS_DQ_GROUP: - return dqp->q_mount->m_quotainfo->qi_gquotaip; + return mp->m_quotainfo->qi_gquotaip; case XFS_DQ_PROJ: - return dqp->q_mount->m_quotainfo->qi_pquotaip; + return mp->m_quotainfo->qi_pquotaip; default: ASSERT(0); } @@ -164,11 +170,27 @@ extern void xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint); /* quota ops */ extern int xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint); -extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t, - uint, struct qc_dqblk *); +extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t *, + uint, struct qc_dqblk *, uint); extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint, struct qc_dqblk *); extern int xfs_qm_scall_quotaon(struct xfs_mount *, uint); extern int xfs_qm_scall_quotaoff(struct xfs_mount *, uint); +static inline struct xfs_def_quota * +xfs_get_defquota(struct xfs_dquot *dqp, struct xfs_quotainfo *qi) +{ + struct xfs_def_quota *defq; + + if (XFS_QM_ISUDQ(dqp)) + defq = &qi->qi_usr_default; + else if (XFS_QM_ISGDQ(dqp)) + defq = &qi->qi_grp_default; + else { + ASSERT(XFS_QM_ISPDQ(dqp)); + defq = &qi->qi_prj_default; + } + return defq; +} + #endif /* __XFS_QM_H__ */ diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 3640c6e896af..f4d0e0a8f517 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -404,6 +404,7 @@ xfs_qm_scall_setqlim( struct xfs_disk_dquot *ddq; struct xfs_dquot *dqp; struct xfs_trans *tp; + struct xfs_def_quota *defq; int error; xfs_qcnt_t hard, soft; @@ -431,6 +432,8 @@ xfs_qm_scall_setqlim( ASSERT(error != -ENOENT); goto out_unlock; } + + defq = xfs_get_defquota(dqp, q); xfs_dqunlock(dqp); tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM); @@ -458,8 +461,8 @@ xfs_qm_scall_setqlim( ddq->d_blk_softlimit = cpu_to_be64(soft); xfs_dquot_set_prealloc_limits(dqp); if (id == 0) { - q->qi_bhardlimit = hard; - q->qi_bsoftlimit = soft; + defq->bhardlimit = hard; + defq->bsoftlimit = soft; } } else { xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft); @@ -474,8 +477,8 @@ xfs_qm_scall_setqlim( ddq->d_rtb_hardlimit = cpu_to_be64(hard); ddq->d_rtb_softlimit = cpu_to_be64(soft); if (id == 0) { - q->qi_rtbhardlimit = hard; - q->qi_rtbsoftlimit = soft; + defq->rtbhardlimit = hard; + defq->rtbsoftlimit = soft; } } else { xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft); @@ -491,8 +494,8 @@ xfs_qm_scall_setqlim( ddq->d_ino_hardlimit = cpu_to_be64(hard); ddq->d_ino_softlimit = cpu_to_be64(soft); if (id == 0) { - q->qi_ihardlimit = hard; - q->qi_isoftlimit = soft; + defq->ihardlimit = hard; + defq->isoftlimit = soft; } } else { xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft); @@ -635,9 +638,10 @@ out: int xfs_qm_scall_getquota( struct xfs_mount *mp, - xfs_dqid_t id, + xfs_dqid_t *id, uint type, - struct qc_dqblk *dst) + struct qc_dqblk *dst, + uint dqget_flags) { struct xfs_dquot *dqp; int error; @@ -647,7 +651,7 @@ xfs_qm_scall_getquota( * we aren't passing the XFS_QMOPT_DOALLOC flag. If it doesn't * exist, we'll get ENOENT back. */ - error = xfs_qm_dqget(mp, NULL, id, type, 0, &dqp); + error = xfs_qm_dqget(mp, NULL, *id, type, dqget_flags, &dqp); if (error) return error; @@ -660,6 +664,9 @@ xfs_qm_scall_getquota( goto out_put; } + /* Fill in the ID we actually read from disk */ + *id = be32_to_cpu(dqp->q_core.d_id); + memset(dst, 0, sizeof(*dst)); dst->d_spc_hardlimit = XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); @@ -701,7 +708,7 @@ xfs_qm_scall_getquota( if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) || (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) || (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) && - id != 0) { + *id != 0) { if ((dst->d_space > dst->d_spc_softlimit) && (dst->d_spc_softlimit > 0)) { ASSERT(dst->d_spc_timer != 0); diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7795e0d01382..f82d79a8c694 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -231,14 +231,45 @@ xfs_fs_get_dqblk( struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); + xfs_dqid_t id; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; if (!XFS_IS_QUOTA_ON(mp)) return -ESRCH; - return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), qdq); + id = from_kqid(&init_user_ns, qid); + return xfs_qm_scall_getquota(mp, &id, + xfs_quota_type(qid.type), qdq, 0); +} + +/* Return quota info for active quota >= this qid */ +STATIC int +xfs_fs_get_nextdqblk( + struct super_block *sb, + struct kqid *qid, + struct qc_dqblk *qdq) +{ + int ret; + struct xfs_mount *mp = XFS_M(sb); + xfs_dqid_t id; + + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + if (!XFS_IS_QUOTA_ON(mp)) + return -ESRCH; + + id = from_kqid(&init_user_ns, *qid); + ret = xfs_qm_scall_getquota(mp, &id, + xfs_quota_type(qid->type), qdq, + XFS_QMOPT_DQNEXT); + if (ret) + return ret; + + /* ID may be different, so convert back what we got */ + *qid = make_kqid(current_user_ns(), qid->type, id); + return 0; + } STATIC int @@ -267,5 +298,6 @@ const struct quotactl_ops xfs_quotactl_operations = { .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, + .get_nextdqblk = xfs_fs_get_nextdqblk, .set_dqblk = xfs_fs_set_dqblk, }; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index be02a68b2fe2..abf44435d04a 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1272,7 +1272,7 @@ xfs_rtpick_extent( ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL)); - seqp = (__uint64_t *)&mp->m_rbmip->i_d.di_atime; + seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime; if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) { mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM; *seqp = 0; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 391d797cb53f..c8d58426008e 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1296,11 +1296,7 @@ DEFINE_IOMAP_EVENT(xfs_map_blocks_found); DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc); DEFINE_IOMAP_EVENT(xfs_get_blocks_found); DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc); -DEFINE_IOMAP_EVENT(xfs_gbmap_direct); -DEFINE_IOMAP_EVENT(xfs_gbmap_direct_new); -DEFINE_IOMAP_EVENT(xfs_gbmap_direct_update); -DEFINE_IOMAP_EVENT(xfs_gbmap_direct_none); -DEFINE_IOMAP_EVENT(xfs_gbmap_direct_endio); +DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct); DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), @@ -1340,6 +1336,9 @@ DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert); DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound); DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize); DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof); +DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write); +DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten); +DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 4f18fd92ca13..d6c9c3e9e02b 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -497,6 +497,7 @@ xfsaild( long tout = 0; /* milliseconds */ current->flags |= PF_MEMALLOC; + set_freezable(); while (!kthread_should_stop()) { if (tout && tout <= 20) @@ -519,14 +520,14 @@ xfsaild( if (!xfs_ail_min(ailp) && ailp->xa_target == ailp->xa_target_prev) { spin_unlock(&ailp->xa_lock); - schedule(); + freezable_schedule(); tout = 0; continue; } spin_unlock(&ailp->xa_lock); if (tout) - schedule_timeout(msecs_to_jiffies(tout)); + freezable_schedule_timeout(msecs_to_jiffies(tout)); __set_current_state(TASK_RUNNING); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 75798412859a..8ee29ca132dc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -155,7 +155,7 @@ xfs_trans_get_buf_map( ASSERT(xfs_buf_islocked(bp)); if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) { xfs_buf_stale(bp); - XFS_BUF_DONE(bp); + bp->b_flags |= XBF_DONE; } ASSERT(bp->b_transp == tp); @@ -518,7 +518,7 @@ xfs_trans_log_buf(xfs_trans_t *tp, * inside the b_bdstrat callback so that this won't get written to * disk. */ - XFS_BUF_DONE(bp); + bp->b_flags |= XBF_DONE; ASSERT(atomic_read(&bip->bli_refcount) > 0); bp->b_iodone = xfs_buf_iodone_callbacks; @@ -534,8 +534,8 @@ xfs_trans_log_buf(xfs_trans_t *tp, */ if (bip->bli_flags & XFS_BLI_STALE) { bip->bli_flags &= ~XFS_BLI_STALE; - ASSERT(XFS_BUF_ISSTALE(bp)); - XFS_BUF_UNSTALE(bp); + ASSERT(bp->b_flags & XBF_STALE); + bp->b_flags &= ~XBF_STALE; bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL; } @@ -600,7 +600,7 @@ xfs_trans_binval( * If the buffer is already invalidated, then * just return. */ - ASSERT(XFS_BUF_ISSTALE(bp)); + ASSERT(bp->b_flags & XBF_STALE); ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY))); ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF)); ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK)); diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 995170194df0..c3d547211d16 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -609,17 +609,20 @@ xfs_trans_dqresv( xfs_qcnt_t total_count; xfs_qcnt_t *resbcountp; xfs_quotainfo_t *q = mp->m_quotainfo; + struct xfs_def_quota *defq; xfs_dqlock(dqp); + defq = xfs_get_defquota(dqp, q); + if (flags & XFS_TRANS_DQ_RES_BLKS) { hardlimit = be64_to_cpu(dqp->q_core.d_blk_hardlimit); if (!hardlimit) - hardlimit = q->qi_bhardlimit; + hardlimit = defq->bhardlimit; softlimit = be64_to_cpu(dqp->q_core.d_blk_softlimit); if (!softlimit) - softlimit = q->qi_bsoftlimit; + softlimit = defq->bsoftlimit; timer = be32_to_cpu(dqp->q_core.d_btimer); warns = be16_to_cpu(dqp->q_core.d_bwarns); warnlimit = dqp->q_mount->m_quotainfo->qi_bwarnlimit; @@ -628,10 +631,10 @@ xfs_trans_dqresv( ASSERT(flags & XFS_TRANS_DQ_RES_RTBLKS); hardlimit = be64_to_cpu(dqp->q_core.d_rtb_hardlimit); if (!hardlimit) - hardlimit = q->qi_rtbhardlimit; + hardlimit = defq->rtbhardlimit; softlimit = be64_to_cpu(dqp->q_core.d_rtb_softlimit); if (!softlimit) - softlimit = q->qi_rtbsoftlimit; + softlimit = defq->rtbsoftlimit; timer = be32_to_cpu(dqp->q_core.d_rtbtimer); warns = be16_to_cpu(dqp->q_core.d_rtbwarns); warnlimit = dqp->q_mount->m_quotainfo->qi_rtbwarnlimit; @@ -672,10 +675,10 @@ xfs_trans_dqresv( warnlimit = dqp->q_mount->m_quotainfo->qi_iwarnlimit; hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit); if (!hardlimit) - hardlimit = q->qi_ihardlimit; + hardlimit = defq->ihardlimit; softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit); if (!softlimit) - softlimit = q->qi_isoftlimit; + softlimit = defq->isoftlimit; if (hardlimit && total_count > hardlimit) { xfs_quota_warn(mp, dqp, QUOTA_NL_IHARDWARN); diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index b97f1df910ab..11a3af08b5c7 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -75,18 +75,10 @@ xfs_trans_ichgtime( tv = current_fs_time(inode->i_sb); - if ((flags & XFS_ICHGTIME_MOD) && - !timespec_equal(&inode->i_mtime, &tv)) { + if (flags & XFS_ICHGTIME_MOD) inode->i_mtime = tv; - ip->i_d.di_mtime.t_sec = tv.tv_sec; - ip->i_d.di_mtime.t_nsec = tv.tv_nsec; - } - if ((flags & XFS_ICHGTIME_CHG) && - !timespec_equal(&inode->i_ctime, &tv)) { + if (flags & XFS_ICHGTIME_CHG) inode->i_ctime = tv; - ip->i_d.di_ctime.t_sec = tv.tv_sec; - ip->i_d.di_ctime.t_nsec = tv.tv_nsec; - } } /* @@ -125,7 +117,7 @@ xfs_trans_log_inode( */ if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) && IS_I_VERSION(VFS_I(ip))) { - ip->i_d.di_changecount = ++VFS_I(ip)->i_version; + VFS_I(ip)->i_version++; flags |= XFS_ILOG_CORE; } |