[11/37] xfs: support file data forks containing metadata btrees

Message ID	173463579943.1571512.17410968882975339484.stgit@frogsfrogsfrogs (mailing list archive)
State	New
Headers	show Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8E37F1ACEAA for <linux-xfs@vger.kernel.org>; Thu, 19 Dec 2024 19:26:16 +0000 (UTC) Date: Thu, 19 Dec 2024 11:26:15 -0800 Subject: [PATCH 11/37] xfs: support file data forks containing metadata btrees From: "Darrick J. Wong" <djwong@kernel.org> To: djwong@kernel.org Cc: hch@lst.de, linux-xfs@vger.kernel.org, hch@lst.de Message-ID: <173463579943.1571512.17410968882975339484.stgit@frogsfrogsfrogs> In-Reply-To: <173463579653.1571512.7862891421559358642.stgit@frogsfrogsfrogs> References: <173463579653.1571512.7862891421559358642.stgit@frogsfrogsfrogs> Precedence: bulk MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit
Series	[01/37] xfs: add some rtgroup inode helpers \| expand [01/37] xfs: add some rtgroup inode helpers [02/37] xfs: prepare rmap btree cursor tracepoints for realtime [03/37] xfs: simplify the xfs_rmap_{alloc,free}_extent calling conventions [04/37] xfs: introduce realtime rmap btree ondisk definitions [05/37] xfs: realtime rmap btree transaction reservations [06/37] xfs: add realtime rmap btree operations [07/37] xfs: prepare rmap functions to deal with rtrmapbt [08/37] xfs: add a realtime flag to the rmap update log redo items [09/37] xfs: support recovering rmap intent items targetting realtime extents [10/37] xfs: pretty print metadata file types in error messages [11/37] xfs: support file data forks containing metadata btrees [12/37] xfs: add realtime reverse map inode to metadata directory [13/37] xfs: add metadata reservations for realtime rmap btrees [14/37] xfs: wire up a new metafile type for the realtime rmap [15/37] xfs: wire up rmap map and unmap to the realtime rmapbt [16/37] xfs: create routine to allocate and initialize a realtime rmap btree inode [17/37] xfs: wire up getfsmap to the realtime reverse mapping btree [18/37] xfs: check that the rtrmapbt maxlevels doesn't increase when growing fs [19/37] xfs: report realtime rmap btree corruption errors to the health system [20/37] xfs: allow queued realtime intents to drain before scrubbing [21/37] xfs: scrub the realtime rmapbt [22/37] xfs: cross-reference realtime bitmap to realtime rmapbt scrubber [23/37] xfs: cross-reference the realtime rmapbt [24/37] xfs: scan rt rmap when we're doing an intense rmap check of bmbt mappings [25/37] xfs: scrub the metadir path of rt rmap btree files [26/37] xfs: walk the rt reverse mapping tree when rebuilding rmap [27/37] xfs: online repair of realtime file bmaps [28/37] xfs: repair inodes that have realtime extents [29/37] xfs: repair rmap btree inodes [30/37] xfs: online repair of realtime bitmaps for a realtime group [31/37] xfs: support repairing metadata btrees rooted in metadir inodes [32/37] xfs: online repair of the realtime rmap btree [33/37] xfs: create a shadow rmap btree during realtime rmap repair [34/37] xfs: hook live realtime rmap operations during a repair operation [35/37] xfs: don't shut down the filesystem for media failures beyond end of log [36/37] xfs: react to fsdax failure notifications on the rt device [37/37] xfs: enable realtime rmap btree

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 469fc7afa591b4..41ea4283c43cb4 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -997,7 +997,8 @@ enum xfs_dinode_fmt { XFS_DINODE_FMT_LOCAL, /* bulk data */ XFS_DINODE_FMT_EXTENTS, /* struct xfs_bmbt_rec */ XFS_DINODE_FMT_BTREE, /* struct xfs_bmdr_block */ - XFS_DINODE_FMT_UUID /* added long ago, but never used */ + XFS_DINODE_FMT_UUID, /* added long ago, but never used */ + XFS_DINODE_FMT_META_BTREE, /* metadata btree */ }; #define XFS_INODE_FORMAT_STR \ @@ -1005,7 +1006,8 @@ enum xfs_dinode_fmt { { XFS_DINODE_FMT_LOCAL, "local" }, \ { XFS_DINODE_FMT_EXTENTS, "extent" }, \ { XFS_DINODE_FMT_BTREE, "btree" }, \ - { XFS_DINODE_FMT_UUID, "uuid" } + { XFS_DINODE_FMT_UUID, "uuid" }, \ + { XFS_DINODE_FMT_META_BTREE, "meta_btree" } /* * Max values for extnum and aextnum. diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 424861fbf1bd49..1648d72d6ed95a 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -441,6 +441,16 @@ xfs_dinode_verify_fork( if (di_nextents > max_extents) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp)) + return __this_address; + if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) + return __this_address; + switch (be16_to_cpu(dip->di_metatype)) { + default: + return __this_address; + } + break; default: return __this_address; } @@ -460,6 +470,10 @@ xfs_dinode_verify_forkoff( if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp) || !xfs_has_parent(mp)) + return __this_address; + fallthrough; case XFS_DINODE_FMT_LOCAL: /* fall through ... */ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ case XFS_DINODE_FMT_BTREE: @@ -637,9 +651,6 @@ xfs_dinode_verify( if (mode && nextents + naextents > nblocks) return __this_address; - if (nextents + naextents == 0 && nblocks != 0) - return __this_address; - if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents) return __this_address; @@ -743,6 +754,12 @@ xfs_dinode_verify( return fa; } + /* metadata inodes containing btrees always have zero extent count */ + if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) { + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + } + return NULL; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 60853bac289a39..1a782339396dc3 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -267,6 +267,12 @@ xfs_iformat_data_fork( return xfs_iformat_extents(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_BTREE: return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); + case XFS_DINODE_FMT_META_BTREE: + switch (ip->i_metatype) { + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); @@ -601,6 +607,19 @@ xfs_iflush_fork( } break; + case XFS_DINODE_FMT_META_BTREE: + ASSERT(whichfork == XFS_DATA_FORK); + + if (!(iip->ili_fields & brootflag[whichfork])) + break; + + switch (ip->i_metatype) { + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7e00312225ed10..0d7ad692822d48 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -983,6 +983,7 @@ xchk_bmap( case XFS_DINODE_FMT_UUID: case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_META_BTREE: /* No mappings to check. */ if (whichfork == XFS_COW_FORK) xchk_fblock_set_corrupt(sc, whichfork, 0); diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c index 7c4955482641f7..141d36f1da9a71 100644 --- a/fs/xfs/scrub/bmap_repair.c +++ b/fs/xfs/scrub/bmap_repair.c @@ -731,6 +731,7 @@ xrep_bmap_check_inputs( case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_UUID: + case XFS_DINODE_FMT_META_BTREE: return -ECANCELED; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 25ee66e7649d40..2e911f38deaebe 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -502,6 +502,10 @@ xchk_dinode( if (!S_ISREG(mode) && !S_ISDIR(mode)) xchk_ino_set_corrupt(sc, ino); break; + case XFS_DINODE_FMT_META_BTREE: + if (!S_ISREG(mode)) + xchk_ino_set_corrupt(sc, ino); + break; case XFS_DINODE_FMT_UUID: default: xchk_ino_set_corrupt(sc, ino); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 5a58ddd27bd2f5..7faa27472b9129 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -888,6 +888,25 @@ xrep_dinode_bad_bmbt_fork( return false; } +/* Check a metadata-btree fork. */ +STATIC bool +xrep_dinode_bad_metabt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size, + int whichfork) +{ + if (whichfork != XFS_DATA_FORK) + return true; + + switch (be16_to_cpu(dip->di_metatype)) { + default: + return true; + } + + return false; +} + /* * Check the data fork for things that will fail the ifork verifiers or the * ifork formatters. @@ -968,6 +987,11 @@ xrep_dinode_check_dfork( XFS_DATA_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, dfork_size, + XFS_DATA_FORK)) + return true; + break; default: return true; } @@ -1088,6 +1112,11 @@ xrep_dinode_check_afork( XFS_ATTR_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, afork_size, + XFS_ATTR_FORK)) + return true; + break; default: return true; } @@ -1241,6 +1270,13 @@ xrep_dinode_ensure_forkoff( bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); dfork_min = xfs_bmap_broot_space(sc->mp, bmdr); break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + default: + dfork_min = 0; + break; + } + break; default: dfork_min = 0; break; diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c index a0a227d183d28d..2a0b9e3d0fbaee 100644 --- a/fs/xfs/scrub/rmap_repair.c +++ b/fs/xfs/scrub/rmap_repair.c @@ -499,6 +499,14 @@ xrep_rmap_scan_iext( return xrep_rmap_stash_accumulated(rf); } +static int +xrep_rmap_scan_meta_btree( + struct xrep_rmap_ifork *rf, + struct xfs_inode *ip) +{ + return -EFSCORRUPTED; /* XXX placeholder */ +} + /* Find all the extents from a given AG in an inode fork. */ STATIC int xrep_rmap_scan_ifork( @@ -512,14 +520,14 @@ xrep_rmap_scan_ifork( .whichfork = whichfork, }; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + bool mappings_done; int error = 0; if (!ifp) return 0; - if (ifp->if_format == XFS_DINODE_FMT_BTREE) { - bool mappings_done; - + switch (ifp->if_format) { + case XFS_DINODE_FMT_BTREE: /* * Scan the bmap btree for data device mappings. This includes * the btree blocks themselves, even if this is a realtime @@ -528,15 +536,18 @@ xrep_rmap_scan_ifork( error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done); if (error || mappings_done) return error; - } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { - return 0; + fallthrough; + case XFS_DINODE_FMT_EXTENTS: + /* Scan incore extent cache if this isn't a realtime file. */ + if (xfs_ifork_is_realtime(ip, whichfork)) + return 0; + + return xrep_rmap_scan_iext(&rf, ifp); + case XFS_DINODE_FMT_META_BTREE: + return xrep_rmap_scan_meta_btree(&rf, ip); } - /* Scan incore extent cache if this isn't a realtime file. */ - if (xfs_ifork_is_realtime(ip, whichfork)) - return 0; - - return xrep_rmap_scan_iext(&rf, ifp); + return 0; } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c8ad2606f928b2..c95fe1b1de4e6f 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2382,7 +2382,16 @@ xfs_iflush( __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } - if (S_ISREG(VFS_I(ip)->i_mode)) { + if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) { + if (!S_ISREG(VFS_I(ip)->i_mode) || + !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT, + __func__, xfs_metafile_type_str(ip->i_metatype), + ip->i_ino, ip); + goto flush_out; + } + } else if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE, @@ -2422,6 +2431,14 @@ xfs_iflush( goto flush_out; } + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT, + __func__, ip->i_ino, ip); + goto flush_out; + } + /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 912f0b1bc3cb70..a174f64b8bb250 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -242,6 +242,7 @@ xfs_inode_item_data_fork_size( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: if ((iip->ili_fields & XFS_ILOG_DBROOT) && ip->i_df.if_broot_bytes > 0) { *nbytes += ip->i_df.if_broot_bytes; @@ -362,6 +363,7 @@ xfs_inode_item_format_data_fork( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: iip->ili_fields &= ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV); diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index e70d2611456bc9..6e9b3bfc718c0b 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -266,6 +266,35 @@ xlog_dinode_verify_extent_counts( return 0; } +static inline int +xlog_recover_inode_dbroot( + struct xfs_mount *mp, + void *src, + unsigned int len, + struct xfs_dinode *dip) +{ + void *dfork = XFS_DFORK_DPTR(dip); + unsigned int dsize = XFS_DFORK_DSIZE(dip, mp); + + switch (dip->di_format) { + case XFS_DINODE_FMT_BTREE: + xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize); + break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + default: + ASSERT(0); + return -EFSCORRUPTED; + } + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; +} + STATIC int xlog_recover_inode_commit_pass2( struct xlog *log, @@ -393,8 +422,9 @@ xlog_recover_inode_commit_pass2( if (unlikely(S_ISREG(ldip->di_mode))) { - if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && - (ldip->di_format != XFS_DINODE_FMT_BTREE)) { + if (ldip->di_format != XFS_DINODE_FMT_EXTENTS && + ldip->di_format != XFS_DINODE_FMT_BTREE && + ldip->di_format != XFS_DINODE_FMT_META_BTREE) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for regular file", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); @@ -475,9 +505,9 @@ xlog_recover_inode_commit_pass2( break; case XFS_ILOG_DBROOT: - xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len, - (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip), - XFS_DFORK_DSIZE(dip, mp)); + error = xlog_recover_inode_dbroot(mp, src, len, dip); + if (error) + goto out_release; break; default: diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 8b7bb1f5ae3c6f..a098935163b7c2 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2299,6 +2299,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID); +TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE); DECLARE_EVENT_CLASS(xfs_swap_extent_class, TP_PROTO(struct xfs_inode *ip, int which),

[11/37] xfs: support file data forks containing metadata btrees

Commit Message

Patch