[12/52] xfs: define the format of rt groups

Message ID	173498942677.2295836.7924241153553017959.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 BDE4F1C3BF0 for <linux-xfs@vger.kernel.org>; Mon, 23 Dec 2024 22:01:21 +0000 (UTC) Date: Mon, 23 Dec 2024 14:01:20 -0800 Subject: [PATCH 12/52] xfs: define the format of rt groups From: "Darrick J. Wong" <djwong@kernel.org> To: djwong@kernel.org, aalbersh@kernel.org Cc: hch@lst.de, linux-xfs@vger.kernel.org Message-ID: <173498942677.2295836.7924241153553017959.stgit@frogsfrogsfrogs> In-Reply-To: <173498942411.2295836.4988904181656691611.stgit@frogsfrogsfrogs> References: <173498942411.2295836.4988904181656691611.stgit@frogsfrogsfrogs> Precedence: bulk MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit
Series	[01/52] xfs: create incore realtime group structures \| expand [01/52] xfs: create incore realtime group structures [02/52] xfs: define locking primitives for realtime groups [03/52] xfs: add a lockdep class key for rtgroup inodes [04/52] xfs: support caching rtgroup metadata inodes [05/52] xfs: add a xfs_bmap_free_rtblocks helper [06/52] xfs: move RT bitmap and summary information to the rtgroup [07/52] xfs: support creating per-RTG files in growfs [08/52] xfs: refactor xfs_rtbitmap_blockcount [09/52] xfs: refactor xfs_rtsummary_blockcount [10/52] xfs: make RT extent numbers relative to the rtgroup [11/52] libfrog: add memchr_inv [12/52] xfs: define the format of rt groups [13/52] xfs: update realtime super every time we update the primary fs super [14/52] xfs: export realtime group geometry via XFS_FSOP_GEOM [15/52] xfs: check that rtblock extents do not break rtsupers or rtgroups [16/52] xfs: add a helper to prevent bmap merges across rtgroup boundaries [17/52] xfs: add frextents to the lazysbcounters when rtgroups enabled [18/52] xfs: record rt group metadata errors in the health system [19/52] xfs: export the geometry of realtime groups to userspace [20/52] xfs: add block headers to realtime bitmap and summary blocks [21/52] xfs: encode the rtbitmap in big endian format [22/52] xfs: encode the rtsummary in big endian format [23/52] xfs: grow the realtime section when realtime groups are enabled [24/52] xfs: support logging EFIs for realtime extents [25/52] xfs: support error injection when freeing rt extents [26/52] xfs: use realtime EFI to free extents when rtgroups are enabled [27/52] xfs: don't merge ioends across RTGs [28/52] xfs: make the RT allocator rtgroup aware [29/52] xfs: scrub the realtime group superblock [30/52] xfs: scrub metadir paths for rtgroup metadata [31/52] xfs: mask off the rtbitmap and summary inodes when metadir in use [32/52] xfs: create helpers to deal with rounding xfs_fileoff_t to rtx boundaries [33/52] xfs: create helpers to deal with rounding xfs_filblks_t to rtx boundaries [34/52] xfs: make xfs_rtblock_t a segmented address like xfs_fsblock_t [35/52] xfs: adjust min_block usage in xfs_verify_agbno [36/52] xfs: move the min and max group block numbers to xfs_group [37/52] xfs: implement busy extent tracking for rtgroups [38/52] xfs: use metadir for quota inodes [39/52] xfs: scrub quota file metapaths [40/52] xfs: enable metadata directory feature [41/52] xfs: convert struct typedefs in xfs_ondisk.h [42/52] xfs: separate space btree structures in xfs_ondisk.h [43/52] xfs: port ondisk structure checks from xfs/122 to the kernel [44/52] xfs: remove unknown compat feature check in superblock write validation [45/52] xfs: fix sparse inode limits on runt AG [46/52] xfs: switch to multigrain timestamps [47/52] xfs: don't call xfs_bmap_same_rtgroup in xfs_bmap_add_extent_hole_delay [48/52] xfs: return a 64-bit block count from xfs_btree_count_blocks [49/52] xfs: fix error bailout in xfs_rtginode_create [50/52] xfs: update btree keys correctly when _insrec splits an inode root block [51/52] xfs: fix sb_spino_align checks for large fsblock sizes [52/52] xfs: return from xfs_symlink_verify early on V4 filesystems

diff --git a/include/libxfs.h b/include/libxfs.h index df38d875143ed9..5689f58c640168 100644 --- a/include/libxfs.h +++ b/include/libxfs.h @@ -98,6 +98,7 @@ struct iomap; #include "xfs_metafile.h" #include "xfs_metadir.h" #include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" #ifndef ARRAY_SIZE #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/include/xfs_mount.h b/include/xfs_mount.h index 7406825cf7f57a..31ac60d93c61cc 100644 --- a/include/xfs_mount.h +++ b/include/xfs_mount.h @@ -248,12 +248,14 @@ __XFS_HAS_FEAT(metadir, METADIR) static inline bool xfs_has_rtgroups(struct xfs_mount *mp) { - return false; + /* all metadir file systems also allow rtgroups */ + return xfs_has_metadir(mp); } static inline bool xfs_has_rtsb(struct xfs_mount *mp) { - return false; + /* all rtgroups filesystems with an rt section have an rtsb */ + return xfs_has_rtgroups(mp) && xfs_has_realtime(mp); } /* Kernel mount features that we don't support */ diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h index 620cd13b8ef796..1fc9c784b05054 100644 --- a/libxfs/libxfs_priv.h +++ b/libxfs/libxfs_priv.h @@ -53,6 +53,7 @@ #include "libfrog/radix-tree.h" #include "libfrog/bitmask.h" #include "libfrog/div64.h" +#include "libfrog/util.h" #include "atomic.h" #include "spinlock.h" #include "linux-err.h" diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h index 867060d60e8583..3cf044a2d5f2a9 100644 --- a/libxfs/xfs_format.h +++ b/libxfs/xfs_format.h @@ -265,8 +265,15 @@ struct xfs_dsb { uuid_t sb_meta_uuid; /* metadata file system unique id */ __be64 sb_metadirino; /* metadata directory tree root */ + __be32 sb_rgcount; /* # of realtime groups */ + __be32 sb_rgextents; /* size of rtgroup in rtx */ - /* must be padded to 64 bit alignment */ + /* + * The size of this structure must be padded to 64 bit alignment. + * + * NOTE: Don't forget to update secondary_sb_whack in xfs_repair when + * adding new fields here. + */ }; #define XFS_SB_CRC_OFF offsetof(struct xfs_dsb, sb_crc) @@ -716,6 +723,39 @@ union xfs_suminfo_raw { __u32 old; }; +/* + * Realtime allocation groups break the rt section into multiple pieces that + * could be locked independently. Realtime block group numbers are 32-bit + * quantities. Block numbers within a group are also 32-bit quantities, but + * the upper bit must never be set. rtgroup 0 might have a superblock in it, + * so the minimum size of an rtgroup is 2 rtx. + */ +#define XFS_MAX_RGBLOCKS ((xfs_rgblock_t)(1U << 31) - 1) +#define XFS_MIN_RGEXTENTS ((xfs_rtxlen_t)2) +#define XFS_MAX_RGNUMBER ((xfs_rgnumber_t)(-1U)) + +#define XFS_RTSB_MAGIC 0x46726F67 /* 'Frog' */ + +/* + * Realtime superblock - on disk version. Must be padded to 64 bit alignment. + * The first block of the realtime volume contains this superblock. + */ +struct xfs_rtsb { + __be32 rsb_magicnum; /* magic number == XFS_RTSB_MAGIC */ + __le32 rsb_crc; /* superblock crc */ + + __be32 rsb_pad; /* zero */ + unsigned char rsb_fname[XFSLABEL_MAX]; /* file system name */ + + uuid_t rsb_uuid; /* user-visible file system unique id */ + uuid_t rsb_meta_uuid; /* metadata file system unique id */ + + /* must be padded to 64 bit alignment */ +}; + +#define XFS_RTSB_CRC_OFF offsetof(struct xfs_rtsb, rsb_crc) +#define XFS_RTSB_DADDR ((xfs_daddr_t)0) /* daddr in rt section */ + /* * XFS Timestamps * ============== diff --git a/libxfs/xfs_ondisk.h b/libxfs/xfs_ondisk.h index 8bca86e350fdc1..38b314113d8f24 100644 --- a/libxfs/xfs_ondisk.h +++ b/libxfs/xfs_ondisk.h @@ -37,7 +37,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_dinode, 176); XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot, 104); XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk, 136); - XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 272); + XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 280); XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec, 16); @@ -53,6 +53,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t, 4); XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t, 4); XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb, 56); /* dir/attr trees */ XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr, 80); diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c index edcfb09e29fa18..84ca5447ca770f 100644 --- a/libxfs/xfs_rtbitmap.c +++ b/libxfs/xfs_rtbitmap.c @@ -1155,6 +1155,21 @@ xfs_rtbitmap_blockcount_len( return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize); } +/* How many rt extents does each rtbitmap file track? */ +static inline xfs_rtbxlen_t +xfs_rtbitmap_bitcount( + struct xfs_mount *mp) +{ + if (!mp->m_sb.sb_rextents) + return 0; + + /* rtgroup size can be nonzero even if rextents is zero */ + if (xfs_has_rtgroups(mp)) + return mp->m_sb.sb_rgextents; + + return mp->m_sb.sb_rextents; +} + /* * Compute the number of rtbitmap blocks used for a given file system. */ @@ -1162,7 +1177,7 @@ xfs_filblks_t xfs_rtbitmap_blockcount( struct xfs_mount *mp) { - return xfs_rtbitmap_blockcount_len(mp, mp->m_sb.sb_rextents); + return xfs_rtbitmap_blockcount_len(mp, xfs_rtbitmap_bitcount(mp)); } /* @@ -1176,8 +1191,7 @@ xfs_rtsummary_blockcount( { unsigned long long rsumwords; - *rsumlevels = xfs_compute_rextslog(mp->m_sb.sb_rextents) + 1; - + *rsumlevels = xfs_compute_rextslog(xfs_rtbitmap_bitcount(mp)) + 1; rsumwords = xfs_rtbitmap_blockcount(mp) * (*rsumlevels); return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG); } diff --git a/libxfs/xfs_rtgroup.c b/libxfs/xfs_rtgroup.c index 4f2e6be2ae48cc..e294a295b3d0d8 100644 --- a/libxfs/xfs_rtgroup.c +++ b/libxfs/xfs_rtgroup.c @@ -480,3 +480,84 @@ xfs_rtginode_load_parent( return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups", XFS_METAFILE_DIR, &mp->m_rtdirip); } + +/* Check superblock fields for a read or a write. */ +static xfs_failaddr_t +xfs_rtsb_verify_common( + struct xfs_buf *bp) +{ + struct xfs_rtsb *rsb = bp->b_addr; + + if (!xfs_verify_magic(bp, rsb->rsb_magicnum)) + return __this_address; + if (rsb->rsb_pad) + return __this_address; + + /* Everything to the end of the fs block must be zero */ + if (memchr_inv(rsb + 1, 0, BBTOB(bp->b_length) - sizeof(*rsb))) + return __this_address; + + return NULL; +} + +/* Check superblock fields for a read or revalidation. */ +static inline xfs_failaddr_t +xfs_rtsb_verify_all( + struct xfs_buf *bp) +{ + struct xfs_rtsb *rsb = bp->b_addr; + struct xfs_mount *mp = bp->b_mount; + xfs_failaddr_t fa; + + fa = xfs_rtsb_verify_common(bp); + if (fa) + return fa; + + if (memcmp(&rsb->rsb_fname, &mp->m_sb.sb_fname, XFSLABEL_MAX)) + return __this_address; + if (!uuid_equal(&rsb->rsb_uuid, &mp->m_sb.sb_uuid)) + return __this_address; + if (!uuid_equal(&rsb->rsb_meta_uuid, &mp->m_sb.sb_meta_uuid)) + return __this_address; + + return NULL; +} + +static void +xfs_rtsb_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_buf_verify_cksum(bp, XFS_RTSB_CRC_OFF)) { + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + return; + } + + fa = xfs_rtsb_verify_all(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +static void +xfs_rtsb_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtsb_verify_common(bp); + if (fa) { + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + + xfs_buf_update_cksum(bp, XFS_RTSB_CRC_OFF); +} + +const struct xfs_buf_ops xfs_rtsb_buf_ops = { + .name = "xfs_rtsb", + .magic = { 0, cpu_to_be32(XFS_RTSB_MAGIC) }, + .verify_read = xfs_rtsb_read_verify, + .verify_write = xfs_rtsb_write_verify, + .verify_struct = xfs_rtsb_verify_all, +}; diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c index 2a5368c266ee91..3c80413b67f6ec 100644 --- a/libxfs/xfs_sb.c +++ b/libxfs/xfs_sb.c @@ -231,11 +231,22 @@ xfs_validate_sb_read( return 0; } +/* Return the number of extents covered by a single rt bitmap file */ +static xfs_rtbxlen_t +xfs_extents_per_rbm( + struct xfs_sb *sbp) +{ + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) + return sbp->sb_rgextents; + return sbp->sb_rextents; +} + static uint64_t -xfs_sb_calc_rbmblocks( +xfs_expected_rbmblocks( struct xfs_sb *sbp) { - return howmany_64(sbp->sb_rextents, NBBY * sbp->sb_blocksize); + return howmany_64(xfs_extents_per_rbm(sbp), NBBY * sbp->sb_blocksize); } /* Validate the realtime geometry */ @@ -257,7 +268,7 @@ xfs_validate_rt_geometry( if (sbp->sb_rextents == 0 || sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) || sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) || - sbp->sb_rbmblocks != xfs_sb_calc_rbmblocks(sbp)) + sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp)) return false; return true; @@ -338,6 +349,59 @@ xfs_validate_sb_write( return 0; } +static int +xfs_validate_sb_rtgroups( + struct xfs_mount *mp, + struct xfs_sb *sbp) +{ + uint64_t groups; + + if (sbp->sb_rextsize == 0) { + xfs_warn(mp, +"Realtime extent size must not be zero."); + return -EINVAL; + } + + if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) { + xfs_warn(mp, +"Realtime group size (%u) must be less than %u rt extents.", + sbp->sb_rgextents, + XFS_MAX_RGBLOCKS / sbp->sb_rextsize); + return -EINVAL; + } + + if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) { + xfs_warn(mp, +"Realtime group size (%u) must be at least %u rt extents.", + sbp->sb_rgextents, XFS_MIN_RGEXTENTS); + return -EINVAL; + } + + if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) { + xfs_warn(mp, +"Realtime groups (%u) must be less than %u.", + sbp->sb_rgcount, XFS_MAX_RGNUMBER); + return -EINVAL; + } + + groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents); + if (groups != sbp->sb_rgcount) { + xfs_warn(mp, +"Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.", + sbp->sb_rgcount, groups); + return -EINVAL; + } + + /* Exchange-range is required for fsr to work on realtime files */ + if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) { + xfs_warn(mp, +"Realtime groups feature requires exchange-range support."); + return -EINVAL; + } + + return 0; +} + /* Check the validity of the SB. */ STATIC int xfs_validate_sb_common( @@ -349,6 +413,7 @@ xfs_validate_sb_common( uint32_t agcount = 0; uint32_t rem; bool has_dalign; + int error; if (!xfs_verify_magic(bp, dsb->sb_magicnum)) { xfs_warn(mp, @@ -412,6 +477,12 @@ xfs_validate_sb_common( sbp->sb_spino_align); return -EINVAL; } + + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { + error = xfs_validate_sb_rtgroups(mp, sbp); + if (error) + return error; + } } else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) { xfs_notice(mp, @@ -703,13 +774,15 @@ __xfs_sb_from_disk( if (convert_xquota) xfs_sb_quota_from_disk(to); - if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) + if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = be64_to_cpu(from->sb_metadirino); - else + to->sb_rgcount = be32_to_cpu(from->sb_rgcount); + to->sb_rgextents = be32_to_cpu(from->sb_rgextents); + } else { to->sb_metadirino = NULLFSINO; - - to->sb_rgcount = 1; - to->sb_rgextents = 0; + to->sb_rgcount = 1; + to->sb_rgextents = 0; + } } void @@ -858,8 +931,11 @@ xfs_sb_to_disk( if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); - if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) + if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = cpu_to_be64(from->sb_metadirino); + to->sb_rgcount = cpu_to_be32(from->sb_rgcount); + to->sb_rgextents = cpu_to_be32(from->sb_rgextents); + } } /* @@ -999,9 +1075,9 @@ xfs_mount_sb_set_rextsize( mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize); mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize); - mp->m_rgblocks = 0; - mp->m_rgblklog = 0; - mp->m_rgblkmask = (uint64_t)-1; + mp->m_rgblocks = sbp->sb_rgextents * sbp->sb_rextsize; + mp->m_rgblklog = log2_if_power2(mp->m_rgblocks); + mp->m_rgblkmask = mask64_if_power2(mp->m_rgblocks); rgs->blocks = 0; rgs->blklog = 0; diff --git a/libxfs/xfs_shared.h b/libxfs/xfs_shared.h index 33b84a3a83ff63..552365d212ea26 100644 --- a/libxfs/xfs_shared.h +++ b/libxfs/xfs_shared.h @@ -39,6 +39,7 @@ extern const struct xfs_buf_ops xfs_inode_buf_ra_ops; extern const struct xfs_buf_ops xfs_refcountbt_buf_ops; extern const struct xfs_buf_ops xfs_rmapbt_buf_ops; extern const struct xfs_buf_ops xfs_rtbuf_ops; +extern const struct xfs_buf_ops xfs_rtsb_buf_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;

[12/52] xfs: define the format of rt groups

Commit Message

Patch