diff options
87 files changed, 10972 insertions, 4011 deletions
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 1b98cfa342ab..f42fcf1b5465 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -71,6 +71,23 @@ config XFS_RT If unsure, say N. +config XFS_ONLINE_SCRUB + bool "XFS online metadata check support" + default n + depends on XFS_FS + help + If you say Y here you will be able to check metadata on a + mounted XFS filesystem. This feature is intended to reduce + filesystem downtime by supplementing xfs_repair. The key + advantage here is to look for problems proactively so that + they can be dealt with in a controlled manner. + + This feature is considered EXPERIMENTAL. Use with caution! + + See the xfs_scrub man page in section 8 for additional information. + + If unsure, say N. + config XFS_WARN bool "XFS Verbose Warnings" depends on XFS_FS && !XFS_DEBUG diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index a6e955bfead8..7ceb41a9786a 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -49,6 +49,7 @@ xfs-y += $(addprefix libxfs/, \ xfs_dquot_buf.o \ xfs_ialloc.o \ xfs_ialloc_btree.o \ + xfs_iext_tree.o \ xfs_inode_fork.o \ xfs_inode_buf.o \ xfs_log_rlimit.o \ @@ -135,3 +136,31 @@ xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o + +# online scrub/repair +ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) + +# Tracepoints like to blow up, so build that before everything else + +xfs-y += $(addprefix scrub/, \ + trace.o \ + agheader.o \ + alloc.o \ + attr.o \ + bmap.o \ + btree.o \ + common.o \ + dabtree.o \ + dir.o \ + ialloc.o \ + inode.o \ + parent.o \ + refcount.o \ + rmap.o \ + scrub.o \ + symlink.o \ + ) + +xfs-$(CONFIG_XFS_RT) += scrub/rtbitmap.o +xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o +endif diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 4d85992d75b2..758f37ac5ad3 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -119,8 +119,7 @@ kmem_zone_free(kmem_zone_t *zone, void *ptr) static inline void kmem_zone_destroy(kmem_zone_t *zone) { - if (zone) - kmem_cache_destroy(zone); + kmem_cache_destroy(zone); } extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t); diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index df3e600835e8..2291f4224e24 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -27,6 +27,7 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_alloc.h" +#include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_cksum.h" diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index f965ce832bc0..0da80019a917 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -31,6 +31,7 @@ #include "xfs_alloc_btree.h" #include "xfs_alloc.h" #include "xfs_extent_busy.h" +#include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_cksum.h" #include "xfs_trace.h" @@ -2931,3 +2932,52 @@ xfs_alloc_query_all( query.fn = fn; return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query); } + +/* Find the size of the AG, in blocks. */ +xfs_agblock_t +xfs_ag_block_count( + struct xfs_mount *mp, + xfs_agnumber_t agno) +{ + ASSERT(agno < mp->m_sb.sb_agcount); + + if (agno < mp->m_sb.sb_agcount - 1) + return mp->m_sb.sb_agblocks; + return mp->m_sb.sb_dblocks - (agno * mp->m_sb.sb_agblocks); +} + +/* + * Verify that an AG block number pointer neither points outside the AG + * nor points at static metadata. + */ +bool +xfs_verify_agbno( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_agblock_t agbno) +{ + xfs_agblock_t eoag; + + eoag = xfs_ag_block_count(mp, agno); + if (agbno >= eoag) + return false; + if (agbno <= XFS_AGFL_BLOCK(mp)) + return false; + return true; +} + +/* + * Verify that an FS block number pointer neither points outside the + * filesystem nor points at static AG metadata. + */ +bool +xfs_verify_fsbno( + struct xfs_mount *mp, + xfs_fsblock_t fsbno) +{ + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); + + if (agno >= mp->m_sb.sb_agcount) + return false; + return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno)); +} diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index ef26edc2e938..7ba2d129d504 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -232,5 +232,9 @@ int xfs_alloc_query_range(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn, void *priv); int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn, void *priv); +xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno); +bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_agblock_t agbno); +bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno); #endif /* __XFS_ALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 5c16db86b38f..53cc8b986eac 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -397,13 +397,9 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) /* rounded down */ offset = (XFS_LITINO(mp, dp->i_d.di_version) - bytes) >> 3; - switch (dp->i_d.di_format) { - case XFS_DINODE_FMT_DEV: + if (dp->i_d.di_format == XFS_DINODE_FMT_DEV) { minforkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; return (offset >= minforkoff) ? minforkoff : 0; - case XFS_DINODE_FMT_UUID: - minforkoff = roundup(sizeof(uuid_t), 8) >> 3; - return (offset >= minforkoff) ? minforkoff : 0; } /* diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 89263797cf32..08df809e2315 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -38,6 +38,7 @@ #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" #include "xfs_rtalloc.h" +#include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" @@ -112,28 +113,21 @@ xfs_bmap_compute_maxlevels( STATIC int /* error */ xfs_bmbt_lookup_eq( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, + struct xfs_bmbt_irec *irec, int *stat) /* success/failure */ { - cur->bc_rec.b.br_startoff = off; - cur->bc_rec.b.br_startblock = bno; - cur->bc_rec.b.br_blockcount = len; + cur->bc_rec.b = *irec; return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); } STATIC int /* error */ -xfs_bmbt_lookup_ge( +xfs_bmbt_lookup_first( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, int *stat) /* success/failure */ { - cur->bc_rec.b.br_startoff = off; - cur->bc_rec.b.br_startblock = bno; - cur->bc_rec.b.br_blockcount = len; + cur->bc_rec.b.br_startoff = 0; + cur->bc_rec.b.br_startblock = 0; + cur->bc_rec.b.br_blockcount = 0; return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); } @@ -160,21 +154,17 @@ static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork) } /* - * Update the record referred to by cur to the value given - * by [off, bno, len, state]. + * Update the record referred to by cur to the value given by irec * This either works (return 0) or gets an EFSCORRUPTED error. */ STATIC int xfs_bmbt_update( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, - xfs_exntst_t state) + struct xfs_bmbt_irec *irec) { union xfs_btree_rec rec; - xfs_bmbt_disk_set_allf(&rec.bmbt, off, bno, len, state); + xfs_bmbt_disk_set_all(&rec.bmbt, irec); return xfs_btree_update(cur, &rec); } @@ -242,7 +232,6 @@ xfs_bmap_forkoff_reset( { if (whichfork == XFS_ATTR_FORK && ip->i_d.di_format != XFS_DINODE_FMT_DEV && - ip->i_d.di_format != XFS_DINODE_FMT_UUID && ip->i_d.di_format != XFS_DINODE_FMT_BTREE) { uint dfl_forkoff = xfs_default_attroffset(ip) >> 3; @@ -499,31 +488,6 @@ error_norelse: } /* - * Add bmap trace insert entries for all the contents of the extent records. - */ -void -xfs_bmap_trace_exlist( - xfs_inode_t *ip, /* incore inode pointer */ - xfs_extnum_t cnt, /* count of entries in the list */ - int whichfork, /* data or attr or cow fork */ - unsigned long caller_ip) -{ - xfs_extnum_t idx; /* extent record index */ - xfs_ifork_t *ifp; /* inode fork pointer */ - int state = 0; - - if (whichfork == XFS_ATTR_FORK) - state |= BMAP_ATTRFORK; - else if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(cnt == xfs_iext_count(ifp)); - for (idx = 0; idx < cnt; idx++) - trace_xfs_extlist(ip, idx, state, caller_ip); -} - -/* * Validate that the bmbt_irecs being returned from bmapi are valid * given the caller's original parameters. Specifically check the * ranges of the returned irecs to ensure that they only extend beyond @@ -657,8 +621,8 @@ xfs_bmap_btree_to_extents( cbno = be64_to_cpu(*pp); *logflagsp = 0; #ifdef DEBUG - if ((error = xfs_btree_check_lptr(cur, cbno, 1))) - return error; + XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, + xfs_btree_check_lptr(cur, cbno, 1)); #endif error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); @@ -703,14 +667,14 @@ xfs_bmap_extents_to_btree( xfs_bmbt_rec_t *arp; /* child record pointer */ struct xfs_btree_block *block; /* btree root block */ xfs_btree_cur_t *cur; /* bmap btree cursor */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ int error; /* error return value */ - xfs_extnum_t i, cnt; /* extent record index */ xfs_ifork_t *ifp; /* inode fork pointer */ xfs_bmbt_key_t *kp; /* root block key pointer */ xfs_mount_t *mp; /* mount structure */ - xfs_extnum_t nextents; /* number of file extents */ xfs_bmbt_ptr_t *pp; /* root block address pointer */ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec rec; + xfs_extnum_t cnt = 0; mp = ip->i_mount; ASSERT(whichfork != XFS_COW_FORK); @@ -789,15 +753,12 @@ xfs_bmap_extents_to_btree( XFS_BTNUM_BMAP, 0, 0, ip->i_ino, XFS_BTREE_LONG_PTRS); - arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); - nextents = xfs_iext_count(ifp); - for (cnt = i = 0; i < nextents; i++) { - ep = xfs_iext_get_ext(ifp, i); - if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) { - arp->l0 = cpu_to_be64(ep->l0); - arp->l1 = cpu_to_be64(ep->l1); - arp++; cnt++; - } + for_each_xfs_iext(ifp, &icur, &rec) { + if (isnullstartblock(rec.br_startblock)) + continue; + arp = XFS_BMBT_REC_ADDR(mp, ablock, 1 + cnt); + xfs_bmbt_disk_set_all(arp, &rec); + cnt++; } ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork)); xfs_btree_set_numrecs(ablock, cnt); @@ -845,6 +806,8 @@ xfs_bmap_local_to_extents_empty( xfs_bmap_forkoff_reset(ip, whichfork); ifp->if_flags &= ~XFS_IFINLINE; ifp->if_flags |= XFS_IFEXTENTS; + ifp->if_u1.if_root = NULL; + ifp->if_height = 0; XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); } @@ -868,6 +831,7 @@ xfs_bmap_local_to_extents( xfs_alloc_arg_t args; /* allocation arguments */ xfs_buf_t *bp; /* buffer for extent block */ struct xfs_bmbt_irec rec; + struct xfs_iext_cursor icur; /* * We don't want to deal with the case of keeping inode data inline yet. @@ -885,8 +849,7 @@ xfs_bmap_local_to_extents( flags = 0; error = 0; - ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == - XFS_IFINLINE); + ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS)) == XFS_IFINLINE); memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = ip->i_mount; @@ -930,15 +893,16 @@ xfs_bmap_local_to_extents( xfs_bmap_local_to_extents_empty(ip, whichfork); flags |= XFS_ILOG_CORE; + ifp->if_u1.if_root = NULL; + ifp->if_height = 0; + rec.br_startoff = 0; rec.br_startblock = args.fsbno; rec.br_blockcount = 1; rec.br_state = XFS_EXT_NORM; - xfs_iext_insert(ip, 0, 1, &rec, 0); + xfs_iext_first(ifp, &icur); + xfs_iext_insert(ip, &icur, &rec, 0); - trace_xfs_bmap_post_update(ip, 0, - whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0, - _THIS_IP_); XFS_IFORK_NEXT_SET(ip, whichfork, 1); ip->i_d.di_nblocks = 1; xfs_trans_mod_dquot_byino(tp, ip, @@ -973,7 +937,8 @@ xfs_bmap_add_attrfork_btree( cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK); cur->bc_private.b.dfops = dfops; cur->bc_private.b.firstblock = *firstblock; - if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat))) + error = xfs_bmbt_lookup_first(cur, &stat); + if (error) goto error0; /* must be at least one entry */ XFS_WANT_CORRUPTED_GOTO(mp, stat == 1, error0); @@ -1124,9 +1089,6 @@ xfs_bmap_add_attrfork( case XFS_DINODE_FMT_DEV: ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; break; - case XFS_DINODE_FMT_UUID: - ip->i_d.di_forkoff = roundup(sizeof(uuid_t), 8) >> 3; - break; case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -1206,32 +1168,35 @@ trans_cancel: */ /* - * Read in the extents to if_extents. - * All inode fields are set up by caller, we just traverse the btree - * and copy the records in. If the file system cannot contain unwritten - * extents, the records are checked for no "state" flags. + * Read in extents from a btree-format inode. */ -int /* error */ -xfs_bmap_read_extents( - xfs_trans_t *tp, /* transaction pointer */ |