diff options
Diffstat (limited to 'fs/xfs')
171 files changed, 16838 insertions, 2911 deletions
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index fffd6fffdce0..ae0ca6858496 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -3,7 +3,7 @@ config XFS_FS tristate "XFS filesystem support" depends on BLOCK select EXPORTFS - select LIBCRC32C + select CRC32 select FS_IOMAP help XFS is a high performance journaling filesystem which originated diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index ed9b0dabc1f1..5bf501cf8271 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -51,6 +51,8 @@ xfs-y += $(addprefix libxfs/, \ xfs_rmap_btree.o \ xfs_refcount.o \ xfs_refcount_btree.o \ + xfs_rtrefcount_btree.o \ + xfs_rtrmap_btree.o \ xfs_sb.o \ xfs_symlink_remote.o \ xfs_trans_inode.o \ @@ -62,6 +64,7 @@ xfs-y += $(addprefix libxfs/, \ xfs-$(CONFIG_XFS_RT) += $(addprefix libxfs/, \ xfs_rtbitmap.o \ xfs_rtgroup.o \ + xfs_zones.o \ ) # highlevel code @@ -134,7 +137,11 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ xfs_quotaops.o # xfs_rtbitmap is shared with libxfs -xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o +xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o \ + xfs_zone_alloc.o \ + xfs_zone_gc.o \ + xfs_zone_info.o \ + xfs_zone_space_resv.o xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o @@ -193,6 +200,8 @@ xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rgsuper.o \ rtbitmap.o \ + rtrefcount.o \ + rtrmap.o \ rtsummary.o \ ) @@ -232,6 +241,8 @@ xfs-y += $(addprefix scrub/, \ xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rtbitmap_repair.o \ + rtrefcount_repair.o \ + rtrmap_repair.o \ rtsummary_repair.o \ ) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index b59cb461e096..e6ba914f6d06 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -301,7 +301,7 @@ xfs_get_aghdr_buf( struct xfs_buf *bp; int error; - error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp); + error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, &bp); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index f5d853089019..fb79215a509d 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -114,6 +114,7 @@ xfs_ag_resv_needed( case XFS_AG_RESV_RMAPBT: len -= xfs_perag_resv(pag, type)->ar_reserved; break; + case XFS_AG_RESV_METAFILE: case XFS_AG_RESV_NONE: /* empty */ break; @@ -347,6 +348,7 @@ xfs_ag_resv_alloc_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: @@ -389,6 +391,7 @@ xfs_ag_resv_free_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 3d33e17f2e5c..7839efe050bf 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -33,8 +33,6 @@ struct kmem_cache *xfs_extfree_item_cache; struct workqueue_struct *xfs_alloc_wq; -#define XFS_ABSDIFF(a,b) (((a) <= (b)) ? ((b) - (a)) : ((a) - (b))) - #define XFSA_FIXUP_BNO_OK 1 #define XFSA_FIXUP_CNT_OK 2 @@ -410,8 +408,8 @@ xfs_alloc_compute_diff( if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) { if (newlen1 < newlen2 || (newlen1 == newlen2 && - XFS_ABSDIFF(newbno1, wantbno) > - XFS_ABSDIFF(newbno2, wantbno))) + abs_diff(newbno1, wantbno) > + abs_diff(newbno2, wantbno))) newbno1 = newbno2; } else if (newbno2 != NULLAGBLOCK) newbno1 = newbno2; @@ -427,7 +425,7 @@ xfs_alloc_compute_diff( } else newbno1 = freeend - wantlen; *newbnop = newbno1; - return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno); + return newbno1 == NULLAGBLOCK ? 0 : abs_diff(newbno1, wantbno); } /* diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 17875ad865f5..8c04acd30d48 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1004,9 +1004,7 @@ xfs_attr_add_fork( unsigned int blks; /* space reservation */ int error; /* error return value */ - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); blks = XFS_ADDAFORK_SPACE_RES(mp); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 5255f93bae31..63255820b58a 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -34,13 +34,13 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_icache.h" #include "xfs_iomap.h" #include "xfs_health.h" #include "xfs_bmap_item.h" #include "xfs_symlink_remote.h" #include "xfs_inode_util.h" #include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" struct kmem_cache *xfs_bmap_intent_cache; @@ -171,18 +171,16 @@ xfs_bmbt_update( * Compute the worst-case number of indirect blocks that will be used * for ip's delayed extent of length "len". */ -STATIC xfs_filblks_t +xfs_filblks_t xfs_bmap_worst_indlen( - xfs_inode_t *ip, /* incore inode pointer */ - xfs_filblks_t len) /* delayed extent length */ + struct xfs_inode *ip, /* incore inode pointer */ + xfs_filblks_t len) /* delayed extent length */ { - int level; /* btree level number */ - int maxrecs; /* maximum record count at this level */ - xfs_mount_t *mp; /* mount structure */ - xfs_filblks_t rval; /* return value */ + struct xfs_mount *mp = ip->i_mount; + int maxrecs = mp->m_bmap_dmxr[0]; + int level; + xfs_filblks_t rval; - mp = ip->i_mount; - maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); level++) { @@ -615,7 +613,7 @@ xfs_bmap_btree_to_extents( xfs_trans_binval(tp, cbp); if (cur->bc_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -659,12 +657,11 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); + block = xfs_bmap_broot_realloc(ip, whichfork, 1); /* * Fill in the root. */ - block = ifp->if_broot; xfs_bmbt_init_block(ip, block, NULL, 1, 1); /* * Need a cursor. Can't allocate until bb_level is filled in. @@ -746,7 +743,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ifp->if_format = XFS_DINODE_FMT_EXTENTS; ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); @@ -1043,9 +1040,7 @@ xfs_bmap_add_attrfork( int error; /* error return value */ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); ASSERT(!xfs_inode_has_attr_fork(ip)); @@ -2575,146 +2570,6 @@ done: } /* - * Convert a hole to a delayed allocation. - */ -STATIC void -xfs_bmap_add_extent_hole_delay( - xfs_inode_t *ip, /* incore inode pointer */ - int whichfork, - struct xfs_iext_cursor *icur, - xfs_bmbt_irec_t *new) /* new data to add to file extents */ -{ - struct xfs_ifork *ifp; /* inode fork pointer */ - xfs_bmbt_irec_t left; /* left neighbor extent entry */ - xfs_filblks_t newlen=0; /* new indirect size */ - xfs_filblks_t oldlen=0; /* old indirect size */ - xfs_bmbt_irec_t right; /* right neighbor extent entry */ - uint32_t state = xfs_bmap_fork_to_state(whichfork); - xfs_filblks_t temp; /* temp for indirect calculations */ - - ifp = xfs_ifork_ptr(ip, whichfork); - ASSERT(isnullstartblock(new->br_startblock)); - - /* - * Check and set flags if this segment has a left neighbor - */ - if (xfs_iext_peek_prev_extent(ifp, icur, &left)) { - state |= BMAP_LEFT_VALID; - if (isnullstartblock(left.br_startblock)) - state |= BMAP_LEFT_DELAY; - } - - /* - * Check and set flags if the current (right) segment exists. - * If it doesn't exist, we're converting the hole at end-of-file. - */ - if (xfs_iext_get_extent(ifp, icur, &right)) { - state |= BMAP_RIGHT_VALID; - if (isnullstartblock(right.br_startblock)) - state |= BMAP_RIGHT_DELAY; - } - - /* - * Set contiguity flags on the left and right neighbors. - * Don't let extents get too large, even if the pieces are contiguous. - */ - if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) && - left.br_startoff + left.br_blockcount == new->br_startoff && - left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN) - state |= BMAP_LEFT_CONTIG; - - if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) && - new->br_startoff + new->br_blockcount == right.br_startoff && - new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN && - (!(state & BMAP_LEFT_CONTIG) || - (left.br_blockcount + new->br_blockcount + - right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))) - state |= BMAP_RIGHT_CONTIG; - - /* - * Switch out based on the contiguity flags. - */ - switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { - case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: - /* - * New allocation is contiguous with delayed allocations - * on the left and on the right. - * Merge all three into a single extent record. - */ - temp = left.br_blockcount + new->br_blockcount + - right.br_blockcount; - - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock) + - startblockval(right.br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - left.br_startblock = nullstartblock(newlen); - left.br_blockcount = temp; - - xfs_iext_remove(ip, icur, state); - xfs_iext_prev(ifp, icur); - xfs_iext_update_extent(ip, state, icur, &left); - break; - - case BMAP_LEFT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the left. - * Merge the new allocation with the left neighbor. - */ - temp = left.br_blockcount + new->br_blockcount; - - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - left.br_blockcount = temp; - left.br_startblock = nullstartblock(newlen); - - xfs_iext_prev(ifp, icur); - xfs_iext_update_extent(ip, state, icur, &left); - break; - - case BMAP_RIGHT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the right. - * Merge the new allocation with the right neighbor. - */ - temp = new->br_blockcount + right.br_blockcount; - oldlen = startblockval(new->br_startblock) + - startblockval(right.br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - right.br_startoff = new->br_startoff; - right.br_startblock = nullstartblock(newlen); - right.br_blockcount = temp; - xfs_iext_update_extent(ip, state, icur, &right); - break; - - case 0: - /* - * New allocation is not contiguous with another - * delayed allocation. - * Insert a new entry. - */ - oldlen = newlen = 0; - xfs_iext_insert(ip, icur, new, state); - break; - } - if (oldlen != newlen) { - ASSERT(oldlen > newlen); - xfs_add_fdblocks(ip->i_mount, oldlen - newlen); - - /* - * Nothing to do for disk quota accounting here. - */ - xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen); - } -} - -/* * Convert a hole to a real allocation. */ STATIC int /* error */ @@ -3566,12 +3421,12 @@ xfs_bmap_btalloc_at_eof( int error; /* - * If there are already extents in the file, try an exact EOF block - * allocation to extend the file as a contiguous extent. If that fails, - * or it's the first allocation in a file, just try for a stripe aligned - * allocation. + * If there are already extents in the file, and xfs_bmap_adjacent() has + * given a better blkno, try an exact EOF block allocation to extend the + * file as a contiguous extent. If that fails, or it's the first + * allocation in a file, just try for a stripe aligned allocation. */ - if (ap->offset) { + if (ap->eof) { xfs_extlen_t nextminlen = 0; /* @@ -3739,7 +3594,8 @@ xfs_bmap_btalloc_best_length( int error; ap->blkno = XFS_INO_TO_FSB(args->mp, ap->ip->i_ino); - xfs_bmap_adjacent(ap); + if (!xfs_bmap_adjacent(ap)) + ap->eof = false; /* * Search for an allocation group with a single extent large enough for @@ -4041,144 +3897,6 @@ xfs_bmapi_read( return 0; } -/* - * Add a delayed allocation extent to an inode. Blocks are reserved from the - * global pool and the extent inserted into the inode in-core extent tree. - * - * On entry, got refers to the first extent beyond the offset of the extent to - * allocate or eof is specified if no such extent exists. On return, got refers - * to the extent record that was inserted to the inode fork. - * - * Note that the allocated extent may have been merged with contiguous extents - * during insertion into the inode fork. Thus, got does not reflect the current - * state of the inode fork on return. If necessary, the caller can use lastx to - * look up the updated record in the inode fork. - */ -int -xfs_bmapi_reserve_delalloc( - struct xfs_inode *ip, - int whichfork, - xfs_fileoff_t off, - xfs_filblks_t len, - xfs_filblks_t prealloc, - struct xfs_bmbt_irec *got, - struct xfs_iext_cursor *icur, - int eof) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); - xfs_extlen_t alen; - xfs_extlen_t indlen; - uint64_t fdblocks; - int error; - xfs_fileoff_t aoff; - bool use_cowextszhint = - whichfork == XFS_COW_FORK && !prealloc; - -retry: - /* - * Cap the alloc length. Keep track of prealloc so we know whether to - * tag the inode before we return. - */ - aoff = off; - alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN); - if (!eof) - alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff); - if (prealloc && alen >= len) - prealloc = alen - len; - - /* - * If we're targetting the COW fork but aren't creating a speculative - * posteof preallocation, try to expand the reservation to align with - * the COW extent size hint if there's sufficient free space. - * - * Unlike the data fork, the CoW cancellation functions will free all - * the reservations at inactivation, so we don't require that every - * delalloc reservation have a dirty pagecache. - */ - if (use_cowextszhint) { - struct xfs_bmbt_irec prev; - xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip); - - if (!xfs_iext_peek_prev_extent(ifp, icur, &prev)) - prev.br_startoff = NULLFILEOFF; - - error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof, - 1, 0, &aoff, &alen); - ASSERT(!error); - } - - /* - * Make a transaction-less quota reservation for delayed allocation - * blocks. This number gets adjusted later. We return if we haven't - * allocated blocks already inside this loop. - */ - error = xfs_quota_reserve_blkres(ip, alen); - if (error) - goto out; - - /* - * Split changing sb for alen and indlen since they could be coming - * from different places. - */ - indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen); - ASSERT(indlen > 0); - - fdblocks = indlen; - if (XFS_IS_REALTIME_INODE(ip)) { - error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen)); - if (error) - goto out_unreserve_quota; - } else { - fdblocks += alen; - } - - error = xfs_dec_fdblocks(mp, fdblocks, false); - if (error) - goto out_unreserve_frextents; - - ip->i_delayed_blks += alen; - xfs_mod_delalloc(ip, alen, indlen); - - got->br_startoff = aoff; - got->br_startblock = nullstartblock(indlen); - got->br_blockcount = alen; - got->br_state = XFS_EXT_NORM; - - xfs_bmap_add_extent_hole_delay(ip, whichfork, icur, got); - - /* - * Tag the inode if blocks were preallocated. Note that COW fork - * preallocation can occur at the start or end of the extent, even when - * prealloc == 0, so we must also check the aligned offset and length. - */ - if (whichfork == XFS_DATA_FORK && prealloc) - xfs_inode_set_eofblocks_tag(ip); - if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) - xfs_inode_set_cowblocks_tag(ip); - - return 0; - -out_unreserve_frextents: - if (XFS_IS_REALTIME_INODE(ip)) - xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen)); -out_unreserve_quota: - if (XFS_IS_QUOTA_ON(mp)) - xfs_quota_unreserve_blkres(ip, alen); -out: - if (error == -ENOSPC || error == -EDQUOT) { - trace_xfs_delalloc_enospc(ip, off, len); - - if (prealloc || use_cowextszhint) { - /* retry without any preallocation */ - use_cowextszhint = false; - prealloc = 0; - goto retry; - } - } - return error; -} - static int xfs_bmapi_allocate( struct xfs_bmalloca *bma) @@ -4567,8 +4285,9 @@ xfs_bmapi_write( * the refcount btree for orphan recovery. */ if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, - bma.length); + xfs_refcount_alloc_cow_extent(tp, + XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); } /* Deal with the allocated space we found. */ @@ -4743,7 +4462,8 @@ xfs_bmapi_convert_one_delalloc( *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length); + xfs_refcount_alloc_cow_extent(tp, XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, whichfork); @@ -4948,7 +4668,8 @@ xfs_bmap_del_extent_delay( int whichfork, struct xfs_iext_cursor *icur, struct xfs_bmbt_irec *got, - struct xfs_bmbt_irec *del) + struct xfs_bmbt_irec *del, + uint32_t bflags) /* bmapi flags */ { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); @@ -5068,10 +4789,18 @@ xfs_bmap_del_extent_delay( da_diff = da_old - da_new; fdblocks = da_diff; - if (isrt) - xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount)); - else + if (bflags & XFS_BMAPI_REMAP) { + ; + } else if (isrt) { + xfs_rtbxlen_t rtxlen; + + rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount); + if (xfs_is_zoned_inode(ip)) + xfs_zoned_add_available(mp, rtxlen); + xfs_add_frextents(mp, rtxlen); + } else { fdblocks += del->br_blockcount; + } xfs_add_fdblocks(mp, fdblocks); xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff); @@ -5391,7 +5120,7 @@ xfs_bmap_del_extent_real( bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { - xfs_refcount_decrease_extent(tp, del); + xfs_refcount_decrease_extent(tp, isrt, del); } else if (isrt && !xfs_has_rtgroups(mp)) { error = xfs_bmap_free_rtblocks(tp, del); } else { @@ -5670,7 +5399,8 @@ __xfs_bunmapi( delete: if (wasdel) { - xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del); + xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, + &del, flags); } else { error = xfs_bmap_del_extent_real(ip, tp, &icur, cur, &del, &tmp_logflags, whichfork, @@ -6501,9 +6231,8 @@ xfs_get_extsz_hint( * No point in aligning allocations if we need to COW to actually * write to them. */ - if (xfs_is_always_cow_inode(ip)) - return 0; - if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) + if (!xfs_is_always_cow_inode(ip) && + (ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) return ip->i_extsize; if (XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1) @@ -6526,7 +6255,13 @@ xfs_get_cowextsz_hint( a = 0; if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) a = ip->i_cowextsize; - b = xfs_get_extsz_hint(ip); + if (XFS_IS_REALTIME_INODE(ip)) { + b = 0; + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) + b = ip->i_extsize; + } else { + b = xfs_get_extsz_hint(ip); + } a = max(a, b); if (a == 0) diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 4b721d935994..b4d9c6e0f3f9 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -204,7 +204,7 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extnum_t nexts, int *done); void xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got, - struct xfs_bmbt_irec *del); + struct xfs_bmbt_irec *del, uint32_t bflags); void xfs_bmap_del_extent_cow(struct xfs_inode *ip, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); @@ -219,10 +219,6 @@ int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *done, xfs_fileoff_t stop_fsb); int xfs_bmap_split_extent(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t split_offset); -int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork, - xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc, - struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur, - int eof); int xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork, xfs_off_t offset, struct iomap *iomap, unsigned int *seq); int xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp, @@ -233,6 +229,7 @@ xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip, int fork); int xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap, struct xfs_alloc_arg *args); +xfs_filblks_t xfs_bmap_worst_indlen(struct xfs_inode *ip, xfs_filblks_t len); enum xfs_bmap_intent_type { XFS_BMAP_MAP = 1, diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 3464be771f95..908d7b050e9c 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -516,6 +516,116 @@ xfs_bmbt_keys_contiguous( be64_to_cpu(key2->bmbt.br_startoff)); } +static inline void +xfs_bmbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_bmbt_ptr_t)); +} + +/* + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. + * + * The caller must not request to add more records than would fit in the + * on-disk inode root. If the if_broot is currently NULL, then if we are + * adding records, one will be allocated. The caller must also not request + * that the number of records go below zero, although it can go to zero. + * + * ip -- the inode whose if_broot area is changing + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. + */ +struct xfs_btree_block * +xfs_bmap_broot_realloc( + struct xfs_inode *ip, + int whichfork, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + + /* + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. + */ + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just + * allocate it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need + * to realloc() it and shift the pointers to their new + * location. The records don't change location because + * they are kept butted up against the btree block header. + */ + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + xfs_bmbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs); + return broot; + } + + /* + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); + + /* + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. + */ + xfs_bmbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + return broot; +} + +static struct xfs_btree_block * +xfs_bmbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + new_numrecs); +} + const struct xfs_btree_ops xfs_bmbt_ops = { .name = "bmap", .type = XFS_BTREE_TYPE_INODE, @@ -543,6 +653,7 @@ const struct xfs_btree_ops xfs_bmbt_ops = { .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, .keys_contiguous = xfs_bmbt_keys_contiguous, + .broot_realloc = xfs_bmbt_broot_realloc, }; /* diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h index 49a3bae3f6ec..b238d559ab03 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.h +++ b/fs/xfs/libxfs/xfs_bmap_btree.h @@ -198,4 +198,7 @@ xfs_bmap_bmdr_space(struct xfs_btree_block *bb) return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); } +struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, + int whichfork, unsigned int new_numrecs); + #endif /* __XFS_BMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 68ee1c299c25..299ce7fd11b0 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -30,6 +30,12 @@ #include "xfs_health.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap.h" +#include "xfs_rmap.h" +#include "xfs_quota.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" /* * Btree magic numbers. @@ -1537,12 +1543,16 @@ xfs_btree_log_recs( int first, int last) { + if (!bp) { + xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, + xfs_ilog_fbroot(cur->bc_ino.whichfork)); + return; + } xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_rec_offset(cur, first), xfs_btree_rec_offset(cur, last + 1) - 1); - } /* @@ -3078,6 +3088,131 @@ xfs_btree_split( #define xfs_btree_split __xfs_btree_split #endif /* __KERNEL__ */ +/* Move the records from a root leaf block to a separate block. */ +STATIC void +xfs_btree_promote_leaf_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + union xfs_btree_key *kp; + union xfs_btree_ptr *pp; + struct xfs_btree_block *broot; + int numrecs = xfs_btree_get_numrecs(block); + + /* Copy the records from the leaf broot into the new child block. */ + rp = xfs_btree_rec_addr(cur, 1, block); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, crp, rp, numrecs); + + /* + * Increment the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * leaf to a node block. Free the existing leaf broot so that nobody + * thinks we need to migrate node pointers when we realloc the broot + * buffer after bumping nlevels. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels++; + cur->bc_levels[1].ptr = 1; + + /* + * Allocate a new node broot and initialize it to point to the new + * child block. + */ + broot = cur->bc_ops->broot_realloc(cur, 1); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, + cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino); + + pp = xfs_btree_ptr_addr(cur, 1, broot); + kp = xfs_btree_key_addr(cur, 1, broot); + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, 0, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_recs(cur, cbp, 1, numrecs); +} + +/* + * Move the keys and pointers from a root block to a separate block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_promote_node_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + int numrecs = xfs_btree_get_numrecs(block); + + /* + * Increase tree height, adjusting the root block level to match. + * We cannot change the root btree node size until we've copied the + * block contents to the new child block. + */ + be16_add_cpu(&block->bb_level, 1); + cur->bc_nlevels++; + cur->bc_levels[level + 1].ptr = 1; + + /* + * Adjust the root btree record count, then copy the keys from the old + * root to the new child block. + */ + xfs_btree_set_numrecs(block, 1); + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, ckp, kp, numrecs); + + /* Check the pointers and copy them to the new child block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, cpp, pp, numrecs); + + /* + * Set the first keyptr to point to the new child block, then shrink + * the memory buffer for the root block. + */ + error = xfs_btree_debug_check_ptr(cur, cptr, 0, level); + if (error) + return error; + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + cur->bc_ops->broot_realloc(cur, 1); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, level, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_keys(cur, cbp, 1, numrecs); + xfs_btree_log_ptrs(cur, cbp, 1, numrecs); + return 0; +} + /* * Copy the old inode root contents into a real block and make the * broot point to it. @@ -3091,14 +3226,10 @@ xfs_btree_new_iroot( struct xfs_buf *cbp; /* buffer for cblock */ struct xfs_btree_block *block; /* btree block */ struct xfs_btree_block *cblock; /* child btree block */ - union xfs_btree_key *ckp; /* child key pointer */ - union xfs_btree_ptr *cpp; /* child ptr pointer */ - union xfs_btree_key *kp; /* pointer to btree key */ - union xfs_btree_ptr *pp; /* pointer to block addr */ + union xfs_btree_ptr aptr; union xfs_btree_ptr nptr; /* new block addr */ int level; /* btree level */ int error; /* error return code */ - int i; /* loop counter */ XFS_BTREE_STATS_INC(cur, newroot); @@ -3107,10 +3238,15 @@ xfs_btree_new_iroot( level = cur->bc_nlevels - 1; block = xfs_btree_get_iroot(cur); - pp = xfs_btree_ptr_addr(cur, 1, block); + ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)); + if (level > 0) + aptr = *xfs_btree_ptr_addr(cur, 1, block); + else + aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp, + cur->bc_ino.ip->i_ino)); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = xfs_btree_alloc_block(cur, pp, &nptr, stat); + error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat); if (error) goto error0; if (*stat == 0) @@ -3136,47 +3272,16 @@ xfs_btree_new_iroot( cblock->bb_u.s.bb_blkno = bno; } - be16_add_cpu(&block->bb_level, 1); - xfs_btree_set_numrecs(block, 1); - cur->bc_nlevels++; - ASSERT(cur->bc_nlevels <= cur->bc_maxlevels); - cur->bc_levels[level + 1].ptr = 1; - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock)); - - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) { - error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (level > 0) { + error = xfs_btree_promote_node_iroot(cur, block, level, cbp, + &nptr, cblock); if (error) goto error0; + } else { + xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock); } - xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock)); - - error = xfs_btree_debug_check_ptr(cur, &nptr, 0, level); - if (error) - goto error0; - - xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - - xfs_iroot_realloc(cur->bc_ino.ip, - 1 - xfs_btree_get_numrecs(cblock), - cur->bc_ino.whichfork); - - xfs_btree_setbuf(cur, level, cbp); - - /* - * Do all this logging at the end so that - * the root is at the right level. - */ - xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); - xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - - *logflags |= - XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); + *logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); *stat = 1; return 0; error0: @@ -3347,7 +3452,7 @@ xfs_btree_make_block_unfull( if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3693,6 +3798,97 @@ error0: return error; } +/* Move the records from a child leaf block to the root block. */ +STATIC void +xfs_btree_demote_leaf_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int numrecs) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + struct xfs_btree_block *broot; + + /* + * Decrease the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * node to a leaf. Free the old node broot so that we can get a fresh + * leaf broot. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels--; + + /* + * Allocate a new leaf broot and copy the records from the old child. + * Detach the old child from the cursor. + */ + broot = cur->bc_ops->broot_realloc(cur, numrecs); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs, + cur->bc_ino.ip->i_ino); + + rp = xfs_btree_rec_addr(cur, 1, broot); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, rp, crp, numrecs); + + cur->bc_levels[0].bp = NULL; +} + +/* + * Move the keyptrs from a child node block to the root block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_demote_node_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int level, + int numrecs) +{ + struct xfs_btree_block *block; + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + + /* + * Adjust the root btree node size and the record count to match the + * doomed child so that we can copy the keyptrs ahead of changing the + * tree shape. + */ + block = cur->bc_ops->broot_realloc(cur, numrecs); + + xfs_btree_set_numrecs(block, numrecs); + ASSERT(block->bb_numrecs == cblock->bb_numrecs); + + /* Copy keys from the doomed block. */ + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, kp, ckp, numrecs); + + /* Copy pointers from the doomed block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + + /* Decrease tree height, adjusting the root block level to match. */ + cur->bc_levels[level - 1].bp = NULL; + be16_add_cpu(&block->bb_level, -1); + cur->bc_nlevels--; + return 0; +} + /* * Try to merge a non-leaf block back into the inode root. * @@ -3705,34 +3901,31 @@ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { - int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; - union xfs_btree_key *kp; - union xfs_btree_key *ckp; - union xfs_btree_ptr *pp; - union xfs_btree_ptr *cpp; struct xfs_buf *cbp; int level; - int index; int numrecs; int error; #ifdef DEBUG union xfs_btree_ptr ptr; #endif - int i; ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); - ASSERT(cur->bc_nlevels > 1); + ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) || + cur->bc_nlevels > 1); /* * Don't deal with the root block needs to be a leaf case. * We're just going to turn the thing back into extents anyway. */ level = cur->bc_nlevels - 1; - if (level == 1) + if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) + goto out0; + + /* If we're already a leaf, jump out. */ + if (level == 0) goto out0; /* @@ -3762,40 +3955,20 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - index = numrecs - cur->bc_ops->get_maxrecs(cur, level); - if (index) { - xfs_iroot_realloc(cur->bc_ino.ip, index, - cur->bc_ino.whichfork); - block = ifp->if_broot; - } - - be16_add_cpu(&block->bb_numrecs, index); - ASSERT(block->bb_numrecs == cblock->bb_numrecs); - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, kp, ckp, numrecs); - - pp = xfs_btree_ptr_addr(cur, 1, block); - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - - for (i = 0; i < numrecs; i++) { - error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (level > 1) { + error = xfs_btree_demote_node_child(cur, cblock, level, + numrecs); if (error) return error; - } - - xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + } else + xfs_btree_demote_leaf_child(cur, cblock, numrecs); error = xfs_btree_free_block(cur, cbp); if (error) return error; - cur->bc_levels[level - 1].bp = NULL; - be16_add_cpu(&block->bb_level, -1); xfs_trans_log_inode(cur->bc_tp, ip, XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork)); - cur->bc_nlevels--; out0: return 0; } @@ -3949,10 +4122,10 @@ xfs_btree_delrec( /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's - * nothing left to do. + * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { - xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs); error = xfs_btree_kill_iroot(cur); if (error) @@ -5360,6 +5533,12 @@ xfs_btree_init_cur_caches(void) error = xfs_refcountbt_init_cur_cache(); if (error) goto err; + error = xfs_rtrmapbt_init_cur_cache(); + if (error) + goto err; + error = xfs_rtrefcountbt_init_cur_cache(); + if (error) + goto err; return 0; err: @@ -5376,6 +5555,8 @@ xfs_btree_destroy_cur_caches(void) xfs_bmbt_destroy_cur_cache(); xfs_rmapbt_destroy_cur_cache(); xfs_refcountbt_destroy_cur_cache(); + xfs_rtrmapbt_destroy_cur_cache(); + xfs_rtrefcountbt_destroy_cur_cache(); } /* Move the btree cursor before the first record. */ @@ -5404,3 +5585,67 @@ xfs_btree_goto_left_edge( return 0; } + +/* Allocate a block for an inode-rooted metadata btree. */ +int +xfs_btree_alloc_metafile_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfs_alloc_arg args = { + .mp = cur->bc_mp, + .tp = cur->bc_tp, + .resv = XFS_AG_RESV_METAFILE, + .minlen = 1, + .maxlen = 1, + .prod = 1, + }; + struct xfs_inode *ip = cur->bc_ino.ip; + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino)); + if (error) + return error; + if (args.fsbno == NULLFSBLOCK) { + *stat = 0; + return 0; + } + ASSERT(args.len == 1); + + xfs_metafile_resv_alloc_space(ip, &args); + + new->l = cpu_to_be64(args.fsbno); + *stat = 1; + return 0; +} + +/* Free a block from an inode-rooted metadata btree. */ +int +xfs_btree_free_metafile_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfs_owner_info oinfo; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip = cur->bc_ino.ip; + struct xfs_trans *tp = cur->bc_tp; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE, + 0); + if (error) + return error; + + xfs_metafile_resv_free_space(ip, tp, 1); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index c5bff273cae2..355b304696e6 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -135,7 +135,7 @@ struct xfs_btree_ops { /* offset of btree stats array */ unsigned int statoff; - /* sick mask for health reporting (only for XFS_BTREE_TYPE_AG) */ + /* sick mask for health reporting (not for bmap btrees) */ unsigned int sick_mask; /* cursor operations */ @@ -213,11 +213,27 @@ struct xfs_btree_ops { const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask); + + /* + * Reallocate the space for if_broot to fit the number of records. + * Move the records and pointers in if_broot to fit the new size. When + * shrinking this will eliminate holes between the records and pointers + * created by the caller. When growing this will create holes to be + * filled in by the caller. + * + * The caller must not request to add more records than would fit in + * the on-disk inode root. If the if_broot is currently NULL, then if + * we are adding records, one will be allocated. The caller must also + * not request that the number of records go below zero, although it + * can go to zero. + */ + struct xfs_btree_block *(*broot_realloc)(struct xfs_btree_cur *cur, + unsigned int new_numrecs); }; /* btree geometry flags */ #define XFS_BTGEO_OVERLAPPING (1U << 0) /* overlapping intervals */ - +#define XFS_BTGEO_IROOT_RECORDS (1U << 1) /* iroot can store records */ union xfs_btree_irec { struct xfs_alloc_rec_incore a; @@ -281,7 +297,7 @@ struct xfs_btree_cur struct { unsigned int nr_ops; /* # record updates */ unsigned int shape_changes; /* # of extent splits */ - } bc_refc; /* refcountbt */ + } bc_refc; /* refcountbt/rtrefcountbt */ }; /* Must be at the end of the struct! */ @@ -687,4 +703,10 @@ xfs_btree_at_iroot( level == cur->bc_nlevels - 1; } +int xfs_btree_alloc_metafile_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *newp, + int *stat); +int xfs_btree_free_metafile_block(struct xfs_btree_cur *cur, + struct xfs_buf *bp); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index df3d613675a1..f2f7b4305413 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -18,6 +18,7 @@ #include "xfs_ag.h" #include "xfs_buf_item.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" /* Set the root of an in-memory btree. */ void diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index 694929703152..5ed84f9cc877 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -134,6 +134,7 @@ xfs_btree_stage_ifakeroot( cur->bc_ino.ifake = ifake; cur->bc_nlevels = ifake->if_levels; cur->bc_ino.forksize = ifake->if_fork_size; + cur->bc_ino.whichfork = XFS_STAGING_FORK; cur->bc_flags |= XFS_BTREE_STAGING; } @@ -573,6 +574,7 @@ xfs_btree_bload_compute_geometry( struct xfs_btree_bload *bbl, uint64_t nr_records) { + const struct xfs_btree_ops *ops = cur->bc_ops; uint64_t nr_blocks = 0; uint64_t nr_this_level; @@ -599,7 +601,7 @@ xfs_btree_bload_compute_geometry( xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level, &avg_per_block, &level_blocks, &dontcare64); - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + if (ops->type == XFS_BTREE_TYPE_INODE) { /* * If all the items we want to store at this level * would fit in the inode root block, then we have our @@ -607,7 +609,9 @@ xfs_btree_bload_compute_geometry( * * Note that bmap btrees forbid records in the root. */ - if (level != 0 && nr_this_level <= avg_per_block) { + if ((level != 0 || + (ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) && + nr_this_level <= avg_per_block) { nr_blocks++; break; } @@ -658,7 +662,7 @@ xfs_btree_bload_compute_geometry( return -EOVERFLOW; bbl->btree_height = cur->bc_nlevels; - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) + if (ops->type == XFS_BTREE_TYPE_INODE) bbl->nr_blocks = nr_blocks - 1; else bbl->nr_blocks = nr_blocks; diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index ec51b8465e61..9effd95ddcd4 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -68,7 +68,9 @@ struct xfs_defer_op_type { extern const struct xfs_defer_op_type xfs_bmap_update_defer_type; extern const struct xfs_defer_op_type xfs_refcount_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type; extern const struct xfs_defer_op_type xfs_rmap_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrmap_update_defer_type; extern const struct xfs_defer_op_type xfs_extent_free_defer_type; extern const struct xfs_defer_op_type xfs_agfl_free_defer_type; extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type; diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 202468223bf9..1775abcfa04d 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -197,7 +197,7 @@ xfs_da_unmount( /* * Return 1 if directory contains only "." and "..". */ -int +static bool xfs_dir_isempty( xfs_inode_t *dp) { @@ -205,9 +205,9 @@ xfs_dir_isempty( ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_disk_size == 0) /* might happen during shutdown. */ - return 1; + return true; if (dp->i_disk_size > xfs_inode_data_fork_size(dp)) - return 0; + return false; sfp = dp->i_df.if_data; return !sfp->count; } @@ -379,12 +379,11 @@ xfs_dir_cilookup_result( !(args->op_flags & XFS_DA_OP_CILOOKUP)) return -EEXIST; - args->value = kmalloc(len, + args->value = kmemdup(name, len, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_RETRY_MAYFAIL); if (!args->value) return -ENOMEM; - memcpy(args->value, name, len); args->valuelen = len; return -EEXIST; } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index 576068ed81fa..a6594a5a941d 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -58,7 +58,6 @@ extern void xfs_dir_startup(void); extern int xfs_da_mount(struct xfs_mount *mp); extern void xfs_da_unmount(struct xfs_mount *mp); -extern int xfs_dir_isempty(struct xfs_inode *dp); extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_inode *pdp); extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp, diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 7002d7676a78..a53c5d40e084 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -64,7 +64,8 @@ #define XFS_ERRTAG_WB_DELAY_MS 42 #define XFS_ERRTAG_WRITE_DELAY_MS 43 #define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44 -#define XFS_ERRTAG_MAX 45 +#define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45 +#define XFS_ERRTAG_MAX 46 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -113,5 +114,6 @@ #define XFS_RANDOM_WB_DELAY_MS 3000 #define XFS_RANDOM_WRITE_DELAY_MS 3000 #define XFS_RANDOM_EXCHMAPS_FINISH_ONE 1 +#define XFS_RANDOM_METAFILE_RESV_CRITICAL 4 #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 2021396651de..3f1d6a98c118 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -662,7 +662,9 @@ xfs_exchmaps_rmapbt_blocks( if (!xfs_has_rmapbt(mp)) return 0; if (XFS_IS_REALTIME_INODE(req->ip1)) - return 0; + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * + XFS_RTRMAPADD_SPACE_RES(mp); return howmany_64(req->nr_exchanges, XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 4d47a3e723aa..9566a7623365 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -178,9 +178,10 @@ typedef struct xfs_sb { xfs_rgnumber_t sb_rgcount; /* number of realtime groups */ xfs_rtxlen_t sb_rgextents; /* size of a realtime group in rtx */ - uint8_t sb_rgblklog; /* rt group number shift */ uint8_t sb_pad[7]; /* zeroes */ + xfs_rfsblock_t sb_rtstart; /* start of internal RT section (FSB) */ + xfs_filblks_t sb_rtreserved; /* reserved (zoned) RT blocks */ /* must be padded to 64 bit alignment */ } xfs_sb_t; @@ -270,9 +271,10 @@ struct xfs_dsb { __be64 sb_metadirino; /* metadata directory tree root */ __be32 sb_rgcount; /* # of realtime groups */ __be32 sb_rgextents; /* size of rtgroup in rtx */ - __u8 sb_rgblklog; /* rt group number shift */ __u8 sb_pad[7]; /* zeroes */ + __be64 sb_rtstart; /* start of internal RT section (FSB) */ + __be64 sb_rtreserved; /* reserved (zoned) RT blocks */ /* * The size of this structure must be padded to 64 bit alignment. @@ -395,6 +397,9 @@ xfs_sb_has_ro_compat_feature( #define XFS_SB_FEAT_INCOMPAT_EXCHRANGE (1 << 6) /* exchangerange supported */ #define XFS_SB_FEAT_INCOMPAT_PARENT (1 << 7) /* parent pointers */ #define XFS_SB_FEAT_INCOMPAT_METADIR (1 << 8) /* metadata dir tree */ +#define XFS_SB_FEAT_INCOMPAT_ZONED (1 << 9) /* zoned RT allocator */ +#define XFS_SB_FEAT_INCOMPAT_ZONE_GAPS (1 << 10) /* RTGs have LBA gaps */ + #define XFS_SB_FEAT_INCOMPAT_ALL \ (XFS_SB_FEAT_INCOMPAT_FTYPE | \ XFS_SB_FEAT_INCOMPAT_SPINODES | \ @@ -404,7 +409,9 @@ xfs_sb_has_ro_compat_feature( XFS_SB_FEAT_INCOMPAT_NREXT64 | \ XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \ XFS_SB_FEAT_INCOMPAT_PARENT | \ - XFS_SB_FEAT_INCOMPAT_METADIR) + XFS_SB_FEAT_INCOMPAT_METADIR | \ + XFS_SB_FEAT_INCOMPAT_ZONED | \ + XFS_SB_FEAT_INCOMPAT_ZONE_GAPS) #define XFS_SB_FEAT_INCOMPAT_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_ALL static inline bool @@ -857,6 +864,8 @@ enum xfs_metafile_type { XFS_METAFILE_PRJQUOTA, /* project quota */ XFS_METAFILE_RTBITMAP, /* rt bitmap */ XFS_METAFILE_RTSUMMARY, /* rt summary */ + XFS_METAFILE_RTRMAP, /* rt rmap */ + XFS_METAFILE_RTREFCOUNT, /* rt refcount */ XFS_METAFILE_MAX } __packed; @@ -868,7 +877,9 @@ enum xfs_metafile_type { { XFS_METAFILE_GRPQUOTA, "grpquota" }, \ { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ - { XFS_METAFILE_RTSUMMARY, "rtsummary" } + { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ + { XFS_METAFILE_RTRMAP, "rtrmap" }, \ + { XFS_METAFILE_RTREFCOUNT, "rtrefcount" } /* * On-disk inode structure. @@ -948,7 +959,12 @@ struct xfs_dinode { __be64 di_changecount; /* number of attribute changes */ __be64 di_lsn; /* flush sequence */ __be64 di_flags2; /* more random flags */ - __be32 di_cowextsize; /* basic cow extent size for file */ + union { + /* basic cow extent size for (regular) file */ + __be32 di_cowextsize; + /* used blocks in RTG for (zoned) rtrmap inode */ + __be32 di_used_blocks; + }; __u8 di_pad2[12]; /* more padding for future expansion */ /* fields only written to during inode creation */ @@ -997,7 +1013,8 @@ 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 +1022,8 @@ 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. @@ -1726,6 +1744,24 @@ typedef __be32 xfs_rmap_ptr_t; XFS_IBT_BLOCK(mp) + 1) /* + * Realtime Reverse mapping btree format definitions + * + * This is a btree for reverse mapping records for realtime volumes + */ +#define XFS_RTRMAP_CRC_MAGIC 0x4d415052 /* 'MAPR' */ + +/* + * rtrmap root header, on-disk form only. + */ +struct xfs_rtrmap_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-based btree pointer type */ +typedef __be64 xfs_rtrmap_ptr_t; + +/* * Reference Count Btree format definitions * */ @@ -1768,12 +1804,29 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -#define MAXREFCOUNT ((xfs_nlink_t)~0U) -#define MAXREFCEXTLEN ((xfs_extlen_t)~0U) +#define XFS_REFC_REFCOUNT_MAX ((xfs_nlink_t)~0U) +#define XFS_REFC_LEN_MAX ((xfs_extlen_t)~0U) /* btree pointer type */ typedef __be32 xfs_refcount_ptr_t; +/* + * Realtime Reference Count btree format definitions + * + * This is a btree for reference count records for realtime volumes + */ +#define XFS_RTREFC_CRC_MAGIC 0x52434e54 /* 'RCNT' */ + +/* + * rt refcount root header, on-disk form only. + */ +struct xfs_rtrefcount_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-rooted btree pointer type */ +typedef __be64 xfs_rtrefcount_ptr_t; /* * BMAP Btree format definitions diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 41ce4d3d650e..12463ba766da 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -189,7 +189,9 @@ struct xfs_fsop_geom { uint32_t checked; /* o: checked fs & rt metadata */ __u32 rgextents; /* rt extents in a realtime group */ __u32 rgcount; /* number of realtime groups */ - __u64 reserved[16]; /* reserved space */ + __u64 rtstart; /* start of internal rt section */ + __u64 rtreserved; /* RT (zoned) reserved blocks */ + __u64 reserved[14]; /* reserved space */ }; #define XFS_FSOP_GEOM_SICK_COUNTERS (1 << 0) /* summary counters */ @@ -247,6 +249,7 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */ #define XFS_FSOP_GEOM_FLAGS_PARENT (1 << 25) /* linux parent pointers */ #define XFS_FSOP_GEOM_FLAGS_METADIR (1 << 26) /* metadata directories */ +#define XFS_FSOP_GEOM_FLAGS_ZONED (1 << 27) /* zoned rt device */ /* * Minimum and maximum sizes need for growth checks. @@ -737,9 +740,11 @@ struct xfs_scrub_metadata { #define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */ #define XFS_SCRUB_TYPE_METAPATH 29 /* metadata directory tree paths */ #define XFS_SCRUB_TYPE_RGSUPER 30 /* realtime superblock */ +#define XFS_SCRUB_TYPE_RTRMAPBT 31 /* rtgroup reverse mapping btree */ +#define XFS_SCRUB_TYPE_RTREFCBT 32 /* realtime reference count btree */ /* Number of scrub subcommands. */ -#define XFS_SCRUB_TYPE_NR 31 +#define XFS_SCRUB_TYPE_NR 33 /* * This special type code only applies to the vectored scrub implementation. @@ -829,9 +834,11 @@ struct xfs_scrub_vec_head { #define XFS_SCRUB_METAPATH_USRQUOTA (5) /* user quota */ #define XFS_SCRUB_METAPATH_GRPQUOTA (6) /* group quota */ #define XFS_SCRUB_METAPATH_PRJQUOTA (7) /* project quota */ +#define XFS_SCRUB_METAPATH_RTRMAPBT (8) /* realtime reverse mapping */ +#define XFS_SCRUB_METAPATH_RTREFCOUNTBT (9) /* realtime refcount */ /* Number of metapath sm_ino values */ -#define XFS_SCRUB_METAPATH_NR (8) +#define XFS_SCRUB_METAPATH_NR (10) /* * ioctl limits @@ -993,6 +1000,8 @@ struct xfs_rtgroup_geometry { #define XFS_RTGROUP_GEOM_SICK_SUPER (1U << 0) /* superblock */ #define XFS_RTGROUP_GEOM_SICK_BITMAP (1U << 1) /* rtbitmap */ #define XFS_RTGROUP_GEOM_SICK_SUMMARY (1U << 2) /* rtsummary */ +#define XFS_RTGROUP_GEOM_SICK_RMAPBT (1U << 3) /* reverse mappings */ +#define XFS_RTGROUP_GEOM_SICK_REFCNTBT (1U << 4) /* reference counts */ /* * ioctl commands that are used by Linux filesystems @@ -1073,6 +1082,15 @@ struct xfs_rtgroup_geometry { #define XFS_IOC_COMMIT_RANGE _IOW ('X', 131, struct xfs_commit_range) /* XFS_IOC_GETFSUUID ---------- deprecated 140 */ +/* + * Devices supported by a single XFS file system. Reported in fsmaps fmr_device + * when using internal RT devices. + */ +enum xfs_device { + XFS_DEV_DATA = 1, + XFS_DEV_LOG = 2, + XFS_DEV_RT = 3, +}; #ifndef HAVE_BBMACROS /* diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h index 242b05627c7a..4423932a2313 100644 --- a/fs/xfs/libxfs/xfs_group.h +++ b/fs/xfs/libxfs/xfs_group.h @@ -19,10 +19,23 @@ struct xfs_group { #ifdef __KERNEL__ /* -- kernel only structures below this line -- */ - /* - * Track freed but not yet committed extents. - */ - struct xfs_extent_busy_tree *xg_busy_extents; + union { + /* + * For perags and non-zoned RT groups: + * Track freed but not yet committed extents. + */ + struct xfs_extent_busy_tree *xg_busy_extents; + + /* + * For zoned RT groups: + * List of groups that need a zone reset. + * + * The zonegc code forces a log flush of the rtrmap inode before + * resetting the write pointer, so there is no need for + * individual busy extent tracking. + */ + struct xfs_group *xg_next_reset; + }; /* * Bitsets of per-ag metadata that have been checked and/or are sick. @@ -107,9 +120,15 @@ xfs_gbno_to_daddr( xfs_agblock_t gbno) { struct xfs_mount *mp = xg->xg_mount; - uint32_t blocks = mp->m_groups[xg->xg_type].blocks; + struct xfs_groups *g = &mp->m_groups[xg->xg_type]; + xfs_fsblock_t fsbno; + + if (g->has_daddr_gaps) + fsbno = xfs_gbno_to_fsb(xg, gbno); + else + fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno; - return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno); + return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno); } static inline uint32_t diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index d34986ac18c3..b31000f7190c 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -70,6 +70,8 @@ struct xfs_rtgroup; #define XFS_SICK_RG_SUPER (1 << 0) /* rt group superblock */ #define XFS_SICK_RG_BITMAP (1 << 1) /* rt group bitmap */ #define XFS_SICK_RG_SUMMARY (1 << 2) /* rt groups summary */ +#define XFS_SICK_RG_RMAPBT (1 << 3) /* reverse mappings */ +#define XFS_SICK_RG_REFCNTBT (1 << 4) /* reference counts */ /* Observable health issues for AG metadata. */ #define XFS_SICK_AG_SB (1 << 0) /* superblock */ @@ -115,7 +117,9 @@ struct xfs_rtgroup; #define XFS_SICK_RG_PRIMARY (XFS_SICK_RG_SUPER | \ XFS_SICK_RG_BITMAP | \ - XFS_SICK_RG_SUMMARY) + XFS_SICK_RG_SUMMARY | \ + XFS_SICK_RG_RMAPBT | \ + XFS_SICK_RG_REFCNTBT) #define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \ XFS_SICK_AG_AGF | \ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index f3a840a425f5..0c47b5c6ca7d 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -364,7 +364,7 @@ xfs_ialloc_inode_init( (j * M_IGEO(mp)->blocks_per_cluster)); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize * M_IGEO(mp)->blocks_per_cluster, - XBF_UNMAPPED, &fbuf); + 0, &fbuf); if (error) return error; @@ -1927,7 +1927,7 @@ xfs_dialloc( * that we can immediately allocate, but then we allow allocation on the * second pass if we fail to find an AG with free inodes in it. */ - if (percpu_counter_read_positive(&mp->m_fdblocks) < + if (xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) < mp->m_low_space[XFS_LOWSP_1_PCNT]) { ok_alloc = false; low_space = true; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 424861fbf1bd..aa13fc00afd7 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -137,7 +137,7 @@ xfs_imap_to_bp( int error; error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno, - imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops); + imap->im_len, 0, bpp, &xfs_inode_buf_ops); if (xfs_metadata_is_sick(error)) xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno), XFS_SICK_AG_INODES); @@ -252,7 +252,10 @@ xfs_inode_from_disk( be64_to_cpu(from->di_changecount)); ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime); ip->i_diflags2 = be64_to_cpu(from->di_flags2); + /* also covers the di_used_blocks union arm: */ ip->i_cowextsize = be32_to_cpu(from->di_cowextsize); + BUILD_BUG_ON(sizeof(from->di_cowextsize) != + sizeof(from->di_used_blocks)); } error = xfs_iformat_data_fork(ip, from); @@ -349,6 +352,7 @@ xfs_inode_to_disk( to->di_changecount = cpu_to_be64(inode_peek_iversion(inode)); to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime); to->di_flags2 = cpu_to_be64(ip->i_diflags2); + /* also covers the di_used_blocks union arm: */ to->di_cowextsize = cpu_to_be32(ip->i_cowextsize); to->di_ino = cpu_to_be64(ip->i_ino); to->di_lsn = cpu_to_be64(lsn); @@ -441,6 +445,30 @@ 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)) { + case XFS_METAFILE_RTRMAP: + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use + * the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(mp)) + return __this_address; + break; + case XFS_METAFILE_RTREFCOUNT: + /* same comment about growfs and rmap inodes applies */ + if (!xfs_has_reflink(mp)) + return __this_address; + break; + default: + return __this_address; + } + break; default: return __this_address; } @@ -460,6 +488,10 @@ 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 +669,6 @@ 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; @@ -723,14 +752,22 @@ xfs_dinode_verify( return __this_address; /* don't let reflink and realtime mix */ - if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME)) + if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME) && + !xfs_has_rtreflink(mp)) return __this_address; - /* COW extent size hint validation */ - fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize), - mode, flags, flags2); - if (fa) - return fa; + if (xfs_has_zoned(mp) && + dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) { + if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents) + return __this_address; + } else { + /* COW extent size hint validation */ + fa = xfs_inode_validate_cowextsize(mp, + be32_to_cpu(dip->di_cowextsize), + mode, flags, flags2); + if (fa) + return fa; + } /* bigtime iflag can only happen on bigtime filesystems */ if (xfs_dinode_has_bigtime(dip) && @@ -743,6 +780,12 @@ 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; } @@ -878,11 +921,29 @@ xfs_inode_validate_cowextsize( bool rt_flag; bool hint_flag; uint32_t cowextsize_bytes; + uint32_t blocksize_bytes; rt_flag = (flags & XFS_DIFLAG_REALTIME); hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE); cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize); + /* + * Similar to extent size hints, a directory can be configured to + * propagate realtime status and a CoW extent size hint to newly + * created files even if there is no realtime device, and the hints on + * disk can become misaligned if the sysadmin changes the rt extent + * size while adding the realtime device. + * + * Therefore, we can only enforce the rextsize alignment check against + * regular realtime files, and rely on callers to decide when alignment + * checks are appropriate, and fix things up as needed. + */ + + if (rt_flag) + blocksize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + else + blocksize_bytes = mp->m_sb.sb_blocksize; + if (hint_flag && !xfs_has_reflink(mp)) return __this_address; @@ -896,16 +957,13 @@ xfs_inode_validate_cowextsize( if (mode && !hint_flag && cowextsize != 0) return __this_address; - if (hint_flag && rt_flag) - return __this_address; - - if (cowextsize_bytes % mp->m_sb.sb_blocksize) + if (cowextsize_bytes % blocksize_bytes) return __this_address; if (cowextsize > XFS_MAX_BMBT_EXTLEN) return __this_address; - if (cowextsize > mp->m_sb.sb_agblocks / 2) + if (!rt_flag && cowextsize > mp->m_sb.sb_agblocks / 2) return __this_address; return NULL; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1158ca48626b..4f99b90add55 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -27,6 +27,8 @@ #include "xfs_errortag.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -178,7 +180,7 @@ xfs_iformat_btree( struct xfs_mount *mp = ip->i_mount; xfs_bmdr_block_t *dfp; struct xfs_ifork *ifp; - /* REFERENCED */ + struct xfs_btree_block *broot; int nrecs; int size; int level; @@ -211,16 +213,13 @@ xfs_iformat_btree( return -EFSCORRUPTED; } - ifp->if_broot_bytes = size; - ifp->if_broot = kmalloc(size, - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - ASSERT(ifp->if_broot != NULL); + broot = xfs_broot_alloc(ifp, size); /* * Copy and convert from the on-disk structure * to the in-memory structure. */ xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork), - ifp->if_broot, size); + broot, size); ifp->if_bytes = 0; ifp->if_data = NULL; @@ -270,6 +269,16 @@ 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) { + case XFS_METAFILE_RTRMAP: + return xfs_iformat_rtrmap(ip, dip); + case XFS_METAFILE_RTREFCOUNT: + return xfs_iformat_rtrefcount(ip, dip); + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); @@ -363,135 +372,68 @@ xfs_iformat_attr_fork( } /* - * Reallocate the space for if_broot based on the number of records - * being added or deleted as indicated in rec_diff. Move the records - * and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by - * the caller. When growing this will create holes to be filled in - * by the caller. - * - * The caller must not request to add more records than would fit in - * the on-disk inode root. If the if_broot is currently NULL, then - * if we are adding records, one will be allocated. The caller must also - * not request that the number of records go below zero, although - * it can go to zero. - * - * ip -- the inode whose if_broot area is changing - * ext_diff -- the change in the number of records, positive or negative, - * requested for the if_broot array. + * Allocate the if_broot component of an inode fork so that it is @new_size + * bytes in size, using __GFP_NOLOCKDEP like all the other code that + * initializes a broot during inode load. Returns if_broot. */ -void -xfs_iroot_realloc( - xfs_inode_t *ip, - int rec_diff, - int whichfork) +struct xfs_btree_block * +xfs_broot_alloc( + struct xfs_ifork *ifp, + size_t new_size) { - struct xfs_mount *mp = ip->i_mount; - int cur_max; - struct xfs_ifork *ifp; - struct xfs_btree_block *new_broot; - int new_max; - size_t new_size; - char *np; - char *op; + ASSERT(ifp->if_broot == NULL); - /* - * Handle the degenerate case quietly. - */ - if (rec_diff == 0) { - return; - } + ifp->if_broot = kmalloc(new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} - ifp = xfs_ifork_ptr(ip, whichfork); - if (rec_diff > 0) { - /* - * If there wasn't any memory allocated before, just - * allocate it now and get out. - */ - if (ifp->if_broot_bytes == 0) { - new_size = xfs_bmap_broot_space_calc(mp, rec_diff); - ifp->if_broot = kmalloc(new_size, - GFP_KERNEL | __GFP_NOFAIL); - ifp->if_broot_bytes = (int)new_size; - return; - } +/* + * Reallocate the if_broot component of an inode fork so that it is @new_size + * bytes in size. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_realloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + /* No size change? No action needed. */ + if (new_size == ifp->if_broot_bytes) + return ifp->if_broot; - /* - * If there is already an existing if_broot, then we need - * to realloc() it and shift the pointers to their new - * location. The records don't change location because - * they are kept butted up against the btree block header. - */ - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - new_size = xfs_bmap_broot_space_calc(mp, new_max); - ifp->if_broot = krealloc(ifp->if_broot, new_size, - GFP_KERNEL | __GFP_NOFAIL); - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - (int)new_size); - ifp->if_broot_bytes = (int)new_size; - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); - return; + /* New size is zero, free it. */ + if (new_size == 0) { + ifp->if_broot_bytes = 0; + kfree(ifp->if_broot); + ifp->if_broot = NULL; + return NULL; } /* - * rec_diff is less than 0. In this case, we are shrinking the - * if_broot buffer. It must already exist. If we go to zero - * records, just get rid of the root and clear the status bit. + * Shrinking the iroot means we allocate a new smaller object and copy + * it. We don't trust krealloc not to nop on realloc-down. */ - ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0)); - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - ASSERT(new_max >= 0); - if (new_max > 0) - new_size = xfs_bmap_broot_space_calc(mp, new_max); - else - new_size = 0; - if (new_size > 0) { - new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, - xfs_bmbt_block_len(ip->i_mount)); - } else { - new_broot = NULL; + if (ifp->if_broot_bytes > 0 && ifp->if_broot_bytes > new_size) { + struct xfs_btree_block *old_broot = ifp->if_broot; + + ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + memcpy(ifp->if_broot, old_broot, new_size); + kfree(old_broot); + return ifp->if_broot; } /* - * Only copy the keys and pointers if there are any. + * Growing the iroot means we can krealloc. This may get us the same + * object. */ - if (new_max > 0) { - /* - * First copy the keys. - */ - op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); - np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); - - /* - * Then copy the pointers. - */ - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, - (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - } - kfree(ifp->if_broot); - ifp->if_broot = new_broot; - ifp->if_broot_bytes = (int)new_size; - if (ifp->if_broot) - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return; + ifp->if_broot = krealloc(ifp->if_broot, new_size, + GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; } - /* * This is called when the amount of space needed for if_data * is increased or decreased. The change in size is indicated by @@ -671,6 +613,25 @@ 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) { + case XFS_METAFILE_RTRMAP: + xfs_iflush_rtrmap(ip, dip); + break; + case XFS_METAFILE_RTREFCOUNT: + xfs_iflush_rtrefcount(ip, dip); + break; + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 2373d12fd474..69ed0919d60b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -170,7 +170,11 @@ void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, void xfs_idestroy_fork(struct xfs_ifork *ifp); void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, int whichfork); -void xfs_iroot_realloc(struct xfs_inode *, int, int); +struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, + size_t new_size); +struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, + size_t new_size); + int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c index deb0b7c00a1f..48fe49a5f050 100644 --- a/fs/xfs/libxfs/xfs_inode_util.c +++ b/fs/xfs/libxfs/xfs_inode_util.c @@ -322,6 +322,7 @@ xfs_inode_init( if (xfs_has_v3inodes(mp)) { inode_set_iversion(inode, 1); + /* also covers the di_used_blocks union arm: */ ip->i_cowextsize = 0; times |= XFS_ICHGTIME_CREATE; } diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 15dec19b6c32..0d637c276db0 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -250,6 +250,10 @@ typedef struct xfs_trans_header { #define XFS_LI_XMD 0x1249 /* mapping exchange done */ #define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */ #define XFS_LI_EFD_RT 0x124b /* realtime extent free done */ +#define XFS_LI_RUI_RT 0x124c /* realtime rmap update intent */ +#define XFS_LI_RUD_RT 0x124d /* realtime rmap update done */ +#define XFS_LI_CUI_RT 0x124e /* realtime refcount update intent */ +#define XFS_LI_CUD_RT 0x124f /* realtime refcount update done */ #define XFS_LI_TYPE_DESC \ { XFS_LI_EFI, "XFS_LI_EFI" }, \ @@ -271,7 +275,11 @@ typedef struct xfs_trans_header { { XFS_LI_XMI, "XFS_LI_XMI" }, \ { XFS_LI_XMD, "XFS_LI_XMD" }, \ { XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \ - { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" } + { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }, \ + { XFS_LI_RUI_RT, "XFS_LI_RUI_RT" }, \ + { XFS_LI_RUD_RT, "XFS_LI_RUD_RT" }, \ + { XFS_LI_CUI_RT, "XFS_LI_CUI_RT" }, \ + { XFS_LI_CUD_RT, "XFS_LI_CUD_RT" } /* * Inode Log Item Format definitions. @@ -351,12 +359,6 @@ struct xfs_inode_log_format_32 { */ #define XFS_ILOG_IVERSION 0x8000 -#define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ - XFS_ILOG_DBROOT | XFS_ILOG_DEV | \ - XFS_ILOG_ADATA | XFS_ILOG_AEXT | \ - XFS_ILOG_ABROOT | XFS_ILOG_DOWNER | \ - XFS_ILOG_AOWNER) - #define XFS_ILOG_DFORK (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ XFS_ILOG_DBROOT) @@ -473,7 +475,12 @@ struct xfs_log_dinode { xfs_lsn_t di_lsn; uint64_t di_flags2; /* more random flags */ - uint32_t di_cowextsize; /* basic cow extent size for file */ + union { + /* basic cow extent size for (regular) file */ + uint32_t di_cowextsize; + /* used blocks in RTG for (zoned) rtrmap inode */ + uint32_t di_used_blocks; + }; uint8_t di_pad2[12]; /* more padding for future expansion */ /* fields only written to during inode creation */ diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 5397a8ff004d..66c7916fb5cd 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -79,6 +79,10 @@ extern const struct xlog_recover_item_ops xlog_xmi_item_ops; extern const struct xlog_recover_item_ops xlog_xmd_item_ops; extern const struct xlog_recover_item_ops xlog_rtefi_item_ops; extern const struct xlog_recover_item_ops xlog_rtefd_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrud_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcud_item_ops; /* * Macros, structures, prototypes for internal log manager use. diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c index bae7377c0f22..178e89711cb7 100644 --- a/fs/xfs/libxfs/xfs_metadir.c +++ b/fs/xfs/libxfs/xfs_metadir.c @@ -29,6 +29,10 @@ #include "xfs_dir2_priv.h" #include "xfs_parent.h" #include "xfs_health.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_btree.h" +#include "xfs_alloc.h" /* * Metadata Directory Tree diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c index adeb25d1a444..225923e463c4 100644 --- a/fs/xfs/libxfs/xfs_metafile.c +++ b/fs/xfs/libxfs/xfs_metafile.c @@ -17,6 +17,31 @@ #include "xfs_metafile.h" #include "xfs_trace.h" #include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_alloc.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" + +static const struct { + enum xfs_metafile_type mtype; + const char *name; +} xfs_metafile_type_strs[] = { XFS_METAFILE_TYPE_STR }; + +const char * +xfs_metafile_type_str(enum xfs_metafile_type metatype) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(xfs_metafile_type_strs); i++) { + if (xfs_metafile_type_strs[i].mtype == metatype) + return xfs_metafile_type_strs[i].name; + } + + return NULL; +} /* Set up an inode to be recognized as a metadata directory inode. */ void @@ -50,3 +75,248 @@ xfs_metafile_clear_iflag( ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } + +/* + * Is the metafile reservations at or beneath a certain threshold? + */ +static inline bool +xfs_metafile_resv_can_cover( + struct xfs_mount *mp, + int64_t rhs) +{ + /* + * The amount of space that can be allocated to this metadata file is + * the remaining reservation for the particular metadata file + the + * global free block count. Take care of the first case to avoid + * touching the per-cpu counter. + */ + if (mp->m_metafile_resv_avail >= rhs) + return true; + + /* + * There aren't enough blocks left in the inode's reservation, but it + * isn't critical unless there also isn't enough free space. + */ + return xfs_compare_freecounter(mp, XC_FREE_BLOCKS, + rhs - mp->m_metafile_resv_avail, 2048) >= 0; +} + +/* + * Is the metafile reservation critically low on blocks? For now we'll define + * that as the number of blocks we can get our hands on being less than 10% of + * what we reserved or less than some arbitrary number (maximum btree height). + */ +bool +xfs_metafile_resv_critical( + struct xfs_mount *mp) +{ + ASSERT(xfs_has_metadir(mp)); + + trace_xfs_metafile_resv_critical(mp, 0); + + if (!xfs_metafile_resv_can_cover(mp, mp->m_rtbtree_maxlevels)) + return true; + + if (!xfs_metafile_resv_can_cover(mp, + div_u64(mp->m_metafile_resv_target, 10))) + return true; + + return XFS_TEST_ERROR(false, mp, XFS_ERRTAG_METAFILE_RESV_CRITICAL); +} + +/* Allocate a block from the metadata file's reservation. */ +void +xfs_metafile_resv_alloc_space( + struct xfs_inode *ip, + struct xfs_alloc_arg *args) +{ + struct xfs_mount *mp = ip->i_mount; + int64_t len = args->len; + + ASSERT(xfs_is_metadir_inode(ip)); + ASSERT(args->resv == XFS_AG_RESV_METAFILE); + + trace_xfs_metafile_resv_alloc_space(mp, args->len); + + /* + * Allocate the blocks from the metadata inode's block reservation + * and update the ondisk sb counter. + */ + mutex_lock(&mp->m_metafile_resv_lock); + if (mp->m_metafile_resv_avail > 0) { + int64_t from_resv; + + from_resv = min_t(int64_t, len, mp->m_metafile_resv_avail); + mp->m_metafile_resv_avail -= from_resv; + xfs_mod_delalloc(ip, 0, -from_resv); + xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS, + -from_resv); + len -= from_resv; + } + + /* + * Any allocation in excess of the reservation requires in-core and + * on-disk fdblocks updates. If we can grab @len blocks from the + * in-core fdblocks then all we need to do is update the on-disk + * superblock; if not, then try to steal some from the transaction's + * block reservation. Overruns are only expected for rmap btrees. + */ + if (len) { + unsigned int field; + int error; + + error = xfs_dec_fdblocks(ip->i_mount, len, true); + if (error) + field = XFS_TRANS_SB_FDBLOCKS; + else + field = XFS_TRANS_SB_RES_FDBLOCKS; + + xfs_trans_mod_sb(args->tp, field, -len); + } + + mp->m_metafile_resv_used += args->len; + mutex_unlock(&mp->m_metafile_resv_lock); + + ip->i_nblocks += args->len; + xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE); +} + +/* Free a block to the metadata file's reservation. */ +void +xfs_metafile_resv_free_space( + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_filblks_t len) +{ + struct xfs_mount *mp = ip->i_mount; + int64_t to_resv; + + ASSERT(xfs_is_metadir_inode(ip)); + + trace_xfs_metafile_resv_free_space(mp, len); + + ip->i_nblocks -= len; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + mutex_lock(&mp->m_metafile_resv_lock); + mp->m_metafile_resv_used -= len; + + /* + * Add the freed blocks back into the inode's delalloc reservation + * until it reaches the maximum size. Update the ondisk fdblocks only. + */ + to_resv = mp->m_metafile_resv_target - + (mp->m_metafile_resv_used + mp->m_metafile_resv_avail); + if (to_resv > 0) { + to_resv = min_t(int64_t, to_resv, len); + mp->m_metafile_resv_avail += to_resv; + xfs_mod_delalloc(ip, 0, to_resv); + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv); + len -= to_resv; + } + mutex_unlock(&mp->m_metafile_resv_lock); + + /* + * Everything else goes back to the filesystem, so update the in-core + * and on-disk counters. + */ + if (len) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len); +} + +static void +__xfs_metafile_resv_free( + struct xfs_mount *mp) +{ + if (mp->m_metafile_resv_avail) { + xfs_mod_sb_delalloc(mp, -(int64_t)mp->m_metafile_resv_avail); + xfs_add_fdblocks(mp, mp->m_metafile_resv_avail); + } + mp->m_metafile_resv_avail = 0; + mp->m_metafile_resv_used = 0; + mp->m_metafile_resv_target = 0; +} + +/* Release unused metafile space reservation. */ +void +xfs_metafile_resv_free( + struct xfs_mount *mp) +{ + if (!xfs_has_metadir(mp)) + return; + + trace_xfs_metafile_resv_free(mp, 0); + + mutex_lock(&mp->m_metafile_resv_lock); + __xfs_metafile_resv_free(mp); + mutex_unlock(&mp->m_metafile_resv_lock); +} + +/* Set up a metafile space reservation. */ +int +xfs_metafile_resv_init( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + xfs_filblks_t used = 0, target = 0; + xfs_filblks_t hidden_space; + xfs_rfsblock_t dblocks_avail = mp->m_sb.sb_dblocks / 4; + int error = 0; + + if (!xfs_has_metadir(mp)) + return 0; + + /* + * Free any previous reservation to have a clean slate. + */ + mutex_lock(&mp->m_metafile_resv_lock); + __xfs_metafile_resv_free(mp); + + /* + * Currently the only btree metafiles that require reservations are the + * rtrmap and the rtrefcount. Anything new will have to be added here + * as well. + */ + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + if (xfs_has_rtrmapbt(mp)) { + used += rtg_rmap(rtg)->i_nblocks; + target += xfs_rtrmapbt_calc_reserves(mp); + } + if (xfs_has_rtreflink(mp)) { + used += rtg_refcount(rtg)->i_nblocks; + target += xfs_rtrefcountbt_calc_reserves(mp); + } + } + + if (!target) + goto out_unlock; + + /* + * Space taken by the per-AG metadata btrees are accounted on-disk as + * used space. We therefore only hide the space that is reserved but + * not used by the trees. + */ + if (used > target) + target = used; + else if (target > dblocks_avail) + target = dblocks_avail; + hidden_space = target - used; + + error = xfs_dec_fdblocks(mp, hidden_space, true); + if (error) { + trace_xfs_metafile_resv_init_error(mp, 0); + goto out_unlock; + } + + xfs_mod_sb_delalloc(mp, hidden_space); + + mp->m_metafile_resv_target = target; + mp->m_metafile_resv_used = used; + mp->m_metafile_resv_avail = hidden_space; + + trace_xfs_metafile_resv_init(mp, target); + +out_unlock: + mutex_unlock(&mp->m_metafile_resv_lock); + return error; +} diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h index acec400123db..ae6f9e779b98 100644 --- a/fs/xfs/libxfs/xfs_metafile.h +++ b/fs/xfs/libxfs/xfs_metafile.h @@ -6,6 +6,8 @@ #ifndef __XFS_METAFILE_H__ #define __XFS_METAFILE_H__ +const char *xfs_metafile_type_str(enum xfs_metafile_type metatype); + /* All metadata files must have these flags set. */ #define XFS_METAFILE_DIFLAGS (XFS_DIFLAG_IMMUTABLE | \ XFS_DIFLAG_SYNC | \ @@ -21,6 +23,17 @@ void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip, enum xfs_metafile_type metafile_type); void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip); +/* Space reservations for metadata inodes. */ +struct xfs_alloc_arg; + +bool xfs_metafile_resv_critical(struct xfs_mount *mp); +void xfs_metafile_resv_alloc_space(struct xfs_inode *ip, + struct xfs_alloc_arg *args); +void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp, + xfs_filblks_t len); +void xfs_metafile_resv_free(struct xfs_mount *mp); +int xfs_metafile_resv_init(struct xfs_mount *mp); + /* Code specific to kernel/userspace; must be provided externally. */ int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino, diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index ad0dedf00f18..5ed44fdf7491 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -83,6 +83,10 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw, 4); XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48); + XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); + XFS_CHECK_STRUCT_SIZE(xfs_rtrefcount_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrefcount_root, 4); /* * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad @@ -229,8 +233,8 @@ xfs_check_ondisk_structs(void) 16299260424LL); /* superblock field checks we got from xfs/122 */ - XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 288); - XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 288); + XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 304); + XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 304); XFS_CHECK_SB_OFFSET(sb_magicnum, 0); XFS_CHECK_SB_OFFSET(sb_blocksize, 4); XFS_CHECK_SB_OFFSET(sb_dblocks, 8); @@ -291,6 +295,8 @@ xfs_check_ondisk_structs(void) XFS_CHECK_SB_OFFSET(sb_rgextents, 276); XFS_CHECK_SB_OFFSET(sb_rgblklog, 280); XFS_CHECK_SB_OFFSET(sb_pad, 281); + XFS_CHECK_SB_OFFSET(sb_rtstart, 288); + XFS_CHECK_SB_OFFSET(sb_rtreserved, 296); } #endif /* __XFS_ONDISK_H */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 2dbab68b4fe6..cebe83f7842a 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -25,6 +25,9 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_refcount_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_refcount_intent_cache; @@ -128,7 +131,7 @@ xfs_refcount_check_irec( struct xfs_perag *pag, const struct xfs_refcount_irec *irec) { - if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) return __this_address; if (!xfs_refcount_check_domain(irec)) @@ -138,12 +141,43 @@ xfs_refcount_check_irec( if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) return __this_address; - if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) return __this_address; return NULL; } +xfs_failaddr_t +xfs_rtrefcount_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_rgbext(rtg, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) + return __this_address; + + return NULL; +} + +static inline xfs_failaddr_t +xfs_refcount_check_btrec( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec) +{ + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + return xfs_rtrefcount_check_irec(to_rtg(cur->bc_group), irec); + return xfs_refcount_check_irec(to_perag(cur->bc_group), irec); +} + static inline int xfs_refcount_complain_bad_rec( struct xfs_btree_cur *cur, @@ -152,9 +186,15 @@ xfs_refcount_complain_bad_rec( { struct xfs_mount *mp = cur->bc_mp; - xfs_warn(mp, + if (xfs_btree_is_rtrefcount(cur->bc_ops)) { + xfs_warn(mp, + "RT Refcount BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); + } else { + xfs_warn(mp, "Refcount BTree record corruption in AG %d detected at %pS!", cur->bc_group->xg_gno, fa); + } xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); @@ -180,7 +220,7 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), irec); + fa = xfs_refcount_check_btrec(cur, irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, irec); @@ -853,9 +893,9 @@ xfs_refc_merge_refcount( const struct xfs_refcount_irec *irec, enum xfs_refc_adjust_op adjust) { - /* Once a record hits MAXREFCOUNT, it is pinned there forever */ - if (irec->rc_refcount == MAXREFCOUNT) - return MAXREFCOUNT; + /* Once a record hits XFS_REFC_REFCOUNT_MAX, it is pinned forever */ + if (irec->rc_refcount == XFS_REFC_REFCOUNT_MAX) + return XFS_REFC_REFCOUNT_MAX; return irec->rc_refcount + adjust; } @@ -898,7 +938,7 @@ xfs_refc_want_merge_center( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount + right->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; *ulenp = ulen; @@ -933,7 +973,7 @@ xfs_refc_want_merge_left( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -967,7 +1007,7 @@ xfs_refc_want_merge_right( * hence we need to catch u32 addition overflows here. */ ulen += cright->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -1065,7 +1105,7 @@ xfs_refcount_still_have_space( */ overhead = xfs_allocfree_block_count(cur->bc_mp, cur->bc_refc.shape_changes); - overhead += cur->bc_mp->m_refc_maxlevels; + overhead += cur->bc_maxlevels; overhead *= cur->bc_mp->m_sb.sb_blocksize; /* @@ -1085,6 +1125,22 @@ xfs_refcount_still_have_space( cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } +/* Schedule an extent free. */ +static int +xrefc_free_extent( + struct xfs_btree_cur *cur, + struct xfs_refcount_irec *rec) +{ + unsigned int flags = 0; + + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + flags |= XFS_FREE_EXTENT_REALTIME; + + return xfs_free_extent_later(cur->bc_tp, + xfs_gbno_to_fsb(cur->bc_group, rec->rc_startblock), + rec->rc_blockcount, NULL, XFS_AG_RESV_NONE, flags); +} + /* * Adjust the refcounts of middle extents. At this point we should have * split extents that crossed the adjustment range; merged with adjacent @@ -1101,7 +1157,6 @@ xfs_refcount_adjust_extents( struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; - xfs_fsblock_t fsbno; /* Merging did all the work already. */ if (*aglen == 0) @@ -1117,7 +1172,7 @@ xfs_refcount_adjust_extents( if (error) goto out_error; if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_SHARED; @@ -1154,11 +1209,7 @@ xfs_refcount_adjust_extents( goto out_error; } } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - tmp.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &tmp); if (error) goto out_error; } @@ -1196,7 +1247,7 @@ xfs_refcount_adjust_extents( * Adjust the reference count and either update the tree * (incr) or free the blocks (decr). */ - if (ext.rc_refcount == MAXREFCOUNT) + if (ext.rc_refcount == XFS_REFC_REFCOUNT_MAX) goto skip; ext.rc_refcount += adj; trace_xfs_refcount_modify_extent(cur, &ext); @@ -1216,11 +1267,7 @@ xfs_refcount_adjust_extents( } goto advloop; } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - ext.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &ext); if (error) goto out_error; } @@ -1417,12 +1464,122 @@ xfs_refcount_finish_one( } /* + * Set up a continuation a deferred rtrefcount operation by updating the + * intent. Checks to make sure we're not going to run off the end of the + * rtgroup. + */ +static inline int +xfs_rtrefcount_continue_op( + struct xfs_btree_cur *cur, + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + if (XFS_IS_CORRUPT(mp, !xfs_verify_rgbext(rtg, new_agbno, + ri->ri_blockcount))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + ri->ri_startblock = xfs_rgbno_to_rtb(rtg, new_agbno); + + ASSERT(xfs_verify_rtbext(mp, ri->ri_startblock, ri->ri_blockcount)); + return 0; +} + +/* + * Process one of the deferred realtime refcount operations. We pass back the + * btree cursor to maintain our lock on the btree between calls. + */ +int +xfs_rtrefcount_finish_one( + struct xfs_trans *tp, + struct xfs_refcount_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + struct xfs_btree_cur *rcur = *pcur; + int error = 0; + xfs_rgblock_t bno; + unsigned long nr_ops = 0; + int shape_changes = 0; + + bno = xfs_rtb_to_rgbno(mp, ri->ri_startblock); + + trace_xfs_refcount_deferred(mp, ri); + + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; + + /* + * If we haven't gotten a cursor or the cursor AG doesn't match + * the startblock, get one now. + */ + if (rcur != NULL && rcur->bc_group != ri->ri_group) { + nr_ops = rcur->bc_refc.nr_ops; + shape_changes = rcur->bc_refc.shape_changes; + xfs_btree_del_cursor(rcur, 0); + rcur = NULL; + *pcur = NULL; + } + if (rcur == NULL) { + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_REFCOUNT); + *pcur = rcur = xfs_rtrefcountbt_init_cursor(tp, rtg); + + rcur->bc_refc.nr_ops = nr_ops; + rcur->bc_refc.shape_changes = shape_changes; + } + + switch (ri->ri_type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_ALLOC_COW: + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + case XFS_REFCOUNT_FREE_COW: + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, ri); + return error; +} + +/* * Record a refcount intent for later processing. */ static void __xfs_refcount_add( struct xfs_trans *tp, enum xfs_refcount_intent_type type, + bool isrt, xfs_fsblock_t startblock, xfs_extlen_t blockcount) { @@ -1434,6 +1591,7 @@ __xfs_refcount_add( ri->ri_type = type; ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; + ri->ri_realtime = isrt; xfs_refcount_defer_add(tp, ri); } @@ -1444,12 +1602,13 @@ __xfs_refcount_add( void xfs_refcount_increase_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1459,12 +1618,13 @@ xfs_refcount_increase_extent( void xfs_refcount_decrease_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1666,7 +1826,7 @@ xfs_refcount_adjust_cow_extents( goto out_error; } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_COW; @@ -1820,6 +1980,7 @@ __xfs_refcount_cow_free( void xfs_refcount_alloc_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1828,17 +1989,17 @@ xfs_refcount_alloc_cow_extent( if (!xfs_has_reflink(mp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len); + __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, isrt, fsb, len); /* Add rmap entry */ - xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + xfs_rmap_alloc_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ void xfs_refcount_free_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1848,9 +2009,8 @@ xfs_refcount_free_cow_extent( return; /* Remove rmap entry */ - xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); - __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len); + xfs_rmap_free_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); + __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, isrt, fsb, len); } struct xfs_refcount_recovery { @@ -1879,8 +2039,7 @@ xfs_refcount_recover_extent( INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - if (xfs_refcount_check_irec(to_perag(cur->bc_group), &rr->rr_rrec) != - NULL || + if (xfs_refcount_check_btrec(cur, &rr->rr_rrec) != NULL || XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { xfs_btree_mark_sick(cur); @@ -1895,12 +2054,13 @@ xfs_refcount_recover_extent( /* Find and remove leftover CoW reservations. */ int xfs_refcount_recover_cow_leftovers( - struct xfs_mount *mp, - struct xfs_perag *pag) + struct xfs_group *xg) { + struct xfs_mount *mp = xg->xg_mount; + bool isrt = xg->xg_type == XG_TYPE_RTG; struct xfs_trans *tp; struct xfs_btree_cur *cur; - struct xfs_buf *agbp; + struct xfs_buf *agbp = NULL; struct xfs_refcount_recovery *rr, *n; struct list_head debris; union xfs_btree_irec low = { @@ -1913,10 +2073,19 @@ xfs_refcount_recover_cow_leftovers( xfs_fsblock_t fsb; int error; - /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + /* reflink filesystems must not have groups larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_RGBLOCKS >= XFS_REFC_COWFLAG); BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); - if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) - return -EOPNOTSUPP; + + if (isrt) { + if (!xfs_has_rtgroups(mp)) + return 0; + if (xfs_group_max_blocks(xg) >= XFS_MAX_RGBLOCKS) + return -EOPNOTSUPP; + } else { + if (xfs_group_max_blocks(xg) > XFS_MAX_CRC_AG_BLOCKS) + return -EOPNOTSUPP; + } INIT_LIST_HEAD(&debris); @@ -1934,16 +2103,24 @@ xfs_refcount_recover_cow_leftovers( if (error) return error; - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); - if (error) - goto out_trans; - cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + if (isrt) { + xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(xg)); + } else { + error = xfs_alloc_read_agf(to_perag(xg), tp, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, to_perag(xg)); + } /* Find all the leftover CoW staging extents. */ error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agbp); + if (agbp) + xfs_trans_brelse(tp, agbp); + else + xfs_rtgroup_unlock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); xfs_trans_cancel(tp); if (error) goto out_free; @@ -1956,14 +2133,15 @@ xfs_refcount_recover_cow_leftovers( goto out_free; /* Free the orphan record */ - fsb = xfs_agbno_to_fsb(pag, rr->rr_rrec.rc_startblock); - xfs_refcount_free_cow_extent(tp, fsb, + fsb = xfs_gbno_to_fsb(xg, rr->rr_rrec.rc_startblock); + xfs_refcount_free_cow_extent(tp, isrt, fsb, rr->rr_rrec.rc_blockcount); /* Free the block. */ error = xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) goto out_trans; @@ -2028,7 +2206,7 @@ xfs_refcount_query_range_helper( xfs_failaddr_t fa; xfs_refcount_btrec_to_irec(rec, &irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), &irec); + fa = xfs_refcount_check_btrec(cur, &irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, &irec); diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 62d78afcf1f3..f2e299a716a4 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -12,6 +12,7 @@ struct xfs_perag; struct xfs_btree_cur; struct xfs_bmbt_irec; struct xfs_refcount_irec; +struct xfs_rtgroup; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); @@ -60,6 +61,7 @@ struct xfs_refcount_intent { enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; + bool ri_realtime; }; /* Check that the refcount is appropriate for the record domain. */ @@ -74,24 +76,25 @@ xfs_refcount_check_domain( return true; } -void xfs_refcount_increase_extent(struct xfs_trans *tp, +void xfs_refcount_increase_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -void xfs_refcount_decrease_extent(struct xfs_trans *tp, +void xfs_refcount_decrease_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -extern int xfs_refcount_finish_one(struct xfs_trans *tp, +int xfs_refcount_finish_one(struct xfs_trans *tp, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); +int xfs_rtrefcount_finish_one(struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared); -void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -void xfs_refcount_free_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, - struct xfs_perag *pag); +void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +void xfs_refcount_free_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +int xfs_refcount_recover_cow_leftovers(struct xfs_group *xg); /* * While we're adjusting the refcounts records of an extent, we have @@ -120,6 +123,8 @@ extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag, const struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_rtrefcount_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index d0df68dc3131..3cdf50563fec 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -25,6 +25,8 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_rmap_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" struct kmem_cache *xfs_rmap_intent_cache; @@ -264,11 +266,77 @@ xfs_rmap_check_irec( return NULL; } +static xfs_failaddr_t +xfs_rtrmap_check_meta_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (irec->rm_offset != 0) + return __this_address; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return __this_address; + + switch (irec->rm_owner) { + case XFS_RMAP_OWN_FS: + if (irec->rm_startblock != 0) + return __this_address; + if (irec->rm_blockcount != mp->m_sb.sb_rextsize) + return __this_address; + return NULL; + case XFS_RMAP_OWN_COW: + if (!xfs_has_rtreflink(mp)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, + irec->rm_blockcount)) + return __this_address; + return NULL; + default: + return __this_address; + } + + return NULL; +} + +static xfs_failaddr_t +xfs_rtrmap_check_inode_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (!xfs_verify_ino(mp, irec->rm_owner)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, irec->rm_blockcount)) + return __this_address; + if (!xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + return NULL; +} + +xfs_failaddr_t +xfs_rtrmap_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + if (irec->rm_blockcount == 0) + return __this_address; + if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK)) + return __this_address; + if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)) + return xfs_rtrmap_check_meta_irec(rtg, irec); + return xfs_rtrmap_check_inode_irec(rtg, irec); +} + static inline xfs_failaddr_t xfs_rmap_check_btrec( struct xfs_btree_cur *cur, const struct xfs_rmap_irec *irec) { + if (xfs_btree_is_rtrmap(cur->bc_ops) || + xfs_btree_is_mem_rtrmap(cur->bc_ops)) + return xfs_rtrmap_check_irec(to_rtg(cur->bc_group), irec); return xfs_rmap_check_irec(to_perag(cur->bc_group), irec); } @@ -283,6 +351,10 @@ xfs_rmap_complain_bad_rec( if (xfs_btree_is_mem_rmap(cur->bc_ops)) xfs_warn(mp, "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa); + else if (xfs_btree_is_rtrmap(cur->bc_ops)) + xfs_warn(mp, + "RT Reverse Mapping BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); else xfs_warn(mp, "Reverse Mapping BTree record corruption in AG %d detected at %pS!", @@ -525,7 +597,7 @@ xfs_rmap_free_check_owner( struct xfs_btree_cur *cur, uint64_t ltoff, struct xfs_rmap_irec *rec, - xfs_filblks_t len, + xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags) @@ -2556,6 +2628,47 @@ __xfs_rmap_finish_intent( } } +static int +xfs_rmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_perag *pag = to_perag(ri->ri_group); + struct xfs_buf *agbp = NULL; + int error; + + /* + * Refresh the freelist before we start changing the rmapbt, because a + * shape change could cause us to allocate blocks. + */ + error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + if (error) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return error; + } + if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return -EFSCORRUPTED; + } + *pcur = xfs_rmapbt_init_cursor(tp->t_mountp, tp, agbp, pag); + return 0; +} + +static int +xfs_rtrmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + *pcur = xfs_rtrmapbt_init_cursor(tp, rtg); + return 0; +} + /* * Process one of the deferred rmap operations. We pass back the * btree cursor to maintain our lock on the rmapbt between calls. @@ -2571,8 +2684,6 @@ xfs_rmap_finish_one( { struct xfs_owner_info oinfo; struct xfs_mount *mp = tp->t_mountp; - struct xfs_btree_cur *rcur = *pcur; - struct xfs_buf *agbp = NULL; xfs_agblock_t bno; bool unwritten; int error = 0; @@ -2586,38 +2697,26 @@ xfs_rmap_finish_one( * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ - if (rcur != NULL && rcur->bc_group != ri->ri_group) { - xfs_btree_del_cursor(rcur, 0); - rcur = NULL; + if (*pcur != NULL && (*pcur)->bc_group != ri->ri_group) { + xfs_btree_del_cursor(*pcur, 0); *pcur = NULL; } - if (rcur == NULL) { - struct xfs_perag *pag = to_perag(ri->ri_group); - - /* - * Refresh the freelist before we start changing the - * rmapbt, because a shape change could cause us to - * allocate blocks. - */ - error = xfs_free_extent_fix_freelist(tp, pag, &agbp); - if (error) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + if (*pcur == NULL) { + if (ri->ri_group->xg_type == XG_TYPE_RTG) + error = xfs_rtrmap_finish_init_cursor(tp, ri, pcur); + else + error = xfs_rmap_finish_init_cursor(tp, ri, pcur); + if (error) return error; - } - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); - return -EFSCORRUPTED; - } - - *pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); } xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork, ri->ri_bmap.br_startoff); unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN; - bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock); - error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno, + bno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); + error = __xfs_rmap_finish_intent(*pcur, ri->ri_type, bno, ri->ri_bmap.br_blockcount, &oinfo, unwritten); if (error) return error; @@ -2647,6 +2746,7 @@ __xfs_rmap_add( struct xfs_trans *tp, enum xfs_rmap_intent_type type, uint64_t owner, + bool isrt, int whichfork, struct xfs_bmbt_irec *bmap) { @@ -2658,6 +2758,7 @@ __xfs_rmap_add( ri->ri_owner = owner; ri->ri_whichfork = whichfork; ri->ri_bmap = *bmap; + ri->ri_realtime = isrt; xfs_rmap_defer_add(tp, ri); } @@ -2671,6 +2772,7 @@ xfs_rmap_map_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_MAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2678,7 +2780,7 @@ xfs_rmap_map_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_MAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Unmap an extent out of a file. */ @@ -2690,6 +2792,7 @@ xfs_rmap_unmap_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2697,7 +2800,7 @@ xfs_rmap_unmap_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_UNMAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* @@ -2715,6 +2818,7 @@ xfs_rmap_convert_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(mp, whichfork)) return; @@ -2722,15 +2826,15 @@ xfs_rmap_convert_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_CONVERT_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Schedule the creation of an rmap for non-file data. */ void xfs_rmap_alloc_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2739,20 +2843,20 @@ xfs_rmap_alloc_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap); } /* Schedule the deletion of an rmap for non-file data. */ void xfs_rmap_free_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2761,12 +2865,12 @@ xfs_rmap_free_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap); } /* Compare rmap records. Returns -1 if a < b, 1 if a > b, and 0 if equal. */ diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 96b4321d8310..5f39f6e53cd1 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -7,6 +7,7 @@ #define __XFS_RMAP_H__ struct xfs_perag; +struct xfs_rtgroup; static inline void xfs_rmap_ino_bmbt_owner( @@ -174,6 +175,7 @@ struct xfs_rmap_intent { uint64_t ri_owner; struct xfs_bmbt_irec ri_bmap; struct xfs_group *ri_group; + bool ri_realtime; }; /* functions for updating the rmapbt based on bmbt map/unmap operations */ @@ -184,10 +186,10 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *imap); -void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); -void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); +void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); +void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri, struct xfs_btree_cur **pcur); @@ -206,6 +208,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag, const struct xfs_rmap_irec *irec); +xfs_failaddr_t xfs_rtrmap_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec); int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 4ddfb7e395b3..5057536e586c 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1055,7 +1055,7 @@ xfs_rtfree_extent( xfs_rtxlen_t len) /* length of extent freed */ { struct xfs_mount *mp = tp->t_mountp; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xfs_rtalloc_args args = { .mp = mp, .tp = tp, @@ -1123,6 +1123,7 @@ xfs_rtfree_blocks( xfs_extlen_t mod; int error; + ASSERT(!xfs_has_zoned(mp)); ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN); mod = xfs_blen_to_rtxoff(mp, rtlen); @@ -1174,6 +1175,9 @@ xfs_rtalloc_query_range( end = min(end, rtg->rtg_extents - 1); + if (xfs_has_zoned(mp)) + return -EINVAL; + /* Iterate the bitmap, looking for discrepancies. */ while (start <= end) { struct xfs_rtalloc_rec rec; @@ -1268,6 +1272,8 @@ xfs_rtbitmap_blockcount_len( struct xfs_mount *mp, xfs_rtbxlen_t rtextents) { + if (xfs_has_zoned(mp)) + return 0; return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp)); } @@ -1308,6 +1314,11 @@ xfs_rtsummary_blockcount( xfs_rtbxlen_t rextents = xfs_rtbitmap_bitcount(mp); unsigned long long rsumwords; + if (xfs_has_zoned(mp)) { + *rsumlevels = 0; + return 0; + } + *rsumlevels = xfs_compute_rextslog(rextents) + 1; rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels); return howmany_64(rsumwords, mp->m_blockwsize); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h index 16563a44bd13..22e5d9cd95f4 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.h +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -135,6 +135,15 @@ xfs_rtb_to_rtx( return div_u64(rtbno, mp->m_sb.sb_rextsize); } +/* Return the offset of a rtgroup block number within an rt extent. */ +static inline xfs_extlen_t +xfs_rgbno_to_rtxoff( + struct xfs_mount *mp, + xfs_rgblock_t rgbno) +{ + return rgbno % mp->m_sb.sb_rextsize; +} + /* Return the offset of an rt block number within an rt extent. */ static inline xfs_extlen_t xfs_rtb_to_rtxoff( diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 4f3bfc884aff..9186c58e83d5 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -33,6 +33,8 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_metadir.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Find the first usable fsblock in this rtgroup. */ static inline uint32_t @@ -192,16 +194,24 @@ xfs_rtgroup_lock( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); - if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - /* - * Lock both realtime free space metadata inodes for a freespace - * update. - */ - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); - } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + if (!xfs_has_zoned(rtg_mount(rtg))) { + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { + /* + * Lock both realtime free space metadata inodes for a + * freespace update. + */ + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL); + } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); + } } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_ilock(rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Unlock metadata inodes associated with this rt group. */ @@ -214,11 +224,19 @@ xfs_rtgroup_unlock( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); - if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); - } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_iunlock(rtg_refcount(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if (!xfs_has_zoned(rtg_mount(rtg))) { + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { + xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); + } } } @@ -235,12 +253,17 @@ xfs_rtgroup_trans_join( ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)); - if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP], - XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY], - XFS_ILOCK_EXCL); + if (!xfs_has_zoned(rtg_mount(rtg)) && + (rtglock_flags & XFS_RTGLOCK_BITMAP)) { + xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL); } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_trans_ijoin(tp, rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Retrieve rt group geometry. */ @@ -252,7 +275,7 @@ xfs_rtgroup_get_geometry( /* Fill out form. */ memset(rgeo, 0, sizeof(*rgeo)); rgeo->rg_number = rtg_rgno(rtg); - rgeo->rg_length = rtg_group(rtg)->xg_block_count; + rgeo->rg_length = rtg_blocks(rtg); xfs_rtgroup_geom_health(rtg, rgeo); return 0; } @@ -284,7 +307,8 @@ xfs_rtginode_ilock_print_fn( const struct xfs_inode *ip = container_of(m, struct xfs_inode, i_lock.dep_map); - printk(KERN_CONT " rgno=%u", ip->i_projid); + printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid, + xfs_metafile_type_str(ip->i_metatype)); } /* @@ -316,8 +340,10 @@ struct xfs_rtginode_ops { unsigned int sick; /* rtgroup sickness flag */ + unsigned int fmt_mask; /* all valid data fork formats */ + /* Does the fs have this feature? */ - bool (*enabled)(struct xfs_mount *mp); + bool (*enabled)(const struct xfs_mount *mp); /* Create this rtgroup metadata inode and initialize it. */ int (*create)(struct xfs_rtgroup *rtg, @@ -331,14 +357,42 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { .name = "bitmap", .metafile_type = XFS_METAFILE_RTBITMAP, .sick = XFS_SICK_RG_BITMAP, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), + .enabled = xfs_has_nonzoned, .create = xfs_rtbitmap_create, }, [XFS_RTGI_SUMMARY] = { .name = "summary", .metafile_type = XFS_METAFILE_RTSUMMARY, .sick = XFS_SICK_RG_SUMMARY, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), + .enabled = xfs_has_nonzoned, .create = xfs_rtsummary_create, }, + [XFS_RTGI_RMAP] = { + .name = "rmap", + .metafile_type = XFS_METAFILE_RTRMAP, + .sick = XFS_SICK_RG_RMAPBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use the + * rtrmapbt predicate here. + */ + .enabled = xfs_has_rmapbt, + .create = xfs_rtrmapbt_create, + }, + [XFS_RTGI_REFCOUNT] = { + .name = "refcount", + .metafile_type = XFS_METAFILE_RTREFCOUNT, + .sick = XFS_SICK_RG_REFCNTBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* same comment about growfs and rmap inodes applies here */ + .enabled = xfs_has_reflink, + .create = xfs_rtrefcountbt_create, + }, }; /* Return the shortname of this rtgroup inode. */ @@ -435,8 +489,7 @@ xfs_rtginode_load( return error; } - if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { + if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 2d7822644eff..d36a6ae0abe5 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -14,6 +14,8 @@ struct xfs_trans; enum xfs_rtg_inodes { XFS_RTGI_BITMAP, /* allocation bitmap */ XFS_RTGI_SUMMARY, /* allocation summary */ + XFS_RTGI_RMAP, /* rmap btree inode */ + XFS_RTGI_REFCOUNT, /* refcount btree inode */ XFS_RTGI_MAX, }; @@ -35,15 +37,33 @@ struct xfs_rtgroup { xfs_rtxnum_t rtg_extents; /* - * Cache of rt summary level per bitmap block with the invariant that - * rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0, - * or 0 if rsum[i][bbno] == 0 for all i. - * + * For bitmap based RT devices this points to a cache of rt summary + * level per bitmap block with the invariant that rtg_rsum_cache[bbno] + * > the maximum i for which rsum[i][bbno] != 0, or 0 if + * rsum[i][bbno] == 0 for all i. * Reads and writes are serialized by the rsumip inode lock. + * + * For zoned RT devices this points to the open zone structure for + * a group that is open for writers, or is NULL. */ - uint8_t *rtg_rsum_cache; + union { + uint8_t *rtg_rsum_cache; + struct xfs_open_zone *rtg_open_zone; + }; }; +/* + * For zoned RT devices this is set on groups that have no written blocks + * and can be picked by the allocator for opening. + */ +#define XFS_RTG_FREE XA_MARK_0 + +/* + * For zoned RT devices this is set on groups that are fully written and that + * have unused blocks. Used by the garbage collection to pick targets. + */ +#define XFS_RTG_RECLAIMABLE XA_MARK_1 + static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg) { return container_of(xg, struct xfs_rtgroup, rtg_group); @@ -64,6 +84,31 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg) return rtg->rtg_group.xg_gno; } +static inline xfs_rgblock_t rtg_blocks(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_group.xg_block_count; +} + +static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_BITMAP]; +} + +static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_SUMMARY]; +} + +static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_RMAP]; +} + +static inline struct xfs_inode *rtg_refcount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_REFCOUNT]; +} + /* Passive rtgroup references */ static inline struct xfs_rtgroup * xfs_rtgroup_get( @@ -122,6 +167,32 @@ xfs_rtgroup_next( return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1); } +static inline bool +xfs_verify_rgbno( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbno(rtg_group(rtg), rgbno); +} + +/* + * Check that [@rgbno,@len] is a valid extent range in @rtg. + * + * Must only be used for RTG-enabled file systems. + */ +static inline bool +xfs_verify_rgbext( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno, + xfs_extlen_t len) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbext(rtg_group(rtg), rgbno, len); +} + static inline xfs_rtblock_t xfs_rgbno_to_rtb( struct xfs_rtgroup *rtg, @@ -174,10 +245,14 @@ xfs_rtb_to_daddr( xfs_rtblock_t rtbno) { struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; - xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno); - uint64_t start_bno = (xfs_rtblock_t)rgno * g->blocks; - return XFS_FSB_TO_BB(mp, start_bno + (rtbno & g->blkmask)); + if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) { + xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno); + + rtbno = (xfs_rtblock_t)rgno * g->blocks + (rtbno & g->blkmask); + } + + return XFS_FSB_TO_BB(mp, g->start_fsb + rtbno); } static inline xfs_rtblock_t @@ -185,10 +260,11 @@ xfs_daddr_to_rtb( struct xfs_mount *mp, xfs_daddr_t daddr) { - xfs_rfsblock_t bno = XFS_BB_TO_FSBT(mp, daddr); + struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + xfs_rfsblock_t bno; - if (xfs_has_rtgroups(mp)) { - struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb; + if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) { xfs_rgnumber_t rgno; uint32_t rgbno; @@ -223,9 +299,15 @@ int xfs_update_last_rtgroup_size(struct xfs_mount *mp, #define XFS_RTGLOCK_BITMAP (1U << 0) /* Lock the rt bitmap inode in shared mode */ #define XFS_RTGLOCK_BITMAP_SHARED (1U << 1) +/* Lock the rt rmap inode in exclusive mode */ +#define XFS_RTGLOCK_RMAP (1U << 2) +/* Lock the rt refcount inode in exclusive mode */ +#define XFS_RTGLOCK_REFCOUNT (1U << 3) #define XFS_RTGLOCK_ALL_FLAGS (XFS_RTGLOCK_BITMAP | \ - XFS_RTGLOCK_BITMAP_SHARED) + XFS_RTGLOCK_BITMAP_SHARED | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); @@ -248,6 +330,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, bool init); void xfs_rtginode_irele(struct xfs_inode **ipp); +void xfs_rtginode_irele(struct xfs_inode **ipp); + static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno, enum xfs_rtg_inodes type) { diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c new file mode 100644 index 000000000000..3db5e7a4a945 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_refcount.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "xfs_metafile.h" +#include "xfs_health.h" + +static struct kmem_cache *xfs_rtrefcountbt_cur_cache; + +/* + * Realtime Reference Count btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_refcount_btree.c for more information. + * + * This tree is basically the same as the regular refcount btree except that + * it's rooted in an inode. + */ + +static struct xfs_btree_cur * +xfs_rtrefcountbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrefcountbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrefcountbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrefc_mnr[level != 0]; +} + +STATIC int +xfs_rtrefcountbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrefc_mxr[level != 0]; +} + +/* + * Calculate number of records in a realtime refcount btree inode root. + */ +unsigned int +xfs_rtrefcountbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrefcount_root); + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (2 * sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrefcountbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork so that + * we can resize the in-memory buffer to match it. After a resize to the + * maximum size this function returns the same value as + * xfs_rtrefcountbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrefcountbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrefc_mxr[level != 0]; + return xfs_rtrefcountbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +STATIC void +xfs_rtrefcountbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->refc.rc_startblock = rec->refc.rc_startblock; +} + +STATIC void +xfs_rtrefcountbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + __u32 x; + + x = be32_to_cpu(rec->refc.rc_startblock); + x += be32_to_cpu(rec->refc.rc_blockcount) - 1; + key->refc.rc_startblock = cpu_to_be32(x); +} + +STATIC void +xfs_rtrefcountbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); + rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); + rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); +} + +STATIC void +xfs_rtrefcountbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +STATIC int64_t +xfs_rtrefcountbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return (int64_t)be32_to_cpu(kp->rc_startblock) - start; +} + +STATIC int64_t +xfs_rtrefcountbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - + be32_to_cpu(k2->refc.rc_startblock); +} + +static xfs_failaddr_t +xfs_rtrefcountbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_reflink(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrefc_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrefc_mxr[level != 0]); +} + +static void +xfs_rtrefcountbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrefcountbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrefcountbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrefcountbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops = { + .name = "xfs_rtrefcountbt", + .magic = { 0, cpu_to_be32(XFS_RTREFC_CRC_MAGIC) }, + .verify_read = xfs_rtrefcountbt_read_verify, + .verify_write = xfs_rtrefcountbt_write_verify, + .verify_struct = xfs_rtrefcountbt_verify, +}; + +STATIC int +xfs_rtrefcountbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + return be32_to_cpu(k1->refc.rc_startblock) < + be32_to_cpu(k2->refc.rc_startblock); +} + +STATIC int +xfs_rtrefcountbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + return be32_to_cpu(r1->refc.rc_startblock) + + be32_to_cpu(r1->refc.rc_blockcount) <= + be32_to_cpu(r2->refc.rc_startblock); +} + +STATIC enum xbtree_key_contig +xfs_rtrefcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + +static inline void +xfs_rtrefcountbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrefcount_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrefcountbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrefcount_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrefcountbt_maxrecs(mp, old_size, level); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, broot, old_size, + new_size, old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, ifp->if_broot, old_size, + new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrefcount_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrefcountbt_ops = { + .name = "rtrefcount", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_refcount_rec), + .key_len = sizeof(struct xfs_refcount_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_REFC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrefcbt_2), + .sick_mask = XFS_SICK_RG_REFCNTBT, + + .dup_cursor = xfs_rtrefcountbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrefcountbt_get_minrecs, + .get_maxrecs = xfs_rtrefcountbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrefcountbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrefcountbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrefcountbt_init_ptr_from_cur, + .key_diff = xfs_rtrefcountbt_key_diff, + .buf_ops = &xfs_rtrefcountbt_buf_ops, + .diff_two_keys = xfs_rtrefcountbt_diff_two_keys, + .keys_inorder = xfs_rtrefcountbt_keys_inorder, + .recs_inorder = xfs_rtrefcountbt_recs_inorder, + .keys_contiguous = xfs_rtrefcountbt_keys_contiguous, + .broot_realloc = xfs_rtrefcountbt_broot_realloc, +}; + +/* Allocate a new rt refcount btree cursor. */ +struct xfs_btree_cur * +xfs_rtrefcountbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_refcount(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrefcountbt_ops, + mp->m_rtrefc_maxlevels, xfs_rtrefcountbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_refc.nr_ops = 0; + cur->bc_refc.shape_changes = 0; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + cur->bc_ino.whichfork = XFS_DATA_FORK; + return cur; +} + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrefcountbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a realtime refcount btree block. */ +static inline unsigned int +xfs_rtrefcountbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Calculate number of records in an refcount btree block. + */ +unsigned int +xfs_rtrefcountbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTREFCOUNT_BLOCK_LEN; + return xfs_rtrefcountbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime refcount btrees. */ +unsigned int +xfs_rtrefcountbt_maxlevels_ondisk(void) +{ + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; + + /* We need at most one record for every block in an rt group. */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); +} + +int __init +xfs_rtrefcountbt_init_cur_cache(void) +{ + xfs_rtrefcountbt_cur_cache = kmem_cache_create("xfs_rtrefcountbt_cur", + xfs_btree_cur_sizeof( + xfs_rtrefcountbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrefcountbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrefcountbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrefcountbt_cur_cache); + xfs_rtrefcountbt_cur_cache = NULL; +} + +/* Compute the maximum height of a realtime refcount btree. */ +void +xfs_rtrefcountbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtreflink(mp)) { + mp->m_rtrefc_maxlevels = 0; + return; + } + + /* + * The realtime refcountbt lives on the data device, which means that + * its maximum height is constrained by the size of the data device and + * the height required to store one refcount record for each rtextent + * in an rt group. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrefc_mnr, + mp->m_sb.sb_dblocks); + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrefc_mnr, + mp->m_sb.sb_rgextents); + + /* Add one level to handle the inode root level. */ + mp->m_rtrefc_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrefcount btree size for some records. */ +unsigned long long +xfs_rtrefcountbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrefc_mnr, len); +} + +/* + * Calculate the maximum refcount btree size. + */ +static unsigned long long +xfs_rtrefcountbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrefc_mxr[0] == 0) + return 0; + + return xfs_rtrefcountbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + * We need enough space to hold one record for every rt extent in the rtgroup. + */ +xfs_filblks_t +xfs_rtrefcountbt_calc_reserves( + struct xfs_mount *mp) +{ + if (!xfs_has_rtreflink(mp)) + return 0; + + return xfs_rtrefcountbt_max_size(mp, mp->m_sb.sb_rgextents); +} + +/* + * Convert on-disk form of btree root to in-memory form. + */ +STATIC void +xfs_rtrefcountbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrefcount_root *dblock, + int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + unsigned int rblocklen; + + rblocklen = xfs_rtrefcount_broot_space(mp, dblock); + + xfs_btree_init_block(mp, rblock, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + tkp = xfs_rtrefcount_key_addr(rblock, 1); + fpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + trp = xfs_rtrefcount_rec_addr(rblock, 1); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reference count btree root in from disk. */ +int +xfs_iformat_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrefcount inodes before adding a realtime + * volume to the filesystem, so we cannot use the rtrefcount predicate + * here. + */ + if (!xfs_has_reflink(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrefc_maxlevels || + xfs_rtrefcount_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrefcount_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrefcountbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* + * Convert in-memory form of btree root to on-disk form. + */ +void +xfs_rtrefcountbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + int rblocklen, + struct xfs_rtrefcount_root *dblock, + int dblocklen) +{ + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int maxrecs; + unsigned int numrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTREFC_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_key_addr(rblock, 1); + tkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + fpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_rec_addr(rblock, 1); + trp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reference count btree root out to disk. */ +void +xfs_iflush_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrefcount_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrefcountbt_to_disk(ip->i_mount, ifp->if_broot, + ifp->if_broot_bytes, dfp, + XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime refcount btree inode. + */ +int +xfs_rtrefcountbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, + xfs_rtrefcount_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.h b/fs/xfs/libxfs/xfs_rtrefcount_btree.h new file mode 100644 index 000000000000..a99b7a8aec86 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTREFCOUNT_BTREE_H__ +#define __XFS_RTREFCOUNT_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; + +/* refcounts only exist on crc enabled filesystems */ +#define XFS_RTREFCOUNT_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrefcountbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrefcountbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrefcountbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrefcountbt_maxrecs(struct xfs_mount *mp, + unsigned int blocklen, bool leaf); +void xfs_rtrefcountbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrefcountbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrefcountbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_refcount_rec * +xfs_rtrefcount_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +unsigned int xfs_rtrefcountbt_maxlevels_ondisk(void); +int __init xfs_rtrefcountbt_init_cur_cache(void); +void xfs_rtrefcountbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrefcountbt_calc_reserves(struct xfs_mount *mp); +unsigned long long xfs_rtrefcountbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +/* Addresses of key, pointers, and records within an ondisk rtrefcount block. */ + +static inline struct xfs_refcount_rec * +xfs_rtrefcount_droot_rec_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_droot_key_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_droot_ptr_addr( + struct xfs_rtrefcount_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrefcount_ptr_addr(bb, index, + xfs_rtrefcountbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrefcount_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTREFCOUNT_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrefcount_broot_space(struct xfs_mount *mp, struct xfs_rtrefcount_root *bb) +{ + return xfs_rtrefcount_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrefcount_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrefcount_root); + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrefcount_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrefcount_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrefcountbt_to_disk(struct xfs_mount *mp, + struct xfs_btree_block *rblock, int rblocklen, + struct xfs_rtrefcount_root *dblock, int dblocklen); +void xfs_iflush_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrefcountbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); + +#endif /* __XFS_RTREFCOUNT_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c new file mode 100644 index 000000000000..9bdc2cbfc113 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -0,0 +1,1054 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_metafile.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_bmap.h" +#include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" + +static struct kmem_cache *xfs_rtrmapbt_cur_cache; + +/* + * Realtime Reverse Map btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_rmap_btree.c for more information. + * + * This tree is basically the same as the regular rmap btree except that it + * is rooted in an inode and does not live in free space. + */ + +static struct xfs_btree_cur * +xfs_rtrmapbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrmapbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrmapbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrmap_mnr[level != 0]; +} + +STATIC int +xfs_rtrmapbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrmap_mxr[level != 0]; +} + +/* Calculate number of records in the ondisk realtime rmap btree inode root. */ +unsigned int +xfs_rtrmapbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrmap_root); + + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork + * so that we can resize the in-memory buffer to match it. After a + * resize to the maximum size this function returns the same value + * as xfs_rtrmapbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrmapbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrmap_mxr[level != 0]; + return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + +STATIC void +xfs_rtrmapbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->rmap.rm_startblock = rec->rmap.rm_startblock; + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); +} + +STATIC void +xfs_rtrmapbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + uint64_t off; + int adj; + + adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; + + key->rmap.rm_startblock = rec->rmap.rm_startblock; + be32_add_cpu(&key->rmap.rm_startblock, adj); + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); + if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || + XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) + return; + off = be64_to_cpu(key->rmap.rm_offset); + off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); + key->rmap.rm_offset = cpu_to_be64(off); +} + +STATIC void +xfs_rtrmapbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); + rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); + rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); + rec->rmap.rm_offset = cpu_to_be64( + xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); +} + +STATIC void +xfs_rtrmapbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + +STATIC int64_t +xfs_rtrmapbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + struct xfs_rmap_irec *rec = &cur->bc_rec.r; + const struct xfs_rmap_key *kp = &key->rmap; + __u64 x, y; + int64_t d; + + d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; + if (d) + return d; + + x = be64_to_cpu(kp->rm_owner); + y = rec->rm_owner; + if (x > y) + return 1; + else if (y > x) + return -1; + + x = offset_keymask(be64_to_cpu(kp->rm_offset)); + y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); + if (x > y) + return 1; + else if (y > x) + return -1; + return 0; +} + +STATIC int64_t +xfs_rtrmapbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + const struct xfs_rmap_key *kp1 = &k1->rmap; + const struct xfs_rmap_key *kp2 = &k2->rmap; + int64_t d; + __u64 x, y; + + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + + d = (int64_t)be32_to_cpu(kp1->rm_startblock) - + be32_to_cpu(kp2->rm_startblock); + if (d) + return d; + + if (!mask || mask->rmap.rm_owner) { + x = be64_to_cpu(kp1->rm_owner); + y = be64_to_cpu(kp2->rm_owner); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + x = offset_keymask(be64_to_cpu(kp1->rm_offset)); + y = offset_keymask(be64_to_cpu(kp2->rm_offset)); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + return 0; +} + +static xfs_failaddr_t +xfs_rtrmapbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_rmapbt(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrmap_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrmap_mxr[level != 0]); +} + +static void +xfs_rtrmapbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrmapbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrmapbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrmapbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrmapbt_buf_ops = { + .name = "xfs_rtrmapbt", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_read_verify, + .verify_write = xfs_rtrmapbt_write_verify, + .verify_struct = xfs_rtrmapbt_verify, +}; + +STATIC int +xfs_rtrmapbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(k1->rmap.rm_startblock); + y = be32_to_cpu(k2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(k1->rmap.rm_owner); + b = be64_to_cpu(k2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC int +xfs_rtrmapbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(r1->rmap.rm_startblock); + y = be32_to_cpu(r2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(r1->rmap.rm_owner); + b = be64_to_cpu(r2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC enum xbtree_key_contig +xfs_rtrmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->rmap.rm_startblock); + + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + +static inline void +xfs_rtrmapbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrmapbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, + old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, + new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrmap_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrmapbt_ops = { + .name = "rtrmap", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_OVERLAPPING | + XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_2), + .sick_mask = XFS_SICK_RG_RMAPBT, + + .dup_cursor = xfs_rtrmapbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrmapbt_get_minrecs, + .get_maxrecs = xfs_rtrmapbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, + .broot_realloc = xfs_rtrmapbt_broot_realloc, +}; + +/* Allocate a new rt rmap btree cursor. */ +struct xfs_btree_cur * +xfs_rtrmapbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_rmap(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_ino.whichfork = XFS_DATA_FORK; + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + + return cur; +} + +#ifdef CONFIG_XFS_BTREE_IN_MEM +/* + * Validate an in-memory realtime rmap btree block. Callers are allowed to + * generate an in-memory btree even if the ondisk feature is not enabled. + */ +static xfs_failaddr_t +xfs_rtrmapbt_mem_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + unsigned int level; + unsigned int maxrecs; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + + level = be16_to_cpu(block->bb_level); + if (xfs_has_rmapbt(mp)) { + if (level >= mp->m_rtrmap_maxlevels) + return __this_address; + } else { + if (level >= xfs_rtrmapbt_maxlevels_ondisk()) + return __this_address; + } + + maxrecs = xfs_rtrmapbt_maxrecs(mp, XFBNO_BLOCKSIZE, level == 0); + return xfs_btree_memblock_verify(bp, maxrecs); +} + +static void +xfs_rtrmapbt_mem_rw_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa = xfs_rtrmapbt_mem_verify(bp); + + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +/* skip crc checks on in-memory btrees to save time */ +static const struct xfs_buf_ops xfs_rtrmapbt_mem_buf_ops = { + .name = "xfs_rtrmapbt_mem", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_mem_rw_verify, + .verify_write = xfs_rtrmapbt_mem_rw_verify, + .verify_struct = xfs_rtrmapbt_mem_verify, +}; + +const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = { + .type = XFS_BTREE_TYPE_MEM, + .geom_flags = XFS_BTGEO_OVERLAPPING, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_mem_2), + + .dup_cursor = xfbtree_dup_cursor, + .set_root = xfbtree_set_root, + .alloc_block = xfbtree_alloc_block, + .free_block = xfbtree_free_block, + .get_minrecs = xfbtree_get_minrecs, + .get_maxrecs = xfbtree_get_maxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfbtree_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_mem_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, +}; + +/* Create a cursor for an in-memory btree. */ +struct xfs_btree_cur * +xfs_rtrmapbt_mem_cursor( + struct xfs_rtgroup *rtg, + struct xfs_trans *tp, + struct xfbtree *xfbt) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + cur->bc_mem.xfbtree = xfbt; + cur->bc_nlevels = xfbt->nlevels; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + return cur; +} + +/* Create an in-memory realtime rmap btree. */ +int +xfs_rtrmapbt_mem_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + xfs_rgnumber_t rgno) +{ + xfbt->owner = rgno; + return xfbtree_init(mp, xfbt, btp, &xfs_rtrmapbt_mem_ops); +} +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrmapbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a rt reverse mapping btree block. */ +static inline unsigned int +xfs_rtrmapbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / + (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Calculate number of records in an rt reverse mapping btree block. + */ +unsigned int +xfs_rtrmapbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTRMAP_BLOCK_LEN; + return xfs_rtrmapbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime reverse mapping btrees. */ +unsigned int +xfs_rtrmapbt_maxlevels_ondisk(void) +{ + unsigned long long max_dblocks; + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrmapbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrmapbt_block_maxrecs(blocklen, false) / 2; + + /* + * Compute the asymptotic maxlevels for an rtrmapbt on any rtreflink fs. + * + * On a reflink filesystem, each block in an rtgroup can have up to + * 2^32 (per the refcount record format) owners, which means that + * theoretically we could face up to 2^64 rmap records. However, we're + * likely to run out of blocks in the data device long before that + * happens, which means that we must compute the max height based on + * what the btree will look like if it consumes almost all the blocks + * in the data device due to maximal sharing factor. + */ + max_dblocks = -1U; /* max ag count */ + max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; + return xfs_btree_space_to_height(minrecs, max_dblocks); +} + +int __init +xfs_rtrmapbt_init_cur_cache(void) +{ + xfs_rtrmapbt_cur_cache = kmem_cache_create("xfs_rtrmapbt_cur", + xfs_btree_cur_sizeof(xfs_rtrmapbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrmapbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrmapbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_cur_cache = NULL; +} + +/* Compute the maximum height of an rt reverse mapping btree. */ +void +xfs_rtrmapbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtrmapbt(mp)) { + mp->m_rtrmap_maxlevels = 0; + return; + } + + /* + * The realtime rmapbt lives on the data device, which means that its + * maximum height is constrained by the size of the data device and + * the height required to store one rmap record for each block in an + * rt group. + * + * On a reflink filesystem, each rt block can have up to 2^32 (per the + * refcount record format) owners, which means that theoretically we + * could face up to 2^64 rmap records. This makes the computation of + * maxlevels based on record count meaningless, so we only consider the + * size of the data device. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrmap_mnr, + mp->m_sb.sb_dblocks); + if (xfs_has_rtreflink(mp)) { + mp->m_rtrmap_maxlevels = d_maxlevels + 1; + return; + } + + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrmap_mnr, + mp->m_groups[XG_TYPE_RTG].blocks); + + /* Add one level to handle the inode root level. */ + mp->m_rtrmap_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrmap btree size for some records. */ +unsigned long long +xfs_rtrmapbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrmap_mnr, len); +} + +/* + * Calculate the maximum rmap btree size. + */ +static unsigned long long +xfs_rtrmapbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrmap_mxr[0] == 0) + return 0; + + return xfs_rtrmapbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + */ +xfs_filblks_t +xfs_rtrmapbt_calc_reserves( + struct xfs_mount *mp) +{ + uint32_t blocks = mp->m_groups[XG_TYPE_RTG].blocks; + + if (!xfs_has_rtrmapbt(mp)) + return 0; + + /* Reserve 1% of the rtgroup or enough for 1 block per record. */ + return max_t(xfs_filblks_t, blocks / 100, + xfs_rtrmapbt_max_size(mp, blocks)); +} + +/* Convert on-disk form of btree root to in-memory form. */ +STATIC void +xfs_rtrmapbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); + unsigned int numrecs; + unsigned int maxrecs; + + xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + numrecs = be16_to_cpu(dblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_droot_key_addr(dblock, 1); + tkp = xfs_rtrmap_key_addr(rblock, 1); + fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_droot_rec_addr(dblock, 1); + trp = xfs_rtrmap_rec_addr(rblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reverse mapping btree root in from disk. */ +int +xfs_iformat_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrmap inodes before adding a realtime volume + * to the filesystem, so we cannot use the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrmap_maxlevels || + xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrmap_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* Convert in-memory form of btree root to on-disk form. */ +void +xfs_rtrmapbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + unsigned int rblocklen, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen) +{ + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + numrecs = be16_to_cpu(rblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_key_addr(rblock, 1); + tkp = xfs_rtrmap_droot_key_addr(dblock, 1); + fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_rec_addr(rblock, 1); + trp = xfs_rtrmap_droot_rec_addr(dblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reverse mapping btree root out to disk. */ +void +xfs_iflush_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, + dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime rmap btree inode. + */ +int +xfs_rtrmapbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, xfs_rtrmap_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrmapbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + + return 0; +} + +/* + * Initialize an rmap for a realtime superblock using the potentially updated + * rt geometry in the provided @mp. + */ +int +xfs_rtrmapbt_init_rtsb( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + struct xfs_trans *tp) +{ + struct xfs_rmap_irec rmap = { + .rm_blockcount = mp->m_sb.sb_rextsize, + .rm_owner = XFS_RMAP_OWN_FS, + }; + struct xfs_btree_cur *cur; + int error; + + ASSERT(xfs_has_rtsb(mp)); + ASSERT(rtg_rgno(rtg) == 0); + + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + error = xfs_rmap_map_raw(cur, &rmap); + xfs_btree_del_cursor(cur, error); + return error; +} + +/* + * Return the highest rgbno currently tracked by the rmap for this rtg. + */ +xfs_rgblock_t +xfs_rtrmap_highest_rgbno( + struct xfs_rtgroup *rtg) +{ + struct xfs_btree_block *block = rtg_rmap(rtg)->i_df.if_broot; + union xfs_btree_key key = {}; + struct xfs_btree_cur *cur; + + if (block->bb_numrecs == 0) + return NULLRGBLOCK; + cur = xfs_rtrmapbt_init_cursor(NULL, rtg); + xfs_btree_get_keys(cur, block, &key); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + return be32_to_cpu(key.__rmap_bigkey[1].rm_startblock); +} diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h new file mode 100644 index 000000000000..e328fd62a149 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTRMAP_BTREE_H__ +#define __XFS_RTRMAP_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; +struct xfbtree; + +/* rmaps only exist on crc enabled filesystems */ +#define XFS_RTRMAP_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrmapbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrmapbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); +void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrmapbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_rmap_rec * +xfs_rtrmap_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_high_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + sizeof(struct xfs_rmap_key) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +unsigned int xfs_rtrmapbt_maxlevels_ondisk(void); + +int __init xfs_rtrmapbt_init_cur_cache(void); +void xfs_rtrmapbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp); + +/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */ + +static inline struct xfs_rmap_rec * +xfs_rtrmap_droot_rec_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_droot_key_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)(block + 1) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_droot_ptr_addr( + struct xfs_rtrmap_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)(block + 1) + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrmap_ptr_addr(bb, index, + xfs_rtrmapbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTRMAP_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb) +{ + return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrmap_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrmap_root); + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrmap_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock, + unsigned int rblocklen, struct xfs_rtrmap_root *dblock, + unsigned int dblocklen); +void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrmapbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); +int xfs_rtrmapbt_init_rtsb(struct xfs_mount *mp, struct xfs_rtgroup *rtg, + struct xfs_trans *tp); + +unsigned long long xfs_rtrmapbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg, + struct xfs_trans *tp, struct xfbtree *xfbtree); +int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree, + struct xfs_buftarg *btp, xfs_rgnumber_t rgno); + +xfs_rgblock_t xfs_rtrmap_highest_rgbno(struct xfs_rtgroup *rtg); + +#endif /* __XFS_RTRMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 3b5623611eba..711e180f9ebb 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -28,6 +28,8 @@ #include "xfs_rtbitmap.h" #include "xfs_exchrange.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -183,6 +185,8 @@ xfs_sb_version_to_features( features |= XFS_FEAT_PARENT; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) features |= XFS_FEAT_METADIR; + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) + features |= XFS_FEAT_ZONED; return features; } @@ -264,6 +268,9 @@ static uint64_t xfs_expected_rbmblocks( struct xfs_sb *sbp) { + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) + return 0; return howmany_64(xfs_extents_per_rbm(sbp), NBBY * xfs_rtbmblock_size(sbp)); } @@ -273,9 +280,15 @@ bool xfs_validate_rt_geometry( struct xfs_sb *sbp) { - if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || - sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) - return false; + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { + if (sbp->sb_rextsize != 1) + return false; + } else { + if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || + sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) + return false; + } if (sbp->sb_rblocks == 0) { if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || @@ -433,6 +446,34 @@ xfs_validate_sb_rtgroups( return 0; } +static int +xfs_validate_sb_zoned( + struct xfs_mount *mp, + struct xfs_sb *sbp) +{ + if (sbp->sb_frextents != 0) { + xfs_warn(mp, +"sb_frextents must be zero for zoned file systems."); + return -EINVAL; + } + + if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) { + xfs_warn(mp, +"sb_rtstart (%lld) overlaps sb_dblocks (%lld).", + sbp->sb_rtstart, sbp->sb_dblocks); + return -EINVAL; + } + + if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) { + xfs_warn(mp, +"sb_rtreserved (%lld) larger than sb_rblocks (%lld).", + sbp->sb_rtreserved, sbp->sb_rblocks); + return -EINVAL; + } + + return 0; +} + /* Check the validity of the SB. */ STATIC int xfs_validate_sb_common( @@ -521,6 +562,11 @@ xfs_validate_sb_common( if (error) return error; } + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + error = xfs_validate_sb_zoned(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, @@ -833,6 +879,14 @@ __xfs_sb_from_disk( to->sb_rgcount = 1; to->sb_rgextents = 0; } + + if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + to->sb_rtstart = be64_to_cpu(from->sb_rtstart); + to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved); + } else { + to->sb_rtstart = 0; + to->sb_rtreserved = 0; + } } void @@ -999,6 +1053,11 @@ xfs_sb_to_disk( to->sb_rbmino = cpu_to_be64(0); to->sb_rsumino = cpu_to_be64(0); } + + if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + to->sb_rtstart = cpu_to_be64(from->sb_rtstart); + to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved); + } } /* @@ -1144,6 +1203,10 @@ xfs_sb_mount_rextsize( rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize; rgs->blklog = mp->m_sb.sb_rgblklog; rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog); + rgs->start_fsb = mp->m_sb.sb_rtstart; + if (xfs_sb_has_incompat_feature(sbp, + XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)) + rgs->has_daddr_gaps = true; } else { rgs->blocks = 0; rgs->blklog = 0; @@ -1215,11 +1278,23 @@ xfs_sb_mount_common( mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; + mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); + mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; + mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; + mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; + mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + true); + mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + false); + mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; + mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; + mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); @@ -1251,8 +1326,7 @@ xfs_log_sb( mp->m_sb.sb_ifree = min_t(uint64_t, percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); - mp->m_sb.sb_fdblocks = - percpu_counter_sum_positive(&mp->m_fdblocks); + mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS); } /* @@ -1261,9 +1335,10 @@ xfs_log_sb( * we handle nearly-lockless reservations, so we must use the _positive * variant here to avoid writing out nonsense frextents. */ - if (xfs_has_rtgroups(mp)) + if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) { mp->m_sb.sb_frextents = - percpu_counter_sum_positive(&mp->m_frextents); + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS); + } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); @@ -1496,6 +1571,8 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE; if (xfs_has_metadir(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR; + if (xfs_has_zoned(mp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED; geo->rtsectsize = sbp->sb_blocksize; geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp); @@ -1516,6 +1593,10 @@ xfs_fs_geometry( geo->rgcount = sbp->sb_rgcount; geo->rgextents = sbp->sb_rgextents; } + if (xfs_has_zoned(mp)) { + geo->rtstart = sbp->sb_rtstart; + geo->rtreserved = sbp->sb_rtreserved; + } } /* Read a secondary superblock. */ diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index e7efdb9ceaf3..b1e0d9bc1f7d 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -42,6 +42,8 @@ extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops; extern const struct xfs_buf_ops xfs_rtsummary_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_rtrefcountbt_buf_ops; +extern const struct xfs_buf_ops xfs_rtrmapbt_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; @@ -55,6 +57,9 @@ extern const struct xfs_btree_ops xfs_bmbt_ops; extern const struct xfs_btree_ops xfs_refcountbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrefcountbt_ops; static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops) { @@ -96,10 +101,26 @@ static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops) { return ops == &xfs_rmapbt_mem_ops; } + +static inline bool xfs_btree_is_mem_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_mem_ops; +} #else # define xfs_btree_is_mem_rmap(...) (false) +# define xfs_btree_is_mem_rtrmap(...) (false) #endif +static inline bool xfs_btree_is_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_ops; +} + +static inline bool xfs_btree_is_rtrefcount(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrefcountbt_ops; +} + /* log size calculation functions */ int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes); int xfs_log_calc_minimum_size(struct xfs_mount *); diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index bab402340b5d..13d00c7166e1 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -92,6 +92,14 @@ xfs_refcountbt_block_count( return num_ops * (2 * mp->m_refc_maxlevels - 1); } +static unsigned int +xfs_rtrefcountbt_block_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + return num_ops * (2 * mp->m_rtrefc_maxlevels - 1); +} + /* * Logging inodes is really tricksy. They are logged in memory format, * which means that what we write into the log doesn't directly translate into @@ -213,7 +221,9 @@ xfs_calc_inode_chunk_res( * Per-extent log reservation for the btree changes involved in freeing or * allocating a realtime extent. We have to be able to log as many rtbitmap * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime - * extents, as well as the realtime summary block. + * extents, as well as the realtime summary block (t1). Realtime rmap btree + * operations happen in a second transaction, so factor in a couple of rtrmapbt + * splits (t2). */ static unsigned int xfs_rtalloc_block_count( @@ -222,10 +232,16 @@ xfs_rtalloc_block_count( { unsigned int rtbmp_blocks; xfs_rtxlen_t rtxlen; + unsigned int t1, t2 = 0; rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN); rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen); - return (rtbmp_blocks + 1) * num_ops; + t1 = (rtbmp_blocks + 1) * num_ops; + + if (xfs_has_rmapbt(mp)) + t2 = num_ops * (2 * mp->m_rtrmap_maxlevels - 1); + + return max(t1, t2); } /* @@ -251,10 +267,13 @@ xfs_rtalloc_block_count( * Compute the log reservation required to handle the refcount update * transaction. Refcount updates are always done via deferred log items. * - * This is calculated as: + * This is calculated as the max of: * Data device refcount updates (t1): * the agfs of the ags containing the blocks: nr_ops * sector size * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + * Realtime refcount updates (t2); + * the rt refcount inode + * the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size */ static unsigned int xfs_calc_refcountbt_reservation( @@ -262,12 +281,20 @@ xfs_calc_refcountbt_reservation( unsigned int nr_ops) { unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int t1, t2 = 0; if (!xfs_has_reflink(mp)) return 0; - return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + t1 = xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + + if (xfs_has_realtime(mp)) + t2 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops), + blksz); + + return max(t1, t2); } /* diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index 1155ff2d37e2..d89b570aafcc 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -14,6 +14,19 @@ #define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp) \ (((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0])) +/* Worst case number of realtime rmaps that can be held in a block. */ +#define XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) \ + (((mp)->m_rtrmap_mxr[0]) - ((mp)->m_rtrmap_mnr[0])) + +/* Adding one realtime rmap could split every level to the top of the tree. */ +#define XFS_RTRMAPADD_SPACE_RES(mp) ((mp)->m_rtrmap_maxlevels) + +/* Blocks we might need to add "b" realtime rmaps to a tree. */ +#define XFS_NRTRMAPADD_SPACE_RES(mp, b) \ + ((((b) + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) - 1) / \ + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * \ + XFS_RTRMAPADD_SPACE_RES(mp)) + /* Worst case number of rmaps that can be held in a block. */ #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) \ (((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0])) diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index bf33c2b1e43e..f6f4f2d4b5db 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -202,6 +202,13 @@ enum xfs_ag_resv_type { * altering fdblocks. If you think you need this you're wrong. */ XFS_AG_RESV_IGNORE, + + /* + * This allocation activity is being done on behalf of a metadata file. + * These files maintain their own permanent space reservations and are + * required to adjust fdblocks using the xfs_metafile_resv_* helpers. + */ + XFS_AG_RESV_METAFILE, }; /* Results of scanning a btree keyspace to check occupancy. */ @@ -226,6 +233,34 @@ enum xfs_group_type { { XG_TYPE_AG, "ag" }, \ { XG_TYPE_RTG, "rtg" } +enum xfs_free_counter { + /* + * Number of free blocks on the data device. + */ + XC_FREE_BLOCKS, + + /* + * Number of free RT extents on the RT device. + */ + XC_FREE_RTEXTENTS, + + /* + * Number of available for use RT extents. + * + * This counter only exists for zoned RT device and indicates the number + * of RT extents that can be directly used by writes. XC_FREE_RTEXTENTS + * also includes blocks that have been written previously and freed, but + * sit in a rtgroup that still needs a zone reset. + */ + XC_FREE_RTAVAILABLE, + XC_FREE_NR, +}; + +#define XFS_FREECOUNTER_STR \ + { XC_FREE_BLOCKS, "blocks" }, \ + { XC_FREE_RTEXTENTS, "rtextents" }, \ + { XC_FREE_RTAVAILABLE, "rtavailable" } + /* * Type verifier functions */ diff --git a/fs/xfs/libxfs/xfs_zones.c b/fs/xfs/libxfs/xfs_zones.c new file mode 100644 index 000000000000..b0791a71931c --- /dev/null +++ b/fs/xfs/libxfs/xfs_zones.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_rtgroup.h" +#include "xfs_zones.h" + +static bool +xfs_zone_validate_empty( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (rtg_rmap(rtg)->i_used_blocks > 0) { + xfs_warn(mp, "empty zone %u has non-zero used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + *write_pointer = 0; + return true; +} + +static bool +xfs_zone_validate_wp( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + xfs_rtblock_t wp_fsb = xfs_daddr_to_rtb(mp, zone->wp); + + if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) { + xfs_warn(mp, "zone %u has too large used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + if (xfs_rtb_to_rgno(mp, wp_fsb) != rtg_rgno(rtg)) { + xfs_warn(mp, "zone %u write pointer (0x%llx) outside of zone.", + rtg_rgno(rtg), wp_fsb); + return false; + } + + *write_pointer = xfs_rtb_to_rgbno(mp, wp_fsb); + if (*write_pointer >= rtg->rtg_extents) { + xfs_warn(mp, "zone %u has invalid write pointer (0x%x).", + rtg_rgno(rtg), *write_pointer); + return false; + } + + return true; +} + +static bool +xfs_zone_validate_full( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) { + xfs_warn(mp, "zone %u has too large used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + *write_pointer = rtg->rtg_extents; + return true; +} + +static bool +xfs_zone_validate_seq( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + switch (zone->cond) { + case BLK_ZONE_COND_EMPTY: + return xfs_zone_validate_empty(zone, rtg, write_pointer); + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + return xfs_zone_validate_wp(zone, rtg, write_pointer); + case BLK_ZONE_COND_FULL: + return xfs_zone_validate_full(zone, rtg, write_pointer); + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + xfs_warn(mp, "zone %u has unsupported zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + default: + xfs_warn(mp, "zone %u has unknown zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + } +} + +static bool +xfs_zone_validate_conv( + struct blk_zone *zone, + struct xfs_rtgroup *rtg) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + switch (zone->cond) { + case BLK_ZONE_COND_NOT_WP: + return true; + default: + xfs_warn(mp, +"conventional zone %u has unsupported zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + } +} + +bool +xfs_zone_validate( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + uint32_t expected_size; + + /* + * Check that the zone capacity matches the rtgroup size stored in the + * superblock. Note that all zones including the last one must have a + * uniform capacity. + */ + if (XFS_BB_TO_FSB(mp, zone->capacity) != g->blocks) { + xfs_warn(mp, +"zone %u capacity (0x%llx) does not match RT group size (0x%x).", + rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->capacity), + g->blocks); + return false; + } + + if (g->has_daddr_gaps) { + expected_size = 1 << g->blklog; + } else { + if (zone->len != zone->capacity) { + xfs_warn(mp, +"zone %u has capacity != size ((0x%llx vs 0x%llx)", + rtg_rgno(rtg), + XFS_BB_TO_FSB(mp, zone->len), + XFS_BB_TO_FSB(mp, zone->capacity)); + return false; + } + expected_size = g->blocks; + } + + if (XFS_BB_TO_FSB(mp, zone->len) != expected_size) { + xfs_warn(mp, +"zone %u length (0x%llx) does match geometry (0x%x).", + rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->len), + expected_size); + } + + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + return xfs_zone_validate_conv(zone, rtg); + case BLK_ZONE_TYPE_SEQWRITE_REQ: + return xfs_zone_validate_seq(zone, rtg, write_pointer); + default: + xfs_warn(mp, "zoned %u has unsupported type 0x%x.", + rtg_rgno(rtg), zone->type); + return false; + } +} diff --git a/fs/xfs/libxfs/xfs_zones.h b/fs/xfs/libxfs/xfs_zones.h new file mode 100644 index 000000000000..c4f1367b2cca --- /dev/null +++ b/fs/xfs/libxfs/xfs_zones.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LIBXFS_ZONES_H +#define _LIBXFS_ZONES_H + +struct xfs_rtgroup; + +/* + * In order to guarantee forward progress for GC we need to reserve at least + * two zones: one that will be used for moving data into and one spare zone + * making sure that we have enough space to relocate a nearly-full zone. + * To allow for slightly sloppy accounting for when we need to reserve the + * second zone, we actually reserve three as that is easier than doing fully + * accurate bookkeeping. + */ +#define XFS_GC_ZONES 3U + +/* + * In addition we need two zones for user writes, one open zone for writing + * and one to still have available blocks without resetting the open zone + * when data in the open zone has been freed. + */ +#define XFS_RESERVED_ZONES (XFS_GC_ZONES + 1) +#define XFS_MIN_ZONES (XFS_RESERVED_ZONES + 1) + +/* + * Always keep one zone out of the general open zone pool to allow for GC to + * happen while other writers are waiting for free space. + */ +#define XFS_OPEN_GC_ZONES 1U +#define XFS_MIN_OPEN_ZONES (XFS_OPEN_GC_ZONES + 1U) + +bool xfs_zone_validate(struct blk_zone *zone, struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer); + +#endif /* _LIBXFS_ZONES_H */ diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 9f8c312dfd3c..303374df44bd 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -69,6 +69,8 @@ STATIC size_t xchk_superblock_ondisk_size( struct xfs_mount *mp) { + if (xfs_has_zoned(mp)) + return offsetofend(struct xfs_dsb, sb_rtreserved); if (xfs_has_metadir(mp)) return offsetofend(struct xfs_dsb, sb_pad); if (xfs_has_metauuid(mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index b45d2b32051a..cd6f0223879f 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -647,7 +647,7 @@ xrep_agfl_fill( xfs_agblock_t agbno = start; int error; - trace_xrep_agfl_insert(sc->sa.pag, agbno, len); + trace_xrep_agfl_insert(pag_group(sc->sa.pag), agbno, len); while (agbno < start + len && af->fl_off < af->flcount) af->agfl_bno[af->fl_off++] = cpu_to_be32(agbno++); diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index 0433363a90b6..bed6a09aa791 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -542,8 +542,9 @@ xrep_abt_dispose_one( /* Add a deferred rmap for each extent we used. */ if (resv->used > 0) - xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno, - resv->used, XFS_RMAP_OWN_AG); + xfs_rmap_alloc_extent(sc->tp, false, + xfs_agbno_to_fsb(pag, resv->agbno), resv->used, + XFS_RMAP_OWN_AG); /* * For each reserved btree block we didn't use, add it to the free diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7e00312225ed..4f1e2574660d 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -21,6 +21,8 @@ #include "xfs_rmap_btree.h" #include "xfs_rtgroup.h" #include "xfs_health.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -143,15 +145,22 @@ static inline bool xchk_bmap_get_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno, + xfs_agblock_t bno, uint64_t owner, struct xfs_rmap_irec *rmap) { + struct xfs_btree_cur **curp = &info->sc->sa.rmap_cur; xfs_fileoff_t offset; unsigned int rflags = 0; int has_rmap; int error; + if (xfs_ifork_is_realtime(info->sc->ip, info->whichfork)) + curp = &info->sc->sr.rmap_cur; + + if (*curp == NULL) + return false; + if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; if (irec->br_state == XFS_EXT_UNWRITTEN) @@ -172,13 +181,13 @@ xchk_bmap_get_rmap( * range rmap lookup to make sure we get the correct owner/offset. */ if (info->is_shared) { - error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le_range(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } else { - error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } - if (!xchk_should_check_xref(info->sc, &error, &info->sc->sa.rmap_cur)) + if (!xchk_should_check_xref(info->sc, &error, curp)) return false; if (!has_rmap) @@ -192,29 +201,29 @@ STATIC void xchk_bmap_xref_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; uint64_t owner = info->sc->ip->i_ino; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* * The rmap must be an exact match for this incore file mapping record, * which may have arisen from multiple ondisk records. */ - if (rmap.rm_startblock != agbno) + if (rmap.rm_startblock != bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end != agbno + irec->br_blockcount) + if (rmap_end != bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -259,7 +268,7 @@ STATIC void xchk_bmap_xref_rmap_cow( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; @@ -269,7 +278,7 @@ xchk_bmap_xref_rmap_cow( return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* @@ -277,12 +286,12 @@ xchk_bmap_xref_rmap_cow( * can start before and end after the physical space allocated to this * mapping. There are no offsets to check. */ - if (rmap.rm_startblock > agbno) + if (rmap.rm_startblock > bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end < agbno + irec->br_blockcount) + if (rmap_end < bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -315,6 +324,8 @@ xchk_bmap_rt_iextent_xref( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec) { + struct xfs_owner_info oinfo; + xfs_rgblock_t rgbno; int error; error = xchk_rtgroup_init_existing(info->sc, @@ -324,10 +335,46 @@ xchk_bmap_rt_iextent_xref( irec->br_startoff, &error)) return; - xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL); + error = xchk_rtgroup_lock(info->sc, &info->sc->sr, XCHK_RTGLOCK_ALL); + if (!xchk_fblock_process_error(info->sc, info->whichfork, + irec->br_startoff, &error)) + goto out_free; + xchk_xref_is_used_rt_space(info->sc, irec->br_startblock, irec->br_blockcount); + if (!xfs_has_rtrmapbt(info->sc->mp)) + goto out_cur; + + rgbno = xfs_rtb_to_rgbno(info->sc->mp, irec->br_startblock); + + switch (info->whichfork) { + case XFS_DATA_FORK: + xchk_bmap_xref_rmap(info, irec, rgbno); + if (!xfs_is_reflink_inode(info->sc->ip)) { + xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, + info->whichfork, irec->br_startoff); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &oinfo); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + } + xchk_xref_is_not_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + break; + case XFS_COW_FORK: + xchk_bmap_xref_rmap_cow(info, irec, rgbno); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &XFS_RMAP_OINFO_COW); + xchk_xref_is_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + break; + } +out_cur: + xchk_rtgroup_btcur_free(&info->sc->sr); +out_free: xchk_rtgroup_free(info->sc, &info->sc->sr); } @@ -614,8 +661,7 @@ xchk_bmap_check_rmap( xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_startblock != - xfs_agbno_to_fsb(to_perag(cur->bc_group), - check_rec.rm_startblock)) + xfs_gbno_to_fsb(cur->bc_group, check_rec.rm_startblock)) xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_blockcount > check_rec.rm_blockcount) @@ -669,6 +715,30 @@ xchk_bmap_check_ag_rmaps( return error; } +/* Make sure each rt rmap has a corresponding bmbt entry. */ +STATIC int +xchk_bmap_check_rt_rmaps( + struct xfs_scrub *sc, + struct xfs_rtgroup *rtg) +{ + struct xchk_bmap_check_rmap_info sbcri; + struct xfs_btree_cur *cur; + int error; + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + + sbcri.sc = sc; + sbcri.whichfork = XFS_DATA_FORK; + error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri); + if (error == -ECANCELED) + error = 0; + + xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + return error; +} + /* * Decide if we want to scan the reverse mappings to determine if the attr * fork /really/ has zero space mappings. @@ -723,10 +793,6 @@ xchk_bmap_check_empty_datafork( { struct xfs_ifork *ifp = &ip->i_df; - /* Don't support realtime rmap checks yet. */ - if (XFS_IS_REALTIME_INODE(ip)) - return false; - /* * If the dinode repair found a bad data fork, it will reset the fork * to extents format with zero records and wait for the this scrubber @@ -777,6 +843,21 @@ xchk_bmap_check_rmaps( struct xfs_perag *pag = NULL; int error; + if (xfs_ifork_is_realtime(sc->ip, whichfork)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xchk_bmap_check_rt_rmaps(sc, rtg); + if (error || + (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; + } + while ((pag = xfs_perag_next(sc->mp, pag))) { error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag); if (error || @@ -957,8 +1038,8 @@ xchk_bmap( switch (whichfork) { case XFS_COW_FORK: - /* No CoW forks on non-reflink filesystems. */ - if (!xfs_has_reflink(mp)) { + /* No CoW forks filesystem doesn't support out of place writes */ + if (!xfs_has_reflink(mp) && !xfs_has_zoned(mp)) { xchk_ino_set_corrupt(sc, sc->ip->i_ino); return 0; } @@ -983,6 +1064,7 @@ 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 7c4955482641..1084213b8e9b 100644 --- a/fs/xfs/scrub/bmap_repair.c +++ b/fs/xfs/scrub/bmap_repair.c @@ -25,11 +25,13 @@ #include "xfs_bmap_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" #include "xfs_refcount.h" #include "xfs_quota.h" #include "xfs_ialloc.h" #include "xfs_ag.h" #include "xfs_reflink.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -99,14 +101,21 @@ xrep_bmap_discover_shared( xfs_filblks_t blockcount) { struct xfs_scrub *sc = rb->sc; + struct xfs_btree_cur *cur; xfs_agblock_t agbno; xfs_agblock_t fbno; xfs_extlen_t flen; int error; - agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); - error = xfs_refcount_find_shared(sc->sa.refc_cur, agbno, blockcount, - &fbno, &flen, false); + if (XFS_IS_REALTIME_INODE(sc->ip)) { + agbno = xfs_rtb_to_rgbno(sc->mp, startblock); + cur = sc->sr.refc_cur; + } else { + agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); + cur = sc->sa.refc_cur; + } + error = xfs_refcount_find_shared(cur, agbno, blockcount, &fbno, &flen, + false); if (error) return error; @@ -359,6 +368,114 @@ xrep_bmap_scan_ag( return error; } +#ifdef CONFIG_XFS_RT +/* Check for any obvious errors or conflicts in the file mapping. */ +STATIC int +xrep_bmap_check_rtfork_rmap( + struct xfs_scrub *sc, + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec) +{ + /* xattr extents are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_ATTR_FORK) + return -EFSCORRUPTED; + + /* bmbt blocks are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) + return -EFSCORRUPTED; + + /* Data extents for non-rt files are never stored on the rt device. */ + if (!XFS_IS_REALTIME_INODE(sc->ip)) + return -EFSCORRUPTED; + + /* Check the file offsets and physical extents. */ + if (!xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Check that this is within the rtgroup. */ + if (!xfs_verify_rgbext(to_rtg(cur->bc_group), rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Record realtime extents that belong to this inode's fork. */ +STATIC int +xrep_bmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_bmap *rb = priv; + int error = 0; + + if (xchk_should_terminate(rb->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rb->sc->ip->i_ino) + return 0; + + error = xrep_bmap_check_rtfork_rmap(rb->sc, cur, rec); + if (error) + return error; + + /* + * Record all blocks allocated to this file even if the extent isn't + * for the fork we're rebuilding so that we can reset di_nblocks later. + */ + rb->nblocks += rec->rm_blockcount; + + /* If this rmap isn't for the fork we want, we're done. */ + if (rb->whichfork == XFS_DATA_FORK && + (rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + if (rb->whichfork == XFS_ATTR_FORK && + !(rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + + return xrep_bmap_from_rmap(rb, rec->rm_offset, + xfs_rgbno_to_rtb(to_rtg(cur->bc_group), + rec->rm_startblock), + rec->rm_blockcount, + rec->rm_flags & XFS_RMAP_UNWRITTEN); +} + +/* Scan the realtime reverse mappings to build the new extent map. */ +STATIC int +xrep_bmap_scan_rtgroup( + struct xrep_bmap *rb, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = rb->sc; + int error; + + if (!xfs_has_rtrmapbt(sc->mp)) + return 0; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT | + XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_bmap_walk_rtrmap, rb); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} +#else +static inline int +xrep_bmap_scan_rtgroup(struct xrep_bmap *rb, struct xfs_rtgroup *rtg) +{ + return -EFSCORRUPTED; +} +#endif + /* Find the delalloc extents from the old incore extent tree. */ STATIC int xrep_bmap_find_delalloc( @@ -410,6 +527,22 @@ xrep_bmap_find_mappings( struct xfs_perag *pag = NULL; int error = 0; + /* + * Iterate the rtrmaps for extents. Metadata files never have content + * on the realtime device, so there's no need to scan them. + */ + if (!xfs_is_metadir_inode(sc->ip)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xrep_bmap_scan_rtgroup(rb, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + } + /* Iterate the rmaps for extents. */ while ((pag = xfs_perag_next(sc->mp, pag))) { error = xrep_bmap_scan_ag(rb, pag); @@ -731,6 +864,7 @@ 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: @@ -753,10 +887,6 @@ xrep_bmap_check_inputs( return -EINVAL; } - /* Don't know how to rebuild realtime data forks. */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return -EOPNOTSUPP; - return 0; } @@ -782,10 +912,6 @@ xrep_bmap_init_reflink_scan( if (whichfork != XFS_DATA_FORK) return RLS_IRRELEVANT; - /* cannot share realtime extents */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return RLS_IRRELEVANT; - return RLS_UNKNOWN; } diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 5cbd94b56582..28ad341df8ee 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -35,6 +35,9 @@ #include "xfs_exchmaps.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap_util.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -719,20 +722,111 @@ xchk_rtgroup_init( return 0; } -void +/* Lock all the rt group metadata inode ILOCKs and wait for intents. */ +int xchk_rtgroup_lock( + struct xfs_scrub *sc, struct xchk_rt *sr, unsigned int rtglock_flags) { - xfs_rtgroup_lock(sr->rtg, rtglock_flags); + int error = 0; + + ASSERT(sr->rtg != NULL); + + /* + * If we're /only/ locking the rtbitmap in shared mode, then we're + * obviously not trying to compare records in two metadata inodes. + * There's no need to drain intents here because the caller (most + * likely the rgsuper scanner) doesn't need that level of consistency. + */ + if (rtglock_flags == XFS_RTGLOCK_BITMAP_SHARED) { + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + sr->rtlock_flags = rtglock_flags; + return 0; + } + + do { + if (xchk_should_terminate(sc, &error)) + return error; + + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + + /* + * If we've grabbed a non-metadata file for scrubbing, we + * assume that holding its ILOCK will suffice to coordinate + * with any rt intent chains involving this inode. + */ + if (sc->ip && !xfs_is_internal_inode(sc->ip)) + break; + + /* + * Decide if the rt group is quiet enough for all metadata to + * be consistent with each other. Regular file IO doesn't get + * to lock all the rt inodes at the same time, which means that + * there could be other threads in the middle of processing a + * chain of deferred ops. + * + * We just locked all the metadata inodes for this rt group; + * now take a look to see if there are any intents in progress. + * If there are, drop the rt group inode locks and wait for the + * intents to drain. Since we hold the rt group inode locks + * for the duration of the scrub, this is the only time we have + * to sample the intents counter; any threads increasing it + * after this point can't possibly be in the middle of a chain + * of rt metadata updates. + * + * Obviously, this should be slanted against scrub and in favor + * of runtime threads. + */ + if (!xfs_group_intent_busy(rtg_group(sr->rtg))) + break; + + xfs_rtgroup_unlock(sr->rtg, rtglock_flags); + + if (!(sc->flags & XCHK_FSGATES_DRAIN)) + return -ECHRNG; + error = xfs_group_intent_drain(rtg_group(sr->rtg)); + if (error) { + if (error == -ERESTARTSYS) + error = -EINTR; + return error; + } + } while (1); + sr->rtlock_flags = rtglock_flags; + + if (xfs_has_rtrmapbt(sc->mp) && (rtglock_flags & XFS_RTGLOCK_RMAP)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (xfs_has_rtreflink(sc->mp) && (rtglock_flags & XFS_RTGLOCK_REFCOUNT)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); + + return 0; +} + +/* + * Free all the btree cursors and other incore data relating to the realtime + * group. This has to be done /before/ committing (or cancelling) the scrub + * transaction. + */ +void +xchk_rtgroup_btcur_free( + struct xchk_rt *sr) +{ + if (sr->rmap_cur) + xfs_btree_del_cursor(sr->rmap_cur, XFS_BTREE_ERROR); + if (sr->refc_cur) + xfs_btree_del_cursor(sr->refc_cur, XFS_BTREE_ERROR); + + sr->refc_cur = NULL; + sr->rmap_cur = NULL; } /* * Unlock the realtime group. This must be done /after/ committing (or * cancelling) the scrub transaction. */ -static void +void xchk_rtgroup_unlock( struct xchk_rt *sr) { @@ -812,6 +906,14 @@ xchk_setup_fs( return xchk_trans_alloc(sc, resblks); } +/* Set us up with a transaction and an empty context to repair rt metadata. */ +int +xchk_setup_rt( + struct xfs_scrub *sc) +{ + return xchk_trans_alloc(sc, xrep_calc_rtgroup_resblks(sc)); +} + /* Set us up with AG headers and btree cursors. */ int xchk_setup_ag_btree( @@ -1379,7 +1481,7 @@ xchk_fsgates_enable( trace_xchk_fsgates_enable(sc, scrub_fsgates); if (scrub_fsgates & XCHK_FSGATES_DRAIN) - xfs_drain_wait_enable(); + xfs_defer_drain_wait_enable(); if (scrub_fsgates & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_enable(); @@ -1573,3 +1675,63 @@ xchk_inode_rootdir_inum(const struct xfs_inode *ip) return mp->m_metadirip->i_ino; return mp->m_rootip->i_ino; } + +static int +xchk_meta_btree_count_blocks( + struct xfs_scrub *sc, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_btree_cur *cur; + int error; + + if (!sc->sr.rtg) { + ASSERT(0); + return -EFSCORRUPTED; + } + + switch (sc->ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, sc->sr.rtg); + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + error = xfs_btree_count_blocks(cur, count); + xfs_btree_del_cursor(cur, error); + if (!error) { + *nextents = 0; + (*count)--; /* don't count the btree iroot */ + } + return error; +} + +/* Count the blocks used by a file, even if it's a metadata inode. */ +int +xchk_inode_count_blocks( + struct xfs_scrub *sc, + int whichfork, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); + + if (!ifp) { + *nextents = 0; + *count = 0; + return 0; + } + + if (ifp->if_format == XFS_DINODE_FMT_META_BTREE) { + ASSERT(whichfork == XFS_DATA_FORK); + return xchk_meta_btree_count_blocks(sc, nextents, count); + } + + return xfs_bmap_count_blocks(sc->tp, sc->ip, whichfork, nextents, + count); +} diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 1182c6fa6180..19877d99f255 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -63,6 +63,7 @@ static inline int xchk_setup_nothing(struct xfs_scrub *sc) /* Setup functions */ int xchk_setup_agheader(struct xfs_scrub *sc); int xchk_setup_fs(struct xfs_scrub *sc); +int xchk_setup_rt(struct xfs_scrub *sc); int xchk_setup_ag_allocbt(struct xfs_scrub *sc); int xchk_setup_ag_iallocbt(struct xfs_scrub *sc); int xchk_setup_ag_rmapbt(struct xfs_scrub *sc); @@ -80,10 +81,14 @@ int xchk_setup_metapath(struct xfs_scrub *sc); int xchk_setup_rtbitmap(struct xfs_scrub *sc); int xchk_setup_rtsummary(struct xfs_scrub *sc); int xchk_setup_rgsuperblock(struct xfs_scrub *sc); +int xchk_setup_rtrmapbt(struct xfs_scrub *sc); +int xchk_setup_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_setup_rtbitmap xchk_setup_nothing # define xchk_setup_rtsummary xchk_setup_nothing # define xchk_setup_rgsuperblock xchk_setup_nothing +# define xchk_setup_rtrmapbt xchk_setup_nothing +# define xchk_setup_rtrefcountbt xchk_setup_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_ino_dqattach(struct xfs_scrub *sc); @@ -125,7 +130,9 @@ xchk_ag_init_existing( #ifdef CONFIG_XFS_RT /* All the locks we need to check an rtgroup. */ -#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP) +#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno, struct xchk_rt *sr); @@ -141,12 +148,17 @@ xchk_rtgroup_init_existing( return error == -ENOENT ? -EFSCORRUPTED : error; } -void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags); +int xchk_rtgroup_lock(struct xfs_scrub *sc, struct xchk_rt *sr, + unsigned int rtglock_flags); +void xchk_rtgroup_unlock(struct xchk_rt *sr); +void xchk_rtgroup_btcur_free(struct xchk_rt *sr); void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr); #else # define xchk_rtgroup_init(sc, rgno, sr) (-EFSCORRUPTED) # define xchk_rtgroup_init_existing(sc, rgno, sr) (-EFSCORRUPTED) -# define xchk_rtgroup_lock(sc, lockflags) do { } while (0) +# define xchk_rtgroup_lock(sc, sr, lockflags) (-EFSCORRUPTED) +# define xchk_rtgroup_unlock(sr) do { } while (0) +# define xchk_rtgroup_btcur_free(sr) do { } while (0) # define xchk_rtgroup_free(sc, sr) do { } while (0) #endif /* CONFIG_XFS_RT */ @@ -252,6 +264,12 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc); (sc)->mp->m_super->s_id, \ (sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \ ##__VA_ARGS__) +#define xchk_xfile_rtgroup_descr(sc, fmt, ...) \ + kasprintf(XCHK_GFP_FLAGS, "XFS (%s): rtgroup 0x%x " fmt, \ + (sc)->mp->m_super->s_id, \ + (sc)->sa.pag ? \ + rtg_rgno((sc)->sr.rtg) : (sc)->sm->sm_agno, \ + ##__VA_ARGS__) /* * Setting up a hook to wait for intents to drain is costly -- we have to take @@ -269,6 +287,8 @@ void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks); int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino, bool *inuse); +int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork, + xfs_extnum_t *nextents, xfs_filblks_t *count); bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip); bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip); diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c index 5b6194cef3e5..38a246b8bf11 100644 --- a/fs/xfs/scrub/cow_repair.c +++ b/fs/xfs/scrub/cow_repair.c @@ -26,6 +26,9 @@ #include "xfs_errortag.h" #include "xfs_icache.h" #include "xfs_refcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -34,6 +37,7 @@ #include "scrub/bitmap.h" #include "scrub/off_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -61,7 +65,10 @@ struct xrep_cow { struct xoff_bitmap bad_fileoffs; /* Bitmap of fsblocks that were removed from the CoW fork. */ - struct xfsb_bitmap old_cowfork_fsblocks; + union { + struct xfsb_bitmap old_cowfork_fsblocks; + struct xrtb_bitmap old_cowfork_rtblocks; + }; /* CoW fork mappings used to scan for bad CoW staging extents. */ struct xfs_bmbt_irec irec; @@ -145,8 +152,7 @@ xrep_cow_mark_shared_staging( xrep_cow_trim_refcount(xc, &rrec, rec); return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), - rrec.rc_startblock), + xfs_gbno_to_fsb(cur->bc_group, rrec.rc_startblock), rrec.rc_blockcount); } @@ -177,9 +183,8 @@ xrep_cow_mark_missing_staging( if (xc->next_bno >= rrec.rc_startblock) goto next; - error = xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), xc->next_bno), + xfs_gbno_to_fsb(cur->bc_group, xc->next_bno), rrec.rc_startblock - xc->next_bno); if (error) return error; @@ -222,8 +227,7 @@ xrep_cow_mark_missing_staging_rmap( } return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), rec_bno), - rec_len); + xfs_gbno_to_fsb(cur->bc_group, rec_bno), rec_len); } /* @@ -311,6 +315,92 @@ out_pag: } /* + * Find any part of the CoW fork mapping that isn't a single-owner CoW staging + * extent and mark the corresponding part of the file range in the bitmap. + */ +STATIC int +xrep_cow_find_bad_rt( + struct xrep_cow *xc) +{ + struct xfs_refcount_irec rc_low = { 0 }; + struct xfs_refcount_irec rc_high = { 0 }; + struct xfs_rmap_irec rm_low = { 0 }; + struct xfs_rmap_irec rm_high = { 0 }; + struct xfs_scrub *sc = xc->sc; + struct xfs_rtgroup *rtg; + int error = 0; + + xc->irec_startbno = xfs_rtb_to_rgbno(sc->mp, xc->irec.br_startblock); + + rtg = xfs_rtgroup_get(sc->mp, + xfs_rtb_to_rgno(sc->mp, xc->irec.br_startblock)); + if (!rtg) + return -EFSCORRUPTED; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + if (error) + goto out_rtg; + + /* Mark any CoW fork extents that are shared. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_SHARED; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_shared_staging, xc); + if (error) + goto out_sr; + + /* Make sure there are CoW staging extents for the whole mapping. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_COW; + xc->next_bno = xc->irec_startbno; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_missing_staging, xc); + if (error) + goto out_sr; + + if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) { + error = xrep_cow_mark_file_range(xc, + xfs_rgbno_to_rtb(rtg, xc->next_bno), + xc->irec_startbno + xc->irec.br_blockcount - + xc->next_bno); + if (error) + goto out_sr; + } + + /* Mark any area has an rmap that isn't a COW staging extent. */ + rm_low.rm_startblock = xc->irec_startbno; + memset(&rm_high, 0xFF, sizeof(rm_high)); + rm_high.rm_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + error = xfs_rmap_query_range(sc->sr.rmap_cur, &rm_low, &rm_high, + xrep_cow_mark_missing_staging_rmap, xc); + if (error) + goto out_sr; + + /* + * If userspace is forcing us to rebuild the CoW fork or someone + * turned on the debugging knob, replace everything in the + * CoW fork and then scan for staging extents in the refcountbt. + */ + if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) { + error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock, + xc->irec.br_blockcount); + if (error) + goto out_rtg; + } + +out_sr: + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); +out_rtg: + xfs_rtgroup_put(rtg); + return error; +} + +/* * Allocate a replacement CoW staging extent of up to the given number of * blocks, and fill out the mapping. */ @@ -343,7 +433,7 @@ xrep_cow_alloc( if (args.fsbno == NULLFSBLOCK) return -ENOSPC; - xfs_refcount_alloc_cow_extent(sc->tp, args.fsbno, args.len); + xfs_refcount_alloc_cow_extent(sc->tp, false, args.fsbno, args.len); repl->fsbno = args.fsbno; repl->len = args.len; @@ -351,6 +441,32 @@ xrep_cow_alloc( } /* + * Allocate a replacement rt CoW staging extent of up to the given number of + * blocks, and fill out the mapping. + */ +STATIC int +xrep_cow_alloc_rt( + struct xfs_scrub *sc, + xfs_extlen_t maxlen, + struct xrep_cow_extent *repl) +{ + xfs_rtxlen_t maxrtx = xfs_rtb_to_rtx(sc->mp, maxlen); + int error; + + error = xfs_trans_reserve_more(sc->tp, 0, maxrtx); + if (error) + return error; + + error = xfs_rtallocate_rtgs(sc->tp, NULLRTBLOCK, 1, maxrtx, 1, false, + false, &repl->fsbno, &repl->len); + if (error) + return error; + + xfs_refcount_alloc_cow_extent(sc->tp, true, repl->fsbno, repl->len); + return 0; +} + +/* * Look up the current CoW fork mapping so that we only allocate enough to * replace a single mapping. If we don't find a mapping that covers the start * of the file range, or we find a delalloc or written extent, something is @@ -467,7 +583,10 @@ xrep_cow_replace_range( */ alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN, nextoff - startoff); - error = xrep_cow_alloc(sc, alloc_len, &repl); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_alloc_rt(sc, alloc_len, &repl); + else + error = xrep_cow_alloc(sc, alloc_len, &repl); if (error) return error; @@ -483,8 +602,12 @@ xrep_cow_replace_range( return error; /* Note the old CoW staging extents; we'll reap them all later. */ - error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, got.br_startblock, - repl.len); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrtb_bitmap_set(&xc->old_cowfork_rtblocks, + got.br_startblock, repl.len); + else + error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, + got.br_startblock, repl.len); if (error) return error; @@ -540,8 +663,16 @@ xrep_bmap_cow( if (!ifp) return 0; - /* realtime files aren't supported yet */ - if (XFS_IS_REALTIME_INODE(sc->ip)) + /* + * Realtime files with large extent sizes are not supported because + * we could encounter an CoW mapping that has been partially written + * out *and* requires replacement, and there's no solution to that. + */ + if (xfs_inode_has_bigrtalloc(sc->ip)) + return -EOPNOTSUPP; + + /* Metadata inodes aren't supposed to have data on the rt volume. */ + if (xfs_is_metadir_inode(sc->ip) && XFS_IS_REALTIME_INODE(sc->ip)) return -EOPNOTSUPP; /* @@ -562,7 +693,10 @@ xrep_bmap_cow( xc->sc = sc; xoff_bitmap_init(&xc->bad_fileoffs); - xfsb_bitmap_init(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_init(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_init(&xc->old_cowfork_fsblocks); for_each_xfs_iext(ifp, &icur, &xc->irec) { if (xchk_should_terminate(sc, &error)) @@ -585,7 +719,10 @@ xrep_bmap_cow( if (xfs_bmap_is_written_extent(&xc->irec)) continue; - error = xrep_cow_find_bad(xc); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_find_bad_rt(xc); + else + error = xrep_cow_find_bad(xc); if (error) goto out_bitmap; } @@ -600,13 +737,20 @@ xrep_bmap_cow( * by the refcount btree, not the inode, so it is correct to treat them * like inode metadata. */ - error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, - &XFS_RMAP_OINFO_COW); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_reap_rtblocks(sc, &xc->old_cowfork_rtblocks, + &XFS_RMAP_OINFO_COW); + else + error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, + &XFS_RMAP_OINFO_COW); if (error) goto out_bitmap; out_bitmap: - xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_destroy(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); xoff_bitmap_destroy(&xc->bad_fileoffs); kfree(xc); return error; diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index ca23cf4db6c5..e629663e460a 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -350,7 +350,7 @@ retry: * The global incore space reservation is taken from the incore * counters, so leave that out of the computation. */ - fsc->fdblocks -= mp->m_resblks_avail; + fsc->fdblocks -= mp->m_free[XC_FREE_BLOCKS].res_avail; /* * Delayed allocation reservations are taken out of the incore counters @@ -413,7 +413,13 @@ xchk_fscount_count_frextents( fsc->frextents = 0; fsc->frextents_delayed = 0; - if (!xfs_has_realtime(mp)) + + /* + * Don't bother verifying and repairing the fs counters for zoned file + * systems as they don't track an on-disk frextents count, and the + * in-memory percpu counter also includes reservations. + */ + if (!xfs_has_realtime(mp) || xfs_has_zoned(mp)) return 0; while ((rtg = xfs_rtgroup_next(mp, rtg))) { @@ -513,8 +519,8 @@ xchk_fscounters( /* Snapshot the percpu counters. */ icount = percpu_counter_sum(&mp->m_icount); ifree = percpu_counter_sum(&mp->m_ifree); - fdblocks = percpu_counter_sum(&mp->m_fdblocks); - frextents = percpu_counter_sum(&mp->m_frextents); + fdblocks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS); + frextents = xfs_sum_freecounter_raw(mp, XC_FREE_RTEXTENTS); /* No negative values, please! */ if (icount < 0 || ifree < 0) @@ -589,15 +595,17 @@ xchk_fscounters( try_again = true; } - if (!xchk_fscount_within_range(sc, fdblocks, &mp->m_fdblocks, - fsc->fdblocks)) { + if (!xchk_fscount_within_range(sc, fdblocks, + &mp->m_free[XC_FREE_BLOCKS].count, fsc->fdblocks)) { if (fsc->frozen) xchk_set_corrupt(sc); else try_again = true; } - if (!xchk_fscount_within_range(sc, frextents, &mp->m_frextents, + if (!xfs_has_zoned(mp) && + !xchk_fscount_within_range(sc, frextents, + &mp->m_free[XC_FREE_RTEXTENTS].count, fsc->frextents - fsc->frextents_delayed)) { if (fsc->frozen) xchk_set_corrupt(sc); diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c index cda13447a373..f0d2b04644e4 100644 --- a/fs/xfs/scrub/fscounters_repair.c +++ b/fs/xfs/scrub/fscounters_repair.c @@ -64,7 +64,7 @@ xrep_fscounters( percpu_counter_set(&mp->m_icount, fsc->icount); percpu_counter_set(&mp->m_ifree, fsc->ifree); - percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks); + xfs_set_freecounter(mp, XC_FREE_BLOCKS, fsc->fdblocks); /* * Online repair is only supported on v5 file systems, which require @@ -74,10 +74,12 @@ xrep_fscounters( * track of the delalloc reservations separately, as they are are * subtracted from m_frextents, but not included in sb_frextents. */ - percpu_counter_set(&mp->m_frextents, - fsc->frextents - fsc->frextents_delayed); - if (!xfs_has_rtgroups(mp)) - mp->m_sb.sb_frextents = fsc->frextents; + if (!xfs_has_zoned(mp)) { + xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, + fsc->frextents - fsc->frextents_delayed); + if (!xfs_has_rtgroups(mp)) + mp->m_sb.sb_frextents = fsc->frextents; + } return 0; } diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index ccc6ca5934ca..3c0f25098b69 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -114,6 +114,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = { XHG_INO, XFS_SICK_INO_DIRTREE }, [XFS_SCRUB_TYPE_METAPATH] = { XHG_FS, XFS_SICK_FS_METAPATH }, [XFS_SCRUB_TYPE_RGSUPER] = { XHG_RTGROUP, XFS_SICK_RG_SUPER }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { XHG_RTGROUP, XFS_SICK_RG_RMAPBT }, + [XFS_SCRUB_TYPE_RTREFCBT] = { XHG_RTGROUP, XFS_SICK_RG_REFCNTBT }, }; /* Return the health status mask for this scrub type. */ diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 25ee66e7649d..bb3f475b6353 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -260,12 +260,7 @@ xchk_inode_extsize( xchk_ino_set_warning(sc, ino); } -/* - * Validate di_cowextsize hint. - * - * The rules are documented at xfs_ioctl_setattr_check_cowextsize(). - * These functions must be kept in sync with each other. - */ +/* Validate di_cowextsize hint. */ STATIC void xchk_inode_cowextsize( struct xfs_scrub *sc, @@ -276,12 +271,32 @@ xchk_inode_cowextsize( uint64_t flags2) { xfs_failaddr_t fa; + uint32_t value = be32_to_cpu(dip->di_cowextsize); + + /* + * The used block counter for rtrmap is checked and repaired elsewhere. + */ + if (xfs_has_zoned(sc->mp) && + dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) + return; - fa = xfs_inode_validate_cowextsize(sc->mp, - be32_to_cpu(dip->di_cowextsize), mode, flags, - flags2); + fa = xfs_inode_validate_cowextsize(sc->mp, value, mode, flags, flags2); if (fa) xchk_ino_set_corrupt(sc, ino); + + /* + * XFS allows a sysadmin to change the rt extent size when adding a rt + * section to a filesystem after formatting. If there are any + * directories with cowextsize and rtinherit set, the hint could become + * misaligned with the new rextsize. The verifier doesn't check this, + * because we allow rtinherit directories even without an rt device. + * Flag this as an administrative warning since we will clean this up + * eventually. + */ + if ((flags & XFS_DIFLAG_RTINHERIT) && + (flags2 & XFS_DIFLAG2_COWEXTSIZE) && + value % sc->mp->m_sb.sb_rextsize > 0) + xchk_ino_set_warning(sc, ino); } /* Make sure the di_flags make sense for the inode. */ @@ -360,8 +375,9 @@ xchk_inode_flags2( if ((flags2 & XFS_DIFLAG2_REFLINK) && !S_ISREG(mode)) goto bad; - /* realtime and reflink make no sense, currently */ - if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK)) + /* realtime and reflink don't always go together */ + if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK) && + !xfs_has_rtreflink(mp)) goto bad; /* no bigtime iflag without the bigtime feature */ @@ -502,6 +518,10 @@ 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); @@ -686,15 +706,13 @@ xchk_inode_xref_bmap( return; /* Walk all the extents to check nextents/naextents/nblocks. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents < xfs_dfork_data_extents(dip)) xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino); - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, &acount); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents != xfs_dfork_attr_extents(dip)) diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 5a58ddd27bd2..a90a011c7e5f 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -38,6 +38,9 @@ #include "xfs_log_priv.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -562,8 +565,6 @@ xrep_dinode_flags( flags2 |= XFS_DIFLAG2_REFLINK; else flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE); - if (flags & XFS_DIFLAG_REALTIME) - flags2 &= ~XFS_DIFLAG2_REFLINK; if (!xfs_has_bigtime(mp)) flags2 &= ~XFS_DIFLAG2_BIGTIME; if (!xfs_has_large_extent_counts(mp)) @@ -709,7 +710,9 @@ xrep_dinode_extsize_hints( XFS_DIFLAG_EXTSZINHERIT); } - if (dip->di_version < 3) + if (dip->di_version < 3 || + (xfs_has_zoned(sc->mp) && + dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP))) return; fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize), @@ -773,17 +776,71 @@ xrep_dinode_count_ag_rmaps( return error; } +/* Count extents and blocks for an inode given an rt rmap. */ +STATIC int +xrep_dinode_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_inode *ri = priv; + int error = 0; + + if (xchk_should_terminate(ri->sc, &error)) + return error; + + /* We only care about this inode. */ + if (rec->rm_owner != ri->sc->sm->sm_ino) + return 0; + + if (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + ri->rt_blocks += rec->rm_blockcount; + ri->rt_extents++; + return 0; +} + +/* Count extents and blocks for an inode from all realtime rmap data. */ +STATIC int +xrep_dinode_count_rtgroup_rmaps( + struct xrep_inode *ri, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = ri->sc; + int error; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, XFS_RTGLOCK_RMAP); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_dinode_walk_rtrmap, + ri); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} + /* Count extents and blocks for a given inode from all rmap data. */ STATIC int xrep_dinode_count_rmaps( struct xrep_inode *ri) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error; - if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp)) + if (!xfs_has_rmapbt(ri->sc->mp)) return -EOPNOTSUPP; + while ((rtg = xfs_rtgroup_next(ri->sc->mp, rtg))) { + error = xrep_dinode_count_rtgroup_rmaps(ri, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + while ((pag = xfs_perag_next(ri->sc->mp, pag))) { error = xrep_dinode_count_ag_rmaps(ri, pag); if (error) { @@ -888,6 +945,85 @@ xrep_dinode_bad_bmbt_fork( return false; } +/* Return true if this rmap-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrmapbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrmap_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrmap_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrmap_maxlevels) + return true; + if (xfs_rtrmap_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + return false; +} + +/* Return true if this refcount-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrefcountbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrefcount_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrefcount_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrefc_maxlevels) + return true; + if (xfs_rtrefcount_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + 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)) { + case XFS_METAFILE_RTRMAP: + return xrep_dinode_bad_rtrmapbt_fork(sc, dip, dfork_size); + case XFS_METAFILE_RTREFCOUNT: + return xrep_dinode_bad_rtrefcountbt_fork(sc, dip, dfork_size); + default: + return true; + } + + return false; +} + /* * Check the data fork for things that will fail the ifork verifiers or the * ifork formatters. @@ -921,9 +1057,17 @@ xrep_dinode_check_dfork( return true; break; case S_IFREG: - if (fmt == XFS_DINODE_FMT_LOCAL) + switch (fmt) { + case XFS_DINODE_FMT_LOCAL: return true; - fallthrough; + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: + break; + default: + return true; + } + break; case S_IFLNK: case S_IFDIR: switch (fmt) { @@ -968,6 +1112,11 @@ 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 +1237,11 @@ 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; } @@ -1135,6 +1289,8 @@ xrep_dinode_ensure_forkoff( uint16_t mode) { struct xfs_bmdr_block *bmdr; + struct xfs_rtrmap_root *rmdr; + struct xfs_rtrefcount_root *rcdr; struct xfs_scrub *sc = ri->sc; xfs_extnum_t attr_extents, data_extents; size_t bmdr_minsz = xfs_bmdr_space_calc(1); @@ -1241,6 +1397,21 @@ 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)) { + case XFS_METAFILE_RTRMAP: + rmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrmap_broot_space(sc->mp, rmdr); + break; + case XFS_METAFILE_RTREFCOUNT: + rcdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrefcount_broot_space(sc->mp, rcdr); + break; + default: + dfork_min = 0; + break; + } + break; default: dfork_min = 0; break; @@ -1389,8 +1560,7 @@ xrep_dinode_core( /* Read the inode cluster buffer. */ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp, - ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp, - NULL); + ri->imap.im_blkno, ri->imap.im_len, 0, &bp, NULL); if (error) return error; @@ -1500,8 +1670,7 @@ xrep_inode_blockcounts( trace_xrep_inode_blockcounts(sc); /* Set data fork counters from the data fork mappings. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (error) return error; if (xfs_is_reflink_inode(sc->ip)) { @@ -1525,8 +1694,8 @@ xrep_inode_blockcounts( /* Set attr fork counters from the attr fork mappings. */ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK); if (ifp) { - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, + &acount); if (error) return error; if (count >= sc->mp->m_sb.sb_dblocks) @@ -1664,10 +1833,6 @@ xrep_inode_flags( /* DAX only applies to files and dirs. */ if (!(S_ISREG(mode) || S_ISDIR(mode))) sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX; - - /* No reflink files on the realtime device. */ - if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) - sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* @@ -1783,6 +1948,20 @@ xrep_inode_pptr( sizeof(struct xfs_attr_sf_hdr), true); } +/* Fix COW extent size hint problems. */ +STATIC void +xrep_inode_cowextsize( + struct xfs_scrub *sc) +{ + /* Fix misaligned CoW extent size hints on a directory. */ + if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (sc->ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + sc->ip->i_extsize % sc->mp->m_sb.sb_rextsize > 0) { + sc->ip->i_cowextsize = 0; + sc->ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + } +} + /* Fix any irregularities in an inode that the verifiers don't catch. */ STATIC int xrep_inode_problems( @@ -1806,6 +1985,7 @@ xrep_inode_problems( if (S_ISDIR(VFS_I(sc->ip)->i_mode)) xrep_inode_dir_size(sc); xrep_inode_extsize(sc); + xrep_inode_cowextsize(sc); trace_xrep_inode_fixed(sc); xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index c678cba1ffc3..e21c16fbd15d 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -21,6 +21,8 @@ #include "xfs_trans_space.h" #include "xfs_attr.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -246,6 +248,10 @@ xchk_setup_metapath( return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP); case XFS_SCRUB_METAPATH_PRJQUOTA: return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ); + case XFS_SCRUB_METAPATH_RTRMAPBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_RMAP); + case XFS_SCRUB_METAPATH_RTREFCOUNTBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_REFCOUNT); default: return -ENOENT; } diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c index 70af27d98734..1588ce971cb8 100644 --- a/fs/xfs/scrub/newbt.c +++ b/fs/xfs/scrub/newbt.c @@ -19,6 +19,8 @@ #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_quota.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -60,7 +62,7 @@ xrep_newbt_estimate_slack( free = sc->sa.pag->pagf_freeblks; sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag)); } else { - free = percpu_counter_sum(&sc->mp->m_fdblocks); + free = xfs_sum_freecounter_raw(sc->mp, XC_FREE_BLOCKS); sz = sc->mp->m_sb.sb_dblocks; } @@ -121,6 +123,43 @@ xrep_newbt_init_inode( } /* + * Initialize accounting resources for staging a new metadata inode btree. + * If the metadata file has a space reservation, the caller must adjust that + * reservation when committing the new ondisk btree. + */ +int +xrep_newbt_init_metadir_inode( + struct xrep_newbt *xnr, + struct xfs_scrub *sc) +{ + struct xfs_owner_info oinfo; + struct xfs_ifork *ifp; + + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS); + if (!ifp) + return -ENOMEM; + + /* + * Allocate new metadir btree blocks with XFS_AG_RESV_NONE because the + * inode metadata space reservations can only account allocated space + * to the i_nblocks. We do not want to change the inode core fields + * until we're ready to commit the new tree, so we allocate the blocks + * as if they were regular file blocks. This exposes us to a higher + * risk of the repair being cancelled due to ENOSPC. + */ + xrep_newbt_init_ag(xnr, sc, &oinfo, + XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino), + XFS_AG_RESV_NONE); + xnr->ifake.if_fork = ifp; + xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, XFS_DATA_FORK); + return 0; +} + +/* * Initialize accounting resources for staging a new btree. Callers are * expected to add their own reservations (and clean them up) manually. */ @@ -224,6 +263,7 @@ xrep_newbt_alloc_ag_blocks( int error = 0; ASSERT(sc->sa.pag != NULL); + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); while (nr_blocks > 0) { struct xfs_alloc_arg args = { @@ -297,6 +337,8 @@ xrep_newbt_alloc_file_blocks( struct xfs_mount *mp = sc->mp; int error = 0; + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); + while (nr_blocks > 0) { struct xfs_alloc_arg args = { .tp = sc->tp, diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h index 3d804d31af24..5ce785599287 100644 --- a/fs/xfs/scrub/newbt.h +++ b/fs/xfs/scrub/newbt.h @@ -63,6 +63,7 @@ void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc, enum xfs_ag_resv_type resv); int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc, int whichfork, const struct xfs_owner_info *oinfo); +int xrep_newbt_init_metadir_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc); int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks); int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len); diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c index c287c755f2c5..3537f3cca6d5 100644 --- a/fs/xfs/scrub/orphanage.c +++ b/fs/xfs/scrub/orphanage.c @@ -167,10 +167,11 @@ xrep_orphanage_create( * directory to control access to a file we put in here. */ if (d_really_is_negative(orphanage_dentry)) { - error = vfs_mkdir(&nop_mnt_idmap, root_inode, orphanage_dentry, - 0750); - if (error) - goto out_dput_orphanage; + orphanage_dentry = vfs_mkdir(&nop_mnt_idmap, root_inode, + orphanage_dentry, 0750); + error = PTR_ERR(orphanage_dentry); + if (IS_ERR(orphanage_dentry)) + goto out_unlock_root; } /* Not a directory? Bail out. */ diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 183d531875ea..58d6d4ed2853 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -212,12 +212,18 @@ xchk_quota_item( if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_warning(sc, XFS_DATA_FORK, + offset); } else { if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + offset); } - if (dq->q_ino.count > fs_icount || dq->q_rtb.count > mp->m_sb.sb_rblocks) + if (dq->q_ino.count > fs_icount) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); /* diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index cd51f10f2920..8f4c8d41f308 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -233,7 +233,7 @@ xrep_quota_item( rqi->need_quotacheck = true; dirty = true; } - if (dq->q_rtb.count > mp->m_sb.sb_rblocks) { + if (!xfs_has_reflink(mp) && dq->q_rtb.count > mp->m_sb.sb_rblocks) { dq->q_rtb.reserved -= dq->q_rtb.count; dq->q_rtb.reserved += mp->m_sb.sb_rblocks; dq->q_rtb.count = mp->m_sb.sb_rblocks; diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index 08230952053b..8703897c0a9c 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -33,6 +33,9 @@ #include "xfs_attr.h" #include "xfs_attr_remote.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -40,6 +43,7 @@ #include "scrub/bitmap.h" #include "scrub/agb_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -310,7 +314,7 @@ xreap_agextent_binval( } out: - trace_xreap_agextent_binval(sc->sa.pag, agbno, *aglenp); + trace_xreap_agextent_binval(pag_group(sc->sa.pag), agbno, *aglenp); } /* @@ -369,7 +373,8 @@ xreap_agextent_select( out_found: *aglenp = len; - trace_xreap_agextent_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_agextent_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -390,6 +395,8 @@ xreap_agextent_iter( xfs_fsblock_t fsbno; int error = 0; + ASSERT(rs->resv != XFS_AG_RESV_METAFILE); + fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno); /* @@ -406,7 +413,8 @@ xreap_agextent_iter( * to run xfs_repair. */ if (crosslinked) { - trace_xreap_dispose_unmap_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), agbno, + *aglenp); rs->force_roll = true; @@ -416,7 +424,8 @@ xreap_agextent_iter( * records from the refcountbt, which will remove the * rmap record as well. */ - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, + *aglenp); return 0; } @@ -424,7 +433,7 @@ xreap_agextent_iter( *aglenp, rs->oinfo); } - trace_xreap_dispose_free_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), agbno, *aglenp); /* * Invalidate as many buffers as we can, starting at agbno. If this @@ -448,7 +457,7 @@ xreap_agextent_iter( if (rs->oinfo == &XFS_RMAP_OINFO_COW) { ASSERT(rs->resv == XFS_AG_RESV_NONE); - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, *aglenp); error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, NULL, rs->resv, XFS_FREE_EXTENT_SKIP_DISCARD); if (error) @@ -675,6 +684,266 @@ xrep_reap_fsblocks( return 0; } +#ifdef CONFIG_XFS_RT +/* + * Figure out the longest run of blocks that we can dispose of with a single + * call. Cross-linked blocks should have their reverse mappings removed, but + * single-owner extents can be freed. Units are rt blocks, not rt extents. + */ +STATIC int +xreap_rgextent_select( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_rgblock_t rgbno_next, + bool *crosslinked, + xfs_extlen_t *rglenp) +{ + struct xfs_scrub *sc = rs->sc; + struct xfs_btree_cur *cur; + xfs_rgblock_t bno = rgbno + 1; + xfs_extlen_t len = 1; + int error; + + /* + * Determine if there are any other rmap records covering the first + * block of this extent. If so, the block is crosslinked. + */ + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + error = xfs_rmap_has_other_keys(cur, rgbno, 1, rs->oinfo, + crosslinked); + if (error) + goto out_cur; + + /* + * Figure out how many of the subsequent blocks have the same crosslink + * status. + */ + while (bno < rgbno_next) { + bool also_crosslinked; + + error = xfs_rmap_has_other_keys(cur, bno, 1, rs->oinfo, + &also_crosslinked); + if (error) + goto out_cur; + + if (*crosslinked != also_crosslinked) + break; + + len++; + bno++; + } + + *rglenp = len; + trace_xreap_agextent_select(rtg_group(sc->sr.rtg), rgbno, len, + *crosslinked); +out_cur: + xfs_btree_del_cursor(cur, error); + return error; +} + +/* + * Dispose of as much of the beginning of this rtgroup extent as possible. + * The number of blocks disposed of will be returned in @rglenp. + */ +STATIC int +xreap_rgextent_iter( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_extlen_t *rglenp, + bool crosslinked) +{ + struct xfs_scrub *sc = rs->sc; + xfs_rtblock_t rtbno; + int error; + + /* + * The only caller so far is CoW fork repair, so we only know how to + * unlink or free CoW staging extents. Here we don't have to worry + * about invalidating buffers! + */ + if (rs->oinfo != &XFS_RMAP_OINFO_COW) { + ASSERT(rs->oinfo == &XFS_RMAP_OINFO_COW); + return -EFSCORRUPTED; + } + ASSERT(rs->resv == XFS_AG_RESV_NONE); + + rtbno = xfs_rgbno_to_rtb(sc->sr.rtg, rgbno); + + /* + * If there are other rmappings, this block is cross linked and must + * not be freed. Remove the forward and reverse mapping and move on. + */ + if (crosslinked) { + trace_xreap_dispose_unmap_extent(rtg_group(sc->sr.rtg), rgbno, + *rglenp); + + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + rs->deferred++; + return 0; + } + + trace_xreap_dispose_free_extent(rtg_group(sc->sr.rtg), rgbno, *rglenp); + + /* + * The CoW staging extent is not crosslinked. Use deferred work items + * to remove the refcountbt records (which removes the rmap records) + * and free the extent. We're not worried about the system going down + * here because log recovery walks the refcount btree to clean out the + * CoW staging extents. + */ + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + error = xfs_free_extent_later(sc->tp, rtbno, *rglenp, NULL, + rs->resv, + XFS_FREE_EXTENT_REALTIME | + XFS_FREE_EXTENT_SKIP_DISCARD); + if (error) + return error; + + rs->deferred++; + return 0; +} + +#define XREAP_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) + +/* + * Break a rt file metadata extent into sub-extents by fate (crosslinked, not + * crosslinked), and dispose of each sub-extent separately. The extent must + * be aligned to a realtime extent. + */ +STATIC int +xreap_rtmeta_extent( + uint64_t rtbno, + uint64_t len, + void *priv) +{ + struct xreap_state *rs = priv; + struct xfs_scrub *sc = rs->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, rtbno); + xfs_rgblock_t rgbno_next = rgbno + len; + int error = 0; + + ASSERT(sc->ip != NULL); + ASSERT(!sc->sr.rtg); + + /* + * We're reaping blocks after repairing file metadata, which means that + * we have to init the xchk_ag structure ourselves. + */ + sc->sr.rtg = xfs_rtgroup_get(sc->mp, xfs_rtb_to_rgno(sc->mp, rtbno)); + if (!sc->sr.rtg) + return -EFSCORRUPTED; + + xfs_rtgroup_lock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + + while (rgbno < rgbno_next) { + xfs_extlen_t rglen; + bool crosslinked; + + error = xreap_rgextent_select(rs, rgbno, rgbno_next, + &crosslinked, &rglen); + if (error) + goto out_unlock; + + error = xreap_rgextent_iter(rs, rgbno, &rglen, crosslinked); + if (error) + goto out_unlock; + + if (xreap_want_defer_finish(rs)) { + error = xfs_defer_finish(&sc->tp); + if (error) + goto out_unlock; + xreap_defer_finish_reset(rs); + } else if (xreap_want_roll(rs)) { + error = xfs_trans_roll_inode(&sc->tp, sc->ip); + if (error) + goto out_unlock; + xreap_reset(rs); + } + + rgbno += rglen; + } + +out_unlock: + xfs_rtgroup_unlock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + xfs_rtgroup_put(sc->sr.rtg); + sc->sr.rtg = NULL; + return error; +} + +/* + * Dispose of every block of every rt metadata extent in the bitmap. + * Do not use this to dispose of the mappings in an ondisk inode fork. + */ +int +xrep_reap_rtblocks( + struct xfs_scrub *sc, + struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xreap_state rs = { + .sc = sc, + .oinfo = oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + + error = xrtb_bitmap_walk(bitmap, xreap_rtmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) + return xrep_defer_finish(sc); + + return 0; +} +#endif /* CONFIG_XFS_RT */ + +/* + * Dispose of every block of an old metadata btree that used to be rooted in a + * metadata directory file. + */ +int +xrep_reap_metadir_fsblocks( + struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap) +{ + /* + * Reap old metadir btree blocks with XFS_AG_RESV_NONE because the old + * blocks are no longer mapped by the inode, and inode metadata space + * reservations can only account freed space to the i_nblocks. + */ + struct xfs_owner_info oinfo; + struct xreap_state rs = { + .sc = sc, + .oinfo = &oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) { + error = xrep_defer_finish(sc); + if (error) + return error; + } + + return xrep_reset_metafile_resv(sc); +} + /* * Metadata files are not supposed to share blocks with anything else. * If blocks are shared, we remove the reverse mapping (thus reducing the @@ -729,7 +998,8 @@ xreap_bmapi_select( } imap->br_blockcount = len; - trace_xreap_bmapi_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_bmapi_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -868,7 +1138,8 @@ xreap_bmapi_binval( } out: - trace_xreap_bmapi_binval(sc->sa.pag, agbno, imap->br_blockcount); + trace_xreap_bmapi_binval(pag_group(sc->sa.pag), agbno, + imap->br_blockcount); return 0; } @@ -895,7 +1166,7 @@ xrep_reap_bmapi_iter( * anybody else who thinks they own the block, even though that * runs the risk of stale buffer warnings in the future. */ - trace_xreap_dispose_unmap_extent(sc->sa.pag, + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); @@ -918,7 +1189,7 @@ xrep_reap_bmapi_iter( * by a block starting before the first block of the extent but overlap * anyway. */ - trace_xreap_dispose_free_extent(sc->sa.pag, + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h index 3f2f1775e29d..4c8f62701fb3 100644 --- a/fs/xfs/scrub/reap.h +++ b/fs/xfs/scrub/reap.h @@ -14,6 +14,15 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap, int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap, const struct xfs_owner_info *oinfo); int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork); +int xrep_reap_metadir_fsblocks(struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap); + +#ifdef CONFIG_XFS_RT +int xrep_reap_rtblocks(struct xfs_scrub *sc, struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo); +#else +# define xrep_reap_rtblocks(...) (-EOPNOTSUPP) +#endif /* CONFIG_XFS_RT */ /* Buffer cache scan context. */ struct xrep_bufscan { diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 1c5e45cc6419..d46528023015 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -421,7 +421,7 @@ xchk_refcount_mergeable( if (r1->rc_refcount != r2->rc_refcount) return false; if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > - MAXREFCEXTLEN) + XFS_REFC_LEN_MAX) return false; return true; diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c index 4e572b81c986..9c8cb5332da0 100644 --- a/fs/xfs/scrub/refcount_repair.c +++ b/fs/xfs/scrub/refcount_repair.c @@ -183,13 +183,13 @@ xrep_refc_stash( if (xchk_should_terminate(sc, &error)) return error; - irec.rc_refcount = min_t(uint64_t, MAXREFCOUNT, refcount); + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); error = xrep_refc_check_ext(rr->sc, &irec); if (error) return error; - trace_xrep_refc_found(sc->sa.pag, &irec); + trace_xrep_refc_found(pag_group(sc->sa.pag), &irec); return xfarray_append(rr->refcount_records, &irec); } @@ -422,7 +422,7 @@ xrep_refc_find_refcounts( /* * Set up a bag to store all the rmap records that we're tracking to * generate a reference count record. If the size of the bag exceeds - * MAXREFCOUNT, we clamp rc_refcount. + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. */ error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); if (error) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 91c8bc055a4f..f8f9ed30f56b 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -37,6 +37,13 @@ #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_dir2.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_zone_alloc.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -62,6 +69,7 @@ xrep_attempt( trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error); xchk_ag_btcur_free(&sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); /* Repair whatever's broken. */ ASSERT(sc->ops->repair); @@ -378,6 +386,41 @@ xrep_calc_ag_resblks( return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz)); } +#ifdef CONFIG_XFS_RT +/* + * Figure out how many blocks to reserve for a rtgroup repair. We calculate + * the worst case estimate for the number of blocks we'd need to rebuild one of + * any type of per-rtgroup btree. + */ +xfs_extlen_t +xrep_calc_rtgroup_resblks( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_scrub_metadata *sm = sc->sm; + uint64_t usedlen; + xfs_extlen_t rmapbt_sz = 0; + + if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) + return 0; + if (!xfs_has_rtgroups(mp)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + usedlen = xfs_rtbxlen_to_blen(mp, xfs_rtgroup_extents(mp, sm->sm_agno)); + ASSERT(usedlen <= XFS_MAX_RGBLOCKS); + + if (xfs_has_rmapbt(mp)) + rmapbt_sz = xfs_rtrmapbt_calc_size(mp, usedlen); + + trace_xrep_calc_rtgroup_resblks_btsize(mp, sm->sm_agno, usedlen, + rmapbt_sz); + + return rmapbt_sz; +} +#endif /* CONFIG_XFS_RT */ + /* * Reconstructing per-AG Btrees * @@ -954,6 +997,27 @@ xrep_ag_init( } #ifdef CONFIG_XFS_RT +/* Initialize all the btree cursors for a RT repair. */ +void +xrep_rtgroup_btcur_init( + struct xfs_scrub *sc, + struct xchk_rt *sr) +{ + struct xfs_mount *mp = sc->mp; + + ASSERT(sr->rtg != NULL); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTRMAPBT && + (sr->rtlock_flags & XFS_RTGLOCK_RMAP) && + xfs_has_rtrmapbt(mp)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTREFCBT && + (sr->rtlock_flags & XFS_RTGLOCK_REFCOUNT) && + xfs_has_rtreflink(mp)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); +} + /* * Given a reference to a rtgroup structure, lock rtgroup btree inodes and * create btree cursors. Must only be called to repair a regular rt file. @@ -972,6 +1036,39 @@ xrep_rtgroup_init( /* Grab our own passive reference from the caller's ref. */ sr->rtg = xfs_rtgroup_hold(rtg); + xrep_rtgroup_btcur_init(sc, sr); + return 0; +} + +/* Ensure that all rt blocks in the given range are not marked free. */ +int +xrep_require_rtext_inuse( + struct xfs_scrub *sc, + xfs_rgblock_t rgbno, + xfs_filblks_t len) +{ + struct xfs_mount *mp = sc->mp; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t endrtx; + bool is_free = false; + int error = 0; + + if (xfs_has_zoned(mp)) { + if (!xfs_zone_rgbno_is_valid(sc->sr.rtg, rgbno + len - 1)) + return -EFSCORRUPTED; + return 0; + } + + startrtx = xfs_rgbno_to_rtx(mp, rgbno); + endrtx = xfs_rgbno_to_rtx(mp, rgbno + len - 1); + + error = xfs_rtalloc_extent_is_free(sc->sr.rtg, sc->tp, startrtx, + endrtx - startrtx + 1, &is_free); + if (error) + return error; + if (is_free) + return -EFSCORRUPTED; + return 0; } #endif /* CONFIG_XFS_RT */ @@ -1237,3 +1334,110 @@ xrep_buf_verify_struct( return fa == NULL; } + +/* Check the sanity of a rmap record for a metadata btree inode. */ +int +xrep_check_ino_btree_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + enum xbtree_recpacking outcome; + int error; + + /* + * Metadata btree inodes never have extended attributes, and all blocks + * should have the bmbt block flag set. + */ + if ((rec->rm_flags & XFS_RMAP_ATTR_FORK) || + !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + /* Make sure the block is within the AG. */ + if (!xfs_verify_agbext(sc->sa.pag, rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock, + rec->rm_blockcount, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + return 0; +} + +/* + * Reset the block count of the inode being repaired, and adjust the dquot + * block usage to match. The inode must not have an xattr fork. + */ +void +xrep_inode_set_nblocks( + struct xfs_scrub *sc, + int64_t new_blocks) +{ + int64_t delta = + new_blocks - sc->ip->i_nblocks; + + sc->ip->i_nblocks = new_blocks; + + xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); + if (delta != 0) + xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, + delta); +} + +/* Reset the block reservation for a metadata inode. */ +int +xrep_reset_metafile_resv( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + int64_t delta; + int error; + + delta = mp->m_metafile_resv_used + mp->m_metafile_resv_avail - + mp->m_metafile_resv_target; + if (delta == 0) + return 0; + + /* + * Too many blocks have been reserved, transfer some from the incore + * reservation back to the filesystem. + */ + if (delta > 0) { + int64_t give_back; + + give_back = min_t(uint64_t, delta, mp->m_metafile_resv_avail); + if (give_back > 0) { + xfs_mod_sb_delalloc(mp, -give_back); + xfs_add_fdblocks(mp, give_back); + mp->m_metafile_resv_avail -= give_back; + } + + return 0; + } + + /* + * Not enough reservation; try to take some blocks from the filesystem + * to the metabtree reservation. + */ + delta = -delta; /* delta is negative here, so invert the sign. */ + error = xfs_dec_fdblocks(mp, delta, true); + while (error == -ENOSPC) { + delta--; + if (delta == 0) { + xfs_warn(sc->mp, +"Insufficient free space to reset metabtree reservation after repair."); + return 0; + } + error = xfs_dec_fdblocks(mp, delta, true); + } + if (error) + return error; + + xfs_mod_sb_delalloc(mp, delta); + mp->m_metafile_resv_avail += delta; + return 0; +} diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index b3b1fe62814e..af0a3a9e5ed9 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -50,7 +50,9 @@ xrep_trans_commit( struct xbitmap; struct xagb_bitmap; +struct xrgb_bitmap; struct xfsb_bitmap; +struct xrtb_bitmap; int xrep_fix_freelist(struct xfs_scrub *sc, int alloc_flags); @@ -97,6 +99,8 @@ int xrep_setup_parent(struct xfs_scrub *sc); int xrep_setup_nlinks(struct xfs_scrub *sc); int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks); int xrep_setup_dirtree(struct xfs_scrub *sc); +int xrep_setup_rtrmapbt(struct xfs_scrub *sc); +int xrep_setup_rtrefcountbt(struct xfs_scrub *sc); /* Repair setup functions */ int xrep_setup_ag_allocbt(struct xfs_scrub *sc); @@ -110,10 +114,18 @@ int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag, #ifdef CONFIG_XFS_RT int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg, struct xchk_rt *sr, unsigned int rtglock_flags); +void xrep_rtgroup_btcur_init(struct xfs_scrub *sc, struct xchk_rt *sr); +int xrep_require_rtext_inuse(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_filblks_t len); +xfs_extlen_t xrep_calc_rtgroup_resblks(struct xfs_scrub *sc); #else # define xrep_rtgroup_init(sc, rtg, sr, lockflags) (-ENOSYS) +# define xrep_calc_rtgroup_resblks(sc) (0) #endif /* CONFIG_XFS_RT */ +int xrep_check_ino_btree_mapping(struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec); + /* Metadata revalidators */ int xrep_revalidate_allocbt(struct xfs_scrub *sc); @@ -147,10 +159,14 @@ int xrep_metapath(struct xfs_scrub *sc); int xrep_rtbitmap(struct xfs_scrub *sc); int xrep_rtsummary(struct xfs_scrub *sc); int xrep_rgsuperblock(struct xfs_scrub *sc); +int xrep_rtrmapbt(struct xfs_scrub *sc); +int xrep_rtrefcountbt(struct xfs_scrub *sc); #else # define xrep_rtbitmap xrep_notsupported # define xrep_rtsummary xrep_notsupported # define xrep_rgsuperblock xrep_notsupported +# define xrep_rtrmapbt xrep_notsupported +# define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_RT */ #ifdef CONFIG_XFS_QUOTA @@ -169,6 +185,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep, void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp); bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops); +void xrep_inode_set_nblocks(struct xfs_scrub *sc, int64_t new_blocks); +int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else @@ -201,6 +219,8 @@ xrep_calc_ag_resblks( return 0; } +#define xrep_calc_rtgroup_resblks xrep_calc_ag_resblks + static inline int xrep_reset_perag_resv( struct xfs_scrub *sc) @@ -228,6 +248,8 @@ xrep_setup_nothing( #define xrep_setup_nlinks xrep_setup_nothing #define xrep_setup_dirtree xrep_setup_nothing #define xrep_setup_metapath xrep_setup_nothing +#define xrep_setup_rtrmapbt xrep_setup_nothing +#define xrep_setup_rtrefcountbt xrep_setup_nothing #define xrep_setup_inode(sc, imap) ((void)0) @@ -265,6 +287,8 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x) #define xrep_dirtree xrep_notsupported #define xrep_metapath xrep_notsupported #define xrep_rgsuperblock xrep_notsupported +#define xrep_rtrmapbt xrep_notsupported +#define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_ONLINE_REPAIR */ diff --git a/fs/xfs/scrub/rgb_bitmap.h b/fs/xfs/scrub/rgb_bitmap.h new file mode 100644 index 000000000000..4c3126b66dcb --- /dev/null +++ b/fs/xfs/scrub/rgb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_SCRUB_RGB_BITMAP_H__ +#define __XFS_SCRUB_RGB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rgblock_t */ + +struct xrgb_bitmap { + struct xbitmap32 rgbitmap; +}; + +static inline void xrgb_bitmap_init(struct xrgb_bitmap *bitmap) +{ + xbitmap32_init(&bitmap->rgbitmap); +} + +static inline void xrgb_bitmap_destroy(struct xrgb_bitmap *bitmap) +{ + xbitmap32_destroy(&bitmap->rgbitmap); +} + +static inline int xrgb_bitmap_set(struct xrgb_bitmap *bitmap, + xfs_rgblock_t start, xfs_extlen_t len) +{ + return xbitmap32_set(&bitmap->rgbitmap, start, len); +} + +static inline int xrgb_bitmap_walk(struct xrgb_bitmap *bitmap, + xbitmap32_walk_fn fn, void *priv) +{ + return xbitmap32_walk(&bitmap->rgbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RGB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 463b3573bb76..d189732d0e24 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -13,6 +13,7 @@ #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" +#include "xfs_rmap.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" @@ -34,6 +35,7 @@ xchk_rgsuperblock_xref( return; xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); + xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); } int @@ -61,7 +63,9 @@ xchk_rgsuperblock( if (!xchk_xref_process_error(sc, 0, 0, &error)) return error; - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; /* * Since we already validated the rt superblock at mount time, we don't diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c index a0a227d183d2..f5f73078ffe2 100644 --- a/fs/xfs/scrub/rmap_repair.c +++ b/fs/xfs/scrub/rmap_repair.c @@ -31,6 +31,9 @@ #include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_ag.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -499,6 +502,69 @@ 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) +{ + struct xfs_scrub *sc = rf->rr->sc; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *cur = NULL; + enum xfs_rtg_inodes type; + int error; + + if (rf->whichfork != XFS_DATA_FORK) + return -EFSCORRUPTED; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + type = XFS_RTGI_RMAP; + break; + case XFS_METAFILE_RTREFCOUNT: + type = XFS_RTGI_REFCOUNT; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + if (ip == rtg->rtg_inodes[type]) + goto found; + } + + /* + * We should never find an rt metadata btree inode that isn't + * associated with an rtgroup yet has ondisk blocks allocated to it. + */ + if (ip->i_nblocks) { + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; + +found: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, rtg); + break; + default: + ASSERT(0); + error = -EFSCORRUPTED; + goto out_rtg; + } + + error = xrep_rmap_scan_iroot_btree(rf, cur); + xfs_btree_del_cursor(cur, error); +out_rtg: + xfs_rtgroup_rele(rtg); + return error; +} + /* Find all the extents from a given AG in an inode fork. */ STATIC int xrep_rmap_scan_ifork( @@ -512,14 +578,14 @@ 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 +594,18 @@ 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; } /* @@ -1552,7 +1621,7 @@ xrep_rmapbt_live_update( if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo)) goto out_unlock; - trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p); + trace_xrep_rmap_live_update(pag_group(rr->sc->sa.pag), action, p); error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); if (error) diff --git a/fs/xfs/scrub/rtb_bitmap.h b/fs/xfs/scrub/rtb_bitmap.h new file mode 100644 index 000000000000..1313ef605511 --- /dev/null +++ b/fs/xfs/scrub/rtb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2022-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_SCRUB_RTB_BITMAP_H__ +#define __XFS_SCRUB_RTB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rtblock_t */ + +struct xrtb_bitmap { + struct xbitmap64 rtbitmap; +}; + +static inline void xrtb_bitmap_init(struct xrtb_bitmap *bitmap) +{ + xbitmap64_init(&bitmap->rtbitmap); +} + +static inline void xrtb_bitmap_destroy(struct xrtb_bitmap *bitmap) +{ + xbitmap64_destroy(&bitmap->rtbitmap); +} + +static inline int xrtb_bitmap_set(struct xrtb_bitmap *bitmap, + xfs_rtblock_t start, xfs_filblks_t len) +{ + return xbitmap64_set(&bitmap->rtbitmap, start, len); +} + +static inline int xrtb_bitmap_walk(struct xrtb_bitmap *bitmap, + xbitmap64_walk_fn fn, void *priv) +{ + return xbitmap64_walk(&bitmap->rtbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RTB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 376a36fd9a9c..d5ff8609dbfb 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -9,17 +9,25 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_rtbitmap.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_bit.h" +#include "xfs_rtgroup.h" #include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" +#include "xfs_zone_alloc.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" +#include "scrub/tempexch.h" #include "scrub/rtbitmap.h" +#include "scrub/btree.h" /* Set us up with the realtime metadata locked. */ int @@ -30,10 +38,15 @@ xchk_setup_rtbitmap( struct xchk_rtbitmap *rtb; int error; - rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS); + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + rtb = kzalloc(struct_size(rtb, words, xchk_rtbitmap_wordcnt(sc)), + XCHK_GFP_FLAGS); if (!rtb) return -ENOMEM; sc->buf = rtb; + rtb->sc = sc; error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); if (error) @@ -49,8 +62,7 @@ xchk_setup_rtbitmap( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]); + error = xchk_install_live_inode(sc, rtg_bitmap(sc->sr.rtg)); if (error) return error; @@ -58,12 +70,15 @@ xchk_setup_rtbitmap( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + /* * Now that we've locked the rtbitmap, we can't race with growfsrt * trying to expand the bitmap or change the size of the rt volume. * Hence it is safe to compute and check the geometry values. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rtb->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rtb->rextslog = xfs_compute_rextslog(rtb->rextents); @@ -73,7 +88,32 @@ xchk_setup_rtbitmap( return 0; } -/* Realtime bitmap. */ +/* Per-rtgroup bitmap contents. */ + +/* Cross-reference rtbitmap entries with other metadata. */ +STATIC void +xchk_rtbitmap_xref( + struct xchk_rtbitmap *rtb, + xfs_rtblock_t startblock, + xfs_rtblock_t blockcount) +{ + struct xfs_scrub *sc = rtb->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, startblock); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + if (!sc->sr.rmap_cur) + return; + + xchk_xref_has_no_rt_owner(sc, rgbno, blockcount); + xchk_xref_is_not_rt_shared(sc, rgbno, blockcount); + xchk_xref_is_not_rt_cow_staging(sc, rgbno, blockcount); + + if (rtb->next_free_rgbno < rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + rgbno - rtb->next_free_rgbno); + rtb->next_free_rgbno = rgbno + blockcount; +} /* Scrub a free extent record from the realtime bitmap. */ STATIC int @@ -83,7 +123,8 @@ xchk_rtbitmap_rec( const struct xfs_rtalloc_rec *rec, void *priv) { - struct xfs_scrub *sc = priv; + struct xchk_rtbitmap *rtb = priv; + struct xfs_scrub *sc = rtb->sc; xfs_rtblock_t startblock; xfs_filblks_t blockcount; @@ -92,6 +133,12 @@ xchk_rtbitmap_rec( if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount)) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); + + xchk_rtbitmap_xref(rtb, startblock, blockcount); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return -ECANCELED; + return 0; } @@ -139,15 +186,16 @@ xchk_rtbitmap_check_extents( return error; } -/* Scrub the realtime bitmap. */ +/* Scrub this group's realtime bitmap. */ int xchk_rtbitmap( struct xfs_scrub *sc) { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xchk_rtbitmap *rtb = sc->buf; + xfs_rgblock_t last_rgbno; int error; /* Is sb_rextents correct? */ @@ -200,10 +248,20 @@ xchk_rtbitmap( if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) return error; - error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc); + rtb->next_free_rgbno = 0; + error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, rtb); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) return error; + /* + * Check that the are rmappings for all rt extents between the end of + * the last free extent we saw and the last possible extent in the rt + * group. + */ + last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1; + if (rtb->next_free_rgbno < last_rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + last_rgbno - rtb->next_free_rgbno); return 0; } @@ -215,7 +273,6 @@ xchk_xref_is_used_rt_space( xfs_extlen_t len) { struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; xfs_rtxnum_t startext; xfs_rtxnum_t endext; bool is_free; @@ -224,6 +281,13 @@ xchk_xref_is_used_rt_space( if (xchk_skip_xref(sc->sm)) return; + if (xfs_has_zoned(sc->mp)) { + if (!xfs_zone_rgbno_is_valid(rtg, + xfs_rtb_to_rgbno(sc->mp, rtbno) + len - 1)) + xchk_ino_xref_set_corrupt(sc, rtg_rmap(rtg)->i_ino); + return; + } + startext = xfs_rtb_to_rtx(sc->mp, rtbno); endext = xfs_rtb_to_rtx(sc->mp, rtbno + len - 1); error = xfs_rtalloc_extent_is_free(rtg, sc->tp, startext, @@ -231,5 +295,5 @@ xchk_xref_is_used_rt_space( if (!xchk_should_check_xref(sc, &error, NULL)) return; if (is_free) - xchk_ino_xref_set_corrupt(sc, rbmip->i_ino); + xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino); } diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h index 85304ff019e1..fe52b877253d 100644 --- a/fs/xfs/scrub/rtbitmap.h +++ b/fs/xfs/scrub/rtbitmap.h @@ -6,17 +6,72 @@ #ifndef __XFS_SCRUB_RTBITMAP_H__ #define __XFS_SCRUB_RTBITMAP_H__ +/* + * We use an xfile to construct new bitmap blocks for the portion of the + * rtbitmap file that we're replacing. Whereas the ondisk bitmap must be + * accessed through the buffer cache, the xfile bitmap supports direct + * word-level accesses. Therefore, we create a small abstraction for linear + * access. + */ +typedef unsigned long long xrep_wordoff_t; +typedef unsigned int xrep_wordcnt_t; + +/* Mask to round an rtx down to the nearest bitmap word. */ +#define XREP_RTBMP_WORDMASK ((1ULL << XFS_NBWORDLOG) - 1) + + struct xchk_rtbitmap { + struct xfs_scrub *sc; + uint64_t rextents; uint64_t rbmblocks; unsigned int rextslog; unsigned int resblks; + + /* The next free rt group block number that we expect to see. */ + xfs_rgblock_t next_free_rgbno; + +#ifdef CONFIG_XFS_ONLINE_REPAIR + /* stuff for staging a new bitmap */ + struct xfs_rtalloc_args args; + struct xrep_tempexch tempexch; +#endif + + /* The next rtgroup block we expect to see during our rtrmapbt walk. */ + xfs_rgblock_t next_rgbno; + + /* rtgroup lock flags */ + unsigned int rtglock_flags; + + /* rtword position of xfile as we write buffers to disk. */ + xrep_wordoff_t prep_wordoff; + + /* In-Memory rtbitmap for repair. */ + union xfs_rtword_raw words[]; }; #ifdef CONFIG_XFS_ONLINE_REPAIR int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb); + +/* + * How big should the words[] buffer be? + * + * For repairs, we want a full fsblock worth of space so that we can memcpy a + * buffer full of 1s into the xfile bitmap. The xfile bitmap doesn't have + * rtbitmap block headers, so we don't use blockwsize. Scrub doesn't use the + * words buffer at all. + */ +static inline unsigned int +xchk_rtbitmap_wordcnt( + struct xfs_scrub *sc) +{ + if (xchk_could_repair(sc)) + return sc->mp->m_sb.sb_blocksize >> XFS_WORDLOG; + return 0; +} #else # define xrep_setup_rtbitmap(sc, rtb) (0) +# define xchk_rtbitmap_wordcnt(sc) (0) #endif /* CONFIG_XFS_ONLINE_REPAIR */ #endif /* __XFS_SCRUB_RTBITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c index 0fef98e9f834..203a1a97c502 100644 --- a/fs/xfs/scrub/rtbitmap_repair.c +++ b/fs/xfs/scrub/rtbitmap_repair.c @@ -12,32 +12,66 @@ #include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" +#include "xfs_rtalloc.h" #include "xfs_inode.h" #include "xfs_bit.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_extent_busy.h" +#include "xfs_refcount.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" #include "scrub/repair.h" #include "scrub/xfile.h" +#include "scrub/tempfile.h" +#include "scrub/tempexch.h" +#include "scrub/reap.h" #include "scrub/rtbitmap.h" -/* Set up to repair the realtime bitmap file metadata. */ +/* rt bitmap content repairs */ + +/* Set up to repair the realtime bitmap for this group. */ int xrep_setup_rtbitmap( struct xfs_scrub *sc, struct xchk_rtbitmap *rtb) { struct xfs_mount *mp = sc->mp; - unsigned long long blocks = 0; + char *descr; + unsigned long long blocks = mp->m_sb.sb_rbmblocks; + int error; + + error = xrep_tempfile_create(sc, S_IFREG); + if (error) + return error; + + /* Create an xfile to hold our reconstructed bitmap. */ + descr = xchk_xfile_rtgroup_descr(sc, "bitmap file"); + error = xfile_create(descr, blocks * mp->m_sb.sb_blocksize, &sc->xfile); + kfree(descr); + if (error) + return error; /* - * Reserve enough blocks to write out a completely new bmbt for a - * maximally fragmented bitmap file. We do not hold the rtbitmap - * ILOCK yet, so this is entirely speculative. + * Reserve enough blocks to write out a completely new bitmap file, + * plus twice as many blocks as we would need if we can only allocate + * one block per data fork mapping. This should cover the + * preallocation of the temporary file and exchanging the extent + * mappings. + * + * We cannot use xfs_exchmaps_estimate because we have not yet + * constructed the replacement bitmap and therefore do not know how + * many extents it will use. By the time we do, we will have a dirty + * transaction (which we cannot drop because we cannot drop the + * rtbitmap ILOCK) and cannot ask for more reservation. */ - blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks); + blocks += xfs_bmbt_calc_size(mp, blocks) * 2; if (blocks > UINT_MAX) return -EOPNOTSUPP; @@ -45,6 +79,325 @@ xrep_setup_rtbitmap( return 0; } +static inline xrep_wordoff_t +rtx_to_wordoff( + struct xfs_mount *mp, + xfs_rtxnum_t rtx) +{ + return rtx >> XFS_NBWORDLOG; +} + +static inline xrep_wordcnt_t +rtxlen_to_wordcnt( + xfs_rtxlen_t rtxlen) +{ + return rtxlen >> XFS_NBWORDLOG; +} + +/* Helper functions to record rtwords in an xfile. */ + +static inline int +xfbmp_load( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t *word) +{ + union xfs_rtword_raw urk; + int error; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + error = xfile_load(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); + if (error) + return error; + + *word = be32_to_cpu(urk.rtg); + return 0; +} + +static inline int +xfbmp_store( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const xfs_rtword_t word) +{ + union xfs_rtword_raw urk; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + urk.rtg = cpu_to_be32(word); + return xfile_store(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyin( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_store(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyout( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_load(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +/* Perform a logical OR operation on an rtword in the incore bitmap. */ +static int +xrep_rtbitmap_or( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t mask) +{ + xfs_rtword_t word; + int error; + + error = xfbmp_load(rtb, wordoff, &word); + if (error) + return error; + + trace_xrep_rtbitmap_or(rtb->sc->mp, wordoff, mask, word); + + return xfbmp_store(rtb, wordoff, word | mask); +} + +/* + * Mark as free every rt extent between the next rt block we expected to see + * in the rtrmap records and the given rt block. + */ +STATIC int +xrep_rtbitmap_mark_free( + struct xchk_rtbitmap *rtb, + xfs_rgblock_t rgbno) +{ + struct xfs_mount *mp = rtb->sc->mp; + struct xchk_rt *sr = &rtb->sc->sr; + struct xfs_rtgroup *rtg = sr->rtg; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t nextrtx; + xrep_wordoff_t wordoff, nextwordoff; + unsigned int bit; + unsigned int bufwsize; + xfs_extlen_t mod; + xfs_rtword_t mask; + enum xbtree_recpacking outcome; + int error; + + if (!xfs_verify_rgbext(rtg, rtb->next_rgbno, rgbno - rtb->next_rgbno)) + return -EFSCORRUPTED; + + /* + * Convert rt blocks to rt extents The block range we find must be + * aligned to an rtextent boundary on both ends. + */ + startrtx = xfs_rgbno_to_rtx(mp, rtb->next_rgbno); + mod = xfs_rgbno_to_rtxoff(mp, rtb->next_rgbno); + if (mod) + return -EFSCORRUPTED; + + nextrtx = xfs_rgbno_to_rtx(mp, rgbno - 1) + 1; + mod = xfs_rgbno_to_rtxoff(mp, rgbno - 1); + if (mod != mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Must not be shared or CoW staging. */ + if (sr->refc_cur) { + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_SHARED, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_COW, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + } + + trace_xrep_rtbitmap_record_free(mp, startrtx, nextrtx - 1); + + /* Set bits as needed to round startrtx up to the nearest word. */ + bit = startrtx & XREP_RTBMP_WORDMASK; + if (bit) { + xfs_rtblock_t len = nextrtx - startrtx; + unsigned int lastbit; + + lastbit = min(bit + len, XFS_NBWORD); + mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, startrtx), + mask); + if (error || lastbit - bit == len) + return error; + startrtx += XFS_NBWORD - bit; + } + + /* Set bits as needed to round nextrtx down to the nearest word. */ + bit = nextrtx & XREP_RTBMP_WORDMASK; + if (bit) { + mask = ((xfs_rtword_t)1 << bit) - 1; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, nextrtx), + mask); + if (error || startrtx + bit == nextrtx) + return error; + nextrtx -= bit; + } + + trace_xrep_rtbitmap_record_free_bulk(mp, startrtx, nextrtx - 1); + + /* Set all the words in between, up to a whole fs block at once. */ + wordoff = rtx_to_wordoff(mp, startrtx); + nextwordoff = rtx_to_wordoff(mp, nextrtx); + bufwsize = mp->m_sb.sb_blocksize >> XFS_WORDLOG; + + while (wordoff < nextwordoff) { + xrep_wordoff_t rem; + xrep_wordcnt_t wordcnt; + + wordcnt = min_t(xrep_wordcnt_t, nextwordoff - wordoff, + bufwsize); + + /* + * Try to keep us aligned to the rtwords buffer to reduce the + * number of xfile writes. + */ + rem = wordoff & (bufwsize - 1); + if (rem) + wordcnt = min_t(xrep_wordcnt_t, wordcnt, + bufwsize - rem); + + error = xfbmp_copyin(rtb, wordoff, rtb->words, wordcnt); + if (error) + return error; + + wordoff += wordcnt; + } + + return 0; +} + +/* Set free space in the rtbitmap based on rtrmapbt records. */ +STATIC int +xrep_rtbitmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtbitmap *rtb = priv; + int error = 0; + + if (xchk_should_terminate(rtb->sc, &error)) + return error; + + if (rtb->next_rgbno < rec->rm_startblock) { + error = xrep_rtbitmap_mark_free(rtb, rec->rm_startblock); + if (error) + return error; + } + + rtb->next_rgbno = max(rtb->next_rgbno, + rec->rm_startblock + rec->rm_blockcount); + return 0; +} + +/* + * Walk the rtrmapbt to find all the gaps between records, and mark the gaps + * in the realtime bitmap that we're computing. + */ +STATIC int +xrep_rtbitmap_find_freespace( + struct xchk_rtbitmap *rtb) +{ + struct xfs_scrub *sc = rtb->sc; + struct xfs_mount *mp = sc->mp; + struct xfs_rtgroup *rtg = sc->sr.rtg; + uint64_t blockcount; + int error; + + /* Prepare a buffer of ones so that we can accelerate bulk setting. */ + memset(rtb->words, 0xFF, mp->m_sb.sb_blocksize); + + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_rtbitmap_walk_rtrmap, + rtb); + if (error) + goto out; + + /* + * Mark as free every possible rt extent from the last one we saw to + * the end of the rt group. + */ + blockcount = rtg->rtg_extents * mp->m_sb.sb_rextsize; + if (rtb->next_rgbno < blockcount) { + error = xrep_rtbitmap_mark_free(rtb, blockcount); + if (error) + goto out; + } + +out: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +static int +xrep_rtbitmap_prep_buf( + struct xfs_scrub *sc, + struct xfs_buf *bp, + void *data) +{ + struct xchk_rtbitmap *rtb = data; + struct xfs_mount *mp = sc->mp; + union xfs_rtword_raw *ondisk; + int error; + + rtb->args.mp = sc->mp; + rtb->args.tp = sc->tp; + rtb->args.rbmbp = bp; + ondisk = xfs_rbmblock_wordptr(&rtb->args, 0); + rtb->args.rbmbp = NULL; + + error = xfbmp_copyout(rtb, rtb->prep_wordoff, ondisk, + mp->m_blockwsize); + if (error) + return error; + + if (xfs_has_rtgroups(sc->mp)) { + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC); + hdr->rt_owner = cpu_to_be64(sc->ip->i_ino); + hdr->rt_blkno = cpu_to_be64(xfs_buf_daddr(bp)); + hdr->rt_lsn = 0; + uuid_copy(&hdr->rt_uuid, &sc->mp->m_sb.sb_meta_uuid); + bp->b_ops = &xfs_rtbitmap_buf_ops; + } else { + bp->b_ops = &xfs_rtbuf_ops; + } + + rtb->prep_wordoff += mp->m_blockwsize; + xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTBITMAP_BUF); + return 0; +} + /* * Make sure that the given range of the data fork of the realtime file is * mapped to written blocks. The caller must ensure that the inode is joined @@ -160,9 +513,18 @@ xrep_rtbitmap( { struct xchk_rtbitmap *rtb = sc->buf; struct xfs_mount *mp = sc->mp; + struct xfs_group *xg = rtg_group(sc->sr.rtg); unsigned long long blocks = 0; + unsigned int busy_gen; int error; + /* We require the realtime rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(sc->mp)) + return -EOPNOTSUPP; + /* We require atomic file exchange range to rebuild anything. */ + if (!xfs_has_exchange_range(sc->mp)) + return -EOPNOTSUPP; + /* Impossibly large rtbitmap means we can't touch the filesystem. */ if (rtb->rbmblocks > U32_MAX) return 0; @@ -195,6 +557,79 @@ xrep_rtbitmap( if (error) return error; - /* Fix inconsistent bitmap geometry */ - return xrep_rtbitmap_geometry(sc, rtb); + /* + * Fix inconsistent bitmap geometry. This function returns with a + * clean scrub transaction. + */ + error = xrep_rtbitmap_geometry(sc, rtb); + if (error) + return error; + + /* + * Make sure the busy extent list is clear because we can't put extents + * on there twice. + */ + if (!xfs_extent_busy_list_empty(xg, &busy_gen)) { + error = xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0); + if (error) + return error; + } + + /* + * Generate the new rtbitmap data. We don't need the rtbmp information + * once this call is finished. + */ + error = xrep_rtbitmap_find_freespace(rtb); + if (error) + return error; + + /* + * Try to take ILOCK_EXCL of the temporary file. We had better be the + * only ones holding onto this inode, but we can't block while holding + * the rtbitmap file's ILOCK_EXCL. + */ + while (!xrep_tempfile_ilock_nowait(sc)) { + if (xchk_should_terminate(sc, &error)) + return error; + delay(1); + } + + /* + * Make sure we have space allocated for the part of the bitmap + * file that corresponds to this group. We already joined sc->ip. + */ + xfs_trans_ijoin(sc->tp, sc->tempip, 0); + error = xrep_tempfile_prealloc(sc, 0, rtb->rbmblocks); + if (error) + return error; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + return error; + + /* Copy the bitmap file that we generated. */ + error = xrep_tempfile_copyin(sc, 0, rtb->rbmblocks, + xrep_rtbitmap_prep_buf, rtb); + if (error) + return error; + error = xrep_tempfile_set_isize(sc, + XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)); + if (error) + return error; + + /* + * Now exchange the data fork contents. We're done with the temporary + * buffer, so we can reuse it for the tempfile exchmaps information. + */ + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rtb->rbmblocks, &rtb->tempexch); + if (error) + return error; + + error = xrep_tempexch_contents(sc, &rtb->tempexch); + if (error) + return error; + + /* Free the old rtbitmap blocks if they're not in use. */ + return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK); } diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c new file mode 100644 index 000000000000..4c5dffc73641 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount.c @@ -0,0 +1,661 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trans.h" +#include "xfs_btree.h" +#include "xfs_rmap.h" +#include "xfs_refcount.h" +#include "xfs_inode.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/repair.h" + +/* Set us up with the realtime refcount metadata locked. */ +int +xchk_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrefcountbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_refcount(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime Reference count btree scrubber. */ + +/* + * Confirming Reference Counts via Reverse Mappings + * + * We want to count the reverse mappings overlapping a refcount record + * (bno, len, refcount), allowing for the possibility that some of the + * overlap may come from smaller adjoining reverse mappings, while some + * comes from single extents which overlap the range entirely. The + * outer loop is as follows: + * + * 1. For all reverse mappings overlapping the refcount extent, + * a. If a given rmap completely overlaps, mark it as seen. + * b. Otherwise, record the fragment (in agbno order) for later + * processing. + * + * Once we've seen all the rmaps, we know that for all blocks in the + * refcount record we want to find $refcount owners and we've already + * visited $seen extents that overlap all the blocks. Therefore, we + * need to find ($refcount - $seen) owners for every block in the + * extent; call that quantity $target_nr. Proceed as follows: + * + * 2. Pull the first $target_nr fragments from the list; all of them + * should start at or before the start of the extent. + * Call this subset of fragments the working set. + * 3. Until there are no more unprocessed fragments, + * a. Find the shortest fragments in the set and remove them. + * b. Note the block number of the end of these fragments. + * c. Pull the same number of fragments from the list. All of these + * fragments should start at the block number recorded in the + * previous step. + * d. Put those fragments in the set. + * 4. Check that there are $target_nr fragments remaining in the list, + * and that they all end at or beyond the end of the refcount extent. + * + * If the refcount is correct, all the check conditions in the algorithm + * should always hold true. If not, the refcount is incorrect. + */ +struct xchk_rtrefcnt_frag { + struct list_head list; + struct xfs_rmap_irec rm; +}; + +struct xchk_rtrefcnt_check { + struct xfs_scrub *sc; + struct list_head fragments; + + /* refcount extent we're examining */ + xfs_rgblock_t bno; + xfs_extlen_t len; + xfs_nlink_t refcount; + + /* number of owners seen */ + xfs_nlink_t seen; +}; + +/* + * Decide if the given rmap is large enough that we can redeem it + * towards refcount verification now, or if it's a fragment, in + * which case we'll hang onto it in the hopes that we'll later + * discover that we've collected exactly the correct number of + * fragments as the rtrefcountbt says we should have. + */ +STATIC int +xchk_rtrefcountbt_rmap_check( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtrefcnt_check *refchk = priv; + struct xchk_rtrefcnt_frag *frag; + xfs_rgblock_t rm_last; + xfs_rgblock_t rc_last; + int error = 0; + + if (xchk_should_terminate(refchk->sc, &error)) + return error; + + rm_last = rec->rm_startblock + rec->rm_blockcount - 1; + rc_last = refchk->bno + refchk->len - 1; + + /* Confirm that a single-owner refc extent is a CoW stage. */ + if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) { + xchk_btree_xref_set_corrupt(refchk->sc, cur, 0); + return 0; + } + + if (rec->rm_startblock <= refchk->bno && rm_last >= rc_last) { + /* + * The rmap overlaps the refcount record, so we can confirm + * one refcount owner seen. + */ + refchk->seen++; + } else { + /* + * This rmap covers only part of the refcount record, so + * save the fragment for later processing. If the rmapbt + * is healthy each rmap_irec we see will be in agbno order + * so we don't need insertion sort here. + */ + frag = kmalloc(sizeof(struct xchk_rtrefcnt_frag), + XCHK_GFP_FLAGS); + if (!frag) + return -ENOMEM; + memcpy(&frag->rm, rec, sizeof(frag->rm)); + list_add_tail(&frag->list, &refchk->fragments); + } + + return 0; +} + +/* + * Given a bunch of rmap fragments, iterate through them, keeping + * a running tally of the refcount. If this ever deviates from + * what we expect (which is the rtrefcountbt's refcount minus the + * number of extents that totally covered the rtrefcountbt extent), + * we have a rtrefcountbt error. + */ +STATIC void +xchk_rtrefcountbt_process_rmap_fragments( + struct xchk_rtrefcnt_check *refchk) +{ + struct list_head worklist; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + xfs_rgblock_t bno; + xfs_rgblock_t rbno; + xfs_rgblock_t next_rbno; + xfs_nlink_t nr; + xfs_nlink_t target_nr; + + target_nr = refchk->refcount - refchk->seen; + if (target_nr == 0) + return; + + /* + * There are (refchk->rc.rc_refcount - refchk->nr refcount) + * references we haven't found yet. Pull that many off the + * fragment list and figure out where the smallest rmap ends + * (and therefore the next rmap should start). All the rmaps + * we pull off should start at or before the beginning of the + * refcount record's range. + */ + INIT_LIST_HEAD(&worklist); + rbno = NULLRGBLOCK; + + /* Make sure the fragments actually /are/ in bno order. */ + bno = 0; + list_for_each_entry(frag, &refchk->fragments, list) { + if (frag->rm.rm_startblock < bno) + goto done; + bno = frag->rm.rm_startblock; + } + + /* + * Find all the rmaps that start at or before the refc extent, + * and put them on the worklist. + */ + nr = 0; + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno < rbno) + rbno = bno; + list_move_tail(&frag->list, &worklist); + nr++; + } + + /* + * We should have found exactly $target_nr rmap fragments starting + * at or before the refcount extent. + */ + if (nr != target_nr) + goto done; + + while (!list_empty(&refchk->fragments)) { + /* Discard any fragments ending at rbno from the worklist. */ + nr = 0; + next_rbno = NULLRGBLOCK; + list_for_each_entry_safe(frag, n, &worklist, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno != rbno) { + if (bno < next_rbno) + next_rbno = bno; + continue; + } + list_del(&frag->list); + kfree(frag); + nr++; + } + + /* Try to add nr rmaps starting at rbno to the worklist. */ + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (frag->rm.rm_startblock != rbno) + goto done; + list_move_tail(&frag->list, &worklist); + if (next_rbno > bno) + next_rbno = bno; + nr--; + if (nr == 0) + break; + } + + /* + * If we get here and nr > 0, this means that we added fewer + * items to the worklist than we discarded because the fragment + * list ran out of items. Therefore, we cannot maintain the + * required refcount. Something is wrong, so we're done. + */ + if (nr) + goto done; + + rbno = next_rbno; + } + + /* + * Make sure the last extent we processed ends at or beyond + * the end of the refcount extent. + */ + if (rbno < refchk->bno + refchk->len) + goto done; + + /* Actually record us having seen the remaining refcount. */ + refchk->seen = refchk->refcount; +done: + /* Delete fragments and work list. */ + list_for_each_entry_safe(frag, n, &worklist, list) { + list_del(&frag->list); + kfree(frag); + } + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Use the rmap entries covering this extent to verify the refcount. */ +STATIC void +xchk_rtrefcountbt_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + struct xchk_rtrefcnt_check refchk = { + .sc = sc, + .bno = irec->rc_startblock, + .len = irec->rc_blockcount, + .refcount = irec->rc_refcount, + .seen = 0, + }; + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Cross-reference with the rmapbt to confirm the refcount. */ + memset(&low, 0, sizeof(low)); + low.rm_startblock = irec->rc_startblock; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1; + + INIT_LIST_HEAD(&refchk.fragments); + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check, &refchk); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + goto out_free; + + xchk_rtrefcountbt_process_rmap_fragments(&refchk); + if (irec->rc_refcount != refchk.seen) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + +out_free: + list_for_each_entry_safe(frag, n, &refchk.fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Cross-reference with the other btrees. */ +STATIC void +xchk_rtrefcountbt_xref( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rc_startblock), + irec->rc_blockcount); + xchk_rtrefcountbt_xref_rmap(sc, irec); +} + +struct xchk_rtrefcbt_records { + /* Previous refcount record. */ + struct xfs_refcount_irec prev_rec; + + /* The next rtgroup block where we aren't expecting shared extents. */ + xfs_rgblock_t next_unshared_rgbno; + + /* Number of CoW blocks we expect. */ + xfs_extlen_t cow_blocks; + + /* Was the last record a shared or CoW staging extent? */ + enum xfs_refc_domain prev_domain; +}; + +static inline bool +xchk_rtrefcount_mergeable( + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *r2) +{ + const struct xfs_refcount_irec *r1 = &rrc->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (r1->rc_blockcount > 0) + return false; + + if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) + return false; + if (r1->rc_refcount != r2->rc_refcount) + return false; + if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > + XFS_REFC_LEN_MAX) + return false; + + return true; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrefcountbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrefcount_mergeable(rrc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&rrc->prev_rec, irec, sizeof(struct xfs_refcount_irec)); +} + +STATIC int +xchk_rtrefcountbt_rmap_check_gap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + xfs_rgblock_t *next_bno = priv; + + if (*next_bno != NULLRGBLOCK && rec->rm_startblock < *next_bno) + return -ECANCELED; + + *next_bno = rec->rm_startblock + rec->rm_blockcount; + return 0; +} + +/* + * Make sure that a gap in the reference count records does not correspond to + * overlapping records (i.e. shared extents) in the reverse mappings. + */ +static inline void +xchk_rtrefcountbt_xref_gaps( + struct xfs_scrub *sc, + struct xchk_rtrefcbt_records *rrc, + xfs_rtblock_t bno) +{ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + xfs_rgblock_t next_bno = NULLRGBLOCK; + int error; + + if (bno <= rrc->next_unshared_rgbno || !sc->sr.rmap_cur || + xchk_skip_xref(sc->sm)) + return; + + memset(&low, 0, sizeof(low)); + low.rm_startblock = rrc->next_unshared_rgbno; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = bno - 1; + + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check_gap, &next_bno); + if (error == -ECANCELED) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + else + xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur); +} + +/* Scrub a rtrefcountbt record. */ +STATIC int +xchk_rtrefcountbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xfs_mount *mp = bs->cur->bc_mp; + struct xchk_rtrefcbt_records *rrc = bs->private; + struct xfs_refcount_irec irec; + u32 mod; + + xfs_refcount_btrec_to_irec(rec, &irec); + if (xfs_rtrefcount_check_irec(to_rtg(bs->cur->bc_group), &irec) != + NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + /* We can only share full rt extents. */ + mod = xfs_rgbno_to_rtxoff(mp, irec.rc_startblock); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + mod = xfs_extlen_to_rtxmod(mp, irec.rc_blockcount); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + if (irec.rc_domain == XFS_REFC_DOMAIN_COW) + rrc->cow_blocks += irec.rc_blockcount; + + /* Shared records always come before CoW records. */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED && + rrc->prev_domain == XFS_REFC_DOMAIN_COW) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + rrc->prev_domain = irec.rc_domain; + + xchk_rtrefcountbt_check_mergeable(bs, rrc, &irec); + xchk_rtrefcountbt_xref(bs->sc, &irec); + + /* + * If this is a record for a shared extent, check that all blocks + * between the previous record and this one have at most one reverse + * mapping. + */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED) { + xchk_rtrefcountbt_xref_gaps(bs->sc, rrc, irec.rc_startblock); + rrc->next_unshared_rgbno = irec.rc_startblock + + irec.rc_blockcount; + } + + return 0; +} + +/* Make sure we have as many refc blocks as the rmap says. */ +STATIC void +xchk_refcount_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_owner_info *btree_oinfo, + xfs_extlen_t cow_blocks) +{ + xfs_filblks_t refcbt_blocks = 0; + xfs_filblks_t blocks; + int error; + + if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Check that we saw as many refcbt blocks as the rmap knows about. */ + error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); + if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) + return; + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + return; + if (blocks != refcbt_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + + /* Check that we saw as many cow blocks as the rmap knows about. */ + error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, + &XFS_RMAP_OINFO_COW, &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (blocks != cow_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* Scrub the refcount btree for some AG. */ +int +xchk_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xfs_owner_info btree_oinfo; + struct xchk_rtrefcbt_records rrc = { + .cow_blocks = 0, + .next_unshared_rgbno = 0, + .prev_domain = XFS_REFC_DOMAIN_SHARED, + }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&btree_oinfo, rtg_refcount(sc->sr.rtg)->i_ino, + XFS_DATA_FORK); + error = xchk_btree(sc, sc->sr.refc_cur, xchk_rtrefcountbt_rec, + &btree_oinfo, &rrc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + /* + * Check that all blocks between the last refcount > 1 record and the + * end of the rt volume have at most one reverse mapping. + */ + xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); + + xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + + return 0; +} + +/* xref check that a cow staging extent is marked in the rtrefcountbt. */ +void +xchk_xref_is_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + struct xfs_refcount_irec rc; + int has_refcount; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + /* Find the CoW staging extent. */ + error = xfs_refcount_lookup_le(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + error = xfs_refcount_get_rec(sc->sr.refc_cur, &rc, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + /* CoW lookup returned a shared extent record? */ + if (rc.rc_domain != XFS_REFC_DOMAIN_COW) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + + /* Must be at least as long as what was passed in */ + if (rc.rc_blockcount < len) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* + * xref check that the extent is not shared. Only file data blocks + * can have multiple owners. + */ +void +xchk_xref_is_not_rt_shared( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, + XFS_REFC_DOMAIN_SHARED, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* xref check that the extent is not being used for CoW staging. */ +void +xchk_xref_is_not_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} diff --git a/fs/xfs/scrub/rtrefcount_repair.c b/fs/xfs/scrub/rtrefcount_repair.c new file mode 100644 index 000000000000..983362447826 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount_repair.c @@ -0,0 +1,761 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_ialloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_refcount.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_error.h" +#include "xfs_health.h" +#include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" +#include "scrub/rcbag.h" + +/* + * Rebuilding the Reference Count Btree + * ==================================== + * + * This algorithm is "borrowed" from xfs_repair. Imagine the rmap + * entries as rectangles representing extents of physical blocks, and + * that the rectangles can be laid down to allow them to overlap each + * other; then we know that we must emit a refcnt btree entry wherever + * the amount of overlap changes, i.e. the emission stimulus is + * level-triggered: + * + * - --- + * -- ----- ---- --- ------ + * -- ---- ----------- ---- --------- + * -------------------------------- ----------- + * ^ ^ ^^ ^^ ^ ^^ ^^^ ^^^^ ^ ^^ ^ ^ ^ + * 2 1 23 21 3 43 234 2123 1 01 2 3 0 + * + * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner). + * + * Note that in the actual refcnt btree we don't store the refcount < 2 + * cases because the bnobt tells us which blocks are free; single-use + * blocks aren't recorded in the bnobt or the refcntbt. If the rmapbt + * supports storing multiple entries covering a given block we could + * theoretically dispense with the refcntbt and simply count rmaps, but + * that's inefficient in the (hot) write path, so we'll take the cost of + * the extra tree to save time. Also there's no guarantee that rmap + * will be enabled. + * + * Given an array of rmaps sorted by physical block number, a starting + * physical block (sp), a bag to hold rmaps that cover sp, and the next + * physical block where the level changes (np), we can reconstruct the + * rt refcount btree as follows: + * + * While there are still unprocessed rmaps in the array, + * - Set sp to the physical block (pblk) of the next unprocessed rmap. + * - Add to the bag all rmaps in the array where startblock == sp. + * - Set np to the physical block where the bag size will change. This + * is the minimum of (the pblk of the next unprocessed rmap) and + * (startblock + len of each rmap in the bag). + * - Record the bag size as old_bag_size. + * + * - While the bag isn't empty, + * - Remove from the bag all rmaps where startblock + len == np. + * - Add to the bag all rmaps in the array where startblock == np. + * - If the bag size isn't old_bag_size, store the refcount entry + * (sp, np - sp, bag_size) in the refcnt btree. + * - If the bag is empty, break out of the inner loop. + * - Set old_bag_size to the bag size + * - Set sp = np. + * - Set np to the physical block where the bag size will change. + * This is the minimum of (the pblk of the next unprocessed rmap) + * and (startblock + len of each rmap in the bag). + * + * Like all the other repairers, we make a list of all the refcount + * records we need, then reinitialize the rt refcount btree root and + * insert all the records. + */ + +struct xrep_rtrefc { + /* refcount extents */ + struct xfarray *refcount_records; + + /* new refcountbt information */ + struct xrep_newbt new_btree; + + /* old refcountbt blocks */ + struct xfsb_bitmap old_rtrefcountbt_blocks; + + struct xfs_scrub *sc; + + /* get_records()'s position in the rt refcount record array. */ + xfarray_idx_t array_cur; + + /* # of refcountbt blocks */ + xfs_filblks_t btblocks; +}; + +/* Set us up to repair refcount btrees. */ +int +xrep_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + char *descr; + int error; + + descr = xchk_xfile_ag_descr(sc, "rmap record bag"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + return error; +} + +/* Check for any obvious conflicts with this shared/CoW staging extent. */ +STATIC int +xrep_rtrefc_check_ext( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *rec) +{ + xfs_rgblock_t last; + + if (xfs_rtrefcount_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + if (xfs_rgbno_to_rtxoff(sc->mp, rec->rc_startblock) != 0) + return -EFSCORRUPTED; + + last = rec->rc_startblock + rec->rc_blockcount - 1; + if (xfs_rgbno_to_rtxoff(sc->mp, last) != sc->mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Make sure this isn't free space or misaligned. */ + return xrep_require_rtext_inuse(sc, rec->rc_startblock, + rec->rc_blockcount); +} + +/* Record a reference count extent. */ +STATIC int +xrep_rtrefc_stash( + struct xrep_rtrefc *rr, + enum xfs_refc_domain domain, + xfs_rgblock_t bno, + xfs_extlen_t len, + uint64_t refcount) +{ + struct xfs_refcount_irec irec = { + .rc_startblock = bno, + .rc_blockcount = len, + .rc_refcount = refcount, + .rc_domain = domain, + }; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); + + error = xrep_rtrefc_check_ext(rr->sc, &irec); + if (error) + return error; + + trace_xrep_refc_found(rtg_group(rr->sc->sr.rtg), &irec); + + return xfarray_append(rr->refcount_records, &irec); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrefc_stash_cow( + struct xrep_rtrefc *rr, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + return xrep_rtrefc_stash(rr, XFS_REFC_DOMAIN_COW, bno, len, 1); +} + +/* Decide if an rmap could describe a shared extent. */ +static inline bool +xrep_rtrefc_rmap_shareable( + const struct xfs_rmap_irec *rmap) +{ + /* rt metadata are never sharable */ + if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + return false; + + /* Unwritten file blocks are not shareable. */ + if (rmap->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + + return true; +} + +/* Grab the next (abbreviated) rmap record from the rmapbt. */ +STATIC int +xrep_rtrefc_walk_rmaps( + struct xrep_rtrefc *rr, + struct xfs_rmap_irec *rmap, + bool *have_rec) +{ + struct xfs_btree_cur *cur = rr->sc->sr.rmap_cur; + struct xfs_mount *mp = cur->bc_mp; + int have_gt; + int error = 0; + + *have_rec = false; + + /* + * Loop through the remaining rmaps. Remember CoW staging + * extents and the refcountbt blocks from the old tree for later + * disposal. We can only share written data fork extents, so + * keep looping until we find an rmap for one. + */ + do { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfs_btree_increment(cur, 0, &have_gt); + if (error) + return error; + if (!have_gt) + return 0; + + error = xfs_rmap_get_rec(cur, rmap, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, !have_gt)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + if (rmap->rm_owner == XFS_RMAP_OWN_COW) { + error = xrep_rtrefc_stash_cow(rr, rmap->rm_startblock, + rmap->rm_blockcount); + if (error) + return error; + } else if (xfs_is_sb_inum(mp, rmap->rm_owner) || + (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + } while (!xrep_rtrefc_rmap_shareable(rmap)); + + *have_rec = true; + return 0; +} + +static inline uint32_t +xrep_rtrefc_encode_startblock( + const struct xfs_refcount_irec *irec) +{ + uint32_t start; + + start = irec->rc_startblock & ~XFS_REFC_COWFLAG; + if (irec->rc_domain == XFS_REFC_DOMAIN_COW) + start |= XFS_REFC_COWFLAG; + + return start; +} + +/* + * Compare two refcount records. We want to sort in order of increasing block + * number. + */ +static int +xrep_rtrefc_extent_cmp( + const void *a, + const void *b) +{ + const struct xfs_refcount_irec *ap = a; + const struct xfs_refcount_irec *bp = b; + uint32_t sa, sb; + + sa = xrep_rtrefc_encode_startblock(ap); + sb = xrep_rtrefc_encode_startblock(bp); + + if (sa > sb) + return 1; + if (sa < sb) + return -1; + return 0; +} + +/* + * Sort the refcount extents by startblock or else the btree records will be in + * the wrong order. Make sure the records do not overlap in physical space. + */ +STATIC int +xrep_rtrefc_sort_records( + struct xrep_rtrefc *rr) +{ + struct xfs_refcount_irec irec; + xfarray_idx_t cur; + enum xfs_refc_domain dom = XFS_REFC_DOMAIN_SHARED; + xfs_rgblock_t next_rgbno = 0; + int error; + + error = xfarray_sort(rr->refcount_records, xrep_rtrefc_extent_cmp, + XFARRAY_SORT_KILLABLE); + if (error) + return error; + + foreach_xfarray_idx(rr->refcount_records, cur) { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfarray_load(rr->refcount_records, cur, &irec); + if (error) + return error; + + if (dom == XFS_REFC_DOMAIN_SHARED && + irec.rc_domain == XFS_REFC_DOMAIN_COW) { + dom = irec.rc_domain; + next_rgbno = 0; + } + + if (dom != irec.rc_domain) + return -EFSCORRUPTED; + if (irec.rc_startblock < next_rgbno) + return -EFSCORRUPTED; + + next_rgbno = irec.rc_startblock + irec.rc_blockcount; + } + + return error; +} + +/* Record extents that belong to the realtime refcount inode. */ +STATIC int +xrep_rtrefc_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrefcountbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* + * Walk forward through the rmap btree to collect all rmaps starting at + * @bno in @rmap_bag. These represent the file(s) that share ownership of + * the current block. Upon return, the rmap cursor points to the last record + * satisfying the startblock constraint. + */ +static int +xrep_rtrefc_push_rmaps_at( + struct xrep_rtrefc *rr, + struct rcbag *rcstack, + xfs_rgblock_t bno, + struct xfs_rmap_irec *rmap, + bool *have) +{ + struct xfs_scrub *sc = rr->sc; + int have_gt; + int error; + + while (*have && rmap->rm_startblock == bno) { + error = rcbag_add(rcstack, rr->sc->tp, rmap); + if (error) + return error; + + error = xrep_rtrefc_walk_rmaps(rr, rmap, have); + if (error) + return error; + } + + error = xfs_btree_decrement(sc->sr.rmap_cur, 0, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(sc->mp, !have_gt)) { + xfs_btree_mark_sick(sc->sr.rmap_cur); + return -EFSCORRUPTED; + } + + return 0; +} + +/* Scan one AG for reverse mappings for the realtime refcount btree. */ +STATIC int +xrep_rtrefc_scan_ag( + struct xrep_rtrefc *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrefc_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +/* Iterate all the rmap records to generate reference count data. */ +STATIC int +xrep_rtrefc_find_refcounts( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct rcbag *rcstack; + struct xfs_perag *pag = NULL; + uint64_t old_stack_height; + xfs_rgblock_t sbno; + xfs_rgblock_t cbno; + xfs_rgblock_t nbno; + bool have; + int error; + + /* Scan for old rtrefc btree blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrefc_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + xrep_rtgroup_btcur_init(sc, &sc->sr); + + /* + * Set up a bag to store all the rmap records that we're tracking to + * generate a reference count record. If this exceeds + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. + */ + error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); + if (error) + goto out_cur; + + /* Start the rtrmapbt cursor to the left of all records. */ + error = xfs_btree_goto_left_edge(sc->sr.rmap_cur); + if (error) + goto out_bag; + + /* Process reverse mappings into refcount data. */ + while (xfs_btree_has_more_records(sc->sr.rmap_cur)) { + struct xfs_rmap_irec rmap; + + /* Push all rmaps with pblk == sbno onto the stack */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (!have) + break; + sbno = cbno = rmap.rm_startblock; + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, sbno, &rmap, + &have); + if (error) + goto out_bag; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + old_stack_height = rcbag_count(rcstack); + + /* While stack isn't empty... */ + while (rcbag_count(rcstack) > 0) { + /* Pop all rmaps that end at nbno */ + error = rcbag_remove_ending_at(rcstack, sc->tp, nbno); + if (error) + goto out_bag; + + /* Push array items that start at nbno */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (have) { + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, + nbno, &rmap, &have); + if (error) + goto out_bag; + } + + /* Emit refcount if necessary */ + ASSERT(nbno > cbno); + if (rcbag_count(rcstack) != old_stack_height) { + if (old_stack_height > 1) { + error = xrep_rtrefc_stash(rr, + XFS_REFC_DOMAIN_SHARED, + cbno, nbno - cbno, + old_stack_height); + if (error) + goto out_bag; + } + cbno = nbno; + } + + /* Stack empty, go find the next rmap */ + if (rcbag_count(rcstack) == 0) + break; + old_stack_height = rcbag_count(rcstack); + sbno = nbno; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, + &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + } + } + + ASSERT(rcbag_count(rcstack) == 0); +out_bag: + rcbag_free(&rcstack); +out_cur: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +/* Retrieve refcountbt data for bulk load. */ +STATIC int +xrep_rtrefc_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + error = xfarray_load(rr->refcount_records, rr->array_cur++, + &cur->bc_rec.rc); + if (error) + return error; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrefc_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrefc_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrefcount_broot_space_calc(cur->bc_mp, level, + nr_this_level); +} + +/* + * Use the collected refcount information to stage a new rt refcount btree. If + * this is successful we'll return with the new btree root information logged + * to the repair transaction but not yet committed. + */ +STATIC int +xrep_rtrefc_build_new_tree( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *refc_cur; + int error; + + error = xrep_rtrefc_sort_records(rr); + if (error) + return error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime refcount inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrefc_get_records; + rr->new_btree.bload.claim_block = xrep_rtrefc_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrefc_iroot_size; + + refc_cur = xfs_rtrefcountbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(refc_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need. */ + error = xfs_btree_bload_compute_geometry(refc_cur, &rr->new_btree.bload, + xfarray_length(rr->refcount_records)); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrefcountbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_refcount(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* Add all observed refcount records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + rr->array_cur = XFARRAY_CURSOR_INIT; + error = xfs_btree_bload(refc_cur, &rr->new_btree.bload, rr); + if (error) + goto err_cur; + + /* + * Install the new rtrefc btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrefcountbt_commit_staged_btree(refc_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(refc_cur, 0); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); +err_cur: + xfs_btree_del_cursor(refc_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* Rebuild the rt refcount btree. */ +int +xrep_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrefc *rr; + struct xfs_mount *mp = sc->mp; + char *descr; + int error; + + /* We require the rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(mp)) + return -EOPNOTSUPP; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrefc), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + rr->sc = sc; + + /* Set up enough storage to handle one refcount record per rt extent. */ + descr = xchk_xfile_ag_descr(sc, "reference count records"); + error = xfarray_create(descr, mp->m_sb.sb_rextents, + sizeof(struct xfs_refcount_irec), + &rr->refcount_records); + kfree(descr); + if (error) + goto out_rr; + + /* Collect all reference counts. */ + xfsb_bitmap_init(&rr->old_rtrefcountbt_blocks); + error = xrep_rtrefc_find_refcounts(rr); + if (error) + goto out_bitmap; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the refcount information. */ + error = xrep_rtrefc_build_new_tree(rr); + if (error) + goto out_bitmap; + + /* + * Free all the extents that were allocated to the former rtrefcountbt + * and aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, + &rr->old_rtrefcountbt_blocks); + if (error) + goto out_bitmap; + +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrefcountbt_blocks); + xfarray_destroy(rr->refcount_records); +out_rr: + kfree(rr); + return error; +} diff --git a/fs/xfs/scrub/rtrmap.c b/fs/xfs/scrub/rtrmap.c new file mode 100644 index 000000000000..12989fe80e8b --- /dev/null +++ b/fs/xfs/scrub/rtrmap.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" + +/* Set us up with the realtime metadata locked. */ +int +xchk_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrmapbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_rmap(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime reverse mapping. */ + +struct xchk_rtrmap { + /* + * The furthest-reaching of the rmapbt records that we've already + * processed. This enables us to detect overlapping records for space + * allocations that cannot be shared. + */ + struct xfs_rmap_irec overlap_rec; + + /* + * The previous rmapbt record, so that we can check for two records + * that could be one. + */ + struct xfs_rmap_irec prev_rec; +}; + +static inline bool +xchk_rtrmapbt_is_shareable( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *irec) +{ + if (!xfs_has_rtreflink(sc->mp)) + return false; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + return true; +} + +/* Flag failures for records that overlap but cannot. */ +STATIC void +xchk_rtrmapbt_check_overlapping( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + xfs_rtblock_t pnext, inext; + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + /* No previous record? */ + if (cr->overlap_rec.rm_blockcount == 0) + goto set_prev; + + /* Do overlap_rec and irec overlap? */ + pnext = cr->overlap_rec.rm_startblock + cr->overlap_rec.rm_blockcount; + if (pnext <= irec->rm_startblock) + goto set_prev; + + /* Overlap is only allowed if both records are data fork mappings. */ + if (!xchk_rtrmapbt_is_shareable(bs->sc, &cr->overlap_rec) || + !xchk_rtrmapbt_is_shareable(bs->sc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + /* Save whichever rmap record extends furthest. */ + inext = irec->rm_startblock + irec->rm_blockcount; + if (pnext > inext) + return; + +set_prev: + memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Decide if two reverse-mapping records can be merged. */ +static inline bool +xchk_rtrmap_mergeable( + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *r2) +{ + const struct xfs_rmap_irec *r1 = &cr->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (cr->prev_rec.rm_blockcount == 0) + return false; + + if (r1->rm_owner != r2->rm_owner) + return false; + if (r1->rm_startblock + r1->rm_blockcount != r2->rm_startblock) + return false; + if ((unsigned long long)r1->rm_blockcount + r2->rm_blockcount > + XFS_RMAP_LEN_MAX) + return false; + if (r1->rm_flags != r2->rm_flags) + return false; + return r1->rm_offset + r1->rm_blockcount == r2->rm_offset; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrmapbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrmap_mergeable(cr, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Cross-reference a rmap against the refcount btree. */ +STATIC void +xchk_rtrmapbt_xref_rtrefc( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + xfs_rgblock_t fbno; + xfs_extlen_t flen; + bool is_inode; + bool is_bmbt; + bool is_attr; + bool is_unwritten; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + is_inode = !XFS_RMAP_NON_INODE_OWNER(irec->rm_owner); + is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK; + is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK; + is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN; + + /* If this is shared, must be a data fork extent. */ + error = xfs_refcount_find_shared(sc->sr.refc_cur, irec->rm_startblock, + irec->rm_blockcount, &fbno, &flen, false); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (flen != 0 && (!is_inode || is_attr || is_bmbt || is_unwritten)) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* Cross-reference with other metadata. */ +STATIC void +xchk_rtrmapbt_xref( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock), + irec->rm_blockcount); + if (irec->rm_owner == XFS_RMAP_OWN_COW) + xchk_xref_is_cow_staging(sc, irec->rm_startblock, + irec->rm_blockcount); + else + xchk_rtrmapbt_xref_rtrefc(sc, irec); +} + +/* Scrub a realtime rmapbt record. */ +STATIC int +xchk_rtrmapbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xchk_rtrmap *cr = bs->private; + struct xfs_rmap_irec irec; + + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || + xfs_rtrmap_check_irec(to_rtg(bs->cur->bc_group), &irec) != NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return 0; + + xchk_rtrmapbt_check_mergeable(bs, cr, &irec); + xchk_rtrmapbt_check_overlapping(bs, cr, &irec); + xchk_rtrmapbt_xref(bs->sc, &irec); + return 0; +} + +/* Scrub the realtime rmap btree. */ +int +xchk_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xfs_inode *ip = rtg_rmap(sc->sr.rtg); + struct xfs_owner_info oinfo; + struct xchk_rtrmap cr = { }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, XFS_DATA_FORK); + return xchk_btree(sc, sc->sr.rmap_cur, xchk_rtrmapbt_rec, &oinfo, &cr); +} + +/* xref check that the extent has no realtime reverse mapping at all */ +void +xchk_xref_has_no_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is completely mapped */ +void +xchk_xref_has_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_FULL) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is only owned by a given owner */ +void +xchk_xref_is_only_rt_owned_by( + struct xfs_scrub *sc, + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo) +{ + struct xfs_rmap_matches res; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_count_owners(sc->sr.rmap_cur, bno, len, oinfo, &res); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (res.matches != 1) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.bad_non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c new file mode 100644 index 000000000000..fc2592c53af5 --- /dev/null +++ b/fs/xfs/scrub/rtrmap_repair.c @@ -0,0 +1,987 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_bmap.h" +#include "xfs_bmap_btree.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/rgb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/iscan.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" + +/* + * Realtime Reverse Mapping Btree Repair + * ===================================== + * + * This isn't quite as difficult as repairing the rmap btree on the data + * device, since we only store the data fork extents of realtime files on the + * realtime device. We still have to freeze the filesystem and stop the + * background threads like we do for the rmap repair, but we only have to scan + * realtime inodes. + * + * Collecting entries for the new realtime rmap btree is easy -- all we have + * to do is generate rtrmap entries from the data fork mappings of all realtime + * files in the filesystem. We then scan the rmap btrees of the data device + * looking for extents belonging to the old btree and note them in a bitmap. + * + * To rebuild the realtime rmap btree, we bulk-load the collected mappings into + * a new btree cursor and atomically swap that into the realtime inode. Then + * we can free the blocks from the old btree. + * + * We use the 'xrep_rtrmap' prefix for all the rmap functions. + */ + +/* Context for collecting rmaps */ +struct xrep_rtrmap { + /* new rtrmapbt information */ + struct xrep_newbt new_btree; + + /* lock for the xfbtree and xfile */ + struct mutex lock; + + /* rmap records generated from primary metadata */ + struct xfbtree rtrmap_btree; + + struct xfs_scrub *sc; + + /* bitmap of old rtrmapbt blocks */ + struct xfsb_bitmap old_rtrmapbt_blocks; + + /* Hooks into rtrmap update code. */ + struct xfs_rmap_hook rhook; + + /* inode scan cursor */ + struct xchk_iscan iscan; + + /* in-memory btree cursor for the ->get_blocks walk */ + struct xfs_btree_cur *mcur; + + /* Number of records we're staging in the new btree. */ + uint64_t nr_records; +}; + +/* Set us up to repair rt reverse mapping btrees. */ +int +xrep_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr; + char *descr; + int error; + + xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP); + + descr = xchk_xfile_rtgroup_descr(sc, "reverse mapping records"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrmap), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + + rr->sc = sc; + sc->buf = rr; + return 0; +} + +/* Make sure there's nothing funny about this mapping. */ +STATIC int +xrep_rtrmap_check_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + if (xfs_rtrmap_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Store a reverse-mapping record. */ +static inline int +xrep_rtrmap_stash( + struct xrep_rtrmap *rr, + xfs_rgblock_t startblock, + xfs_extlen_t blockcount, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + struct xfs_rmap_irec rmap = { + .rm_startblock = startblock, + .rm_blockcount = blockcount, + .rm_owner = owner, + .rm_offset = offset, + .rm_flags = flags, + }; + struct xfs_scrub *sc = rr->sc; + struct xfs_btree_cur *mcur; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; + + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + trace_xrep_rtrmap_found(sc->mp, &rmap); + + /* Add entry to in-memory btree. */ + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, sc->tp, &rr->rtrmap_btree); + error = xfs_rmap_map_raw(mcur, &rmap); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp); + if (error) + goto out_abort; + + mutex_unlock(&rr->lock); + return 0; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, sc->tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); + return error; +} + +/* Finding all file and bmbt extents. */ + +/* Context for accumulating rmaps for an inode fork. */ +struct xrep_rtrmap_ifork { + /* + * Accumulate rmap data here to turn multiple adjacent bmaps into a + * single rmap. + */ + struct xfs_rmap_irec accum; + + struct xrep_rtrmap *rr; +}; + +/* Stash an rmap that we accumulated while walking an inode fork. */ +STATIC int +xrep_rtrmap_stash_accumulated( + struct xrep_rtrmap_ifork *rf) +{ + if (rf->accum.rm_blockcount == 0) + return 0; + + return xrep_rtrmap_stash(rf->rr, rf->accum.rm_startblock, + rf->accum.rm_blockcount, rf->accum.rm_owner, + rf->accum.rm_offset, rf->accum.rm_flags); +} + +/* Accumulate a bmbt record. */ +STATIC int +xrep_rtrmap_visit_bmbt( + struct xfs_btree_cur *cur, + struct xfs_bmbt_irec *rec, + void *priv) +{ + struct xrep_rtrmap_ifork *rf = priv; + struct xfs_rmap_irec *accum = &rf->accum; + struct xfs_mount *mp = rf->rr->sc->mp; + xfs_rgblock_t rgbno; + unsigned int rmap_flags = 0; + int error; + + if (xfs_rtb_to_rgno(mp, rec->br_startblock) != + rtg_rgno(rf->rr->sc->sr.rtg)) + return 0; + + if (rec->br_state == XFS_EXT_UNWRITTEN) + rmap_flags |= XFS_RMAP_UNWRITTEN; + + /* If this bmap is adjacent to the previous one, just add it. */ + rgbno = xfs_rtb_to_rgbno(mp, rec->br_startblock); + if (accum->rm_blockcount > 0 && + rec->br_startoff == accum->rm_offset + accum->rm_blockcount && + rgbno == accum->rm_startblock + accum->rm_blockcount && + rmap_flags == accum->rm_flags) { + accum->rm_blockcount += rec->br_blockcount; + return 0; + } + + /* Otherwise stash the old rmap and start accumulating a new one. */ + error = xrep_rtrmap_stash_accumulated(rf); + if (error) + return error; + + accum->rm_startblock = rgbno; + accum->rm_blockcount = rec->br_blockcount; + accum->rm_offset = rec->br_startoff; + accum->rm_flags = rmap_flags; + return 0; +} + +/* + * Iterate the block mapping btree to collect rmap records for anything in this + * fork that maps to the rt volume. Sets @mappings_done to true if we've + * scanned the block mappings in this fork. + */ +STATIC int +xrep_rtrmap_scan_bmbt( + struct xrep_rtrmap_ifork *rf, + struct xfs_inode *ip, + bool *mappings_done) +{ + struct xrep_rtrmap *rr = rf->rr; + struct xfs_btree_cur *cur; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + *mappings_done = false; + + /* + * If the incore extent cache is already loaded, we'll just use the + * incore extent scanner to record mappings. Don't bother walking the + * ondisk extent tree. + */ + if (!xfs_need_iread_extents(ifp)) + return 0; + + /* Accumulate all the mappings in the bmap btree. */ + cur = xfs_bmbt_init_cursor(rr->sc->mp, rr->sc->tp, ip, XFS_DATA_FORK); + error = xfs_bmap_query_all(cur, xrep_rtrmap_visit_bmbt, rf); + xfs_btree_del_cursor(cur, error); + if (error) + return error; + + /* Stash any remaining accumulated rmaps and exit. */ + *mappings_done = true; + return xrep_rtrmap_stash_accumulated(rf); +} + +/* + * Iterate the in-core extent cache to collect rmap records for anything in + * this fork that matches the AG. + */ +STATIC int +xrep_rtrmap_scan_iext( + struct xrep_rtrmap_ifork *rf, + struct xfs_ifork *ifp) +{ + struct xfs_bmbt_irec rec; + struct xfs_iext_cursor icur; + int error; + + for_each_xfs_iext(ifp, &icur, &rec) { + if (isnullstartblock(rec.br_startblock)) + continue; + error = xrep_rtrmap_visit_bmbt(NULL, &rec, rf); + if (error) + return error; + } + + return xrep_rtrmap_stash_accumulated(rf); +} + +/* Find all the extents on the realtime device mapped by an inode fork. */ +STATIC int +xrep_rtrmap_scan_dfork( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + struct xrep_rtrmap_ifork rf = { + .accum = { .rm_owner = ip->i_ino, }, + .rr = rr, + }; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + if (ifp->if_format == XFS_DINODE_FMT_BTREE) { + bool mappings_done; + + /* + * Scan the bmbt for mappings. If the incore extent tree is + * loaded, we want to scan the cached mappings since that's + * faster when the extent counts are very high. + */ + error = xrep_rtrmap_scan_bmbt(&rf, ip, &mappings_done); + if (error || mappings_done) + return error; + } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { + /* realtime data forks should only be extents or btree */ + return -EFSCORRUPTED; + } + + /* Scan incore extent cache. */ + return xrep_rtrmap_scan_iext(&rf, ifp); +} + +/* Record reverse mappings for a file. */ +STATIC int +xrep_rtrmap_scan_inode( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + unsigned int lock_mode; + int error = 0; + + /* Skip the rt rmap btree inode. */ + if (rr->sc->ip == ip) + return 0; + + lock_mode = xfs_ilock_data_map_shared(ip); + + /* Check the data fork if it's on the realtime device. */ + if (XFS_IS_REALTIME_INODE(ip)) { + error = xrep_rtrmap_scan_dfork(rr, ip); + if (error) + goto out_unlock; + } + + xchk_iscan_mark_visited(&rr->iscan, ip); +out_unlock: + xfs_iunlock(ip, lock_mode); + return error; +} + +/* Record extents that belong to the realtime rmap inode. */ +STATIC int +xrep_rtrmap_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrmapbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* Scan one AG for reverse mappings for the realtime rmap btree. */ +STATIC int +xrep_rtrmap_scan_ag( + struct xrep_rtrmap *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrmap_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +struct xrep_rtrmap_stash_run { + struct xrep_rtrmap *rr; + uint64_t owner; +}; + +static int +xrep_rtrmap_stash_run( + uint32_t start, + uint32_t len, + void *priv) +{ + struct xrep_rtrmap_stash_run *rsr = priv; + struct xrep_rtrmap *rr = rsr->rr; + xfs_rgblock_t rgbno = start; + + return xrep_rtrmap_stash(rr, rgbno, len, rsr->owner, 0, 0); +} + +/* + * Emit rmaps for every extent of bits set in the bitmap. Caller must ensure + * that the ranges are in units of FS blocks. + */ +STATIC int +xrep_rtrmap_stash_bitmap( + struct xrep_rtrmap *rr, + struct xrgb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xrep_rtrmap_stash_run rsr = { + .rr = rr, + .owner = oinfo->oi_owner, + }; + + return xrgb_bitmap_walk(bitmap, xrep_rtrmap_stash_run, &rsr); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrmap_walk_cowblocks( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec, + void *priv) +{ + struct xrgb_bitmap *bitmap = priv; + + if (!xfs_refcount_check_domain(irec) || + irec->rc_domain != XFS_REFC_DOMAIN_COW) + return -EFSCORRUPTED; + + return xrgb_bitmap_set(bitmap, irec->rc_startblock, + irec->rc_blockcount); +} + +/* + * Collect rmaps for the blocks containing the refcount btree, and all CoW + * staging extents. + */ +STATIC int +xrep_rtrmap_find_refcount_rmaps( + struct xrep_rtrmap *rr) +{ + struct xrgb_bitmap cow_blocks; /* COWBIT */ + struct xfs_refcount_irec low = { + .rc_startblock = 0, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_refcount_irec high = { + .rc_startblock = -1U, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_scrub *sc = rr->sc; + int error; + + if (!xfs_has_rtreflink(sc->mp)) + return 0; + + xrgb_bitmap_init(&cow_blocks); + + /* Collect rmaps for CoW staging extents. */ + error = xfs_refcount_query_range(sc->sr.refc_cur, &low, &high, + xrep_rtrmap_walk_cowblocks, &cow_blocks); + if (error) + goto out_bitmap; + + /* Generate rmaps for everything. */ + error = xrep_rtrmap_stash_bitmap(rr, &cow_blocks, &XFS_RMAP_OINFO_COW); + if (error) + goto out_bitmap; + +out_bitmap: + xrgb_bitmap_destroy(&cow_blocks); + return error; +} + +/* Count and check all collected records. */ +STATIC int +xrep_rtrmap_check_record( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error; + + error = xrep_rtrmap_check_mapping(rr->sc, rec); + if (error) + return error; + + rr->nr_records++; + return 0; +} + +/* Generate all the reverse-mappings for the realtime device. */ +STATIC int +xrep_rtrmap_find_rmaps( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_perag *pag = NULL; + struct xfs_inode *ip; + struct xfs_btree_cur *mcur; + int error; + + /* Generate rmaps for the realtime superblock */ + if (xfs_has_rtsb(sc->mp) && rtg_rgno(rr->sc->sr.rtg) == 0) { + error = xrep_rtrmap_stash(rr, 0, sc->mp->m_sb.sb_rextsize, + XFS_RMAP_OWN_FS, 0, 0); + if (error) + return error; + } + + /* Find CoW staging extents. */ + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xrep_rtrmap_find_refcount_rmaps(rr); + xchk_rtgroup_btcur_free(&sc->sr); + if (error) + return error; + + /* + * Set up for a potentially lengthy filesystem scan by reducing our + * transaction resource usage for the duration. Specifically: + * + * Unlock the realtime metadata inodes and cancel the transaction to + * release the log grant space while we scan the filesystem. + * + * Create a new empty transaction to eliminate the possibility of the + * inode scan deadlocking on cyclical metadata. + * + * We pass the empty transaction to the file scanning function to avoid + * repeatedly cycling empty transactions. This can be done even though + * we take the IOLOCK to quiesce the file because empty transactions + * do not take sb_internal. + */ + xchk_trans_cancel(sc); + xchk_rtgroup_unlock(&sc->sr); + error = xchk_trans_alloc_empty(sc); + if (error) + return error; + + while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) { + error = xrep_rtrmap_scan_inode(rr, ip); + xchk_irele(sc, ip); + if (error) + break; + + if (xchk_should_terminate(sc, &error)) + break; + } + xchk_iscan_iter_finish(&rr->iscan); + if (error) + return error; + + /* + * Switch out for a real transaction and lock the RT metadata in + * preparation for building a new tree. + */ + xchk_trans_cancel(sc); + error = xchk_setup_rt(sc); + if (error) + return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + + /* + * If a hook failed to update the in-memory btree, we lack the data to + * continue the repair. + */ + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + /* Scan for old rtrmap blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrmap_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + /* + * Now that we have everything locked again, we need to count the + * number of rmap records stashed in the btree. This should reflect + * all actively-owned rt files in the filesystem. At the same time, + * check all our records before we start building a new btree, which + * requires the rtbitmap lock. + */ + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, NULL, &rr->rtrmap_btree); + rr->nr_records = 0; + error = xfs_rmap_query_all(mcur, xrep_rtrmap_check_record, rr); + xfs_btree_del_cursor(mcur, error); + + return error; +} + +/* Building the new rtrmap btree. */ + +/* Retrieve rtrmapbt data for bulk load. */ +STATIC int +xrep_rtrmap_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + int stat = 0; + + error = xfs_btree_increment(rr->mcur, 0, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + error = xfs_rmap_get_rec(rr->mcur, &cur->bc_rec.r, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrmap_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrmap_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrmap_broot_space_calc(cur->bc_mp, level, nr_this_level); +} + +/* + * Use the collected rmap information to stage a new rmap btree. If this is + * successful we'll return with the new btree root information logged to the + * repair transaction but not yet committed. This implements section (III) + * above. + */ +STATIC int +xrep_rtrmap_build_new_tree( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *rmap_cur; + int error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime rmapbt inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrmap_get_records; + rr->new_btree.bload.claim_block = xrep_rtrmap_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrmap_iroot_size; + + rmap_cur = xfs_rtrmapbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(rmap_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need for the rmaps collected. */ + error = xfs_btree_bload_compute_geometry(rmap_cur, + &rr->new_btree.bload, rr->nr_records); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrmapbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_rmap(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* + * Create a cursor to the in-memory btree so that we can bulk load the + * new btree. + */ + rr->mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, NULL, &rr->rtrmap_btree); + error = xfs_btree_goto_left_edge(rr->mcur); + if (error) + goto err_mcur; + + /* Add all observed rmap records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr); + if (error) + goto err_mcur; + + /* + * Install the new rtrmap btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrmapbt_commit_staged_btree(rmap_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(rmap_cur, 0); + xfs_btree_del_cursor(rr->mcur, 0); + rr->mcur = NULL; + + /* + * Now that we've written the new btree to disk, we don't need to keep + * updating the in-memory btree. Abort the scan to stop live updates. + */ + xchk_iscan_abort(&rr->iscan); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); + +err_mcur: + xfs_btree_del_cursor(rr->mcur, error); +err_cur: + xfs_btree_del_cursor(rmap_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* Reaping the old btree. */ + +static inline bool +xrep_rtrmapbt_want_live_update( + struct xchk_iscan *iscan, + const struct xfs_owner_info *oi) +{ + if (xchk_iscan_aborted(iscan)) + return false; + + /* + * We scanned the CoW staging extents before we started the iscan, so + * we need all the updates. + */ + if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner)) + return true; + + /* Ignore updates to files that the scanner hasn't visited yet. */ + return xchk_iscan_want_live_update(iscan, oi->oi_owner); +} + +/* + * Apply a rtrmapbt update from the regular filesystem into our shadow btree. + * We're running from the thread that owns the rtrmap ILOCK and is generating + * the update, so we must be careful about which parts of the struct + * xrep_rtrmap that we change. + */ +static int +xrep_rtrmapbt_live_update( + struct notifier_block *nb, + unsigned long action, + void *data) +{ + struct xfs_rmap_update_params *p = data; + struct xrep_rtrmap *rr; + struct xfs_mount *mp; + struct xfs_btree_cur *mcur; + struct xfs_trans *tp; + void *txcookie; + int error; + + rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb); + mp = rr->sc->mp; + + if (!xrep_rtrmapbt_want_live_update(&rr->iscan, &p->oinfo)) + goto out_unlock; + + trace_xrep_rmap_live_update(rtg_group(rr->sc->sr.rtg), action, p); + + error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); + if (error) + goto out_abort; + + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree); + error = __xfs_rmap_finish_intent(mcur, action, p->startblock, + p->blockcount, &p->oinfo, p->unwritten); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, tp); + if (error) + goto out_cancel; + + xrep_trans_cancel_hook_dummy(&txcookie, tp); + mutex_unlock(&rr->lock); + return NOTIFY_DONE; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, tp); + xrep_trans_cancel_hook_dummy(&txcookie, tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); +out_unlock: + return NOTIFY_DONE; +} + +/* Set up the filesystem scan components. */ +STATIC int +xrep_rtrmap_setup_scan( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + mutex_init(&rr->lock); + xfsb_bitmap_init(&rr->old_rtrmapbt_blocks); + + /* Set up some storage */ + error = xfs_rtrmapbt_mem_init(sc->mp, &rr->rtrmap_btree, sc->xmbtp, + rtg_rgno(sc->sr.rtg)); + if (error) + goto out_bitmap; + + /* Retry iget every tenth of a second for up to 30 seconds. */ + xchk_iscan_start(sc, 30000, 100, &rr->iscan); + + /* + * Hook into live rtrmap operations so that we can update our in-memory + * btree to reflect live changes on the filesystem. Since we drop the + * rtrmap ILOCK to scan all the inodes, we need this piece to avoid + * installing a stale btree. + */ + ASSERT(sc->flags & XCHK_FSGATES_RMAP); + xfs_rmap_hook_setup(&rr->rhook, xrep_rtrmapbt_live_update); + error = xfs_rmap_hook_add(rtg_group(sc->sr.rtg), &rr->rhook); + if (error) + goto out_iscan; + return 0; + +out_iscan: + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); + return error; +} + +/* Tear down scan components. */ +STATIC void +xrep_rtrmap_teardown( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + + xchk_iscan_abort(&rr->iscan); + xfs_rmap_hook_del(rtg_group(sc->sr.rtg), &rr->rhook); + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); +} + +/* Repair the realtime rmap btree. */ +int +xrep_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr = sc->buf; + int error; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + error = xrep_rtrmap_setup_scan(rr); + if (error) + return error; + + /* Collect rmaps for realtime files. */ + error = xrep_rtrmap_find_rmaps(rr); + if (error) + goto out_records; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the rtrmap information. */ + error = xrep_rtrmap_build_new_tree(rr); + if (error) + goto out_records; + + /* + * Free all the extents that were allocated to the former rtrmapbt and + * aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks); + if (error) + goto out_records; + +out_records: + xrep_rtrmap_teardown(rr); + return error; +} diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c index 49fc6250bafc..4ac679c1bd29 100644 --- a/fs/xfs/scrub/rtsummary.c +++ b/fs/xfs/scrub/rtsummary.c @@ -81,8 +81,7 @@ xchk_setup_rtsummary( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + error = xchk_install_live_inode(sc, rtg_summary(sc->sr.rtg)); if (error) return error; @@ -90,6 +89,10 @@ xchk_setup_rtsummary( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP); + if (error) + return error; + /* * Now that we've locked the rtbitmap and rtsummary, we can't race with * growfsrt trying to expand the summary or change the size of the rt @@ -100,7 +103,6 @@ xchk_setup_rtsummary( * exclusively here. If we ever start caring about running concurrent * fsmap with scrub this could be changed. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rts->rbmblocks = xfs_rtbitmap_blockcount(mp); @@ -191,8 +193,7 @@ xchk_rtsum_record_free( rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount); if (!xfs_verify_rtbext(mp, rtbno, rtlen)) { - xchk_ino_xref_set_corrupt(sc, - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino); + xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino); return -EFSCORRUPTED; } @@ -218,7 +219,7 @@ xchk_rtsum_compute( /* If the bitmap size doesn't match the computed size, bail. */ if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) != - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size) + rtg_bitmap(rtg)->i_disk_size) return -EFSCORRUPTED; return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc); @@ -310,8 +311,8 @@ xchk_rtsummary( { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xchk_rtsummary *rts = sc->buf; int error; diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index 8198ea84ad70..d593977d70df 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -165,7 +165,8 @@ xrep_rtsummary( * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. */ - error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, &rts->tempexch); + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rts->rsumblocks, &rts->tempexch); if (error) return error; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 4ba02a490efa..9908850bf76f 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -176,7 +176,7 @@ xchk_fsgates_disable( trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL); if (sc->flags & XCHK_FSGATES_DRAIN) - xfs_drain_wait_disable(); + xfs_defer_drain_wait_disable(); if (sc->flags & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_disable(); @@ -230,6 +230,8 @@ xchk_teardown( int error) { xchk_ag_free(sc, &sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); + if (sc->tp) { if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) error = xfs_trans_commit(sc->tp); @@ -397,12 +399,14 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { }, [XFS_SCRUB_TYPE_RTBITMAP] = { /* realtime bitmap */ .type = ST_RTGROUP, + .has = xfs_has_nonzoned, .setup = xchk_setup_rtbitmap, .scrub = xchk_rtbitmap, .repair = xrep_rtbitmap, }, [XFS_SCRUB_TYPE_RTSUM] = { /* realtime summary */ .type = ST_RTGROUP, + .has = xfs_has_nonzoned, .setup = xchk_setup_rtsummary, .scrub = xchk_rtsummary, .repair = xrep_rtsummary, @@ -470,6 +474,20 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { .has = xfs_has_rtsb, .repair = xrep_rgsuperblock, }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { /* realtime group rmapbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrmapbt, + .scrub = xchk_rtrmapbt, + .has = xfs_has_rtrmapbt, + .repair = xrep_rtrmapbt, + }, + [XFS_SCRUB_TYPE_RTREFCBT] = { /* realtime refcountbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrefcountbt, + .scrub = xchk_rtrefcountbt, + .has = xfs_has_rtreflink, + .repair = xrep_rtrefcountbt, + }, }; static int diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 5dbbe93cb49b..a3f1abc91390 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -96,7 +96,7 @@ struct xchk_meta_ops { int (*repair_eval)(struct xfs_scrub *sc); /* Decide if we even have this piece of metadata. */ - bool (*has)(struct xfs_mount *); + bool (*has)(const struct xfs_mount *); /* type describing required/allowed inputs */ enum xchk_type type; @@ -126,6 +126,10 @@ struct xchk_rt { /* XFS_RTGLOCK_* lock state if locked */ unsigned int rtlock_flags; + + /* rtgroup btrees */ + struct xfs_btree_cur *rmap_cur; + struct xfs_btree_cur *refc_cur; }; struct xfs_scrub { @@ -280,10 +284,14 @@ int xchk_metapath(struct xfs_scrub *sc); int xchk_rtbitmap(struct xfs_scrub *sc); int xchk_rtsummary(struct xfs_scrub *sc); int xchk_rgsuperblock(struct xfs_scrub *sc); +int xchk_rtrmapbt(struct xfs_scrub *sc); +int xchk_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_rtbitmap xchk_nothing # define xchk_rtsummary xchk_nothing # define xchk_rgsuperblock xchk_nothing +# define xchk_rtrmapbt xchk_nothing +# define xchk_rtrefcountbt xchk_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_quota(struct xfs_scrub *sc); @@ -317,8 +325,26 @@ void xchk_xref_is_not_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno, #ifdef CONFIG_XFS_RT void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno, xfs_extlen_t len); +void xchk_xref_has_no_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_has_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_only_rt_owned_by(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len, const struct xfs_owner_info *oinfo); +void xchk_xref_is_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_shared(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); #else # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_no_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_is_only_rt_owned_by(sc, bno, len, oinfo) do { } while (0) +# define xchk_xref_is_rt_cow_staging(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_shared(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_cow_staging(sc, bno, len) do { } while (0) #endif #endif /* __XFS_SCRUB_SCRUB_H__ */ diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index a476c7b2ab75..f8a37ea97791 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -82,6 +82,8 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = "dirtree", [XFS_SCRUB_TYPE_METAPATH] = "metapath", [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", + [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", + [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ diff --git a/fs/xfs/scrub/tempexch.h b/fs/xfs/scrub/tempexch.h index 995ba187c5aa..eccda720c2ca 100644 --- a/fs/xfs/scrub/tempexch.h +++ b/fs/xfs/scrub/tempexch.h @@ -12,7 +12,7 @@ struct xrep_tempexch { }; int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork, - struct xrep_tempexch *ti); + xfs_fileoff_t off, xfs_filblks_t len, struct xrep_tempexch *ti); int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork, struct xrep_tempexch *ti); diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 2d7ca7e1bbca..cf99e0ca51b0 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -606,6 +606,8 @@ STATIC int xrep_tempexch_prep_request( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { struct xfs_exchmaps_req *req = &tx->req; @@ -629,18 +631,19 @@ xrep_tempexch_prep_request( /* Exchange all mappings in both forks. */ req->ip1 = sc->tempip; req->ip2 = sc->ip; - req->startoff1 = 0; - req->startoff2 = 0; + req->startoff1 = off; + req->startoff2 = off; switch (whichfork) { case XFS_ATTR_FORK: req->flags |= XFS_EXCHMAPS_ATTR_FORK; break; case XFS_DATA_FORK: - /* Always exchange sizes when exchanging data fork mappings. */ - req->flags |= XFS_EXCHMAPS_SET_SIZES; + /* Exchange sizes when exchanging all data fork mappings. */ + if (off == 0 && len == XFS_MAX_FILEOFF) + req->flags |= XFS_EXCHMAPS_SET_SIZES; break; } - req->blockcount = XFS_MAX_FILEOFF; + req->blockcount = len; return 0; } @@ -749,6 +752,7 @@ xrep_tempexch_reserve_quota( * or the two inodes have the same dquots. */ if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 || + xfs_is_metadir_inode(req->ip1) || (req->ip1->i_udquot == req->ip2->i_udquot && req->ip1->i_gdquot == req->ip2->i_gdquot && req->ip1->i_pdquot == req->ip2->i_pdquot)) @@ -795,6 +799,8 @@ int xrep_tempexch_trans_reserve( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { int error; @@ -803,7 +809,7 @@ xrep_tempexch_trans_reserve( xfs_assert_ilocked(sc->ip, XFS_ILOCK_EXCL); xfs_assert_ilocked(sc->tempip, XFS_ILOCK_EXCL); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, off, len, tx); if (error) return error; @@ -841,7 +847,8 @@ xrep_tempexch_trans_alloc( ASSERT(sc->tp == NULL); ASSERT(xfs_has_exchange_range(sc->mp)); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, 0, XFS_MAX_FILEOFF, + tx); if (error) return error; diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 98f923ae664d..2450e214103f 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -21,6 +21,7 @@ #include "xfs_rmap.h" #include "xfs_parent.h" #include "xfs_metafile.h" +#include "xfs_rtgroup.h" #include "scrub/scrub.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index d2ae7e93acb0..d7c4ced47c15 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -17,6 +17,7 @@ #include "xfs_bit.h" #include "xfs_quota_defs.h" +struct xfs_rtgroup; struct xfs_scrub; struct xfile; struct xfarray; @@ -40,6 +41,9 @@ struct xchk_dirtree_outcomes; TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); +TRACE_DEFINE_ENUM(XG_TYPE_AG); +TRACE_DEFINE_ENUM(XG_TYPE_RTG); + TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF); @@ -72,6 +76,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTRMAPBT); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTREFCBT); #define XFS_SCRUB_TYPE_STRINGS \ { XFS_SCRUB_TYPE_PROBE, "probe" }, \ @@ -105,7 +111,9 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); { XFS_SCRUB_TYPE_DIRTREE, "dirtree" }, \ { XFS_SCRUB_TYPE_BARRIER, "barrier" }, \ { XFS_SCRUB_TYPE_METAPATH, "metapath" }, \ - { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" } + { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" }, \ + { XFS_SCRUB_TYPE_RTRMAPBT, "rtrmapbt" }, \ + { XFS_SCRUB_TYPE_RTREFCBT, "rtrefcountbt" } #define XFS_SCRUB_FLAG_STRINGS \ { XFS_SCRUB_IFLAG_REPAIR, "repair" }, \ @@ -1956,32 +1964,36 @@ DEFINE_XCHK_METAPATH_EVENT(xchk_metapath_lookup); #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) DECLARE_EVENT_CLASS(xrep_extent_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len), - TP_ARGS(pag, agbno, len), + TP_ARGS(xg, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len) ); #define DEFINE_REPAIR_EXTENT_EVENT(name) \ DEFINE_EVENT(xrep_extent_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len), \ - TP_ARGS(pag, agbno, len)) + TP_ARGS(xg, agbno, len)) DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval); @@ -1989,35 +2001,39 @@ DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval); DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert); DECLARE_EVENT_CLASS(xrep_reap_find_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len, bool crosslinked), - TP_ARGS(pag, agbno, len, crosslinked), + TP_ARGS(xg, agbno, len, crosslinked), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(bool, crosslinked) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; __entry->crosslinked = crosslinked; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x crosslinked %d", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x crosslinked %d", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->crosslinked ? 1 : 0) ); #define DEFINE_REPAIR_REAP_FIND_EVENT(name) \ DEFINE_EVENT(xrep_reap_find_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len, bool crosslinked), \ - TP_ARGS(pag, agbno, len, crosslinked)) + TP_ARGS(xg, agbno, len, crosslinked)) DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select); DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select); @@ -2108,29 +2124,33 @@ TRACE_EVENT(xrep_ibt_found, ) TRACE_EVENT(xrep_refc_found, - TP_PROTO(const struct xfs_perag *pag, + TP_PROTO(const struct xfs_group *xg, const struct xfs_refcount_irec *rec), - TP_ARGS(pag, rec), + TP_ARGS(xg, rec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) + __field(enum xfs_group_type, type) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->agno = xg->xg_gno; + __entry->type = xg->xg_type; __entry->domain = rec->rc_domain; __entry->startblock = rec->rc_startblock; __entry->blockcount = rec->rc_blockcount; __entry->refcount = rec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s %sbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) @@ -2282,6 +2302,32 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize, __entry->rmapbt_sz, __entry->refcbt_sz) ) + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xrep_calc_rtgroup_resblks_btsize, + TP_PROTO(struct xfs_mount *mp, xfs_rgnumber_t rgno, + xfs_rgblock_t usedlen, xfs_rgblock_t rmapbt_sz), + TP_ARGS(mp, rgno, usedlen, rmapbt_sz), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, usedlen) + __field(xfs_rgblock_t, rmapbt_sz) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rgno = rgno; + __entry->usedlen = usedlen; + __entry->rmapbt_sz = rmapbt_sz; + ), + TP_printk("dev %d:%d rgno 0x%x usedlen %u rmapbt %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->usedlen, + __entry->rmapbt_sz) +); +#endif /* CONFIG_XFS_RT */ + TRACE_EVENT(xrep_reset_counters, TP_PROTO(struct xfs_mount *mp, struct xchk_fscounters *fsc), TP_ARGS(mp, fsc), @@ -2680,11 +2726,12 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode); DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode); TRACE_EVENT(xrep_rmap_live_update, - TP_PROTO(const struct xfs_perag *pag, unsigned int op, + TP_PROTO(const struct xfs_group *xg, unsigned int op, const struct xfs_rmap_update_params *p), - TP_ARGS(pag, op, p), + TP_ARGS(xg, op, p), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(unsigned int, op) __field(xfs_agblock_t, agbno) @@ -2694,8 +2741,9 @@ TRACE_EVENT(xrep_rmap_live_update, __field(unsigned int, flags) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->op = op; __entry->agbno = p->startblock; __entry->len = p->blockcount; @@ -2704,10 +2752,12 @@ TRACE_EVENT(xrep_rmap_live_update, if (p->unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x op %d %sbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->op, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->owner, @@ -3605,6 +3655,186 @@ DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link); +#ifdef CONFIG_XFS_RT +DECLARE_EVENT_CLASS(xrep_rtbitmap_class, + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, xfs_rtxnum_t end), + TP_ARGS(mp, start, end), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rtxnum_t, start) + __field(xfs_rtxnum_t, end) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->start = start; + __entry->end = end; + ), + TP_printk("dev %d:%d rtdev %d:%d startrtx 0x%llx endrtx 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->start, + __entry->end) +); +#define DEFINE_REPAIR_RGBITMAP_EVENT(name) \ +DEFINE_EVENT(xrep_rtbitmap_class, name, \ + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, \ + xfs_rtxnum_t end), \ + TP_ARGS(mp, start, end)) +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free); +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free_bulk); + +TRACE_EVENT(xrep_rtbitmap_or, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + xfs_rtword_t mask, xfs_rtword_t word), + TP_ARGS(mp, wordoff, mask, word), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, mask) + __field(unsigned int, word) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->mask = mask; + __entry->word = word; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx mask 0x%x word 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->mask, + __entry->word) +); + +TRACE_EVENT(xrep_rtbitmap_load, + TP_PROTO(struct xfs_rtgroup *rtg, xfs_fileoff_t rbmoff, + xfs_rtxnum_t rtx, xfs_rtxnum_t len), + TP_ARGS(rtg, rbmoff, rtx, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_fileoff_t, rbmoff) + __field(xfs_rtxnum_t, rtx) + __field(xfs_rtxnum_t, len) + ), + TP_fast_assign( + __entry->dev = rtg_mount(rtg)->m_super->s_dev; + __entry->rtdev = rtg_mount(rtg)->m_rtdev_targp->bt_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->rbmoff = rbmoff; + __entry->rtx = rtx; + __entry->len = len; + ), + TP_printk("dev %d:%d rtdev %d:%d rgno 0x%x rbmoff 0x%llx rtx 0x%llx rtxcount 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgno, + __entry->rbmoff, + __entry->rtx, + __entry->len) +); + +TRACE_EVENT(xrep_rtbitmap_load_words, + TP_PROTO(struct xfs_mount *mp, xfs_fileoff_t rbmoff, + unsigned long long wordoff, unsigned int wordcnt), + TP_ARGS(mp, rbmoff, wordoff, wordcnt), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_fileoff_t, rbmoff) + __field(unsigned long long, wordoff) + __field(unsigned int, wordcnt) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rbmoff = rbmoff; + __entry->wordoff = wordoff; + __entry->wordcnt = wordcnt; + ), + TP_printk("dev %d:%d rtdev %d:%d rbmoff 0x%llx wordoff 0x%llx wordcnt 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rbmoff, + __entry->wordoff, + __entry->wordcnt) +); + +TRACE_EVENT(xrep_rtbitmap_load_word, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + unsigned int bit, xfs_rtword_t ondisk_word, + xfs_rtword_t xfile_word, xfs_rtword_t word_mask), + TP_ARGS(mp, wordoff, bit, ondisk_word, xfile_word, word_mask), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, bit) + __field(xfs_rtword_t, ondisk_word) + __field(xfs_rtword_t, xfile_word) + __field(xfs_rtword_t, word_mask) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->bit = bit; + __entry->ondisk_word = ondisk_word; + __entry->xfile_word = xfile_word; + __entry->word_mask = word_mask; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx bit %u ondisk 0x%x(0x%x) inmem 0x%x(0x%x) result 0x%x mask 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->bit, + __entry->ondisk_word, + __entry->ondisk_word & __entry->word_mask, + __entry->xfile_word, + __entry->xfile_word & ~__entry->word_mask, + (__entry->xfile_word & ~__entry->word_mask) | + (__entry->ondisk_word & __entry->word_mask), + __entry->word_mask) +); + +TRACE_EVENT(xrep_rtrmap_found, + TP_PROTO(struct xfs_mount *mp, const struct xfs_rmap_irec *rec), + TP_ARGS(mp, rec), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgblock_t, rgbno) + __field(xfs_extlen_t, len) + __field(uint64_t, owner) + __field(uint64_t, offset) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rgbno = rec->rm_startblock; + __entry->len = rec->rm_blockcount; + __entry->owner = rec->rm_owner; + __entry->offset = rec->rm_offset; + __entry->flags = rec->rm_flags; + ), + TP_printk("dev %d:%d rtdev %d:%d rgbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgbno, + __entry->len, + __entry->owner, + __entry->offset, + __entry->flags) +); +#endif /* CONFIG_XFS_RT */ + #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */ #endif /* _TRACE_XFS_SCRUB_TRACE_H */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 559a3a577097..63151feb9c3f 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. - * Copyright (c) 2016-2018 Christoph Hellwig. + * Copyright (c) 2016-2025 Christoph Hellwig. * All Rights Reserved. */ #include "xfs.h" @@ -19,6 +19,9 @@ #include "xfs_reflink.h" #include "xfs_errortag.h" #include "xfs_error.h" +#include "xfs_icache.h" +#include "xfs_zone_alloc.h" +#include "xfs_rtgroup.h" struct xfs_writepage_ctx { struct iomap_writepage_ctx ctx; @@ -76,6 +79,26 @@ xfs_setfilesize( return xfs_trans_commit(tp); } +static void +xfs_ioend_put_open_zones( + struct iomap_ioend *ioend) +{ + struct iomap_ioend *tmp; + + /* + * Put the open zone for all ioends merged into this one (if any). + */ + list_for_each_entry(tmp, &ioend->io_list, io_list) + xfs_open_zone_put(tmp->io_private); + + /* + * The main ioend might not have an open zone if the submission failed + * before xfs_zone_alloc_and_submit got called. + */ + if (ioend->io_private) + xfs_open_zone_put(ioend->io_private); +} + /* * IO write completion. */ @@ -85,6 +108,7 @@ xfs_end_ioend( { struct xfs_inode *ip = XFS_I(ioend->io_inode); struct xfs_mount *mp = ip->i_mount; + bool is_zoned = xfs_is_zoned_inode(ip); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; unsigned int nofs_flag; @@ -114,10 +138,11 @@ xfs_end_ioend( */ error = blk_status_to_errno(ioend->io_bio.bi_status); if (unlikely(error)) { - if (ioend->io_flags & IOMAP_F_SHARED) { + if (ioend->io_flags & IOMAP_IOEND_SHARED) { + ASSERT(!is_zoned); xfs_reflink_cancel_cow_range(ip, offset, size, true); xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, - offset + size); + offset + size, NULL); } goto done; } @@ -125,14 +150,21 @@ xfs_end_ioend( /* * Success: commit the COW or unwritten blocks if needed. */ - if (ioend->io_flags & IOMAP_F_SHARED) + if (is_zoned) + error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, + ioend->io_private, NULLFSBLOCK); + else if (ioend->io_flags & IOMAP_IOEND_SHARED) error = xfs_reflink_end_cow(ip, offset, size); - else if (ioend->io_type == IOMAP_UNWRITTEN) + else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) error = xfs_iomap_write_unwritten(ip, offset, size, false); - if (!error && xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); + if (!error && + !(ioend->io_flags & IOMAP_IOEND_DIRECT) && + xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, offset, size); done: + if (is_zoned) + xfs_ioend_put_open_zones(ioend); iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); } @@ -175,17 +207,27 @@ xfs_end_io( } } -STATIC void +void xfs_end_bio( struct bio *bio) { struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; unsigned long flags; + /* + * For Appends record the actually written block number and set the + * boundary flag if needed. + */ + if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { + ioend->io_sector = bio->bi_iter.bi_sector; + xfs_mark_rtg_boundary(ioend); + } + spin_lock_irqsave(&ip->i_ioend_lock, flags); if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue, + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, &ip->i_ioend_work)); list_add_tail(&ioend->io_list, &ip->i_ioend_list); spin_unlock_irqrestore(&ip->i_ioend_lock, flags); @@ -394,11 +436,31 @@ allocate_blocks: return 0; } +static bool +xfs_ioend_needs_wq_completion( + struct iomap_ioend *ioend) +{ + /* Changing inode size requires a transaction. */ + if (xfs_ioend_is_append(ioend)) + return true; + + /* Extent manipulation requires a transaction. */ + if (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED)) + return true; + + /* Page cache invalidation cannot be done in irq context. */ + if (ioend->io_flags & IOMAP_IOEND_DONTCACHE) + return true; + + return false; +} + static int -xfs_prepare_ioend( - struct iomap_ioend *ioend, +xfs_submit_ioend( + struct iomap_writepage_ctx *wpc, int status) { + struct iomap_ioend *ioend = wpc->ioend; unsigned int nofs_flag; /* @@ -409,7 +471,7 @@ xfs_prepare_ioend( nofs_flag = memalloc_nofs_save(); /* Convert CoW extents to regular */ - if (!status && (ioend->io_flags & IOMAP_F_SHARED)) { + if (!status && (ioend->io_flags & IOMAP_IOEND_SHARED)) { status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode), ioend->io_offset, ioend->io_size); } @@ -417,10 +479,13 @@ xfs_prepare_ioend( memalloc_nofs_restore(nofs_flag); /* send ioends that might require a transaction to the completion wq */ - if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN || - (ioend->io_flags & IOMAP_F_SHARED)) + if (xfs_ioend_needs_wq_completion(ioend)) ioend->io_bio.bi_end_io = xfs_end_bio; - return status; + + if (status) + return status; + submit_bio(&ioend->io_bio); + return 0; } /* @@ -457,12 +522,107 @@ xfs_discard_folio( * folio itself and not the start offset that is passed in. */ xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos, - folio_pos(folio) + folio_size(folio)); + folio_pos(folio) + folio_size(folio), NULL); } static const struct iomap_writeback_ops xfs_writeback_ops = { .map_blocks = xfs_map_blocks, - .prepare_ioend = xfs_prepare_ioend, + .submit_ioend = xfs_submit_ioend, + .discard_folio = xfs_discard_folio, +}; + +struct xfs_zoned_writepage_ctx { + struct iomap_writepage_ctx ctx; + struct xfs_open_zone *open_zone; +}; + +static inline struct xfs_zoned_writepage_ctx * +XFS_ZWPC(struct iomap_writepage_ctx *ctx) +{ + return container_of(ctx, struct xfs_zoned_writepage_ctx, ctx); +} + +static int +xfs_zoned_map_blocks( + struct iomap_writepage_ctx *wpc, + struct inode *inode, + loff_t offset, + unsigned int len) +{ + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + len); + xfs_filblks_t count_fsb; + struct xfs_bmbt_irec imap, del; + struct xfs_iext_cursor icur; + + if (xfs_is_shutdown(mp)) + return -EIO; + + XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS); + + /* + * All dirty data must be covered by delalloc extents. But truncate can + * remove delalloc extents underneath us or reduce their size. + * Returning a hole tells iomap to not write back any data from this + * range, which is the right thing to do in that case. + * + * Otherwise just tell iomap to treat ranges previously covered by a + * delalloc extent as mapped. The actual block allocation will be done + * just before submitting the bio. + * + * This implies we never map outside folios that are locked or marked + * as under writeback, and thus there is no need check the fork sequence + * count here. + */ + xfs_ilock(ip, XFS_ILOCK_EXCL); + if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap)) + imap.br_startoff = end_fsb; /* fake a hole past EOF */ + if (imap.br_startoff > offset_fsb) { + imap.br_blockcount = imap.br_startoff - offset_fsb; + imap.br_startoff = offset_fsb; + imap.br_startblock = HOLESTARTBLOCK; + imap.br_state = XFS_EXT_NORM; + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, 0); + return 0; + } + end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount); + count_fsb = end_fsb - offset_fsb; + + del = imap; + xfs_trim_extent(&del, offset_fsb, count_fsb); + xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &icur, &imap, &del, + XFS_BMAPI_REMAP); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + + wpc->iomap.type = IOMAP_MAPPED; + wpc->iomap.flags = IOMAP_F_DIRTY; + wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; + wpc->iomap.offset = offset; + wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); + wpc->iomap.flags = IOMAP_F_ANON_WRITE; + + trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); + return 0; +} + +static int +xfs_zoned_submit_ioend( + struct iomap_writepage_ctx *wpc, + int status) +{ + wpc->ioend->io_bio.bi_end_io = xfs_end_bio; + if (status) + return status; + xfs_zone_alloc_and_submit(wpc->ioend, &XFS_ZWPC(wpc)->open_zone); + return 0; +} + +static const struct iomap_writeback_ops xfs_zoned_writeback_ops = { + .map_blocks = xfs_zoned_map_blocks, + .submit_ioend = xfs_zoned_submit_ioend, .discard_folio = xfs_discard_folio, }; @@ -471,10 +631,25 @@ xfs_vm_writepages( struct address_space *mapping, struct writeback_control *wbc) { - struct xfs_writepage_ctx wpc = { }; + struct xfs_inode *ip = XFS_I(mapping->host); + + xfs_iflags_clear(ip, XFS_ITRUNCATED); + + if (xfs_is_zoned_inode(ip)) { + struct xfs_zoned_writepage_ctx xc = { }; + int error; - xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); - return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); + error = iomap_writepages(mapping, wbc, &xc.ctx, + &xfs_zoned_writeback_ops); + if (xc.open_zone) + xfs_open_zone_put(xc.open_zone); + return error; + } else { + struct xfs_writepage_ctx wpc = { }; + + return iomap_writepages(mapping, wbc, &wpc.ctx, + &xfs_writeback_ops); + } } STATIC int @@ -528,12 +703,44 @@ xfs_vm_readahead( } static int -xfs_iomap_swapfile_activate( +xfs_vm_swap_activate( struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { - sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev; + struct xfs_inode *ip = XFS_I(file_inode(swap_file)); + + /* + * Swap file activation can race against concurrent shared extent + * removal in files that have been cloned. If this happens, + * iomap_swapfile_iter() can fail because it encountered a shared + * extent even though an operation is in progress to remove those + * shared extents. + * + * This race becomes problematic when we defer extent removal + * operations beyond the end of a syscall (i.e. use async background + * processing algorithms). Users think the extents are no longer + * shared, but iomap_swapfile_iter() still sees them as shared + * because the refcountbt entries for the extents being removed have + * not yet been updated. Hence the swapon call fails unexpectedly. + * + * The race condition is currently most obvious from the unlink() + * operation as extent removal is deferred until after the last + * reference to the inode goes away. We then process the extent + * removal asynchronously, hence triggers the "syscall completed but + * work not done" condition mentioned above. To close this race + * window, we need to flush any pending inodegc operations to ensure + * they have updated the refcountbt records before we try to map the + * swapfile. + */ + xfs_inodegc_flush(ip->i_mount); + + /* + * Direct the swap code to the correct block device when this file + * sits on the RT device. + */ + sis->bdev = xfs_inode_buftarg(ip)->bt_bdev; + return iomap_swapfile_activate(sis, swap_file, span, &xfs_read_iomap_ops); } @@ -549,11 +756,11 @@ const struct address_space_operations xfs_address_space_operations = { .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .dirty_folio = noop_dirty_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index e0bd68419764..5a7a0f1a0b49 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -9,6 +9,7 @@ extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; -int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); +int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); +void xfs_end_bio(struct bio *bio); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 24fb12986a56..319004bf089f 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -305,11 +305,6 @@ xfs_attr3_root_inactive( XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp); if (error) return error; - error = bp->b_error; - if (error) { - xfs_trans_brelse(*trans, bp); - return error; - } xfs_trans_binval(*trans, bp); /* remove from cache */ /* * Commit the invalidate and start the next transaction. diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0836fea2d6d8..06ca11731e43 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -30,6 +30,7 @@ #include "xfs_reflink.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" /* Kernel only BMAP related definitions and functions */ @@ -436,7 +437,8 @@ xfs_bmap_punch_delalloc_range( struct xfs_inode *ip, int whichfork, xfs_off_t start_byte, - xfs_off_t end_byte) + xfs_off_t end_byte, + struct xfs_zone_alloc_ctx *ac) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); @@ -467,7 +469,21 @@ xfs_bmap_punch_delalloc_range( continue; } - xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del); + if (xfs_is_zoned_inode(ip) && ac) { + /* + * In a zoned buffered write context we need to return + * the punched delalloc allocations to the allocation + * context. This allows reusing them in the following + * iomap iterations. + */ + xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, + &del, XFS_BMAPI_REMAP); + ac->reserved_blocks += del.br_blockcount; + } else { + xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, + &del, 0); + } + if (!xfs_iext_get_extent(ifp, &icur, &got)) break; } @@ -582,7 +598,7 @@ xfs_free_eofblocks( if (ip->i_delayed_blks) { xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize), - LLONG_MAX); + LLONG_MAX, NULL); } xfs_inode_clear_eofblocks_tag(ip); return 0; @@ -825,7 +841,8 @@ int xfs_free_file_space( struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t len) + xfs_off_t len, + struct xfs_zone_alloc_ctx *ac) { struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t startoffset_fsb; @@ -880,7 +897,7 @@ xfs_free_file_space( return 0; if (offset + len > XFS_ISIZE(ip)) len = XFS_ISIZE(ip) - offset; - error = xfs_zero_range(ip, offset, len, NULL); + error = xfs_zero_range(ip, offset, len, ac, NULL); if (error) return error; @@ -968,7 +985,8 @@ int xfs_collapse_file_space( struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t len) + xfs_off_t len, + struct xfs_zone_alloc_ctx *ac) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; @@ -981,7 +999,7 @@ xfs_collapse_file_space( trace_xfs_collapse_file_space(ip); - error = xfs_free_file_space(ip, offset, len); + error = xfs_free_file_space(ip, offset, len, ac); if (error) return error; diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index b29760d36e1a..c477b3361630 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -15,6 +15,7 @@ struct xfs_inode; struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +struct xfs_zone_alloc_ctx; #ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); @@ -31,7 +32,8 @@ xfs_bmap_rtalloc(struct xfs_bmalloca *ap) #endif /* CONFIG_XFS_RT */ void xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, int whichfork, - xfs_off_t start_byte, xfs_off_t end_byte); + xfs_off_t start_byte, xfs_off_t end_byte, + struct xfs_zone_alloc_ctx *ac); struct kgetbmap { __s64 bmv_offset; /* file offset of segment in blocks */ @@ -54,13 +56,13 @@ int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip, /* preallocation and hole punch interface */ int xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t len); + xfs_off_t len); int xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset, - xfs_off_t len); + xfs_off_t len, struct xfs_zone_alloc_ctx *ac); int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset, - xfs_off_t len); + xfs_off_t len, struct xfs_zone_alloc_ctx *ac); int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, - xfs_off_t len); + xfs_off_t len); /* EOF block manipulation functions */ bool xfs_can_free_eofblocks(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b9444ff5c8a5..1a2b3f06fa71 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -22,17 +22,13 @@ #include "xfs_error.h" #include "xfs_ag.h" #include "xfs_buf_mem.h" +#include "xfs_notify_failure.h" struct kmem_cache *xfs_buf_cache; /* * Locking orders * - * xfs_buf_ioacct_inc: - * xfs_buf_ioacct_dec: - * b_sema (caller holds) - * b_lock - * * xfs_buf_stale: * b_sema (caller holds) * b_lock @@ -40,8 +36,7 @@ struct kmem_cache *xfs_buf_cache; * * xfs_buf_rele: * b_lock - * pag_buf_lock - * lru_lock + * lru_lock * * xfs_buftarg_drain_rele * lru_lock @@ -52,95 +47,14 @@ struct kmem_cache *xfs_buf_cache; * b_lock (trylock due to inversion) */ -static int __xfs_buf_submit(struct xfs_buf *bp, bool wait); - -static inline int -xfs_buf_submit( - struct xfs_buf *bp) -{ - return __xfs_buf_submit(bp, !(bp->b_flags & XBF_ASYNC)); -} +static void xfs_buf_submit(struct xfs_buf *bp); +static int xfs_buf_iowait(struct xfs_buf *bp); static inline bool xfs_buf_is_uncached(struct xfs_buf *bp) { return bp->b_rhash_key == XFS_BUF_DADDR_NULL; } -static inline int -xfs_buf_is_vmapped( - struct xfs_buf *bp) -{ - /* - * Return true if the buffer is vmapped. - * - * b_addr is null if the buffer is not mapped, but the code is clever - * enough to know it doesn't have to map a single page, so the check has - * to be both for b_addr and bp->b_page_count > 1. - */ - return bp->b_addr && bp->b_page_count > 1; -} - -static inline int -xfs_buf_vmap_len( - struct xfs_buf *bp) -{ - return (bp->b_page_count * PAGE_SIZE); -} - -/* - * Bump the I/O in flight count on the buftarg if we haven't yet done so for - * this buffer. The count is incremented once per buffer (per hold cycle) - * because the corresponding decrement is deferred to buffer release. Buffers - * can undergo I/O multiple times in a hold-release cycle and per buffer I/O - * tracking adds unnecessary overhead. This is used for sychronization purposes - * with unmount (see xfs_buftarg_drain()), so all we really need is a count of - * in-flight buffers. - * - * Buffers that are never released (e.g., superblock, iclog buffers) must set - * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count - * never reaches zero and unmount hangs indefinitely. - */ -static inline void -xfs_buf_ioacct_inc( - struct xfs_buf *bp) -{ - if (bp->b_flags & XBF_NO_IOACCT) - return; - - ASSERT(bp->b_flags & XBF_ASYNC); - spin_lock(&bp->b_lock); - if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) { - bp->b_state |= XFS_BSTATE_IN_FLIGHT; - percpu_counter_inc(&bp->b_target->bt_io_count); - } - spin_unlock(&bp->b_lock); -} - -/* - * Clear the in-flight state on a buffer about to be released to the LRU or - * freed and unaccount from the buftarg. - */ -static inline void -__xfs_buf_ioacct_dec( - struct xfs_buf *bp) -{ - lockdep_assert_held(&bp->b_lock); - - if (bp->b_state & XFS_BSTATE_IN_FLIGHT) { - bp->b_state &= ~XFS_BSTATE_IN_FLIGHT; - percpu_counter_dec(&bp->b_target->bt_io_count); - } -} - -static inline void -xfs_buf_ioacct_dec( - struct xfs_buf *bp) -{ - spin_lock(&bp->b_lock); - __xfs_buf_ioacct_dec(bp); - spin_unlock(&bp->b_lock); -} - /* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer @@ -164,150 +78,24 @@ xfs_buf_stale( */ bp->b_flags &= ~_XBF_DELWRI_Q; - /* - * Once the buffer is marked stale and unlocked, a subsequent lookup - * could reset b_flags. There is no guarantee that the buffer is - * unaccounted (released to LRU) before that occurs. Drop in-flight - * status now to preserve accounting consistency. - */ spin_lock(&bp->b_lock); - __xfs_buf_ioacct_dec(bp); - atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru))) - atomic_dec(&bp->b_hold); + bp->b_hold--; - ASSERT(atomic_read(&bp->b_hold) >= 1); + ASSERT(bp->b_hold >= 1); spin_unlock(&bp->b_lock); } -static int -xfs_buf_get_maps( - struct xfs_buf *bp, - int map_count) -{ - ASSERT(bp->b_maps == NULL); - bp->b_map_count = map_count; - - if (map_count == 1) { - bp->b_maps = &bp->__b_map; - return 0; - } - - bp->b_maps = kzalloc(map_count * sizeof(struct xfs_buf_map), - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - if (!bp->b_maps) - return -ENOMEM; - return 0; -} - -/* - * Frees b_pages if it was allocated. - */ -static void -xfs_buf_free_maps( - struct xfs_buf *bp) -{ - if (bp->b_maps != &bp->__b_map) { - kfree(bp->b_maps); - bp->b_maps = NULL; - } -} - -static int -_xfs_buf_alloc( - struct xfs_buftarg *target, - struct xfs_buf_map *map, - int nmaps, - xfs_buf_flags_t flags, - struct xfs_buf **bpp) -{ - struct xfs_buf *bp; - int error; - int i; - - *bpp = NULL; - bp = kmem_cache_zalloc(xfs_buf_cache, - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - - /* - * We don't want certain flags to appear in b_flags unless they are - * specifically set by later operations on the buffer. - */ - flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - - atomic_set(&bp->b_hold, 1); - atomic_set(&bp->b_lru_ref, 1); - init_completion(&bp->b_iowait); - INIT_LIST_HEAD(&bp->b_lru); - INIT_LIST_HEAD(&bp->b_list); - INIT_LIST_HEAD(&bp->b_li_list); - sema_init(&bp->b_sema, 0); /* held, no waiters */ - spin_lock_init(&bp->b_lock); - bp->b_target = target; - bp->b_mount = target->bt_mount; - bp->b_flags = flags; - - /* - * Set length and io_length to the same value initially. - * I/O routines should use io_length, which will be the same in - * most cases but may be reset (e.g. XFS recovery). - */ - error = xfs_buf_get_maps(bp, nmaps); - if (error) { - kmem_cache_free(xfs_buf_cache, bp); - return error; - } - - bp->b_rhash_key = map[0].bm_bn; - bp->b_length = 0; - for (i = 0; i < nmaps; i++) { - bp->b_maps[i].bm_bn = map[i].bm_bn; - bp->b_maps[i].bm_len = map[i].bm_len; - bp->b_length += map[i].bm_len; - } - - atomic_set(&bp->b_pin_count, 0); - init_waitqueue_head(&bp->b_waiters); - - XFS_STATS_INC(bp->b_mount, xb_create); - trace_xfs_buf_init(bp, _RET_IP_); - - *bpp = bp; - return 0; -} - -static void -xfs_buf_free_pages( - struct xfs_buf *bp) -{ - uint i; - - ASSERT(bp->b_flags & _XBF_PAGES); - - if (xfs_buf_is_vmapped(bp)) - vm_unmap_ram(bp->b_addr, bp->b_page_count); - - for (i = 0; i < bp->b_page_count; i++) { - if (bp->b_pages[i]) - __free_page(bp->b_pages[i]); - } - mm_account_reclaimed_pages(bp->b_page_count); - - if (bp->b_pages != bp->b_page_array) - kfree(bp->b_pages); - bp->b_pages = NULL; - bp->b_flags &= ~_XBF_PAGES; -} - static void xfs_buf_free_callback( struct callback_head *cb) { struct xfs_buf *bp = container_of(cb, struct xfs_buf, b_rcu); - xfs_buf_free_maps(bp); + if (bp->b_maps != &bp->__b_map) + kfree(bp->b_maps); kmem_cache_free(xfs_buf_cache, bp); } @@ -315,154 +103,219 @@ static void xfs_buf_free( struct xfs_buf *bp) { + unsigned int size = BBTOB(bp->b_length); + + might_sleep(); trace_xfs_buf_free(bp, _RET_IP_); ASSERT(list_empty(&bp->b_lru)); - if (xfs_buftarg_is_mem(bp->b_target)) - xmbuf_unmap_page(bp); - else if (bp->b_flags & _XBF_PAGES) - xfs_buf_free_pages(bp); + if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) + mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); + + if (is_vmalloc_addr(bp->b_addr)) + vfree(bp->b_addr); else if (bp->b_flags & _XBF_KMEM) kfree(bp->b_addr); + else + folio_put(virt_to_folio(bp->b_addr)); call_rcu(&bp->b_rcu, xfs_buf_free_callback); } static int xfs_buf_alloc_kmem( - struct xfs_buf *bp, - xfs_buf_flags_t flags) + struct xfs_buf *bp, + size_t size, + gfp_t gfp_mask) { - gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL; - size_t size = BBTOB(bp->b_length); - - /* Assure zeroed buffer for non-read cases. */ - if (!(flags & XBF_READ)) - gfp_mask |= __GFP_ZERO; + ASSERT(is_power_of_2(size)); + ASSERT(size < PAGE_SIZE); - bp->b_addr = kmalloc(size, gfp_mask); + bp->b_addr = kmalloc(size, gfp_mask | __GFP_NOFAIL); if (!bp->b_addr) return -ENOMEM; - if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) != - ((unsigned long)bp->b_addr & PAGE_MASK)) { - /* b_addr spans two pages - use alloc_page instead */ + /* + * Slab guarantees that we get back naturally aligned allocations for + * power of two sizes. Keep this check as the canary in the coal mine + * if anything changes in slab. + */ + if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)bp->b_addr, size))) { kfree(bp->b_addr); bp->b_addr = NULL; return -ENOMEM; } - bp->b_offset = offset_in_page(bp->b_addr); - bp->b_pages = bp->b_page_array; - bp->b_pages[0] = kmem_to_page(bp->b_addr); - bp->b_page_count = 1; bp->b_flags |= _XBF_KMEM; + trace_xfs_buf_backing_kmem(bp, _RET_IP_); return 0; } +/* + * Allocate backing memory for a buffer. + * + * For tmpfs-backed buffers used by in-memory btrees this directly maps the + * tmpfs page cache folios. + * + * For real file system buffers there are three different kinds backing memory: + * + * The first type backs the buffer by a kmalloc allocation. This is done for + * less than PAGE_SIZE allocations to avoid wasting memory. + * + * The second type is a single folio buffer - this may be a high order folio or + * just a single page sized folio, but either way they get treated the same way + * by the rest of the code - the buffer memory spans a single contiguous memory + * region that we don't have to map and unmap to access the data directly. + * + * The third type of buffer is the vmalloc()d buffer. This provides the buffer + * with the required contiguous memory region but backed by discontiguous + * physical pages. + */ static int -xfs_buf_alloc_pages( +xfs_buf_alloc_backing_mem( struct xfs_buf *bp, xfs_buf_flags_t flags) { + size_t size = BBTOB(bp->b_length); gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN; - long filled = 0; + struct folio *folio; - if (flags & XBF_READ_AHEAD) - gfp_mask |= __GFP_NORETRY; - - /* Make sure that we have a page list */ - bp->b_page_count = DIV_ROUND_UP(BBTOB(bp->b_length), PAGE_SIZE); - if (bp->b_page_count <= XB_PAGES) { - bp->b_pages = bp->b_page_array; - } else { - bp->b_pages = kzalloc(sizeof(struct page *) * bp->b_page_count, - gfp_mask); - if (!bp->b_pages) - return -ENOMEM; - } - bp->b_flags |= _XBF_PAGES; + if (xfs_buftarg_is_mem(bp->b_target)) + return xmbuf_map_backing_mem(bp); /* Assure zeroed buffer for non-read cases. */ if (!(flags & XBF_READ)) gfp_mask |= __GFP_ZERO; + if (flags & XBF_READ_AHEAD) + gfp_mask |= __GFP_NORETRY; + /* - * Bulk filling of pages can take multiple calls. Not filling the entire - * array is not an allocation failure, so don't back off if we get at - * least one extra page. + * For buffers smaller than PAGE_SIZE use a kmalloc allocation if that + * is properly aligned. The slab allocator now guarantees an aligned + * allocation for all power of two sizes, which matches most of the + * smaller than PAGE_SIZE buffers used by XFS. */ - for (;;) { - long last = filled; + if (size < PAGE_SIZE && is_power_of_2(size)) + return xfs_buf_alloc_kmem(bp, size, gfp_mask); - filled = alloc_pages_bulk_array(gfp_mask, bp->b_page_count, - bp->b_pages); - if (filled == bp->b_page_count) { - XFS_STATS_INC(bp->b_mount, xb_page_found); - break; - } - - if (filled != last) - continue; + /* + * Don't bother with the retry loop for single PAGE allocations: vmalloc + * won't do any better. + */ + if (size <= PAGE_SIZE) + gfp_mask |= __GFP_NOFAIL; - if (flags & XBF_READ_AHEAD) { - xfs_buf_free_pages(bp); + /* + * Optimistically attempt a single high order folio allocation for + * larger than PAGE_SIZE buffers. + * + * Allocating a high order folio makes the assumption that buffers are a + * power-of-2 size, matching the power-of-2 folios sizes available. + * + * The exception here are user xattr data buffers, which can be arbitrarily + * sized up to 64kB plus structure metadata, skip straight to the vmalloc + * path for them instead of wasting memory here. + */ + if (size > PAGE_SIZE) { + if (!is_power_of_2(size)) + goto fallback; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; + gfp_mask |= __GFP_NORETRY; + } + folio = folio_alloc(gfp_mask, get_order(size)); + if (!folio) { + if (size <= PAGE_SIZE) return -ENOMEM; - } + trace_xfs_buf_backing_fallback(bp, _RET_IP_); + goto fallback; + } + bp->b_addr = folio_address(folio); + trace_xfs_buf_backing_folio(bp, _RET_IP_); + return 0; +fallback: + for (;;) { + bp->b_addr = __vmalloc(size, gfp_mask); + if (bp->b_addr) + break; + if (flags & XBF_READ_AHEAD) + return -ENOMEM; XFS_STATS_INC(bp->b_mount, xb_page_retries); memalloc_retry_wait(gfp_mask); } + + trace_xfs_buf_backing_vmalloc(bp, _RET_IP_); return 0; } -/* - * Map buffer into kernel address-space if necessary. - */ -STATIC int -_xfs_buf_map_pages( - struct xfs_buf *bp, - xfs_buf_flags_t flags) +static int +xfs_buf_alloc( + struct xfs_buftarg *target, + struct xfs_buf_map *map, + int nmaps, + xfs_buf_flags_t flags, + struct xfs_buf **bpp) { - ASSERT(bp->b_flags & _XBF_PAGES); - if (bp->b_page_count == 1) { - /* A single page buffer is always mappable */ - bp->b_addr = page_address(bp->b_pages[0]); - } else if (flags & XBF_UNMAPPED) { - bp->b_addr = NULL; - } else { - int retried = 0; - unsigned nofs_flag; + struct xfs_buf *bp; + int error; + int i; - /* - * vm_map_ram() will allocate auxiliary structures (e.g. - * pagetables) with GFP_KERNEL, yet we often under a scoped nofs - * context here. Mixing GFP_KERNEL with GFP_NOFS allocations - * from the same call site that can be run from both above and - * below memory reclaim causes lockdep false positives. Hence we - * always need to force this allocation to nofs context because - * we can't pass __GFP_NOLOCKDEP down to auxillary structures to - * prevent false positive lockdep reports. - * - * XXX(dgc): I think dquot reclaim is the only place we can get - * to this function from memory reclaim context now. If we fix - * that like we've fixed inode reclaim to avoid writeback from - * reclaim, this nofs wrapping can go away. - */ - nofs_flag = memalloc_nofs_save(); - do { - bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, - -1); - if (bp->b_addr) - break; - vm_unmap_aliases(); - } while (retried++ <= 1); - memalloc_nofs_restore(nofs_flag); - - if (!bp->b_addr) - return -ENOMEM; + *bpp = NULL; + bp = kmem_cache_zalloc(xfs_buf_cache, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + + /* + * We don't want certain flags to appear in b_flags unless they are + * specifically set by later operations on the buffer. + */ + flags &= ~(XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); + + /* + * A new buffer is held and locked by the owner. This ensures that the + * buffer is owned by the caller and racing RCU lookups right after + * inserting into the hash table are safe (and will have to wait for + * the unlock to do anything non-trivial). + */ + bp->b_hold = 1; + sema_init(&bp->b_sema, 0); /* held, no waiters */ + + spin_lock_init(&bp->b_lock); + atomic_set(&bp->b_lru_ref, 1); + init_completion(&bp->b_iowait); + INIT_LIST_HEAD(&bp->b_lru); + INIT_LIST_HEAD(&bp->b_list); + INIT_LIST_HEAD(&bp->b_li_list); + bp->b_target = target; + bp->b_mount = target->bt_mount; + bp->b_flags = flags; + bp->b_rhash_key = map[0].bm_bn; + bp->b_length = 0; + bp->b_map_count = nmaps; + if (nmaps == 1) + bp->b_maps = &bp->__b_map; + else + bp->b_maps = kcalloc(nmaps, sizeof(struct xfs_buf_map), + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + for (i = 0; i < nmaps; i++) { + bp->b_maps[i].bm_bn = map[i].bm_bn; + bp->b_maps[i].bm_len = map[i].bm_len; + bp->b_length += map[i].bm_len; } + atomic_set(&bp->b_pin_count, 0); + init_waitqueue_head(&bp->b_waiters); + + XFS_STATS_INC(bp->b_mount, xb_create); + trace_xfs_buf_init(bp, _RET_IP_); + + error = xfs_buf_alloc_backing_mem(bp, flags); + if (error) { + xfs_buf_free(bp); + return error; + } + + *bpp = bp; return 0; } @@ -519,7 +372,6 @@ int xfs_buf_cache_init( struct xfs_buf_cache *bch) { - spin_lock_init(&bch->bc_lock); return rhashtable_init(&bch->bc_hash, &xfs_buf_hash_params); } @@ -582,12 +434,26 @@ xfs_buf_find_lock( return -ENOENT; } ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0); - bp->b_flags &= _XBF_KMEM | _XBF_PAGES; + bp->b_flags &= _XBF_KMEM; bp->b_ops = NULL; } return 0; } +static bool +xfs_buf_try_hold( + struct xfs_buf *bp) +{ + spin_lock(&bp->b_lock); + if (bp->b_hold == 0) { + spin_unlock(&bp->b_lock); + return false; + } + bp->b_hold++; + spin_unlock(&bp->b_lock); + return true; +} + static inline int xfs_buf_lookup( struct xfs_buf_cache *bch, @@ -600,7 +466,7 @@ xfs_buf_lookup( rcu_read_lock(); bp = rhashtable_lookup(&bch->bc_hash, map, xfs_buf_hash_params); - if (!bp || !atomic_inc_not_zero(&bp->b_hold)) { + if (!bp || !xfs_buf_try_hold(bp)) { rcu_read_unlock(); return -ENOENT; } @@ -636,36 +502,24 @@ xfs_buf_find_insert( struct xfs_buf *bp; int error; - error = _xfs_buf_alloc(btp, map, nmaps, flags, &new_bp); + error = xfs_buf_alloc(btp, map, nmaps, flags, &new_bp); if (error) goto out_drop_pag; - if (xfs_buftarg_is_mem(new_bp->b_target)) { - error = xmbuf_map_page(new_bp); - } else if (BBTOB(new_bp->b_length) >= PAGE_SIZE || - xfs_buf_alloc_kmem(new_bp, flags) < 0) { - /* - * For buffers that fit entirely within a single page, first - * attempt to allocate the memory from the heap to minimise - * memory usage. If we can't get heap memory for these small - * buffers, we fall back to using the page allocator. - */ - error = xfs_buf_alloc_pages(new_bp, flags); - } - if (error) - goto out_free_buf; + /* The new buffer keeps the perag reference until it is freed. */ + new_bp->b_pag = pag; - spin_lock(&bch->bc_lock); + rcu_read_lock(); bp = rhashtable_lookup_get_insert_fast(&bch->bc_hash, &new_bp->b_rhash_head, xfs_buf_hash_params); if (IS_ERR(bp)) { + rcu_read_unlock(); error = PTR_ERR(bp); - spin_unlock(&bch->bc_lock); goto out_free_buf; } - if (bp && atomic_inc_not_zero(&bp->b_hold)) { + if (bp && xfs_buf_try_hold(bp)) { /* found an existing buffer */ - spin_unlock(&bch->bc_lock); + rcu_read_unlock(); error = xfs_buf_find_lock(bp, flags); if (error) xfs_buf_rele(bp); @@ -673,10 +527,8 @@ xfs_buf_find_insert( *bpp = bp; goto out_free_buf; } + rcu_read_unlock(); - /* The new buffer keeps the perag reference until it is freed. */ - new_bp->b_pag = pag; - spin_unlock(&bch->bc_lock); *bpp = new_bp; return 0; @@ -764,18 +616,6 @@ xfs_buf_get_map( xfs_perag_put(pag); } - /* We do not hold a perag reference anymore. */ - if (!bp->b_addr) { - error = _xfs_buf_map_pages(bp, flags); - if (unlikely(error)) { - xfs_warn_ratelimited(btp->bt_mount, - "%s: failed to map %u pages", __func__, - bp->b_page_count); - xfs_buf_relse(bp); - return error; - } - } - /* * Clear b_error if this is a lookup from a caller that doesn't expect * valid data to be found in the buffer. @@ -796,16 +636,14 @@ out_put_perag: int _xfs_buf_read( - struct xfs_buf *bp, - xfs_buf_flags_t flags) + struct xfs_buf *bp) { - ASSERT(!(flags & XBF_WRITE)); ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL); bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE); - bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - - return xfs_buf_submit(bp); + bp->b_flags |= XBF_READ; + xfs_buf_submit(bp); + return xfs_buf_iowait(bp); } /* @@ -856,6 +694,8 @@ xfs_buf_read_map( struct xfs_buf *bp; int error; + ASSERT(!(flags & (XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD))); + flags |= XBF_READ; *bpp = NULL; @@ -869,21 +709,11 @@ xfs_buf_read_map( /* Initiate the buffer read and wait. */ XFS_STATS_INC(target->bt_mount, xb_get_read); bp->b_ops = ops; - error = _xfs_buf_read(bp, flags); - - /* Readahead iodone already dropped the buffer, so exit. */ - if (flags & XBF_ASYNC) - return 0; + error = _xfs_buf_read(bp); } else { /* Buffer already read; all we need to do is check it. */ error = xfs_buf_reverify(bp, ops); - /* Readahead already finished; drop the buffer and exit. */ - if (flags & XBF_ASYNC) { - xfs_buf_relse(bp); - return 0; - } - /* We do not want read in the flags */ bp->b_flags &= ~XBF_READ; ASSERT(bp->b_ops != NULL || ops == NULL); @@ -935,6 +765,7 @@ xfs_buf_readahead_map( int nmaps, const struct xfs_buf_ops *ops) { + const xfs_buf_flags_t flags = XBF_READ | XBF_ASYNC | XBF_READ_AHEAD; struct xfs_buf *bp; /* @@ -944,9 +775,21 @@ xfs_buf_readahead_map( if (xfs_buftarg_is_mem(target)) return; - xfs_buf_read_map(target, map, nmaps, - XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops, - __this_address); + if (xfs_buf_get_map(target, map, nmaps, flags | XBF_TRYLOCK, &bp)) + return; + trace_xfs_buf_readahead(bp, 0, _RET_IP_); + + if (bp->b_flags & XBF_DONE) { + xfs_buf_reverify(bp, ops); + xfs_buf_relse(bp); + return; + } + XFS_STATS_INC(target->bt_mount, xb_get_read); + bp->b_ops = ops; + bp->b_flags &= ~(XBF_WRITE | XBF_DONE); + bp->b_flags |= flags; + percpu_counter_inc(&target->bt_readahead_count); + xfs_buf_submit(bp); } /* @@ -960,7 +803,6 @@ xfs_buf_read_uncached( struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, - xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { @@ -969,7 +811,7 @@ xfs_buf_read_uncached( *bpp = NULL; - error = xfs_buf_get_uncached(target, numblks, flags, &bp); + error = xfs_buf_get_uncached(target, numblks, &bp); if (error) return error; @@ -981,8 +823,8 @@ xfs_buf_read_uncached( bp->b_ops = ops; xfs_buf_submit(bp); - if (bp->b_error) { - error = bp->b_error; + error = xfs_buf_iowait(bp); + if (error) { xfs_buf_relse(bp); return error; } @@ -995,40 +837,14 @@ int xfs_buf_get_uncached( struct xfs_buftarg *target, size_t numblks, - xfs_buf_flags_t flags, struct xfs_buf **bpp) { int error; - struct xfs_buf *bp; DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks); - *bpp = NULL; - - /* flags might contain irrelevant bits, pass only what we care about */ - error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp); - if (error) - return error; - - if (xfs_buftarg_is_mem(bp->b_target)) - error = xmbuf_map_page(bp); - else - error = xfs_buf_alloc_pages(bp, flags); - if (error) - goto fail_free_buf; - - error = _xfs_buf_map_pages(bp, 0); - if (unlikely(error)) { - xfs_warn(target->bt_mount, - "%s: failed to map pages", __func__); - goto fail_free_buf; - } - - trace_xfs_buf_get_uncached(bp, _RET_IP_); - *bpp = bp; - return 0; - -fail_free_buf: - xfs_buf_free(bp); + error = xfs_buf_alloc(target, &map, 1, 0, bpp); + if (!error) + trace_xfs_buf_get_uncached(*bpp, _RET_IP_); return error; } @@ -1042,7 +858,10 @@ xfs_buf_hold( struct xfs_buf *bp) { trace_xfs_buf_hold(bp, _RET_IP_); - atomic_inc(&bp->b_hold); + + spin_lock(&bp->b_lock); + bp->b_hold++; + spin_unlock(&bp->b_lock); } static void @@ -1050,10 +869,14 @@ xfs_buf_rele_uncached( struct xfs_buf *bp) { ASSERT(list_empty(&bp->b_lru)); - if (atomic_dec_and_test(&bp->b_hold)) { - xfs_buf_ioacct_dec(bp); - xfs_buf_free(bp); + + spin_lock(&bp->b_lock); + if (--bp->b_hold) { + spin_unlock(&bp->b_lock); + return; } + spin_unlock(&bp->b_lock); + xfs_buf_free(bp); } static void @@ -1063,51 +886,30 @@ xfs_buf_rele_cached( struct xfs_buftarg *btp = bp->b_target; struct xfs_perag *pag = bp->b_pag; struct xfs_buf_cache *bch = xfs_buftarg_buf_cache(btp, pag); - bool release; bool freebuf = false; trace_xfs_buf_rele(bp, _RET_IP_); - ASSERT(atomic_read(&bp->b_hold) > 0); - - /* - * We grab the b_lock here first to serialise racing xfs_buf_rele() - * calls. The pag_buf_lock being taken on the last reference only - * serialises against racing lookups in xfs_buf_find(). IOWs, the second - * to last reference we drop here is not serialised against the last - * reference until we take bp->b_lock. Hence if we don't grab b_lock - * first, the last "release" reference can win the race to the lock and - * free the buffer before the second-to-last reference is processed, - * leading to a use-after-free scenario. - */ spin_lock(&bp->b_lock); - release = atomic_dec_and_lock(&bp->b_hold, &bch->bc_lock); - if (!release) { - /* - * Drop the in-flight state if the buffer is already on the LRU - * and it holds the only reference. This is racy because we - * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT - * ensures the decrement occurs only once per-buf. - */ - if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru)) - __xfs_buf_ioacct_dec(bp); + ASSERT(bp->b_hold >= 1); + if (bp->b_hold > 1) { + bp->b_hold--; goto out_unlock; } - /* the last reference has been dropped ... */ - __xfs_buf_ioacct_dec(bp); - if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { + /* we are asked to drop the last reference */ + if (atomic_read(&bp->b_lru_ref)) { /* - * If the buffer is added to the LRU take a new reference to the + * If the buffer is added to the LRU, keep the reference to the * buffer for the LRU and clear the (now stale) dispose list - * state flag + * state flag, else drop the reference. */ - if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) { + if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) bp->b_state &= ~XFS_BSTATE_DISPOSE; - atomic_inc(&bp->b_hold); - } - spin_unlock(&bch->bc_lock); + else + bp->b_hold--; } else { + bp->b_hold--; /* * most of the time buffers will already be removed from the * LRU, so optimise that case by checking for the @@ -1123,7 +925,6 @@ xfs_buf_rele_cached( ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rhashtable_remove_fast(&bch->bc_hash, &bp->b_rhash_head, xfs_buf_hash_params); - spin_unlock(&bch->bc_lock); if (pag) xfs_perag_put(pag); freebuf = true; @@ -1290,6 +1091,7 @@ xfs_buf_ioend_handle_error( { struct xfs_mount *mp = bp->b_mount; struct xfs_error_cfg *cfg; + struct xfs_log_item *lip; /* * If we've already shutdown the journal because of I/O errors, there's @@ -1337,12 +1139,11 @@ xfs_buf_ioend_handle_error( } /* Still considered a transient error. Caller will schedule retries. */ - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_io_fail(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_io_fail(bp); - else - ASSERT(list_empty(&bp->b_li_list)); + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { + set_bit(XFS_LI_FAILED, &lip->li_flags); + clear_bit(XFS_LI_FLUSHING, &lip->li_flags); + } + xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1350,6 +1151,7 @@ xfs_buf_ioend_handle_error( resubmit: xfs_buf_ioerror(bp, 0); bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL); + reinit_completion(&bp->b_iowait); xfs_buf_submit(bp); return true; out_stale: @@ -1360,24 +1162,23 @@ out_stale: return false; } -static void -xfs_buf_ioend( +/* returns false if the caller needs to resubmit the I/O, else true */ +static bool +__xfs_buf_ioend( struct xfs_buf *bp) { trace_xfs_buf_iodone(bp, _RET_IP_); - /* - * Pull in IO completion errors now. We are guaranteed to be running - * single threaded, so we don't need the lock to read b_io_error. - */ - if (!bp->b_error && bp->b_io_error) - xfs_buf_ioerror(bp, bp->b_io_error); - if (bp->b_flags & XBF_READ) { + if (!bp->b_error && is_vmalloc_addr(bp->b_addr)) + invalidate_kernel_vmap_range(bp->b_addr, + roundup(BBTOB(bp->b_length), PAGE_SIZE)); if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read(bp); if (!bp->b_error) bp->b_flags |= XBF_DONE; + if (bp->b_flags & XBF_READ_AHEAD) + percpu_counter_dec(&bp->b_target->bt_readahead_count); } else { if (!bp->b_error) { bp->b_flags &= ~XBF_WRITE_FAIL; @@ -1385,7 +1186,7 @@ xfs_buf_ioend( } if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp)) - return; + return false; /* clear the retry state */ bp->b_last_error = 0; @@ -1400,16 +1201,21 @@ xfs_buf_ioend( if (bp->b_log_item) xfs_buf_item_done(bp); - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_iodone(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_iodone(bp); - + if (bp->b_iodone) + bp->b_iodone(bp); } bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD | _XBF_LOGRECOVERY); + return true; +} +static void +xfs_buf_ioend( + struct xfs_buf *bp) +{ + if (!__xfs_buf_ioend(bp)) + return; if (bp->b_flags & XBF_ASYNC) xfs_buf_relse(bp); else @@ -1423,15 +1229,8 @@ xfs_buf_ioend_work( struct xfs_buf *bp = container_of(work, struct xfs_buf, b_ioend_work); - xfs_buf_ioend(bp); -} - -static void -xfs_buf_ioend_async( - struct xfs_buf *bp) -{ - INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work); - queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work); + if (__xfs_buf_ioend(bp)) + xfs_buf_relse(bp); } void @@ -1484,7 +1283,8 @@ xfs_bwrite( bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_DONE); - error = xfs_buf_submit(bp); + xfs_buf_submit(bp); + error = xfs_buf_iowait(bp); if (error) xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); return error; @@ -1494,188 +1294,104 @@ static void xfs_buf_bio_end_io( struct bio *bio) { - struct xfs_buf *bp = (struct xfs_buf *)bio->bi_private; - - if (!bio->bi_status && - (bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && - XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) - bio->bi_status = BLK_STS_IOERR; + struct xfs_buf *bp = bio->bi_private; - /* - * don't overwrite existing errors - otherwise we can lose errors on - * buffers that require multiple bios to complete. - */ - if (bio->bi_status) { - int error = blk_status_to_errno(bio->bi_status); + if (bio->bi_status) + xfs_buf_ioerror(bp, blk_status_to_errno(bio->bi_status)); + else if ((bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && + XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) + xfs_buf_ioerror(bp, -EIO); - cmpxchg(&bp->b_io_error, 0, error); + if (bp->b_flags & XBF_ASYNC) { + INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work); + queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work); + } else { + complete(&bp->b_iowait); } - if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) - invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); - - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) - xfs_buf_ioend_async(bp); bio_put(bio); } -static void -xfs_buf_ioapply_map( - struct xfs_buf *bp, - int map, - int *buf_offset, - int *count, - blk_opf_t op) -{ - int page_index; - unsigned int total_nr_pages = bp->b_page_count; - int nr_pages; - struct bio *bio; - sector_t sector = bp->b_maps[map].bm_bn; - int size; - int offset; - - /* skip the pages in the buffer before the start offset */ - page_index = 0; - offset = *buf_offset; - while (offset >= PAGE_SIZE) { - page_index++; - offset -= PAGE_SIZE; - } - - /* - * Limit the IO size to the length of the current vector, and update the - * remaining IO count for the next time around. - */ - size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count); - *count -= size; - *buf_offset += size; - -next_chunk: - atomic_inc(&bp->b_io_remaining); - nr_pages = bio_max_segs(total_nr_pages); - - bio = bio_alloc(bp->b_target->bt_bdev, nr_pages, op, GFP_NOIO); - bio->bi_iter.bi_sector = sector; - bio->bi_end_io = xfs_buf_bio_end_io; - bio->bi_private = bp; - - for (; size && nr_pages; nr_pages--, page_index++) { - int rbytes, nbytes = PAGE_SIZE - offset; - - if (nbytes > size) - nbytes = size; - - rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes, - offset); - if (rbytes < nbytes) - break; - - offset = 0; - sector += BTOBB(nbytes); - size -= nbytes; - total_nr_pages--; - } +static inline blk_opf_t +xfs_buf_bio_op( + struct xfs_buf *bp) +{ + blk_opf_t op; - if (likely(bio->bi_iter.bi_size)) { - if (xfs_buf_is_vmapped(bp)) { - flush_kernel_vmap_range(bp->b_addr, - xfs_buf_vmap_len(bp)); - } - submit_bio(bio); - if (size) - goto next_chunk; + if (bp->b_flags & XBF_WRITE) { + op = REQ_OP_WRITE; } else { - /* - * This is guaranteed not to be the last io reference count - * because the caller (xfs_buf_submit) holds a count itself. - */ - atomic_dec(&bp->b_io_remaining); - xfs_buf_ioerror(bp, -EIO); - bio_put(bio); + op = REQ_OP_READ; + if (bp->b_flags & XBF_READ_AHEAD) + op |= REQ_RAHEAD; } + return op | REQ_META; } -STATIC void -_xfs_buf_ioapply( - struct xfs_buf *bp) +static void +xfs_buf_submit_bio( + struct xfs_buf *bp) { - struct blk_plug plug; - blk_opf_t op; - int offset; - int size; - int i; + unsigned int map = 0; + struct blk_plug plug; + struct bio *bio; - /* - * Make sure we capture only current IO errors rather than stale errors - * left over from previous use of the buffer (e.g. failed readahead). - */ - bp->b_error = 0; + if (is_vmalloc_addr(bp->b_addr)) { + unsigned int size = BBTOB(bp->b_length); + unsigned int alloc_size = roundup(size, PAGE_SIZE); + void *data = bp->b_addr; - if (bp->b_flags & XBF_WRITE) { - op = REQ_OP_WRITE; + bio = bio_alloc(bp->b_target->bt_bdev, alloc_size >> PAGE_SHIFT, + xfs_buf_bio_op(bp), GFP_NOIO); + do { + unsigned int len = min(size, PAGE_SIZE); + + ASSERT(offset_in_page(data) == 0); + __bio_add_page(bio, vmalloc_to_page(data), len, 0); + data += len; + size -= len; + } while (size); + + flush_kernel_vmap_range(bp->b_addr, alloc_size); + } else { /* - * Run the write verifier callback function if it exists. If - * this function fails it will mark the buffer with an error and - * the IO should not be dispatched. + * Single folio or slab allocation. Must be contiguous and thus + * only a single bvec is needed. + * + * This uses the page based bio add helper for now as that is + * the lowest common denominator between folios and slab + * allocations. To be replaced with a better block layer + * helper soon (hopefully). */ - if (bp->b_ops) { - bp->b_ops->verify_write(bp); - if (bp->b_error) { - xfs_force_shutdown(bp->b_mount, - SHUTDOWN_CORRUPT_INCORE); - return; - } - } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { - struct xfs_mount *mp = bp->b_mount; - - /* - * non-crc filesystems don't attach verifiers during - * log recovery, so don't warn for such filesystems. - */ - if (xfs_has_crc(mp)) { - xfs_warn(mp, - "%s: no buf ops on daddr 0x%llx len %d", - __func__, xfs_buf_daddr(bp), - bp->b_length); - xfs_hex_dump(bp->b_addr, - XFS_CORRUPTION_DUMP_LEN); - dump_stack(); - } - } - } else { - op = REQ_OP_READ; - if (bp->b_flags & XBF_READ_AHEAD) - op |= REQ_RAHEAD; + bio = bio_alloc(bp->b_target->bt_bdev, 1, xfs_buf_bio_op(bp), + GFP_NOIO); + __bio_add_page(bio, virt_to_page(bp->b_addr), + BBTOB(bp->b_length), + offset_in_page(bp->b_addr)); } - /* we only use the buffer cache for meta-data */ - op |= REQ_META; - - /* in-memory targets are directly mapped, no IO required. */ - if (xfs_buftarg_is_mem(bp->b_target)) { - xfs_buf_ioend(bp); - return; - } + bio->bi_private = bp; + bio->bi_end_io = xfs_buf_bio_end_io; /* - * Walk all the vectors issuing IO on them. Set up the initial offset - * into the buffer and the desired IO size before we start - - * _xfs_buf_ioapply_vec() will modify them appropriately for each - * subsequent call. + * If there is more than one map segment, split out a new bio for each + * map except of the last one. The last map is handled by the + * remainder of the original bio outside the loop. */ - offset = bp->b_offset; - size = BBTOB(bp->b_length); blk_start_plug(&plug); - for (i = 0; i < bp->b_map_count; i++) { - xfs_buf_ioapply_map(bp, i, &offset, &size, op); - if (bp->b_error) - break; - if (size <= 0) - break; /* all done */ + for (map = 0; map < bp->b_map_count - 1; map++) { + struct bio *split; + + split = bio_split(bio, bp->b_maps[map].bm_len, GFP_NOFS, + &fs_bio_set); + split->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + bio_chain(split, bio); + submit_bio(split); } + bio->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + submit_bio(bio); blk_finish_plug(&plug); } @@ -1688,26 +1404,55 @@ xfs_buf_iowait( { ASSERT(!(bp->b_flags & XBF_ASYNC)); - trace_xfs_buf_iowait(bp, _RET_IP_); - wait_for_completion(&bp->b_iowait); - trace_xfs_buf_iowait_done(bp, _RET_IP_); + do { + trace_xfs_buf_iowait(bp, _RET_IP_); + wait_for_completion(&bp->b_iowait); + trace_xfs_buf_iowait_done(bp, _RET_IP_); + } while (!__xfs_buf_ioend(bp)); return bp->b_error; } /* + * Run the write verifier callback function if it exists. If this fails, mark + * the buffer with an error and do not dispatch the I/O. + */ +static bool +xfs_buf_verify_write( + struct xfs_buf *bp) +{ + if (bp->b_ops) { + bp->b_ops->verify_write(bp); + if (bp->b_error) + return false; + } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { + /* + * Non-crc filesystems don't attach verifiers during log + * recovery, so don't warn for such filesystems. + */ + if (xfs_has_crc(bp->b_mount)) { + xfs_warn(bp->b_mount, + "%s: no buf ops on daddr 0x%llx len %d", + __func__, xfs_buf_daddr(bp), + bp->b_length); + xfs_hex_dump(bp->b_addr, XFS_CORRUPTION_DUMP_LEN); + dump_stack(); + } + } + + return true; +} + +/* * Buffer I/O submission path, read or write. Asynchronous submission transfers * the buffer lock ownership and the current reference to the IO. It is not * safe to reference the buffer after a call to this function unless the caller * holds an additional reference itself. */ -static int -__xfs_buf_submit( - struct xfs_buf *bp, - bool wait) +static void +xfs_buf_submit( + struct xfs_buf *bp) { - int error = 0; - trace_xfs_buf_submit(bp, _RET_IP_); ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); @@ -1727,98 +1472,33 @@ __xfs_buf_submit( * state here rather than mount state to avoid corrupting the log tail * on shutdown. */ - if (bp->b_mount->m_log && - xlog_is_shutdown(bp->b_mount->m_log)) { + if (bp->b_mount->m_log && xlog_is_shutdown(bp->b_mount->m_log)) { xfs_buf_ioend_fail(bp); - return -EIO; + return; } - /* - * Grab a reference so the buffer does not go away underneath us. For - * async buffers, I/O completion drops the callers reference, which - * could occur before submission returns. - */ - xfs_buf_hold(bp); - if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); - /* clear the internal error state to avoid spurious errors */ - bp->b_io_error = 0; - /* - * Set the count to 1 initially, this will stop an I/O completion - * callout which happens before we have started all the I/O from calling - * xfs_buf_ioend too early. + * Make sure we capture only current IO errors rather than stale errors + * left over from previous use of the buffer (e.g. failed readahead). */ - atomic_set(&bp->b_io_remaining, 1); - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioacct_inc(bp); - _xfs_buf_ioapply(bp); + bp->b_error = 0; - /* - * If _xfs_buf_ioapply failed, we can get back here with only the IO - * reference we took above. If we drop it to zero, run completion so - * that we don't return to the caller with completion still pending. - */ - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) { - if (bp->b_error || !(bp->b_flags & XBF_ASYNC)) - xfs_buf_ioend(bp); - else - xfs_buf_ioend_async(bp); + if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) { + xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE); + xfs_buf_ioend(bp); + return; } - if (wait) - error = xfs_buf_iowait(bp); - - /* - * Release the hold that keeps the buffer referenced for the entire - * I/O. Note that if the buffer is async, it is not safe to reference - * after this release. - */ - xfs_buf_rele(bp); - return error; -} - -void * -xfs_buf_offset( - struct xfs_buf *bp, - size_t offset) -{ - struct page *page; - - if (bp->b_addr) - return bp->b_addr + offset; - - page = bp->b_pages[offset >> PAGE_SHIFT]; - return page_address(page) + (offset & (PAGE_SIZE-1)); -} - -void -xfs_buf_zero( - struct xfs_buf *bp, - size_t boff, - size_t bsize) -{ - size_t bend; - - bend = boff + bsize; - while (boff < bend) { - struct page *page; - int page_index, page_offset, csize; - - page_index = (boff + bp->b_offset) >> PAGE_SHIFT; - page_offset = (boff + bp->b_offset) & ~PAGE_MASK; - page = bp->b_pages[page_index]; - csize = min_t(size_t, PAGE_SIZE - page_offset, - BBTOB(bp->b_length) - boff); - - ASSERT((csize + page_offset) <= PAGE_SIZE); - - memset(page_address(page) + page_offset, 0, csize); - - boff += csize; + /* In-memory targets are directly mapped, no I/O required. */ + if (xfs_buftarg_is_mem(bp->b_target)) { + xfs_buf_ioend(bp); + return; } + + xfs_buf_submit_bio(bp); } /* @@ -1862,13 +1542,14 @@ xfs_buftarg_drain_rele( struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); struct list_head *dispose = arg; - if (atomic_read(&bp->b_hold) > 1) { + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + if (bp->b_hold > 1) { /* need to wait, so skip it this pass */ + spin_unlock(&bp->b_lock); trace_xfs_buf_drain_buftarg(bp, _RET_IP_); return LRU_SKIP; } - if (!spin_trylock(&bp->b_lock)) - return LRU_SKIP; /* * clear the LRU reference count so the buffer doesn't get @@ -1889,9 +1570,8 @@ xfs_buftarg_wait( struct xfs_buftarg *btp) { /* - * First wait on the buftarg I/O count for all in-flight buffers to be - * released. This is critical as new buffers do not make the LRU until - * they are released. + * First wait for all in-flight readahead buffers to be released. This is + * critical as new buffers do not make the LRU until they are released. * * Next, flush the buffer workqueue to ensure all completion processing * has finished. Just waiting on buffer locks is not sufficient for @@ -1900,7 +1580,7 @@ xfs_buftarg_wait( * all reference counts have been dropped before we start walking the * LRU list. */ - while (percpu_counter_sum(&btp->bt_io_count)) + while (percpu_counter_sum(&btp->bt_readahead_count)) delay(100); flush_workqueue(btp->bt_mount->m_buf_workqueue); } @@ -2017,8 +1697,8 @@ xfs_destroy_buftarg( struct xfs_buftarg *btp) { shrinker_free(btp->bt_shrinker); - ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); - percpu_counter_destroy(&btp->bt_io_count); + ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0); + percpu_counter_destroy(&btp->bt_readahead_count); list_lru_destroy(&btp->bt_lru); } @@ -2072,7 +1752,7 @@ xfs_init_buftarg( if (list_lru_init(&btp->bt_lru)) return -ENOMEM; - if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL)) + if (percpu_counter_init(&btp->bt_readahead_count, 0, GFP_KERNEL)) goto out_destroy_lru; btp->bt_shrinker = @@ -2086,7 +1766,7 @@ xfs_init_buftarg( return 0; out_destroy_io_count: - percpu_counter_destroy(&btp->bt_io_count); + percpu_counter_destroy(&btp->bt_readahead_count); out_destroy_lru: list_lru_destroy(&btp->bt_lru); return -ENOMEM; @@ -2207,7 +1887,7 @@ xfs_buf_delwri_queue( */ bp->b_flags |= _XBF_DELWRI_Q; if (list_empty(&bp->b_list)) { - atomic_inc(&bp->b_hold); + xfs_buf_hold(bp); list_add_tail(&bp->b_list, list); } @@ -2265,72 +1945,26 @@ xfs_buf_cmp( return 0; } -/* - * Submit buffers for write. If wait_list is specified, the buffers are - * submitted using sync I/O and placed on the wait list such that the caller can - * iowait each buffer. Otherwise async I/O is used and the buffers are released - * at I/O completion time. In either case, buffers remain locked until I/O - * completes and the buffer is released from the queue. - */ -static int -xfs_buf_delwri_submit_buffers( - struct list_head *buffer_list, - struct list_head *wait_list) +static bool +xfs_buf_delwri_submit_prep( + struct xfs_buf *bp) { - struct xfs_buf *bp, *n; - int pinned = 0; - struct blk_plug plug; - - list_sort(NULL, buffer_list, xfs_buf_cmp); - - blk_start_plug(&plug); - list_for_each_entry_safe(bp, n, buffer_list, b_list) { - if (!wait_list) { - if (!xfs_buf_trylock(bp)) - continue; - if (xfs_buf_ispinned(bp)) { - xfs_buf_unlock(bp); - pinned++; - continue; - } - } else { - xfs_buf_lock(bp); - } - - /* - * Someone else might have written the buffer synchronously or - * marked it stale in the meantime. In that case only the - * _XBF_DELWRI_Q flag got cleared, and we have to drop the - * reference and remove it from the list here. - */ - if (!(bp->b_flags & _XBF_DELWRI_Q)) { - xfs_buf_list_del(bp); - xfs_buf_relse(bp); - continue; - } - - trace_xfs_buf_delwri_split(bp, _RET_IP_); - - /* - * If we have a wait list, each buffer (and associated delwri - * queue reference) transfers to it and is submitted - * synchronously. Otherwise, drop the buffer from the delwri - * queue and submit async. - */ - bp->b_flags &= ~_XBF_DELWRI_Q; - bp->b_flags |= XBF_WRITE; - if (wait_list) { - bp->b_flags &= ~XBF_ASYNC; - list_move_tail(&bp->b_list, wait_list); - } else { - bp->b_flags |= XBF_ASYNC; - xfs_buf_list_del(bp); - } - __xfs_buf_submit(bp, false); + /* + * Someone else might have written the buffer synchronously or marked it + * stale in the meantime. In that case only the _XBF_DELWRI_Q flag got + * cleared, and we have to drop the reference and remove it from the + * list here. + */ + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + xfs_buf_list_del(bp); + xfs_buf_relse(bp); + return false; } - blk_finish_plug(&plug); - return pinned; + trace_xfs_buf_delwri_split(bp, _RET_IP_); + bp->b_flags &= ~_XBF_DELWRI_Q; + bp->b_flags |= XBF_WRITE; + return true; } /* @@ -2353,7 +1987,30 @@ int xfs_buf_delwri_submit_nowait( struct list_head *buffer_list) { - return xfs_buf_delwri_submit_buffers(buffer_list, NULL); + struct xfs_buf *bp, *n; + int pinned = 0; + struct blk_plug plug; + + list_sort(NULL, buffer_list, xfs_buf_cmp); + + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + if (!xfs_buf_trylock(bp)) + continue; + if (xfs_buf_ispinned(bp)) { + xfs_buf_unlock(bp); + pinned++; + continue; + } + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags |= XBF_ASYNC; + xfs_buf_list_del(bp); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); + + return pinned; } /* @@ -2370,9 +2027,21 @@ xfs_buf_delwri_submit( { LIST_HEAD (wait_list); int error = 0, error2; - struct xfs_buf *bp; + struct xfs_buf *bp, *n; + struct blk_plug plug; + + list_sort(NULL, buffer_list, xfs_buf_cmp); - xfs_buf_delwri_submit_buffers(buffer_list, &wait_list); + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + xfs_buf_lock(bp); + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags &= ~XBF_ASYNC; + list_move_tail(&bp->b_list, &wait_list); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); /* Wait for IO to complete. */ while (!list_empty(&wait_list)) { @@ -2397,14 +2066,9 @@ xfs_buf_delwri_submit( * Push a single buffer on a delwri queue. * * The purpose of this function is to submit a single buffer of a delwri queue - * and return with the buffer still on the original queue. The waiting delwri - * buffer submission infrastructure guarantees transfer of the delwri queue - * buffer reference to a temporary wait list. We reuse this infrastructure to - * transfer the buffer back to the original queue. + * and return with the buffer still on the original queue. * - * Note the buffer transitions from the queued state, to the submitted and wait - * listed state and back to the queued state during this call. The buffer - * locking and queue management logic between _delwri_pushbuf() and + * The buffer locking and queue management logic between _delwri_pushbuf() and * _delwri_queue() guarantee that the buffer cannot be queued to another list * before returning. */ @@ -2413,33 +2077,21 @@ xfs_buf_delwri_pushbuf( struct xfs_buf *bp, struct list_head *buffer_list) { - LIST_HEAD (submit_list); int error; ASSERT(bp->b_flags & _XBF_DELWRI_Q); trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); - /* - * Isolate the buffer to a new local list so we can submit it for I/O - * independently from the rest of the original list. - */ xfs_buf_lock(bp); - list_move(&bp->b_list, &submit_list); - xfs_buf_unlock(bp); - - /* - * Delwri submission clears the DELWRI_Q buffer flag and returns with - * the buffer on the wait list with the original reference. Rather than - * bounce the buffer from a local wait list back to the original list - * after I/O completion, reuse the original list as the wait list. - */ - xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags |= XBF_WRITE; + xfs_buf_submit(bp); /* - * The buffer is now locked, under I/O and wait listed on the original - * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and - * return with the buffer unlocked and on the original queue. + * The buffer is now locked, under I/O but still on the original delwri + * queue. Wait for I/O completion, restore the DELWRI_Q flag and + * return with the buffer unlocked and still on the original queue. */ error = xfs_buf_iowait(bp); bp->b_flags |= _XBF_DELWRI_Q; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 3d56bc7a35cc..d0b065a9a9f0 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -27,19 +27,15 @@ struct xfs_buf; #define XBF_READ (1u << 0) /* buffer intended for reading from device */ #define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ #define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ -#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ #define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ #define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ #define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ #define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1u << 16)/* inode buffer */ -#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ -#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ #define _XBF_KMEM (1u << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ @@ -51,7 +47,6 @@ struct xfs_buf; #define XBF_LIVESCAN (1u << 28) #define XBF_INCORE (1u << 29)/* lookup only, return if found in cache */ #define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ typedef unsigned int xfs_buf_flags_t; @@ -60,31 +55,24 @@ typedef unsigned int xfs_buf_flags_t; { XBF_READ, "READ" }, \ { XBF_WRITE, "WRITE" }, \ { XBF_READ_AHEAD, "READ_AHEAD" }, \ - { XBF_NO_IOACCT, "NO_IOACCT" }, \ { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ - { _XBF_INODES, "INODES" }, \ - { _XBF_DQUOTS, "DQUOTS" }, \ { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ - { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ /* The following interface flags should never be set */ \ { XBF_LIVESCAN, "LIVESCAN" }, \ { XBF_INCORE, "INCORE" }, \ - { XBF_TRYLOCK, "TRYLOCK" }, \ - { XBF_UNMAPPED, "UNMAPPED" } + { XBF_TRYLOCK, "TRYLOCK" } /* * Internal state flags. */ #define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ -#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */ struct xfs_buf_cache { - spinlock_t bc_lock; struct rhashtable bc_hash; }; @@ -121,7 +109,7 @@ struct xfs_buftarg { struct shrinker *bt_shrinker; struct list_lru bt_lru; - struct percpu_counter bt_io_count; + struct percpu_counter bt_readahead_count; struct ratelimit_state bt_ioerror_rl; /* Atomic write unit values */ @@ -132,8 +120,6 @@ struct xfs_buftarg { struct xfs_buf_cache bt_cache[]; }; -#define XB_PAGES 2 - struct xfs_buf_map { xfs_daddr_t bm_bn; /* block number for I/O */ int bm_len; /* size of I/O */ @@ -172,7 +158,7 @@ struct xfs_buf { xfs_daddr_t b_rhash_key; /* buffer cache index */ int b_length; /* size of buffer in BBs */ - atomic_t b_hold; /* reference count */ + unsigned int b_hold; /* reference count */ atomic_t b_lru_ref; /* lru reclaim ref count */ xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ @@ -184,10 +170,9 @@ struct xfs_buf { struct list_head b_lru; /* lru list */ spinlock_t b_lock; /* internal state lock */ unsigned int b_state; /* internal state flags */ - int b_io_error; /* internal IO error state */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; - struct xfs_perag *b_pag; /* contains rbtree root */ + struct xfs_perag *b_pag; struct xfs_mount *b_mount; struct xfs_buftarg *b_target; /* buffer target (device) */ void *b_addr; /* virtual address of buffer */ @@ -196,17 +181,12 @@ struct xfs_buf { struct xfs_buf_log_item *b_log_item; struct list_head b_li_list; /* Log items list head */ struct xfs_trans *b_transp; - struct page **b_pages; /* array of page pointers */ - struct page *b_page_array[XB_PAGES]; /* inline pages */ struct xfs_buf_map *b_maps; /* compound buffer map */ struct xfs_buf_map __b_map; /* inline compound buffer map */ int b_map_count; atomic_t b_pin_count; /* pin count */ - atomic_t b_io_remaining; /* #outstanding I/O requests */ - unsigned int b_page_count; /* size of page array */ - unsigned int b_offset; /* page offset of b_addr, - only for _XBF_KMEM buffers */ int b_error; /* error code on I/O */ + void (*b_iodone)(struct xfs_buf *bp); /* * async write failure retry count. Initialised to zero on the first @@ -293,11 +273,11 @@ xfs_buf_readahead( } int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, - xfs_buf_flags_t flags, struct xfs_buf **bpp); + struct xfs_buf **bpp); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, + size_t numblks, struct xfs_buf **bpp, const struct xfs_buf_ops *ops); -int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); +int _xfs_buf_read(struct xfs_buf *bp); void xfs_buf_hold(struct xfs_buf *bp); /* Releasing Buffers */ @@ -324,12 +304,20 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error, #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address) extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa); void xfs_buf_ioend_fail(struct xfs_buf *); -void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize); void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa); #define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address) /* Buffer Utility Routines */ -extern void *xfs_buf_offset(struct xfs_buf *, size_t); +static inline void *xfs_buf_offset(struct xfs_buf *bp, size_t offset) +{ + return bp->b_addr + offset; +} + +static inline void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize) +{ + memset(bp->b_addr + boff, 0, bsize); +} + extern void xfs_buf_stale(struct xfs_buf *bp); /* Delayed Write Buffer Routines */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 47549cfa61cd..19eb0b7a3e58 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -57,24 +57,6 @@ xfs_buf_log_format_size( (blfp->blf_map_size * sizeof(blfp->blf_data_map[0])); } -static inline bool -xfs_buf_item_straddle( - struct xfs_buf *bp, - uint offset, - int first_bit, - int nbits) -{ - void *first, *last; - - first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT)); - last = xfs_buf_offset(bp, - offset + ((first_bit + nbits) << XFS_BLF_SHIFT)); - - if (last - first != nbits * XFS_BLF_CHUNK) - return true; - return false; -} - /* * Return the number of log iovecs and space needed to log the given buf log * item segment. @@ -91,11 +73,8 @@ xfs_buf_item_size_segment( int *nvecs, int *nbytes) { - struct xfs_buf *bp = bip->bli_buf; int first_bit; int nbits; - int next_bit; - int last_bit; first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0); if (first_bit == -1) @@ -108,15 +87,6 @@ xfs_buf_item_size_segment( nbits = xfs_contig_bits(blfp->blf_data_map, blfp->blf_map_size, first_bit); ASSERT(nbits > 0); - - /* - * Straddling a page is rare because we don't log contiguous - * chunks of unmapped buffers anywhere. - */ - if (nbits > 1 && - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) - goto slow_scan; - (*nvecs)++; *nbytes += nbits * XFS_BLF_CHUNK; @@ -131,40 +101,6 @@ xfs_buf_item_size_segment( } while (first_bit != -1); return; - -slow_scan: - /* Count the first bit we jumped out of the above loop from */ - (*nvecs)++; - *nbytes += XFS_BLF_CHUNK; - last_bit = first_bit; - while (last_bit != -1) { - /* - * This takes the bit number to start looking from and - * returns the next set bit from there. It returns -1 - * if there are no more bits set or the start bit is - * beyond the end of the bitmap. - */ - next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, - last_bit + 1); - /* - * If we run out of bits, leave the loop, - * else if we find a new set of bits bump the number of vecs, - * else keep scanning the current set of bits. - */ - if (next_bit == -1) { - break; - } else if (next_bit != last_bit + 1 || - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) { - last_bit = next_bit; - first_bit = next_bit; - (*nvecs)++; - nbits = 1; - } else { - last_bit++; - nbits++; - } - *nbytes += XFS_BLF_CHUNK; - } } /* @@ -277,8 +213,6 @@ xfs_buf_item_format_segment( struct xfs_buf *bp = bip->bli_buf; uint base_size; int first_bit; - int last_bit; - int next_bit; uint nbits; /* copy the flags across from the base format item */ @@ -323,15 +257,6 @@ xfs_buf_item_format_segment( nbits = xfs_contig_bits(blfp->blf_data_map, blfp->blf_map_size, first_bit); ASSERT(nbits > 0); - - /* - * Straddling a page is rare because we don't log contiguous - * chunks of unmapped buffers anywhere. - */ - if (nbits > 1 && - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) - goto slow_scan; - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, first_bit, nbits); blfp->blf_size++; @@ -347,45 +272,6 @@ xfs_buf_item_format_segment( } while (first_bit != -1); return; - -slow_scan: - ASSERT(bp->b_addr == NULL); - last_bit = first_bit; - nbits = 1; - for (;;) { - /* - * This takes the bit number to start looking from and - * returns the next set bit from there. It returns -1 - * if there are no more bits set or the start bit is - * beyond the end of the bitmap. - */ - next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, - (uint)last_bit + 1); - /* - * If we run out of bits fill in the last iovec and get out of - * the loop. Else if we start a new set of bits then fill in - * the iovec for the series we were looking at and start - * counting the bits in the new one. Else we're still in the - * same set of bits so just keep counting and scanning. - */ - if (next_bit == -1) { - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, - first_bit, nbits); - blfp->blf_size++; - break; - } else if (next_bit != last_bit + 1 || - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) { - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, - first_bit, nbits); - blfp->blf_size++; - first_bit = next_bit; - last_bit = next_bit; - nbits = 1; - } else { - last_bit++; - nbits++; - } - } } /* diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 4d8a6aece995..8cde85259a58 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -54,17 +54,12 @@ bool xfs_buf_item_put(struct xfs_buf_log_item *); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_inode_iodone(struct xfs_buf *); -void xfs_buf_inode_io_fail(struct xfs_buf *bp); #ifdef CONFIG_XFS_QUOTA void xfs_buf_dquot_iodone(struct xfs_buf *); -void xfs_buf_dquot_io_fail(struct xfs_buf *bp); #else static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp) { } -static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp) -{ -} #endif /* CONFIG_XFS_QUOTA */ void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec); diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 6b10390ad3d2..d4c5cef5bc43 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -262,12 +262,18 @@ xlog_recover_validate_buf_type( case XFS_BMAP_MAGIC: bp->b_ops = &xfs_bmbt_buf_ops; break; + case XFS_RTRMAP_CRC_MAGIC: + bp->b_ops = &xfs_rtrmapbt_buf_ops; + break; case XFS_RMAP_CRC_MAGIC: bp->b_ops = &xfs_rmapbt_buf_ops; break; case XFS_REFC_CRC_MAGIC: bp->b_ops = &xfs_refcountbt_buf_ops; break; + case XFS_RTREFC_CRC_MAGIC: + bp->b_ops = &xfs_rtrefcountbt_buf_ops; + break; default: warnmsg = "Bad btree block magic!"; break; @@ -855,6 +861,8 @@ xlog_recover_get_buf_lsn( uuid = &btb->bb_u.s.bb_uuid; break; } + case XFS_RTRMAP_CRC_MAGIC: + case XFS_RTREFC_CRC_MAGIC: case XFS_BMAP_CRC_MAGIC: case XFS_BMAP_MAGIC: { struct xfs_btree_block *btb = blk; @@ -998,7 +1006,6 @@ xlog_recover_buf_commit_pass2( struct xfs_mount *mp = log->l_mp; struct xfs_buf *bp; int error; - uint buf_flags; xfs_lsn_t lsn; /* @@ -1017,13 +1024,8 @@ xlog_recover_buf_commit_pass2( } trace_xfs_log_recover_buf_recover(log, buf_f); - - buf_flags = 0; - if (buf_f->blf_flags & XFS_BLF_INODE_BUF) - buf_flags |= XBF_UNMAPPED; - error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, - buf_flags, &bp, NULL); + 0, &bp, NULL); if (error) return error; diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index 07bebbfb16ee..dcbfa274e06d 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -74,7 +74,7 @@ xmbuf_alloc( /* * We don't want to bother with kmapping data during repair, so don't - * allow highmem pages to back this mapping. + * allow highmem folios to back this mapping. */ mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL); @@ -117,7 +117,7 @@ xmbuf_free( struct xfs_buftarg *btp) { ASSERT(xfs_buftarg_is_mem(btp)); - ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); + ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0); trace_xmbuf_free(btp); @@ -127,14 +127,13 @@ xmbuf_free( kfree(btp); } -/* Directly map a shmem page into the buffer cache. */ +/* Directly map a shmem folio into the buffer cache. */ int -xmbuf_map_page( +xmbuf_map_backing_mem( struct xfs_buf *bp) { struct inode *inode = file_inode(bp->b_target->bt_file); struct folio *folio = NULL; - struct page *page; loff_t pos = BBTOB(xfs_buf_daddr(bp)); int error; @@ -159,39 +158,17 @@ xmbuf_map_page( return -EIO; } - page = folio_file_page(folio, pos >> PAGE_SHIFT); - /* - * Mark the page dirty so that it won't be reclaimed once we drop the - * (potentially last) reference in xmbuf_unmap_page. + * Mark the folio dirty so that it won't be reclaimed once we drop the + * (potentially last) reference in xfs_buf_free. */ - set_page_dirty(page); - unlock_page(page); + folio_set_dirty(folio); + folio_unlock(folio); - bp->b_addr = page_address(page); - bp->b_pages = bp->b_page_array; - bp->b_pages[0] = page; - bp->b_page_count = 1; + bp->b_addr = folio_address(folio) + offset_in_folio(folio, pos); return 0; } -/* Unmap a shmem page that was mapped into the buffer cache. */ -void -xmbuf_unmap_page( - struct xfs_buf *bp) -{ - struct page *page = bp->b_pages[0]; - - ASSERT(xfs_buftarg_is_mem(bp->b_target)); - - put_page(page); - - bp->b_addr = NULL; - bp->b_pages[0] = NULL; - bp->b_pages = NULL; - bp->b_page_count = 0; -} - /* Is this a valid daddr within the buftarg? */ bool xmbuf_verify_daddr( @@ -205,7 +182,7 @@ xmbuf_verify_daddr( return daddr < (inode->i_sb->s_maxbytes >> BBSHIFT); } -/* Discard the page backing this buffer. */ +/* Discard the folio backing this buffer. */ static void xmbuf_stale( struct xfs_buf *bp) @@ -220,7 +197,7 @@ xmbuf_stale( } /* - * Finalize a buffer -- discard the backing page if it's stale, or run the + * Finalize a buffer -- discard the backing folio if it's stale, or run the * write verifier to detect problems. */ int diff --git a/fs/xfs/xfs_buf_mem.h b/fs/xfs/xfs_buf_mem.h index eed4a7b63232..67d525cc1513 100644 --- a/fs/xfs/xfs_buf_mem.h +++ b/fs/xfs/xfs_buf_mem.h @@ -19,16 +19,14 @@ int xmbuf_alloc(struct xfs_mount *mp, const char *descr, struct xfs_buftarg **btpp); void xmbuf_free(struct xfs_buftarg *btp); -int xmbuf_map_page(struct xfs_buf *bp); -void xmbuf_unmap_page(struct xfs_buf *bp); bool xmbuf_verify_daddr(struct xfs_buftarg *btp, xfs_daddr_t daddr); void xmbuf_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp); int xmbuf_finalize(struct xfs_buf *bp); #else # define xfs_buftarg_is_mem(...) (false) -# define xmbuf_map_page(...) (-ENOMEM) -# define xmbuf_unmap_page(...) ((void)0) # define xmbuf_verify_daddr(...) (false) #endif /* CONFIG_XFS_MEMORY_BUFS */ +int xmbuf_map_backing_mem(struct xfs_buf *bp); + #endif /* __XFS_BUF_MEM_H__ */ diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index c4bd145f5ec1..94d0873bcd62 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -90,7 +90,7 @@ xfs_discard_endio_work( /* * Queue up the actual completion to a thread to avoid IRQ-safe locking for - * pagb_lock. + * eb_lock. */ static void xfs_discard_endio( @@ -167,6 +167,14 @@ xfs_discard_extents( return error; } +/* + * Care must be taken setting up the trim cursor as the perags may not have been + * initialised when the cursor is initialised. e.g. a clean mount which hasn't + * read in AGFs and the first operation run on the mounted fs is a trim. This + * can result in perag fields that aren't initialised until + * xfs_trim_gather_extents() calls xfs_alloc_read_agf() to lock down the AG for + * the free space search. + */ struct xfs_trim_cur { xfs_agblock_t start; xfs_extlen_t count; @@ -204,6 +212,14 @@ xfs_trim_gather_extents( if (error) goto out_trans_cancel; + /* + * First time through tcur->count will not have been initialised as + * pag->pagf_longest is not guaranteed to be valid before we read + * the AGF buffer above. + */ + if (!tcur->count) + tcur->count = pag->pagf_longest; + if (tcur->by_bno) { /* sub-AG discard request always starts at tcur->start */ cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag); @@ -350,7 +366,6 @@ xfs_trim_perag_extents( { struct xfs_trim_cur tcur = { .start = start, - .count = pag->pagf_longest, .end = end, .minlen = minlen, }; @@ -844,7 +859,8 @@ xfs_ioc_trim( if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (mp->m_rtdev_targp && + + if (mp->m_rtdev_targp && !xfs_has_zoned(mp) && bdev_max_discard_sectors(mp->m_rtdev_targp->bt_bdev)) rt_bdev = mp->m_rtdev_targp->bt_bdev; if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev) && !rt_bdev) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 84b69f686ba8..b4e32f0860b7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1186,9 +1186,8 @@ xfs_qm_dqflush_done( if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) && (lip->li_lsn == qlip->qli_flush_lsn || test_bit(XFS_LI_FAILED, &lip->li_flags))) { - spin_lock(&ailp->ail_lock); - xfs_clear_li_failed(lip); + clear_bit(XFS_LI_FAILED, &lip->li_flags); if (lip->li_lsn == qlip->qli_flush_lsn) { /* xfs_ail_update_finish() drops the AIL lock */ tail_lsn = xfs_ail_delete_one(ailp, lip); @@ -1230,18 +1229,6 @@ xfs_buf_dquot_iodone( } } -void -xfs_buf_dquot_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - spin_lock(&bp->b_mount->m_ail->ail_lock); - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) - set_bit(XFS_LI_FAILED, &lip->li_flags); - spin_unlock(&bp->b_mount->m_ail->ail_lock); -} - /* Check incore dquot for errors before we flush. */ static xfs_failaddr_t xfs_qm_dqflush_check( @@ -1463,7 +1450,7 @@ xfs_qm_dqflush( * Attach the dquot to the buffer so that we can remove this dquot from * the AIL and release the flush lock once the dquot is synced to disk. */ - bp->b_flags |= _XBF_DQUOTS; + bp->b_iodone = xfs_buf_dquot_iodone; list_add_tail(&lip->li_bio_list, &bp->b_li_list); /* diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index c617bac75361..61217adf5ba5 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -160,6 +160,9 @@ static inline struct xfs_dquot *xfs_inode_dquot( struct xfs_inode *ip, xfs_dqtype_t type) { + if (xfs_is_metadir_inode(ip)) + return NULL; + switch (type) { case XFS_DQTYPE_USER: return ip->i_udquot; diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c index 5ede81fadbd8..fa5f31931efd 100644 --- a/fs/xfs/xfs_drain.c +++ b/fs/xfs/xfs_drain.c @@ -13,28 +13,28 @@ #include "xfs_trace.h" /* - * Use a static key here to reduce the overhead of xfs_drain_rele. If the - * compiler supports jump labels, the static branch will be replaced by a nop - * sled when there are no xfs_drain_wait callers. Online fsck is currently - * the only caller, so this is a reasonable tradeoff. + * Use a static key here to reduce the overhead of xfs_defer_drain_rele. If + * the compiler supports jump labels, the static branch will be replaced by a + * nop sled when there are no xfs_defer_drain_wait callers. Online fsck is + * currently the only caller, so this is a reasonable tradeoff. * * Note: Patching the kernel code requires taking the cpu hotplug lock. Other * parts of the kernel allocate memory with that lock held, which means that * XFS callers cannot hold any locks that might be used by memory reclaim or * writeback when calling the static_branch_{inc,dec} functions. */ -static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate); +static DEFINE_STATIC_KEY_FALSE(xfs_defer_drain_waiter_gate); void -xfs_drain_wait_disable(void) +xfs_defer_drain_wait_disable(void) { - static_branch_dec(&xfs_drain_waiter_gate); + static_branch_dec(&xfs_defer_drain_waiter_gate); } void -xfs_drain_wait_enable(void) +xfs_defer_drain_wait_enable(void) { - static_branch_inc(&xfs_drain_waiter_gate); + static_branch_inc(&xfs_defer_drain_waiter_gate); } void @@ -71,7 +71,7 @@ static inline bool has_waiters(struct wait_queue_head *wq_head) static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr) { if (atomic_dec_and_test(&dr->dr_count) && - static_branch_unlikely(&xfs_drain_waiter_gate) && + static_branch_unlikely(&xfs_defer_drain_waiter_gate) && has_waiters(&dr->dr_waiters)) wake_up(&dr->dr_waiters); } diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h index efcf88df9a5e..4d446dbf65e5 100644 --- a/fs/xfs/xfs_drain.h +++ b/fs/xfs/xfs_drain.h @@ -26,8 +26,8 @@ struct xfs_defer_drain { void xfs_defer_drain_init(struct xfs_defer_drain *dr); void xfs_defer_drain_free(struct xfs_defer_drain *dr); -void xfs_drain_wait_disable(void); -void xfs_drain_wait_enable(void); +void xfs_defer_drain_wait_disable(void); +void xfs_defer_drain_wait_enable(void); /* * Deferred Work Intent Drains @@ -61,6 +61,9 @@ void xfs_drain_wait_enable(void); * All functions that create work items must increment the intent counter as * soon as the item is added to the transaction and cannot drop the counter * until the item is finished or cancelled. + * + * The same principles apply to realtime groups because the rt metadata inode + * ILOCKs are not held across transaction rolls. */ struct xfs_group *xfs_group_intent_get(struct xfs_mount *mp, xfs_fsblock_t fsbno, enum xfs_group_type type); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 78cdc5064a8c..dbd87e137694 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -63,6 +63,7 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_WB_DELAY_MS, XFS_RANDOM_WRITE_DELAY_MS, XFS_RANDOM_EXCHMAPS_FINISH_ONE, + XFS_RANDOM_METAFILE_RESV_CRITICAL, }; struct xfs_errortag_attr { @@ -181,6 +182,7 @@ XFS_ERRORTAG_ATTR_RW(attr_leaf_to_node, XFS_ERRTAG_ATTR_LEAF_TO_NODE); XFS_ERRORTAG_ATTR_RW(wb_delay_ms, XFS_ERRTAG_WB_DELAY_MS); XFS_ERRORTAG_ATTR_RW(write_delay_ms, XFS_ERRTAG_WRITE_DELAY_MS); XFS_ERRORTAG_ATTR_RW(exchmaps_finish_one, XFS_ERRTAG_EXCHMAPS_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(metafile_resv_crit, XFS_ERRTAG_METAFILE_RESV_CRITICAL); static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(noerror), @@ -227,6 +229,7 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(wb_delay_ms), XFS_ERRORTAG_ATTR_LIST(write_delay_ms), XFS_ERRORTAG_ATTR_LIST(exchmaps_finish_one), + XFS_ERRORTAG_ATTR_LIST(metafile_resv_crit), NULL, }; ATTRIBUTE_GROUPS(xfs_errortag); diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 56803863b26c..0b41bdfecdfb 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -119,6 +119,9 @@ xfs_exchrange_reserve_quota( int ip1_error = 0; int error; + ASSERT(!xfs_is_metadir_inode(req->ip1)); + ASSERT(!xfs_is_metadir_inode(req->ip2)); + /* * Don't bother with a quota reservation if we're not enforcing them * or the two inodes have the same dquots. diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index ea43c9a6e54c..da3161572735 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -671,7 +671,7 @@ xfs_extent_busy_wait_all( while ((pag = xfs_perag_next(mp, pag))) xfs_extent_busy_wait_group(pag_group(pag)); - if (xfs_has_rtgroups(mp)) + if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) while ((rtg = xfs_rtgroup_next(mp, rtg))) xfs_extent_busy_wait_group(rtg_group(rtg)); } diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index a25c713ff888..777438b853da 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -29,6 +29,7 @@ #include "xfs_inode.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" struct kmem_cache *xfs_efi_cache; struct kmem_cache *xfs_efd_cache; @@ -767,21 +768,35 @@ xfs_rtextent_free_finish_item( trace_xfs_extent_free_deferred(mp, xefi); - if (!(xefi->xefi_flags & XFS_EFI_CANCELLED)) { - if (*rtgp != to_rtg(xefi->xefi_group)) { - *rtgp = to_rtg(xefi->xefi_group); - xfs_rtgroup_lock(*rtgp, XFS_RTGLOCK_BITMAP); - xfs_rtgroup_trans_join(tp, *rtgp, - XFS_RTGLOCK_BITMAP); - } - error = xfs_rtfree_blocks(tp, *rtgp, - xefi->xefi_startblock, xefi->xefi_blockcount); + if (xefi->xefi_flags & XFS_EFI_CANCELLED) + goto done; + + if (*rtgp != to_rtg(xefi->xefi_group)) { + unsigned int lock_flags; + + if (xfs_has_zoned(mp)) + lock_flags = XFS_RTGLOCK_RMAP; + else + lock_flags = XFS_RTGLOCK_BITMAP; + + *rtgp = to_rtg(xefi->xefi_group); + xfs_rtgroup_lock(*rtgp, lock_flags); + xfs_rtgroup_trans_join(tp, *rtgp, lock_flags); } + + if (xfs_has_zoned(mp)) { + error = xfs_zone_free_blocks(tp, *rtgp, xefi->xefi_startblock, + xefi->xefi_blockcount); + } else { + error = xfs_rtfree_blocks(tp, *rtgp, xefi->xefi_startblock, + xefi->xefi_blockcount); + } + if (error == -EAGAIN) { xfs_efd_from_efi(efdp); return error; } - +done: xfs_efd_add_extent(efdp, xefi); xfs_extent_free_cancel_item(item); return error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 9a435b1ff264..84f08c976ac4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,6 +25,8 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_file.h" +#include "xfs_aops.h" +#include "xfs_zone_alloc.h" #include <linux/dax.h> #include <linux/falloc.h> @@ -150,7 +152,7 @@ xfs_file_fsync( * ensure newly written file data make it to disk before logging the new * inode size in case of an extending write. */ - if (XFS_IS_REALTIME_INODE(ip)) + if (XFS_IS_REALTIME_INODE(ip) && mp->m_rtdev_targp != mp->m_ddev_targp) error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); else if (mp->m_logdev_targp != mp->m_ddev_targp) error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); @@ -360,7 +362,8 @@ xfs_file_write_zero_eof( struct iov_iter *from, unsigned int *iolock, size_t count, - bool *drained_dio) + bool *drained_dio, + struct xfs_zone_alloc_ctx *ac) { struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host); loff_t isize; @@ -414,7 +417,7 @@ xfs_file_write_zero_eof( trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize); xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL); + error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, ac, NULL); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); return error; @@ -431,7 +434,8 @@ STATIC ssize_t xfs_file_write_checks( struct kiocb *iocb, struct iov_iter *from, - unsigned int *iolock) + unsigned int *iolock, + struct xfs_zone_alloc_ctx *ac) { struct inode *inode = iocb->ki_filp->f_mapping->host; size_t count = iov_iter_count(from); @@ -481,7 +485,7 @@ restart: */ if (iocb->ki_pos > i_size_read(inode)) { error = xfs_file_write_zero_eof(iocb, from, iolock, count, - &drained_dio); + &drained_dio, ac); if (error == 1) goto restart; if (error) @@ -491,6 +495,48 @@ restart: return kiocb_modified(iocb); } +static ssize_t +xfs_zoned_write_space_reserve( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from, + unsigned int flags, + struct xfs_zone_alloc_ctx *ac) +{ + loff_t count = iov_iter_count(from); + int error; + + if (iocb->ki_flags & IOCB_NOWAIT) + flags |= XFS_ZR_NOWAIT; + + /* + * Check the rlimit and LFS boundary first so that we don't over-reserve + * by possibly a lot. + * + * The generic write path will redo this check later, and it might have + * changed by then. If it got expanded we'll stick to our earlier + * smaller limit, and if it is decreased the new smaller limit will be + * used and our extra space reservation will be returned after finishing + * the write. + */ + error = generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, &count); + if (error) + return error; + + /* + * Sloppily round up count to file system blocks. + * + * This will often reserve an extra block, but that avoids having to look + * at the start offset, which isn't stable for O_APPEND until taking the + * iolock. Also we need to reserve a block each for zeroing the old + * EOF block and the new start block if they are unaligned. + * + * Any remaining block will be returned after the write. + */ + return xfs_zoned_space_reserve(ip, + XFS_B_TO_FSB(ip->i_mount, count) + 1 + 2, flags, ac); +} + static int xfs_dio_write_end_io( struct kiocb *iocb, @@ -503,6 +549,9 @@ xfs_dio_write_end_io( loff_t offset = iocb->ki_pos; unsigned int nofs_flag; + ASSERT(!xfs_is_zoned_inode(ip) || + !(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW))); + trace_xfs_end_io_direct_write(ip, offset, size); if (xfs_is_shutdown(ip->i_mount)) @@ -582,14 +631,51 @@ static const struct iomap_dio_ops xfs_dio_write_ops = { .end_io = xfs_dio_write_end_io, }; +static void +xfs_dio_zoned_submit_io( + const struct iomap_iter *iter, + struct bio *bio, + loff_t file_offset) +{ + struct xfs_mount *mp = XFS_I(iter->inode)->i_mount; + struct xfs_zone_alloc_ctx *ac = iter->private; + xfs_filblks_t count_fsb; + struct iomap_ioend *ioend; + + count_fsb = XFS_B_TO_FSB(mp, bio->bi_iter.bi_size); + if (count_fsb > ac->reserved_blocks) { + xfs_err(mp, +"allocation (%lld) larger than reservation (%lld).", + count_fsb, ac->reserved_blocks); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + bio_io_error(bio); + return; + } + ac->reserved_blocks -= count_fsb; + + bio->bi_end_io = xfs_end_bio; + ioend = iomap_init_ioend(iter->inode, bio, file_offset, + IOMAP_IOEND_DIRECT); + xfs_zone_alloc_and_submit(ioend, &ac->open_zone); +} + +static const struct iomap_dio_ops xfs_dio_zoned_write_ops = { + .bio_set = &iomap_ioend_bioset, + .submit_io = xfs_dio_zoned_submit_io, + .end_io = xfs_dio_write_end_io, +}; + /* - * Handle block aligned direct I/O writes + * Handle block aligned direct I/O writes. */ static noinline ssize_t xfs_file_dio_write_aligned( struct xfs_inode *ip, struct kiocb *iocb, - struct iov_iter *from) + struct iov_iter *from, + const struct iomap_ops *ops, + const struct iomap_dio_ops *dops, + struct xfs_zone_alloc_ctx *ac) { unsigned int iolock = XFS_IOLOCK_SHARED; ssize_t ret; @@ -597,7 +683,7 @@ xfs_file_dio_write_aligned( ret = xfs_ilock_iocb_for_write(iocb, &iolock); if (ret) return ret; - ret = xfs_file_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock, ac); if (ret) goto out_unlock; @@ -611,11 +697,31 @@ xfs_file_dio_write_aligned( iolock = XFS_IOLOCK_SHARED; } trace_xfs_file_direct_write(iocb, from); - ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, 0, NULL, 0); + ret = iomap_dio_rw(iocb, from, ops, dops, 0, ac, 0); out_unlock: - if (iolock) - xfs_iunlock(ip, iolock); + xfs_iunlock(ip, iolock); + return ret; +} + +/* + * Handle block aligned direct I/O writes to zoned devices. + */ +static noinline ssize_t +xfs_file_dio_write_zoned( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from) +{ + struct xfs_zone_alloc_ctx ac = { }; + ssize_t ret; + + ret = xfs_zoned_write_space_reserve(ip, iocb, from, 0, &ac); + if (ret < 0) + return ret; + ret = xfs_file_dio_write_aligned(ip, iocb, from, + &xfs_zoned_direct_write_iomap_ops, + &xfs_dio_zoned_write_ops, &ac); + xfs_zoned_space_unreserve(ip, &ac); return ret; } @@ -675,7 +781,7 @@ retry_exclusive: goto out_unlock; } - ret = xfs_file_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock, NULL); if (ret) goto out_unlock; @@ -721,9 +827,21 @@ xfs_file_dio_write( /* direct I/O must be aligned to device logical sector size */ if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL; - if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) + + /* + * For always COW inodes we also must check the alignment of each + * individual iovec segment, as they could end up with different + * I/Os due to the way bio_iov_iter_get_pages works, and we'd + * then overwrite an already written block. + */ + if (((iocb->ki_pos | count) & ip->i_mount->m_blockmask) || + (xfs_is_always_cow_inode(ip) && + (iov_iter_alignment(from) & ip->i_mount->m_blockmask))) return xfs_file_dio_write_unaligned(ip, iocb, from); - return xfs_file_dio_write_aligned(ip, iocb, from); + if (xfs_is_zoned_inode(ip)) + return xfs_file_dio_write_zoned(ip, iocb, from); + return xfs_file_dio_write_aligned(ip, iocb, from, + &xfs_direct_write_iomap_ops, &xfs_dio_write_ops, NULL); } static noinline ssize_t @@ -740,7 +858,7 @@ xfs_file_dax_write( ret = xfs_ilock_iocb(iocb, iolock); if (ret) return ret; - ret = xfs_file_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock, NULL); if (ret) goto out; @@ -784,7 +902,7 @@ write_retry: if (ret) return ret; - ret = xfs_file_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock, NULL); if (ret) goto out; @@ -832,6 +950,67 @@ out: } STATIC ssize_t +xfs_file_buffered_write_zoned( + struct kiocb *iocb, + struct iov_iter *from) +{ + struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host); + struct xfs_mount *mp = ip->i_mount; + unsigned int iolock = XFS_IOLOCK_EXCL; + bool cleared_space = false; + struct xfs_zone_alloc_ctx ac = { }; + ssize_t ret; + + ret = xfs_zoned_write_space_reserve(ip, iocb, from, XFS_ZR_GREEDY, &ac); + if (ret < 0) + return ret; + + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + goto out_unreserve; + + ret = xfs_file_write_checks(iocb, from, &iolock, &ac); + if (ret) + goto out_unlock; + + /* + * Truncate the iter to the length that we were actually able to + * allocate blocks for. This needs to happen after + * xfs_file_write_checks, because that assigns ki_pos for O_APPEND + * writes. + */ + iov_iter_truncate(from, + XFS_FSB_TO_B(mp, ac.reserved_blocks) - + (iocb->ki_pos & mp->m_blockmask)); + if (!iov_iter_count(from)) + goto out_unlock; + +retry: + trace_xfs_file_buffered_write(iocb, from); + ret = iomap_file_buffered_write(iocb, from, + &xfs_buffered_write_iomap_ops, &ac); + if (ret == -ENOSPC && !cleared_space) { + /* + * Kick off writeback to convert delalloc space and release the + * usually too pessimistic indirect block reservations. + */ + xfs_flush_inodes(mp); + cleared_space = true; + goto retry; + } + +out_unlock: + xfs_iunlock(ip, iolock); +out_unreserve: + xfs_zoned_space_unreserve(ip, &ac); + if (ret > 0) { + XFS_STATS_ADD(mp, xs_write_bytes, ret); + ret = generic_write_sync(iocb, ret); + } + return ret; +} + +STATIC ssize_t xfs_file_write_iter( struct kiocb *iocb, struct iov_iter *from) @@ -878,6 +1057,8 @@ xfs_file_write_iter( return ret; } + if (xfs_is_zoned_inode(ip)) + return xfs_file_buffered_write_zoned(iocb, from); return xfs_file_buffered_write(iocb, from); } @@ -932,7 +1113,8 @@ static int xfs_falloc_collapse_range( struct file *file, loff_t offset, - loff_t len) + loff_t len, + struct xfs_zone_alloc_ctx *ac) { struct inode *inode = file_inode(file); loff_t new_size = i_size_read(inode) - len; @@ -948,7 +1130,7 @@ xfs_falloc_collapse_range( if (offset + len >= i_size_read(inode)) return -EINVAL; - error = xfs_collapse_file_space(XFS_I(inode), offset, len); + error = xfs_collapse_file_space(XFS_I(inode), offset, len, ac); if (error) return error; return xfs_falloc_setsize(file, new_size); @@ -1004,7 +1186,8 @@ xfs_falloc_zero_range( struct file *file, int mode, loff_t offset, - loff_t len) + loff_t len, + struct xfs_zone_alloc_ctx *ac) { struct inode *inode = file_inode(file); unsigned int blksize = i_blocksize(inode); @@ -1017,7 +1200,7 @@ xfs_falloc_zero_range( if (error) return error; - error = xfs_free_file_space(XFS_I(inode), offset, len); + error = xfs_free_file_space(XFS_I(inode), offset, len, ac); if (error) return error; @@ -1088,22 +1271,18 @@ xfs_falloc_allocate_range( FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE) STATIC long -xfs_file_fallocate( +__xfs_file_fallocate( struct file *file, int mode, loff_t offset, - loff_t len) + loff_t len, + struct xfs_zone_alloc_ctx *ac) { struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - if (mode & ~XFS_FALLOC_FL_SUPPORTED) - return -EOPNOTSUPP; - xfs_ilock(ip, iolock); error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); if (error) @@ -1124,16 +1303,16 @@ xfs_file_fallocate( switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_PUNCH_HOLE: - error = xfs_free_file_space(ip, offset, len); + error = xfs_free_file_space(ip, offset, len, ac); break; case FALLOC_FL_COLLAPSE_RANGE: - error = xfs_falloc_collapse_range(file, offset, len); + error = xfs_falloc_collapse_range(file, offset, len, ac); break; case FALLOC_FL_INSERT_RANGE: error = xfs_falloc_insert_range(file, offset, len); break; case FALLOC_FL_ZERO_RANGE: - error = xfs_falloc_zero_range(file, mode, offset, len); + error = xfs_falloc_zero_range(file, mode, offset, len, ac); break; case FALLOC_FL_UNSHARE_RANGE: error = xfs_falloc_unshare_range(file, mode, offset, len); @@ -1154,6 +1333,54 @@ out_unlock: return error; } +static long +xfs_file_zoned_fallocate( + struct file *file, + int mode, + loff_t offset, + loff_t len) +{ + struct xfs_zone_alloc_ctx ac = { }; + struct xfs_inode *ip = XFS_I(file_inode(file)); + int error; + + error = xfs_zoned_space_reserve(ip, 2, XFS_ZR_RESERVED, &ac); + if (error) + return error; + error = __xfs_file_fallocate(file, mode, offset, len, &ac); + xfs_zoned_space_unreserve(ip, &ac); + return error; +} + +static long +xfs_file_fallocate( + struct file *file, + int mode, + loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + if (mode & ~XFS_FALLOC_FL_SUPPORTED) + return -EOPNOTSUPP; + + /* + * For zoned file systems, zeroing the first and last block of a hole + * punch requires allocating a new block to rewrite the remaining data + * and new zeroes out of place. Get a reservations for those before + * taking the iolock. Dip into the reserved pool because we are + * expected to be able to punch a hole even on a completely full + * file system. + */ + if (xfs_is_zoned_inode(XFS_I(inode)) && + (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE | + FALLOC_FL_COLLAPSE_RANGE))) + return xfs_file_zoned_fallocate(file, mode, offset, len); + return __xfs_file_fallocate(file, mode, offset, len, NULL); +} + STATIC int xfs_file_fadvise( struct file *file, @@ -1347,15 +1574,22 @@ xfs_file_release( * blocks. This avoids open/read/close workloads from removing EOF * blocks that other writers depend upon to reduce fragmentation. * + * Inodes on the zoned RT device never have preallocations, so skip + * taking the locks below. + */ + if (!inode->i_nlink || + !(file->f_mode & FMODE_WRITE) || + (ip->i_diflags & XFS_DIFLAG_APPEND) || + xfs_is_zoned_inode(ip)) + return 0; + + /* * If we can't get the iolock just skip truncating the blocks past EOF * because we could deadlock with the mmap_lock otherwise. We'll get * another chance to drop them once the last reference to the inode is * dropped, so we'll never leak blocks permanently. */ - if (inode->i_nlink && - (file->f_mode & FMODE_WRITE) && - !(ip->i_diflags & XFS_DIFLAG_APPEND) && - !xfs_iflags_test(ip, XFS_EOFBLOCKS_RELEASED) && + if (!xfs_iflags_test(ip, XFS_EOFBLOCKS_RELEASED) && xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (xfs_can_free_eofblocks(ip) && !xfs_iflags_test_and_set(ip, XFS_EOFBLOCKS_RELEASED)) @@ -1469,9 +1703,10 @@ xfs_dax_read_fault( * i_lock (XFS - extent map serialisation) */ static vm_fault_t -xfs_write_fault( +__xfs_write_fault( struct vm_fault *vmf, - unsigned int order) + unsigned int order, + struct xfs_zone_alloc_ctx *ac) { struct inode *inode = file_inode(vmf->vma->vm_file); struct xfs_inode *ip = XFS_I(inode); @@ -1498,13 +1733,50 @@ xfs_write_fault( if (IS_DAX(inode)) ret = xfs_dax_fault_locked(vmf, order, true); else - ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops); + ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops, + ac); xfs_iunlock(ip, lock_mode); sb_end_pagefault(inode->i_sb); return ret; } +static vm_fault_t +xfs_write_fault_zoned( + struct vm_fault *vmf, + unsigned int order) +{ + struct xfs_inode *ip = XFS_I(file_inode(vmf->vma->vm_file)); + unsigned int len = folio_size(page_folio(vmf->page)); + struct xfs_zone_alloc_ctx ac = { }; + int error; + vm_fault_t ret; + + /* + * This could over-allocate as it doesn't check for truncation. + * + * But as the overallocation is limited to less than a folio and will be + * release instantly that's just fine. + */ + error = xfs_zoned_space_reserve(ip, XFS_B_TO_FSB(ip->i_mount, len), 0, + &ac); + if (error < 0) + return vmf_fs_error(error); + ret = __xfs_write_fault(vmf, order, &ac); + xfs_zoned_space_unreserve(ip, &ac); + return ret; +} + +static vm_fault_t +xfs_write_fault( + struct vm_fault *vmf, + unsigned int order) +{ + if (xfs_is_zoned_inode(XFS_I(file_inode(vmf->vma->vm_file)))) + return xfs_write_fault_zoned(vmf, order); + return __xfs_write_fault(vmf, order, NULL); +} + static inline bool xfs_is_write_fault( struct vm_fault *vmf) @@ -1613,7 +1885,8 @@ const struct file_operations xfs_file_operations = { .fadvise = xfs_file_fadvise, .remap_file_range = xfs_file_remap_range, .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC | - FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE, + FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE | + FOP_DONTCACHE, }; const struct file_operations xfs_dir_file_operations = { diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 3290dd8524a6..414b27a86458 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -26,6 +26,8 @@ #include "xfs_rtbitmap.h" #include "xfs_ag.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Convert an xfs_fsmap to an fsmap. */ static void @@ -211,21 +213,20 @@ xfs_getfsmap_is_shared( struct xfs_mount *mp = tp->t_mountp; struct xfs_btree_cur *cur; xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t flen = 0; int error; *stat = false; - if (!xfs_has_reflink(mp)) - return 0; - /* rt files will have no perag structure */ - if (!info->group) + if (!xfs_has_reflink(mp) || !info->group) return 0; - /* Are there any shared blocks here? */ - flen = 0; - cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, - to_perag(info->group)); + if (info->group->xg_type == XG_TYPE_RTG) + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(info->group)); + else + cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, + to_perag(info->group)); + /* Are there any shared blocks here? */ error = xfs_refcount_find_shared(cur, frec->rec_key, XFS_BB_TO_FSBT(mp, frec->len_daddr), &fbno, &flen, false); @@ -832,24 +833,248 @@ xfs_getfsmap_rtdev_rtbitmap( return error; } + +/* Transform a realtime rmapbt record into a fsmap */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_helper( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_fsmap_irec frec = { + .owner = rec->rm_owner, + .offset = rec->rm_offset, + .rm_flags = rec->rm_flags, + .rec_key = rec->rm_startblock, + }; + struct xfs_getfsmap_info *info = priv; + + return xfs_getfsmap_group_helper(info, cur->bc_tp, cur->bc_group, + rec->rm_startblock, rec->rm_blockcount, &frec); +} + +/* Actually query the rtrmap btree. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_query( + struct xfs_trans *tp, + struct xfs_getfsmap_info *info, + struct xfs_btree_cur **curpp) +{ + struct xfs_rtgroup *rtg = to_rtg(info->group); + + /* Query the rtrmapbt */ + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + *curpp = xfs_rtrmapbt_init_cursor(tp, rtg); + return xfs_rmap_query_range(*curpp, &info->low, &info->high, + xfs_getfsmap_rtdev_rmapbt_helper, info); +} + +/* Execute a getfsmap query against the realtime device rmapbt. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt( + struct xfs_trans *tp, + const struct xfs_fsmap *keys, + struct xfs_getfsmap_info *info) +{ + struct xfs_fsmap key0 = *keys; /* struct copy */ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *bt_cur = NULL; + xfs_daddr_t rtstart_daddr; + xfs_rtblock_t start_rtb; + xfs_rtblock_t end_rtb; + xfs_rgnumber_t start_rg, end_rg; + uint64_t eofs; + int error = 0; + + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + mp->m_sb.sb_rblocks); + if (key0.fmr_physical >= eofs) + return 0; + + /* + * On zoned filesystems with an internal rt volume, the volume comes + * immediately after the end of the data volume. However, the + * xfs_rtblock_t address space is relative to the start of the data + * device, which means that the first @rtstart fsblocks do not actually + * point anywhere. If a fsmap query comes in with the low key starting + * below @rtstart, report it as "owned by filesystem". + */ + rtstart_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart); + if (xfs_has_zoned(mp) && key0.fmr_physical < rtstart_daddr) { + struct xfs_fsmap_irec frec = { + .owner = XFS_RMAP_OWN_FS, + .len_daddr = rtstart_daddr, + }; + + /* + * Adjust the start of the query range if we're picking up from + * a previous round, and only emit the record if we haven't + * already gone past. + */ + key0.fmr_physical += key0.fmr_length; + if (key0.fmr_physical < rtstart_daddr) { + error = xfs_getfsmap_helper(tp, info, &frec); + if (error) + return error; + + key0.fmr_physical = rtstart_daddr; + } + + /* Zero the other fields to avoid further adjustments. */ + key0.fmr_owner = 0; + key0.fmr_offset = 0; + key0.fmr_length = 0; + } + + start_rtb = xfs_daddr_to_rtb(mp, key0.fmr_physical); + end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical)); + info->missing_owner = XFS_FMR_OWN_FREE; + + /* + * Convert the fsmap low/high keys to rtgroup based keys. Initialize + * low to the fsmap low key and max out the high key to the end + * of the rtgroup. + */ + info->low.rm_offset = XFS_BB_TO_FSBT(mp, key0.fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->low, &key0); + if (error) + return error; + info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, key0.fmr_length); + xfs_getfsmap_set_irec_flags(&info->low, &key0); + + /* Adjust the low key if we are continuing from where we left off. */ + if (info->low.rm_blockcount == 0) { + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ + info->low.rm_owner = 0; + info->low.rm_offset = 0; + + start_rtb += info->low.rm_blockcount; + if (xfs_rtb_to_daddr(mp, start_rtb) >= eofs) + return 0; + } else { + /* Last record seen was a shareable file data extent */ + info->low.rm_offset += info->low.rm_blockcount; + } + info->low.rm_startblock = xfs_rtb_to_rgbno(mp, start_rtb); + + info->high.rm_startblock = -1U; + info->high.rm_owner = ULLONG_MAX; + info->high.rm_offset = ULLONG_MAX; + info->high.rm_blockcount = 0; + info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS; + + start_rg = xfs_rtb_to_rgno(mp, start_rtb); + end_rg = xfs_rtb_to_rgno(mp, end_rtb); + + while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rg, end_rg))) { + /* + * Set the rtgroup high key from the fsmap high key if this + * is the last rtgroup that we're querying. + */ + info->group = rtg_group(rtg); + if (rtg_rgno(rtg) == end_rg) { + info->high.rm_startblock = + xfs_rtb_to_rgbno(mp, end_rtb); + info->high.rm_offset = + XFS_BB_TO_FSBT(mp, keys[1].fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]); + if (error) + break; + xfs_getfsmap_set_irec_flags(&info->high, &keys[1]); + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR); + bt_cur = NULL; + } + + trace_xfs_fsmap_low_group_key(mp, info->dev, rtg_rgno(rtg), + &info->low); + trace_xfs_fsmap_high_group_key(mp, info->dev, rtg_rgno(rtg), + &info->high); + + error = xfs_getfsmap_rtdev_rmapbt_query(tp, info, &bt_cur); + if (error) + break; + + /* + * Set the rtgroup low key to the start of the rtgroup prior to + * moving on to the next rtgroup. + */ + if (rtg_rgno(rtg) == start_rg) + memset(&info->low, 0, sizeof(info->low)); + + /* + * If this is the last rtgroup, report any gap at the end of it + * before we drop the reference to the perag when the loop + * terminates. + */ + if (rtg_rgno(rtg) == end_rg) { + info->last = true; + error = xfs_getfsmap_rtdev_rmapbt_helper(bt_cur, + &info->high, info); + if (error) + break; + } + info->group = NULL; + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR : + XFS_BTREE_NOERROR); + } + + /* loop termination case */ + if (rtg) { + info->group = NULL; + xfs_rtgroup_rele(rtg); + } + + return error; +} #endif /* CONFIG_XFS_RT */ +static uint32_t +xfs_getfsmap_device( + struct xfs_mount *mp, + enum xfs_device dev) +{ + if (mp->m_sb.sb_rtstart) + return dev; + + switch (dev) { + case XFS_DEV_DATA: + return new_encode_dev(mp->m_ddev_targp->bt_dev); + case XFS_DEV_LOG: + return new_encode_dev(mp->m_logdev_targp->bt_dev); + case XFS_DEV_RT: + if (!mp->m_rtdev_targp) + break; + return new_encode_dev(mp->m_rtdev_targp->bt_dev); + } + + return -1; +} + /* Do we recognize the device? */ STATIC bool xfs_getfsmap_is_valid_device( struct xfs_mount *mp, struct xfs_fsmap *fm) { - if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || - fm->fmr_device == new_encode_dev(mp->m_ddev_targp->bt_dev)) - return true; - if (mp->m_logdev_targp && - fm->fmr_device == new_encode_dev(mp->m_logdev_targp->bt_dev)) - return true; - if (mp->m_rtdev_targp && - fm->fmr_device == new_encode_dev(mp->m_rtdev_targp->bt_dev)) - return true; - return false; + return fm->fmr_device == 0 || + fm->fmr_device == UINT_MAX || + fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_DATA) || + fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_LOG) || + (mp->m_rtdev_targp && + fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_RT)); } /* Ensure that the low key is less than the high key. */ @@ -956,7 +1181,7 @@ xfs_getfsmap( /* Set up our device handlers. */ memset(handlers, 0, sizeof(handlers)); handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); - handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev); + handlers[0].dev = xfs_getfsmap_device(mp, XFS_DEV_DATA); if (use_rmap) handlers[0].fn = xfs_getfsmap_datadev_rmapbt; else @@ -964,14 +1189,21 @@ xfs_getfsmap( if (mp->m_logdev_targp != mp->m_ddev_targp) { handlers[1].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); - handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev); + handlers[1].dev = xfs_getfsmap_device(mp, XFS_DEV_LOG); handlers[1].fn = xfs_getfsmap_logdev; } #ifdef CONFIG_XFS_RT - if (mp->m_rtdev_targp) { + /* + * For zoned file systems there is no rtbitmap, so only support fsmap + * if the callers is privileged enough to use the full rmap version. + */ + if (mp->m_rtdev_targp && (use_rmap || !xfs_has_zoned(mp))) { handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); - handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); - handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; + handlers[2].dev = xfs_getfsmap_device(mp, XFS_DEV_RT); + if (use_rmap) + handlers[2].fn = xfs_getfsmap_rtdev_rmapbt; + else + handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } #endif /* CONFIG_XFS_RT */ @@ -1057,7 +1289,13 @@ xfs_getfsmap( if (tp) xfs_trans_cancel(tp); - head->fmh_oflags = FMH_OF_DEV_T; + + /* + * For internal RT device we need to report different synthetic devices + * for a single physical device, and thus can't report the actual dev_t. + */ + if (!mp->m_sb.sb_rtstart) + head->fmh_oflags = FMH_OF_DEV_T; return error; } diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 28dde215c899..0ada73569394 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -21,6 +21,10 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_trace.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_metafile.h" /* * Write new AG headers to disk. Non-transactional, but need to be @@ -107,12 +111,18 @@ xfs_growfs_data_private( if (nb > mp->m_sb.sb_dblocks) { error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); + XFS_FSS_TO_BB(mp, 1), &bp, NULL); if (error) return error; xfs_buf_relse(bp); } + /* Make sure the new fs size won't cause problems with the log. */ + error = xfs_growfs_check_rtgeom(mp, nb, mp->m_sb.sb_rblocks, + mp->m_sb.sb_rextsize); + if (error) + return error; + nb_div = nb; nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) @@ -220,7 +230,12 @@ xfs_growfs_data_private( error = xfs_fs_reserve_ag_blocks(mp); if (error == -ENOSPC) error = 0; + + /* Compute new maxlevels for rt btrees. */ + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); } + return error; out_trans_cancel: @@ -286,24 +301,30 @@ xfs_growfs_data( struct xfs_mount *mp, struct xfs_growfs_data *in) { - int error = 0; + int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!mutex_trylock(&mp->m_growlock)) return -EWOULDBLOCK; + /* we can't grow the data section when an internal RT section exists */ + if (in->newblocks != mp->m_sb.sb_dblocks && mp->m_sb.sb_rtstart) { + error = -EINVAL; + goto out_unlock; + } + /* update imaxpct separately to the physical grow of the filesystem */ if (in->imaxpct != mp->m_sb.sb_imax_pct) { error = xfs_growfs_imaxpct(mp, in->imaxpct); if (error) - goto out_error; + goto out_unlock; } if (in->newblocks != mp->m_sb.sb_dblocks) { error = xfs_growfs_data_private(mp, in); if (error) - goto out_error; + goto out_unlock; } /* Post growfs calculations needed to reflect new state in operations */ @@ -317,13 +338,12 @@ xfs_growfs_data( /* Update secondary superblocks now the physical grow has completed */ error = xfs_update_secondary_sbs(mp); -out_error: /* - * Increment the generation unconditionally, the error could be from - * updating the secondary superblocks, in which case the new size - * is live already. + * Increment the generation unconditionally, after trying to update the + * secondary superblocks, as the new size is live already at this point. */ mp->m_generation++; +out_unlock: mutex_unlock(&mp->m_growlock); return error; } @@ -352,6 +372,7 @@ xfs_growfs_log( int xfs_reserve_blocks( struct xfs_mount *mp, + enum xfs_free_counter ctr, uint64_t request) { int64_t lcounter, delta; @@ -359,6 +380,8 @@ xfs_reserve_blocks( int64_t free; int error = 0; + ASSERT(ctr < XC_FREE_NR); + /* * With per-cpu counters, this becomes an interesting problem. we need * to work out if we are freeing or allocation blocks first, then we can @@ -377,16 +400,16 @@ xfs_reserve_blocks( * counters directly since we shouldn't have any problems unreserving * space. */ - if (mp->m_resblks > request) { - lcounter = mp->m_resblks_avail - request; + if (mp->m_free[ctr].res_total > request) { + lcounter = mp->m_free[ctr].res_avail - request; if (lcounter > 0) { /* release unused blocks */ fdblks_delta = lcounter; - mp->m_resblks_avail -= lcounter; + mp->m_free[ctr].res_avail -= lcounter; } - mp->m_resblks = request; + mp->m_free[ctr].res_total = request; if (fdblks_delta) { spin_unlock(&mp->m_sb_lock); - xfs_add_fdblocks(mp, fdblks_delta); + xfs_add_freecounter(mp, ctr, fdblks_delta); spin_lock(&mp->m_sb_lock); } @@ -395,7 +418,7 @@ xfs_reserve_blocks( /* * If the request is larger than the current reservation, reserve the - * blocks before we update the reserve counters. Sample m_fdblocks and + * blocks before we update the reserve counters. Sample m_free and * perform a partial reservation if the request exceeds free space. * * The code below estimates how many blocks it can request from @@ -405,10 +428,10 @@ xfs_reserve_blocks( * space to fill it because mod_fdblocks will refill an undersized * reserve when it can. */ - free = percpu_counter_sum(&mp->m_fdblocks) - - xfs_fdblocks_unavailable(mp); - delta = request - mp->m_resblks; - mp->m_resblks = request; + free = xfs_sum_freecounter_raw(mp, ctr) - + xfs_freecounter_unavailable(mp, ctr); + delta = request - mp->m_free[ctr].res_total; + mp->m_free[ctr].res_total = request; if (delta > 0 && free > 0) { /* * We'll either succeed in getting space from the free block @@ -422,9 +445,9 @@ xfs_reserve_blocks( */ fdblks_delta = min(free, delta); spin_unlock(&mp->m_sb_lock); - error = xfs_dec_fdblocks(mp, fdblks_delta, 0); + error = xfs_dec_freecounter(mp, ctr, fdblks_delta, 0); if (!error) - xfs_add_fdblocks(mp, fdblks_delta); + xfs_add_freecounter(mp, ctr, fdblks_delta); spin_lock(&mp->m_sb_lock); } out: @@ -541,6 +564,17 @@ xfs_fs_reserve_ag_blocks( xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", error); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + + err2 = xfs_metafile_resv_init(mp); + if (err2 && err2 != -ENOSPC) { + xfs_warn(mp, + "Error %d reserving realtime metadata reserve pool.", err2); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + + if (!error) + error = err2; } return error; @@ -555,6 +589,7 @@ xfs_fs_unreserve_ag_blocks( { struct xfs_perag *pag = NULL; + xfs_metafile_resv_free(mp); while ((pag = xfs_perag_next(mp, pag))) xfs_ag_resv_free(pag); } diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index 3e2f73bcf831..9d23c361ef56 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -8,7 +8,8 @@ int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in); int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in); -int xfs_reserve_blocks(struct xfs_mount *mp, uint64_t request); +int xfs_reserve_blocks(struct xfs_mount *mp, enum xfs_free_counter cnt, + uint64_t request); int xfs_fs_goingdown(struct xfs_mount *mp, uint32_t inflags); int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index c7c2e6561998..7c541fb373d5 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -447,6 +447,8 @@ static const struct ioctl_sick_map rtgroup_map[] = { { XFS_SICK_RG_SUPER, XFS_RTGROUP_GEOM_SICK_SUPER }, { XFS_SICK_RG_BITMAP, XFS_RTGROUP_GEOM_SICK_BITMAP }, { XFS_SICK_RG_SUMMARY, XFS_RTGROUP_GEOM_SICK_SUMMARY }, + { XFS_SICK_RG_RMAPBT, XFS_RTGROUP_GEOM_SICK_RMAPBT }, + { XFS_SICK_RG_REFCNTBT, XFS_RTGROUP_GEOM_SICK_REFCNTBT }, }; /* Fill out rtgroup geometry health info. */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 7b6c026d01a1..726e29b837e6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -230,7 +230,7 @@ xfs_blockgc_queue( rcu_read_lock(); if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) queue_delayed_work(mp->m_blockgc_wq, &pag->pag_blockgc_work, - msecs_to_jiffies(xfs_blockgc_secs * 1000)); + secs_to_jiffies(xfs_blockgc_secs)); rcu_read_unlock(); } @@ -2073,10 +2073,10 @@ xfs_inodegc_want_queue_rt_file( { struct xfs_mount *mp = ip->i_mount; - if (!XFS_IS_REALTIME_INODE(ip)) + if (!XFS_IS_REALTIME_INODE(ip) || xfs_has_zoned(mp)) return false; - if (__percpu_counter_compare(&mp->m_frextents, + if (xfs_compare_freecounter(mp, XC_FREE_RTEXTENTS, mp->m_low_rtexts[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; @@ -2104,7 +2104,7 @@ xfs_inodegc_want_queue_work( if (items > mp->m_ino_geo.inodes_per_cluster) return true; - if (__percpu_counter_compare(&mp->m_fdblocks, + if (xfs_compare_freecounter(mp, XC_FREE_BLOCKS, mp->m_low_space[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 1ff514b6c035..ee3e0f284287 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1721,8 +1721,7 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * igeo->blocks_per_cluster, - XBF_UNMAPPED, &bp); + mp->m_bsize * igeo->blocks_per_cluster, 0, &bp); if (error) return error; @@ -2385,7 +2384,16 @@ 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, @@ -2425,6 +2433,14 @@ 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 @@ -2718,21 +2734,16 @@ xfs_mmaplock_two_inodes_and_break_dax_layout( struct xfs_inode *ip2) { int error; - bool retry; - struct page *page; if (ip1->i_ino > ip2->i_ino) swap(ip1, ip2); again: - retry = false; /* Lock the first inode */ xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); - error = xfs_break_dax_layouts(VFS_I(ip1), &retry); - if (error || retry) { + error = xfs_break_dax_layouts(VFS_I(ip1)); + if (error) { xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); - if (error == 0 && retry) - goto again; return error; } @@ -2746,8 +2757,8 @@ again: * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable * for this nested lock case. */ - page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); - if (page && page_ref_count(page) != 1) { + error = dax_break_layout(VFS_I(ip2), 0, -1, NULL); + if (error) { xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); goto again; @@ -2991,21 +3002,11 @@ xfs_wait_dax_page( int xfs_break_dax_layouts( - struct inode *inode, - bool *retry) + struct inode *inode) { - struct page *page; - xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL); - page = dax_layout_busy_page(inode->i_mapping); - if (!page) - return 0; - - *retry = true; - return ___wait_var_event(&page->_refcount, - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, - 0, 0, xfs_wait_dax_page(inode)); + return dax_break_layout_inode(inode, xfs_wait_dax_page); } int @@ -3023,8 +3024,8 @@ xfs_break_layouts( retry = false; switch (reason) { case BREAK_UNMAP: - error = xfs_break_dax_layouts(inode, &retry); - if (error || retry) + error = xfs_break_dax_layouts(inode); + if (error) break; fallthrough; case BREAK_WRITE: @@ -3057,5 +3058,6 @@ bool xfs_is_always_cow_inode( const struct xfs_inode *ip) { - return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount); + return xfs_is_zoned_inode(ip) || + (ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount)); } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 1648dc5a8068..eae0159983ca 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -59,8 +59,13 @@ typedef struct xfs_inode { xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */ prid_t i_projid; /* owner's project id */ xfs_extlen_t i_extsize; /* basic/minimum extent size */ - /* cowextsize is only used for v3 inodes, flushiter for v1/2 */ + /* + * i_used_blocks is used for zoned rtrmap inodes, + * i_cowextsize is used for other v3 inodes, + * i_flushiter for v1/2 inodes + */ union { + uint32_t i_used_blocks; /* used blocks in RTG */ xfs_extlen_t i_cowextsize; /* basic cow extent size */ uint16_t i_flushiter; /* incremented on flush */ }; @@ -299,6 +304,11 @@ static inline bool xfs_is_internal_inode(const struct xfs_inode *ip) xfs_is_quota_inode(&mp->m_sb, ip->i_ino); } +static inline bool xfs_is_zoned_inode(const struct xfs_inode *ip) +{ + return xfs_has_zoned(ip->i_mount) && XFS_IS_REALTIME_INODE(ip); +} + bool xfs_is_always_cow_inode(const struct xfs_inode *ip); static inline bool xfs_is_cow_inode(const struct xfs_inode *ip) @@ -593,7 +603,7 @@ xfs_itruncate_extents( return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0); } -int xfs_break_dax_layouts(struct inode *inode, bool *retry); +int xfs_break_dax_layouts(struct inode *inode); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 912f0b1bc3cb..c6cb0b6b9e46 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -157,6 +157,20 @@ xfs_inode_item_precommit( if (flags & XFS_ILOG_IVERSION) flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); + /* + * Inode verifiers do not check that the CoW extent size hint is an + * integer multiple of the rt extent size on a directory with both + * rtinherit and cowextsize flags set. If we're logging a directory + * that is misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + xfs_extlen_to_rtxmod(ip->i_mount, ip->i_cowextsize) > 0) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + flags |= XFS_ILOG_CORE; + } + if (!iip->ili_item.li_buf) { struct xfs_buf *bp; int error; @@ -185,7 +199,7 @@ xfs_inode_item_precommit( xfs_buf_hold(bp); spin_lock(&iip->ili_lock); iip->ili_item.li_buf = bp; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); xfs_trans_brelse(tp, bp); } @@ -242,6 +256,7 @@ 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 +377,7 @@ 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); @@ -580,6 +596,7 @@ xfs_inode_to_log_dinode( to->di_changecount = inode_peek_iversion(inode); to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime); to->di_flags2 = ip->i_diflags2; + /* also covers the di_used_blocks union arm: */ to->di_cowextsize = ip->i_cowextsize; to->di_ino = ip->i_ino; to->di_lsn = lsn; @@ -1023,18 +1040,6 @@ xfs_buf_inode_iodone( list_splice_tail(&flushed_inodes, &bp->b_li_list); } -void -xfs_buf_inode_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - set_bit(XFS_LI_FAILED, &lip->li_flags); - clear_bit(XFS_LI_FLUSHING, &lip->li_flags); - } -} - /* * Clear the inode logging fields so no more flushes are attempted. If we are * on a buffer list, it is now safe to remove it because the buffer is @@ -1084,13 +1089,7 @@ xfs_iflush_abort( * state. Whilst the inode is in the AIL, it should have a valid buffer * pointer for push operations to access - it is only safe to remove the * inode from the buffer once it has been removed from the AIL. - * - * We also clear the failed bit before removing the item from the AIL - * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer - * references the inode item owns and needs to hold until we've fully - * aborted the inode log item and detached it from the buffer. */ - clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags); xfs_trans_ail_delete(&iip->ili_item, 0); /* diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index e70d2611456b..7205fd14f6b3 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -22,6 +22,8 @@ #include "xfs_log_recover.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" STATIC void xlog_recover_inode_ra_pass2( @@ -201,6 +203,7 @@ xfs_log_dinode_to_disk( to->di_crtime = xfs_log_dinode_to_disk_ts(from, from->di_crtime); to->di_flags2 = cpu_to_be64(from->di_flags2); + /* also covers the di_used_blocks union arm: */ to->di_cowextsize = cpu_to_be32(from->di_cowextsize); to->di_ino = cpu_to_be64(from->di_ino); to->di_lsn = cpu_to_be64(lsn); @@ -266,6 +269,41 @@ 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)) { + case XFS_METAFILE_RTRMAP: + xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); + return 0; + case XFS_METAFILE_RTREFCOUNT: + xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize); + return 0; + 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 +431,9 @@ 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 +514,9 @@ 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_ioctl.c b/fs/xfs/xfs_ioctl.c index 0789c18aaa18..d250f7f74e3b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -469,8 +469,21 @@ xfs_fill_fsxattr( } } - if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) - fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { + /* + * Don't let a misaligned CoW extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_cowextsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + fa->fsx_cowextsize = 0; + } else { + fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + } + } + fa->fsx_projid = ip->i_projid; if (ifp && !xfs_need_iread_extents(ifp)) fa->fsx_nextents = xfs_iext_count(ifp); @@ -541,10 +554,6 @@ xfs_ioctl_setattr_xflags( if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || xfs_extlen_to_rtxmod(mp, ip->i_extsize)) return -EINVAL; - - /* Clear reflink if we are actually able to set the rt flag. */ - if (xfs_is_reflink_inode(ip)) - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* diflags2 only valid for v3 inodes. */ @@ -1122,15 +1131,15 @@ xfs_ioctl_getset_resblocks( error = mnt_want_write_file(filp); if (error) return error; - error = xfs_reserve_blocks(mp, fsop.resblks); + error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, fsop.resblks); mnt_drop_write_file(filp); if (error) return error; } spin_lock(&mp->m_sb_lock); - fsop.resblks = mp->m_resblks; - fsop.resblks_avail = mp->m_resblks_avail; + fsop.resblks = mp->m_free[XC_FREE_BLOCKS].res_total; + fsop.resblks_avail = mp->m_free[XC_FREE_BLOCKS].res_avail; spin_unlock(&mp->m_sb_lock); if (copy_to_user(arg, &fsop, sizeof(fsop))) @@ -1146,9 +1155,9 @@ xfs_ioctl_fs_counts( struct xfs_fsop_counts out = { .allocino = percpu_counter_read_positive(&mp->m_icount), .freeino = percpu_counter_read_positive(&mp->m_ifree), - .freedata = percpu_counter_read_positive(&mp->m_fdblocks) - - xfs_fdblocks_unavailable(mp), - .freertx = percpu_counter_read_positive(&mp->m_frextents), + .freedata = xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) - + xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS), + .freertx = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS), }; if (copy_to_user(uarg, &out, sizeof(out))) @@ -1204,7 +1213,16 @@ xfs_file_ioctl( struct xfs_buftarg *target = xfs_inode_buftarg(ip); struct dioattr da; - da.d_mem = da.d_miniosz = target->bt_logical_sectorsize; + da.d_mem = target->bt_logical_sectorsize; + + /* + * See xfs_report_dioalign() for an explanation about why this + * reports a value larger than the sector size for COW inodes. + */ + if (xfs_is_cow_inode(ip)) + da.d_miniosz = xfs_inode_alloc_unitsize(ip); + else + da.d_miniosz = target->bt_logical_sectorsize; da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); if (copy_to_user(arg, &da, sizeof(da))) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d61460309a78..cb23c8871f81 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -30,6 +30,8 @@ #include "xfs_reflink.h" #include "xfs_health.h" #include "xfs_rtbitmap.h" +#include "xfs_icache.h" +#include "xfs_zone_alloc.h" #define XFS_ALLOC_ALIGN(mp, off) \ (((off) >> mp->m_allocsize_log) << mp->m_allocsize_log) @@ -431,13 +433,14 @@ xfs_quota_calc_throttle( static int64_t xfs_iomap_freesp( - struct percpu_counter *counter, + struct xfs_mount *mp, + unsigned int idx, uint64_t low_space[XFS_LOWSP_MAX], int *shift) { int64_t freesp; - freesp = percpu_counter_read_positive(counter); + freesp = xfs_estimate_freecounter(mp, idx); if (freesp < low_space[XFS_LOWSP_5_PCNT]) { *shift = 2; if (freesp < low_space[XFS_LOWSP_4_PCNT]) @@ -536,10 +539,10 @@ xfs_iomap_prealloc_size( if (unlikely(XFS_IS_REALTIME_INODE(ip))) freesp = xfs_rtbxlen_to_blen(mp, - xfs_iomap_freesp(&mp->m_frextents, + xfs_iomap_freesp(mp, XC_FREE_RTEXTENTS, mp->m_low_rtexts, &shift)); else - freesp = xfs_iomap_freesp(&mp->m_fdblocks, mp->m_low_space, + freesp = xfs_iomap_freesp(mp, XC_FREE_BLOCKS, mp->m_low_space, &shift); /* @@ -828,6 +831,10 @@ xfs_direct_write_iomap_begin( if (offset + length > i_size_read(inode)) iomap_flags |= IOMAP_F_DIRTY; + /* HW-offload atomics are always used in this path */ + if (flags & IOMAP_ATOMIC) + iomap_flags |= IOMAP_F_ATOMIC_BIO; + /* * COW writes may allocate delalloc space or convert unwritten COW * extents, so we need to make sure to take the lock exclusively here. @@ -962,6 +969,59 @@ const struct iomap_ops xfs_direct_write_iomap_ops = { .iomap_begin = xfs_direct_write_iomap_begin, }; +#ifdef CONFIG_XFS_RT +/* + * This is really simple. The space has already been reserved before taking the + * IOLOCK, the actual block allocation is done just before submitting the bio + * and only recorded in the extent map on I/O completion. + */ +static int +xfs_zoned_direct_write_iomap_begin( + struct inode *inode, + loff_t offset, + loff_t length, + unsigned flags, + struct iomap *iomap, + struct iomap *srcmap) +{ + struct xfs_inode *ip = XFS_I(inode); + int error; + + ASSERT(!(flags & IOMAP_OVERWRITE_ONLY)); + + /* + * Needs to be pushed down into the allocator so that only writes into + * a single zone can be supported. + */ + if (flags & IOMAP_NOWAIT) + return -EAGAIN; + + /* + * Ensure the extent list is in memory in so that we don't have to do + * read it from the I/O completion handler. + */ + if (xfs_need_iread_extents(&ip->i_df)) { + xfs_ilock(ip, XFS_ILOCK_EXCL); + error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + if (error) + return error; + } + + iomap->type = IOMAP_MAPPED; + iomap->flags = IOMAP_F_DIRTY; + iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; + iomap->offset = offset; + iomap->length = length; + iomap->flags = IOMAP_F_ANON_WRITE; + return 0; +} + +const struct iomap_ops xfs_zoned_direct_write_iomap_ops = { + .iomap_begin = xfs_zoned_direct_write_iomap_begin, +}; +#endif /* CONFIG_XFS_RT */ + static int xfs_dax_write_iomap_end( struct inode *inode, @@ -987,6 +1047,455 @@ const struct iomap_ops xfs_dax_write_iomap_ops = { .iomap_end = xfs_dax_write_iomap_end, }; +/* + * Convert a hole to a delayed allocation. + */ +static void +xfs_bmap_add_extent_hole_delay( + struct xfs_inode *ip, /* incore inode pointer */ + int whichfork, + struct xfs_iext_cursor *icur, + struct xfs_bmbt_irec *new) /* new data to add to file extents */ +{ + struct xfs_ifork *ifp; /* inode fork pointer */ + xfs_bmbt_irec_t left; /* left neighbor extent entry */ + xfs_filblks_t newlen=0; /* new indirect size */ + xfs_filblks_t oldlen=0; /* old indirect size */ + xfs_bmbt_irec_t right; /* right neighbor extent entry */ + uint32_t state = xfs_bmap_fork_to_state(whichfork); + xfs_filblks_t temp; /* temp for indirect calculations */ + + ifp = xfs_ifork_ptr(ip, whichfork); + ASSERT(isnullstartblock(new->br_startblock)); + + /* + * Check and set flags if this segment has a left neighbor + */ + if (xfs_iext_peek_prev_extent(ifp, icur, &left)) { + state |= BMAP_LEFT_VALID; + if (isnullstartblock(left.br_startblock)) + state |= BMAP_LEFT_DELAY; + } + + /* + * Check and set flags if the current (right) segment exists. + * If it doesn't exist, we're converting the hole at end-of-file. + */ + if (xfs_iext_get_extent(ifp, icur, &right)) { + state |= BMAP_RIGHT_VALID; + if (isnullstartblock(right.br_startblock)) + state |= BMAP_RIGHT_DELAY; + } + + /* + * Set contiguity flags on the left and right neighbors. + * Don't let extents get too large, even if the pieces are contiguous. + */ + if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) && + left.br_startoff + left.br_blockcount == new->br_startoff && + left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN) + state |= BMAP_LEFT_CONTIG; + + if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) && + new->br_startoff + new->br_blockcount == right.br_startoff && + new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN && + (!(state & BMAP_LEFT_CONTIG) || + (left.br_blockcount + new->br_blockcount + + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))) + state |= BMAP_RIGHT_CONTIG; + + /* + * Switch out based on the contiguity flags. + */ + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * New allocation is contiguous with delayed allocations + * on the left and on the right. + * Merge all three into a single extent record. + */ + temp = left.br_blockcount + new->br_blockcount + + right.br_blockcount; + + oldlen = startblockval(left.br_startblock) + + startblockval(new->br_startblock) + + startblockval(right.br_startblock); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); + left.br_startblock = nullstartblock(newlen); + left.br_blockcount = temp; + + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &left); + break; + + case BMAP_LEFT_CONTIG: + /* + * New allocation is contiguous with a delayed allocation + * on the left. + * Merge the new allocation with the left neighbor. + */ + temp = left.br_blockcount + new->br_blockcount; + + oldlen = startblockval(left.br_startblock) + + startblockval(new->br_startblock); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); + left.br_blockcount = temp; + left.br_startblock = nullstartblock(newlen); + + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &left); + break; + + case BMAP_RIGHT_CONTIG: + /* + * New allocation is contiguous with a delayed allocation + * on the right. + * Merge the new allocation with the right neighbor. + */ + temp = new->br_blockcount + right.br_blockcount; + oldlen = startblockval(new->br_startblock) + + startblockval(right.br_startblock); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); + right.br_startoff = new->br_startoff; + right.br_startblock = nullstartblock(newlen); + right.br_blockcount = temp; + xfs_iext_update_extent(ip, state, icur, &right); + break; + + case 0: + /* + * New allocation is not contiguous with another + * delayed allocation. + * Insert a new entry. + */ + oldlen = newlen = 0; + xfs_iext_insert(ip, icur, new, state); + break; + } + if (oldlen != newlen) { + ASSERT(oldlen > newlen); + xfs_add_fdblocks(ip->i_mount, oldlen - newlen); + + /* + * Nothing to do for disk quota accounting here. + */ + xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen); + } +} + +/* + * Add a delayed allocation extent to an inode. Blocks are reserved from the + * global pool and the extent inserted into the inode in-core extent tree. + * + * On entry, got refers to the first extent beyond the offset of the extent to + * allocate or eof is specified if no such extent exists. On return, got refers + * to the extent record that was inserted to the inode fork. + * + * Note that the allocated extent may have been merged with contiguous extents + * during insertion into the inode fork. Thus, got does not reflect the current + * state of the inode fork on return. If necessary, the caller can use lastx to + * look up the updated record in the inode fork. + */ +static int +xfs_bmapi_reserve_delalloc( + struct xfs_inode *ip, + int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, + xfs_filblks_t prealloc, + struct xfs_bmbt_irec *got, + struct xfs_iext_cursor *icur, + int eof) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + xfs_extlen_t alen; + xfs_extlen_t indlen; + uint64_t fdblocks; + int error; + xfs_fileoff_t aoff; + bool use_cowextszhint = + whichfork == XFS_COW_FORK && !prealloc; + +retry: + /* + * Cap the alloc length. Keep track of prealloc so we know whether to + * tag the inode before we return. + */ + aoff = off; + alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN); + if (!eof) + alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff); + if (prealloc && alen >= len) + prealloc = alen - len; + + /* + * If we're targetting the COW fork but aren't creating a speculative + * posteof preallocation, try to expand the reservation to align with + * the COW extent size hint if there's sufficient free space. + * + * Unlike the data fork, the CoW cancellation functions will free all + * the reservations at inactivation, so we don't require that every + * delalloc reservation have a dirty pagecache. + */ + if (use_cowextszhint) { + struct xfs_bmbt_irec prev; + xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip); + + if (!xfs_iext_peek_prev_extent(ifp, icur, &prev)) + prev.br_startoff = NULLFILEOFF; + + error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof, + 1, 0, &aoff, &alen); + ASSERT(!error); + } + + /* + * Make a transaction-less quota reservation for delayed allocation + * blocks. This number gets adjusted later. We return if we haven't + * allocated blocks already inside this loop. + */ + error = xfs_quota_reserve_blkres(ip, alen); + if (error) + goto out; + + /* + * Split changing sb for alen and indlen since they could be coming + * from different places. + */ + indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen); + ASSERT(indlen > 0); + + fdblocks = indlen; + if (XFS_IS_REALTIME_INODE(ip)) { + ASSERT(!xfs_is_zoned_inode(ip)); + error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen)); + if (error) + goto out_unreserve_quota; + } else { + fdblocks += alen; + } + + error = xfs_dec_fdblocks(mp, fdblocks, false); + if (error) + goto out_unreserve_frextents; + + ip->i_delayed_blks += alen; + xfs_mod_delalloc(ip, alen, indlen); + + got->br_startoff = aoff; + got->br_startblock = nullstartblock(indlen); + got->br_blockcount = alen; + got->br_state = XFS_EXT_NORM; + + xfs_bmap_add_extent_hole_delay(ip, whichfork, icur, got); + + /* + * Tag the inode if blocks were preallocated. Note that COW fork + * preallocation can occur at the start or end of the extent, even when + * prealloc == 0, so we must also check the aligned offset and length. + */ + if (whichfork == XFS_DATA_FORK && prealloc) + xfs_inode_set_eofblocks_tag(ip); + if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) + xfs_inode_set_cowblocks_tag(ip); + + return 0; + +out_unreserve_frextents: + if (XFS_IS_REALTIME_INODE(ip)) + xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen)); +out_unreserve_quota: + if (XFS_IS_QUOTA_ON(mp)) + xfs_quota_unreserve_blkres(ip, alen); +out: + if (error == -ENOSPC || error == -EDQUOT) { + trace_xfs_delalloc_enospc(ip, off, len); + + if (prealloc || use_cowextszhint) { + /* retry without any preallocation */ + use_cowextszhint = false; + prealloc = 0; + goto retry; + } + } + return error; +} + +static int +xfs_zoned_buffered_write_iomap_begin( + struct inode *inode, + loff_t offset, + loff_t count, + unsigned flags, + struct iomap *iomap, + struct iomap *srcmap) +{ + struct iomap_iter *iter = + container_of(iomap, struct iomap_iter, iomap); + struct xfs_zone_alloc_ctx *ac = iter->private; + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, count); + u16 iomap_flags = IOMAP_F_SHARED; + unsigned int lockmode = XFS_ILOCK_EXCL; + xfs_filblks_t count_fsb; + xfs_extlen_t indlen; + struct xfs_bmbt_irec got; + struct xfs_iext_cursor icur; + int error = 0; + + ASSERT(!xfs_get_extsz_hint(ip)); + ASSERT(!(flags & IOMAP_UNSHARE)); + ASSERT(ac); + + if (xfs_is_shutdown(mp)) + return -EIO; + + error = xfs_qm_dqattach(ip); + if (error) + return error; + + error = xfs_ilock_for_iomap(ip, flags, &lockmode); + if (error) + return error; + + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) || + XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, XFS_DATA_FORK); + error = -EFSCORRUPTED; + goto out_unlock; + } + + XFS_STATS_INC(mp, xs_blk_mapw); + + error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); + if (error) + goto out_unlock; + + /* + * For zeroing operations check if there is any data to zero first. + * + * For regular writes we always need to allocate new blocks, but need to + * provide the source mapping when the range is unaligned to support + * read-modify-write of the whole block in the page cache. + * + * In either case we need to limit the reported range to the boundaries + * of the source map in the data fork. + */ + if (!IS_ALIGNED(offset, mp->m_sb.sb_blocksize) || + !IS_ALIGNED(offset + count, mp->m_sb.sb_blocksize) || + (flags & IOMAP_ZERO)) { + struct xfs_bmbt_irec smap; + struct xfs_iext_cursor scur; + + if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &scur, + &smap)) + smap.br_startoff = end_fsb; /* fake hole until EOF */ + if (smap.br_startoff > offset_fsb) { + /* + * We never need to allocate blocks for zeroing a hole. + */ + if (flags & IOMAP_ZERO) { + xfs_hole_to_iomap(ip, iomap, offset_fsb, + smap.br_startoff); + goto out_unlock; + } + end_fsb = min(end_fsb, smap.br_startoff); + } else { + end_fsb = min(end_fsb, + smap.br_startoff + smap.br_blockcount); + xfs_trim_extent(&smap, offset_fsb, + end_fsb - offset_fsb); + error = xfs_bmbt_to_iomap(ip, srcmap, &smap, flags, 0, + xfs_iomap_inode_sequence(ip, 0)); + if (error) + goto out_unlock; + } + } + + if (!ip->i_cowfp) + xfs_ifork_init_cow(ip); + + if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got)) + got.br_startoff = end_fsb; + if (got.br_startoff <= offset_fsb) { + trace_xfs_reflink_cow_found(ip, &got); + goto done; + } + + /* + * Cap the maximum length to keep the chunks of work done here somewhat + * symmetric with the work writeback does. + */ + end_fsb = min(end_fsb, got.br_startoff); + count_fsb = min3(end_fsb - offset_fsb, XFS_MAX_BMBT_EXTLEN, + XFS_B_TO_FSB(mp, 1024 * PAGE_SIZE)); + + /* + * The block reservation is supposed to cover all blocks that the + * operation could possible write, but there is a nasty corner case + * where blocks could be stolen from underneath us: + * + * 1) while this thread iterates over a larger buffered write, + * 2) another thread is causing a write fault that calls into + * ->page_mkwrite in range this thread writes to, using up the + * delalloc reservation created by a previous call to this function. + * 3) another thread does direct I/O on the range that the write fault + * happened on, which causes writeback of the dirty data. + * 4) this then set the stale flag, which cuts the current iomap + * iteration short, causing the new call to ->iomap_begin that gets + * us here again, but now without a sufficient reservation. + * + * This is a very unusual I/O pattern, and nothing but generic/095 is + * known to hit it. There's not really much we can do here, so turn this + * into a short write. + */ + if (count_fsb > ac->reserved_blocks) { + xfs_warn_ratelimited(mp, +"Short write on ino 0x%llx comm %.20s due to three-way race with write fault and direct I/O", + ip->i_ino, current->comm); + count_fsb = ac->reserved_blocks; + if (!count_fsb) { + error = -EIO; + goto out_unlock; + } + } + + error = xfs_quota_reserve_blkres(ip, count_fsb); + if (error) + goto out_unlock; + + indlen = xfs_bmap_worst_indlen(ip, count_fsb); + error = xfs_dec_fdblocks(mp, indlen, false); + if (error) + goto out_unlock; + ip->i_delayed_blks += count_fsb; + xfs_mod_delalloc(ip, count_fsb, indlen); + + got.br_startoff = offset_fsb; + got.br_startblock = nullstartblock(indlen); + got.br_blockcount = count_fsb; + got.br_state = XFS_EXT_NORM; + xfs_bmap_add_extent_hole_delay(ip, XFS_COW_FORK, &icur, &got); + ac->reserved_blocks -= count_fsb; + iomap_flags |= IOMAP_F_NEW; + + trace_xfs_iomap_alloc(ip, offset, XFS_FSB_TO_B(mp, count_fsb), + XFS_COW_FORK, &got); +done: + error = xfs_bmbt_to_iomap(ip, iomap, &got, flags, iomap_flags, + xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED)); +out_unlock: + xfs_iunlock(ip, lockmode); + return error; +} + static int xfs_buffered_write_iomap_begin( struct inode *inode, @@ -1013,6 +1522,10 @@ xfs_buffered_write_iomap_begin( if (xfs_is_shutdown(mp)) return -EIO; + if (xfs_is_zoned_inode(ip)) + return xfs_zoned_buffered_write_iomap_begin(inode, offset, + count, flags, iomap, srcmap); + /* we can't use delayed allocations when using extent size hints */ if (xfs_get_extsz_hint(ip)) return xfs_direct_write_iomap_begin(inode, offset, count, @@ -1245,10 +1758,13 @@ xfs_buffered_write_delalloc_punch( loff_t length, struct iomap *iomap) { + struct iomap_iter *iter = + container_of(iomap, struct iomap_iter, iomap); + xfs_bmap_punch_delalloc_range(XFS_I(inode), (iomap->flags & IOMAP_F_SHARED) ? XFS_COW_FORK : XFS_DATA_FORK, - offset, offset + length); + offset, offset + length, iter->private); } static int @@ -1485,6 +2001,7 @@ xfs_zero_range( struct xfs_inode *ip, loff_t pos, loff_t len, + struct xfs_zone_alloc_ctx *ac, bool *did_zero) { struct inode *inode = VFS_I(ip); @@ -1495,13 +2012,14 @@ xfs_zero_range( return dax_zero_range(inode, pos, len, did_zero, &xfs_dax_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, - &xfs_buffered_write_iomap_ops); + &xfs_buffered_write_iomap_ops, ac); } int xfs_truncate_page( struct xfs_inode *ip, loff_t pos, + struct xfs_zone_alloc_ctx *ac, bool *did_zero) { struct inode *inode = VFS_I(ip); @@ -1510,5 +2028,5 @@ xfs_truncate_page( return dax_truncate_page(inode, pos, did_zero, &xfs_dax_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, - &xfs_buffered_write_iomap_ops); + &xfs_buffered_write_iomap_ops, ac); } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 8347268af727..d330c4a581b1 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -10,6 +10,7 @@ struct xfs_inode; struct xfs_bmbt_irec; +struct xfs_zone_alloc_ctx; int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, xfs_fileoff_t count_fsb, unsigned int flags, @@ -24,8 +25,9 @@ int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap, u16 iomap_flags, u64 sequence_cookie); int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, - bool *did_zero); -int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, bool *did_zero); + struct xfs_zone_alloc_ctx *ac, bool *did_zero); +int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, + struct xfs_zone_alloc_ctx *ac, bool *did_zero); static inline xfs_filblks_t xfs_aligned_fsb_count( @@ -49,6 +51,7 @@ xfs_aligned_fsb_count( extern const struct iomap_ops xfs_buffered_write_iomap_ops; extern const struct iomap_ops xfs_direct_write_iomap_ops; +extern const struct iomap_ops xfs_zoned_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; extern const struct iomap_ops xfs_xattr_iomap_ops; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 207e0dadffc3..756bd3ca8e00 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -29,6 +29,7 @@ #include "xfs_xattr.h" #include "xfs_file.h" #include "xfs_bmap.h" +#include "xfs_zone_alloc.h" #include <linux/posix_acl.h> #include <linux/security.h> @@ -298,14 +299,14 @@ xfs_vn_create( return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL); } -STATIC int +STATIC struct dentry * xfs_vn_mkdir( struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - return xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL); + return ERR_PTR(xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL)); } STATIC struct dentry * @@ -573,17 +574,43 @@ xfs_stat_blksize( } static void -xfs_get_atomic_write_attr( +xfs_report_dioalign( struct xfs_inode *ip, - unsigned int *unit_min, - unsigned int *unit_max) + struct kstat *stat) { - if (!xfs_inode_can_atomicwrite(ip)) { - *unit_min = *unit_max = 0; - return; - } + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct block_device *bdev = target->bt_bdev; + + stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN; + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + + /* + * For COW inodes, we can only perform out of place writes of entire + * allocation units (blocks or RT extents). + * For writes smaller than the allocation unit, we must fall back to + * buffered I/O to perform read-modify-write cycles. At best this is + * highly inefficient; at worst it leads to page cache invalidation + * races. Tell applications to avoid this by reporting the larger write + * alignment in dio_offset_align, and the smaller read alignment in + * dio_read_offset_align. + */ + stat->dio_read_offset_align = bdev_logical_block_size(bdev); + if (xfs_is_cow_inode(ip)) + stat->dio_offset_align = xfs_inode_alloc_unitsize(ip); + else + stat->dio_offset_align = stat->dio_read_offset_align; +} + +static void +xfs_report_atomic_write( + struct xfs_inode *ip, + struct kstat *stat) +{ + unsigned int unit_min = 0, unit_max = 0; - *unit_min = *unit_max = ip->i_mount->m_sb.sb_blocksize; + if (xfs_inode_can_atomicwrite(ip)) + unit_min = unit_max = ip->i_mount->m_sb.sb_blocksize; + generic_fill_statx_atomic_writes(stat, unit_min, unit_max); } STATIC int @@ -647,22 +674,10 @@ xfs_vn_getattr( stat->rdev = inode->i_rdev; break; case S_IFREG: - if (request_mask & STATX_DIOALIGN) { - struct xfs_buftarg *target = xfs_inode_buftarg(ip); - struct block_device *bdev = target->bt_bdev; - - stat->result_mask |= STATX_DIOALIGN; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - } - if (request_mask & STATX_WRITE_ATOMIC) { - unsigned int unit_min, unit_max; - - xfs_get_atomic_write_attr(ip, &unit_min, - &unit_max); - generic_fill_statx_atomic_writes(stat, - unit_min, unit_max); - } + if (request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN)) + xfs_report_dioalign(ip, stat); + if (request_mask & STATX_WRITE_ATOMIC) + xfs_report_atomic_write(ip, stat); fallthrough; default: stat->blksize = xfs_stat_blksize(ip); @@ -840,6 +855,7 @@ xfs_setattr_size( uint lock_flags = 0; uint resblks = 0; bool did_zeroing = false; + struct xfs_zone_alloc_ctx ac = { }; xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL); ASSERT(S_ISREG(inode->i_mode)); @@ -876,6 +892,28 @@ xfs_setattr_size( inode_dio_wait(inode); /* + * Normally xfs_zoned_space_reserve is supposed to be called outside the + * IOLOCK. For truncate we can't do that since ->setattr is called with + * it already held by the VFS. So for now chicken out and try to + * allocate space under it. + * + * To avoid deadlocks this means we can't block waiting for space, which + * can lead to spurious -ENOSPC if there are no directly available + * blocks. We mitigate this a bit by allowing zeroing to dip into the + * reserved pool, but eventually the VFS calling convention needs to + * change. + */ + if (xfs_is_zoned_inode(ip)) { + error = xfs_zoned_space_reserve(ip, 1, + XFS_ZR_NOWAIT | XFS_ZR_RESERVED, &ac); + if (error) { + if (error == -EAGAIN) + return -ENOSPC; + return error; + } + } + + /* * File data changes must be complete before we start the transaction to * modify the inode. This needs to be done before joining the inode to * the transaction because the inode cannot be unlocked once it is a @@ -888,11 +926,14 @@ xfs_setattr_size( if (newsize > oldsize) { trace_xfs_zero_eof(ip, oldsize, newsize - oldsize); error = xfs_zero_range(ip, oldsize, newsize - oldsize, - &did_zeroing); + &ac, &did_zeroing); } else { - error = xfs_truncate_page(ip, newsize, &did_zeroing); + error = xfs_truncate_page(ip, newsize, &ac, &did_zeroing); } + if (xfs_is_zoned_inode(ip)) + xfs_zoned_space_unreserve(ip, &ac); + if (error) return error; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 05daad8a8d34..980aabc49512 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -20,6 +20,7 @@ #include "xfs_sysfs.h" #include "xfs_sb.h" #include "xfs_health.h" +#include "xfs_zone_alloc.h" struct kmem_cache *xfs_log_ticket_cache; @@ -2744,8 +2745,6 @@ xfs_log_ticket_regrant( if (!ticket->t_cnt) { xlog_grant_add_space(&log->l_reserve_head, ticket->t_unit_res); trace_xfs_log_ticket_regrant_exit(log, ticket); - - ticket->t_curr_res = ticket->t_unit_res; } xfs_log_ticket_put(ticket); @@ -2889,7 +2888,7 @@ xlog_force_and_check_iclog( * * 1. the current iclog is active and has no data; the previous iclog * is in the active or dirty state. - * 2. the current iclog is drity, and the previous iclog is in the + * 2. the current iclog is dirty, and the previous iclog is in the * active or dirty state. * * We may sleep if: @@ -3542,6 +3541,9 @@ xlog_force_shutdown( spin_unlock(&log->l_icloglock); wake_up_var(&log->l_opstate); + if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(log->l_mp)) + xfs_zoned_wake_all(log->l_mp); + return log_error; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 0af3d477197b..2f76531842f8 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1820,6 +1820,10 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = { &xlog_xmd_item_ops, &xlog_rtefi_item_ops, &xlog_rtefd_item_ops, + &xlog_rtrui_item_ops, + &xlog_rtrud_item_ops, + &xlog_rtcui_item_ops, + &xlog_rtcud_item_ops, }; static const struct xlog_recover_item_ops * @@ -3376,7 +3380,7 @@ xlog_do_recover( */ xfs_buf_lock(bp); xfs_buf_hold(bp); - error = _xfs_buf_read(bp, XBF_READ); + error = _xfs_buf_read(bp); if (error) { if (!xlog_is_shutdown(log)) { xfs_buf_ioerror_alert(bp, __this_address); diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 6ed485ff2756..15d410d16bb2 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -173,6 +173,10 @@ xfs_warn_experimental( .opstate = XFS_OPSTATE_WARNED_METADIR, .name = "metadata directory tree", }, + [XFS_EXPERIMENTAL_ZONED] = { + .opstate = XFS_OPSTATE_WARNED_ZONED, + .name = "zoned RT device", + }, }; ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX); BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX); diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 7fb36ced9df7..a92a4d09c8e9 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -99,6 +99,7 @@ enum xfs_experimental_feat { XFS_EXPERIMENTAL_EXCHRANGE, XFS_EXPERIMENTAL_PPTR, XFS_EXPERIMENTAL_METADIR, + XFS_EXPERIMENTAL_ZONED, XFS_EXPERIMENTAL_MAX, }; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 5918f433dba7..00b53f479ece 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -37,7 +37,10 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/stats.h" +#include "xfs_zone_alloc.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); static int xfs_uuid_table_size; @@ -179,14 +182,11 @@ xfs_readsb( /* * Allocate a (locked) buffer to hold the superblock. This will be kept - * around at all times to optimize access to the superblock. Therefore, - * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count - * elevated. + * around at all times to optimize access to the superblock. */ reread: error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), XBF_NO_IOACCT, &bp, - buf_ops); + BTOBB(sector_size), &bp, buf_ops); if (error) { if (loud) xfs_warn(mp, "SB validate failed with error %d.", error); @@ -414,7 +414,7 @@ xfs_check_sizes( } error = xfs_buf_read_uncached(mp->m_ddev_targp, d - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); + XFS_FSS_TO_BB(mp, 1), &bp, NULL); if (error) { xfs_warn(mp, "last sector read failed"); return error; @@ -431,7 +431,7 @@ xfs_check_sizes( } error = xfs_buf_read_uncached(mp->m_logdev_targp, d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); + XFS_FSB_TO_BB(mp, 1), &bp, NULL); if (error) { xfs_warn(mp, "log device read failed"); return error; @@ -462,22 +462,38 @@ xfs_mount_reset_sbqflags( return xfs_sync_sb(mp, false); } +static const char *const xfs_free_pool_name[] = { + [XC_FREE_BLOCKS] = "free blocks", + [XC_FREE_RTEXTENTS] = "free rt extents", + [XC_FREE_RTAVAILABLE] = "available rt extents", +}; + uint64_t -xfs_default_resblks(xfs_mount_t *mp) +xfs_default_resblks( + struct xfs_mount *mp, + enum xfs_free_counter ctr) { - uint64_t resblks; - - /* - * We default to 5% or 8192 fsbs of space reserved, whichever is - * smaller. This is intended to cover concurrent allocation - * transactions when we initially hit enospc. These each require a 4 - * block reservation. Hence by default we cover roughly 2000 concurrent - * allocation reservations. - */ - resblks = mp->m_sb.sb_dblocks; - do_div(resblks, 20); - resblks = min_t(uint64_t, resblks, 8192); - return resblks; + switch (ctr) { + case XC_FREE_BLOCKS: + /* + * Default to 5% or 8192 FSBs of space reserved, whichever is + * smaller. + * + * This is intended to cover concurrent allocation transactions + * when we initially hit ENOSPC. These each require a 4 block + * reservation. Hence by default we cover roughly 2000 + * concurrent allocation reservations. + */ + return min(div_u64(mp->m_sb.sb_dblocks, 20), 8192ULL); + case XC_FREE_RTEXTENTS: + case XC_FREE_RTAVAILABLE: + if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) + return xfs_zoned_default_resblks(mp, ctr); + return 0; + default: + ASSERT(0); + return 0; + } } /* Ensure the summary counts are correct. */ @@ -544,7 +560,7 @@ xfs_check_summary_counts( * If we're mounting the rt volume after recovering the log, recompute * frextents from the rtbitmap file to fix the inconsistency. */ - if (xfs_has_realtime(mp) && !xfs_is_clean(mp)) { + if (xfs_has_realtime(mp) && !xfs_has_zoned(mp) && !xfs_is_clean(mp)) { error = xfs_rtalloc_reinit_frextents(mp); if (error) return error; @@ -650,6 +666,15 @@ xfs_agbtree_compute_maxlevels( mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels); } +/* Compute maximum possible height for realtime btree types for this fs. */ +static inline void +xfs_rtbtree_compute_maxlevels( + struct xfs_mount *mp) +{ + mp->m_rtbtree_maxlevels = max(mp->m_rtrmap_maxlevels, + mp->m_rtrefc_maxlevels); +} + /* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct @@ -670,6 +695,7 @@ xfs_mountfs( uint quotamount = 0; uint quotaflags = 0; int error = 0; + int i; xfs_sb_mount_common(mp, sbp); @@ -718,9 +744,12 @@ xfs_mountfs( xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK); xfs_mount_setup_inode_geom(mp); xfs_rmapbt_compute_maxlevels(mp); + xfs_rtrmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); xfs_agbtree_compute_maxlevels(mp); + xfs_rtbtree_compute_maxlevels(mp); /* * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks @@ -736,27 +765,15 @@ xfs_mountfs( /* enable fail_at_unmount as default */ mp->m_fail_unmount = true; - super_set_sysfs_name_id(mp->m_super); - - error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, - NULL, mp->m_super->s_id); - if (error) - goto out; - - error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype, - &mp->m_kobj, "stats"); + error = xfs_mount_sysfs_init(mp); if (error) - goto out_remove_sysfs; + goto out_remove_scrub_stats; xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs); - error = xfs_error_sysfs_init(mp); - if (error) - goto out_remove_scrub_stats; - error = xfs_errortag_init(mp); if (error) - goto out_remove_error_sysfs; + goto out_remove_sysfs; error = xfs_uuid_mount(mp); if (error) @@ -1020,6 +1037,12 @@ xfs_mountfs( if (xfs_is_readonly(mp) && !xfs_has_norecovery(mp)) xfs_log_clean(mp); + if (xfs_has_zoned(mp)) { + error = xfs_mount_zones(mp); + if (error) + goto out_rtunmount; + } + /* * Complete the quota initialisation, post-log-replay component. */ @@ -1035,22 +1058,28 @@ xfs_mountfs( * privileged transactions. This is needed so that transaction * space required for critical operations can dip into this pool * when at ENOSPC. This is needed for operations like create with - * attr, unwritten extent conversion at ENOSPC, etc. Data allocations - * are not allowed to use this reserved space. + * attr, unwritten extent conversion at ENOSPC, garbage collection + * etc. Data allocations are not allowed to use this reserved space. * * This may drive us straight to ENOSPC on mount, but that implies * we were already there on the last unmount. Warn if this occurs. */ if (!xfs_is_readonly(mp)) { - error = xfs_reserve_blocks(mp, xfs_default_resblks(mp)); - if (error) - xfs_warn(mp, - "Unable to allocate reserve blocks. Continuing without reserve pool."); + for (i = 0; i < XC_FREE_NR; i++) { + error = xfs_reserve_blocks(mp, i, + xfs_default_resblks(mp, i)); + if (error) + xfs_warn(mp, +"Unable to allocate reserve blocks. Continuing without reserve pool for %s.", + xfs_free_pool_name[i]); + } /* Reserve AG blocks for future btree expansion. */ error = xfs_fs_reserve_ag_blocks(mp); if (error && error != -ENOSPC) goto out_agresv; + + xfs_zone_gc_start(mp); } return 0; @@ -1058,6 +1087,8 @@ xfs_mountfs( out_agresv: xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); + if (xfs_has_zoned(mp)) + xfs_unmount_zones(mp); out_rtunmount: xfs_rtunmount_inodes(mp); out_rele_rip: @@ -1105,13 +1136,10 @@ xfs_mountfs( xfs_uuid_unmount(mp); out_remove_errortag: xfs_errortag_del(mp); - out_remove_error_sysfs: - xfs_error_sysfs_del(mp); + out_remove_sysfs: + xfs_mount_sysfs_del(mp); out_remove_scrub_stats: xchk_stats_unregister(mp->m_scrub_stats); - xfs_sysfs_del(&mp->m_stats.xs_kobj); - out_remove_sysfs: - xfs_sysfs_del(&mp->m_kobj); out: return error; } @@ -1137,8 +1165,12 @@ xfs_unmountfs( xfs_inodegc_flush(mp); xfs_blockgc_stop(mp); + if (!test_bit(XFS_OPSTATE_READONLY, &mp->m_opstate)) + xfs_zone_gc_stop(mp); xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); + if (xfs_has_zoned(mp)) + xfs_unmount_zones(mp); xfs_rtunmount_inodes(mp); xfs_irele(mp->m_rootip); if (mp->m_metadirip) @@ -1162,7 +1194,7 @@ xfs_unmountfs( * we only every apply deltas to the superblock and hence the incore * value does not matter.... */ - error = xfs_reserve_blocks(mp, 0); + error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, 0); if (error) xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); @@ -1184,10 +1216,8 @@ xfs_unmountfs( xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount); xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount); xfs_errortag_del(mp); - xfs_error_sysfs_del(mp); xchk_stats_unregister(mp->m_scrub_stats); - xfs_sysfs_del(&mp->m_stats.xs_kobj); - xfs_sysfs_del(&mp->m_kobj); + xfs_mount_sysfs_del(mp); } /* @@ -1209,52 +1239,67 @@ xfs_fs_writable( return true; } +/* + * Estimate the amount of free space that is not available to userspace and is + * not explicitly reserved from the incore fdblocks. This includes: + * + * - The minimum number of blocks needed to support splitting a bmap btree + * - The blocks currently in use by the freespace btrees because they record + * the actual blocks that will fill per-AG metadata space reservations + */ +uint64_t +xfs_freecounter_unavailable( + struct xfs_mount *mp, + enum xfs_free_counter ctr) +{ + if (ctr != XC_FREE_BLOCKS) + return 0; + return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); +} + void xfs_add_freecounter( struct xfs_mount *mp, - struct percpu_counter *counter, + enum xfs_free_counter ctr, uint64_t delta) { - bool has_resv_pool = (counter == &mp->m_fdblocks); + struct xfs_freecounter *counter = &mp->m_free[ctr]; uint64_t res_used; /* * If the reserve pool is depleted, put blocks back into it first. * Most of the time the pool is full. */ - if (!has_resv_pool || mp->m_resblks == mp->m_resblks_avail) { - percpu_counter_add(counter, delta); + if (likely(counter->res_avail == counter->res_total)) { + percpu_counter_add(&counter->count, delta); return; } spin_lock(&mp->m_sb_lock); - res_used = mp->m_resblks - mp->m_resblks_avail; + res_used = counter->res_total - counter->res_avail; if (res_used > delta) { - mp->m_resblks_avail += delta; + counter->res_avail += delta; } else { delta -= res_used; - mp->m_resblks_avail = mp->m_resblks; - percpu_counter_add(counter, delta); + counter->res_avail = counter->res_total; + percpu_counter_add(&counter->count, delta); } spin_unlock(&mp->m_sb_lock); } + +/* Adjust in-core free blocks or RT extents. */ int xfs_dec_freecounter( struct xfs_mount *mp, - struct percpu_counter *counter, + enum xfs_free_counter ctr, uint64_t delta, bool rsvd) { - int64_t lcounter; - uint64_t set_aside = 0; + struct xfs_freecounter *counter = &mp->m_free[ctr]; s32 batch; - bool has_resv_pool; - ASSERT(counter == &mp->m_fdblocks || counter == &mp->m_frextents); - has_resv_pool = (counter == &mp->m_fdblocks); - if (rsvd) - ASSERT(has_resv_pool); + ASSERT(ctr < XC_FREE_NR); /* * Taking blocks away, need to be more accurate the closer we @@ -1264,7 +1309,7 @@ xfs_dec_freecounter( * then make everything serialise as we are real close to * ENOSPC. */ - if (__percpu_counter_compare(counter, 2 * XFS_FDBLOCKS_BATCH, + if (__percpu_counter_compare(&counter->count, 2 * XFS_FDBLOCKS_BATCH, XFS_FDBLOCKS_BATCH) < 0) batch = 1; else @@ -1281,34 +1326,34 @@ xfs_dec_freecounter( * problems (i.e. transaction abort, pagecache discards, etc.) than * slightly premature -ENOSPC. */ - if (has_resv_pool) - set_aside = xfs_fdblocks_unavailable(mp); - percpu_counter_add_batch(counter, -((int64_t)delta), batch); - if (__percpu_counter_compare(counter, set_aside, - XFS_FDBLOCKS_BATCH) >= 0) { - /* we had space! */ - return 0; - } - - /* - * lock up the sb for dipping into reserves before releasing the space - * that took us to ENOSPC. - */ - spin_lock(&mp->m_sb_lock); - percpu_counter_add(counter, delta); - if (!has_resv_pool || !rsvd) - goto fdblocks_enospc; - - lcounter = (long long)mp->m_resblks_avail - delta; - if (lcounter >= 0) { - mp->m_resblks_avail = lcounter; + percpu_counter_add_batch(&counter->count, -((int64_t)delta), batch); + if (__percpu_counter_compare(&counter->count, + xfs_freecounter_unavailable(mp, ctr), + XFS_FDBLOCKS_BATCH) < 0) { + /* + * Lock up the sb for dipping into reserves before releasing the + * space that took us to ENOSPC. + */ + spin_lock(&mp->m_sb_lock); + percpu_counter_add(&counter->count, delta); + if (!rsvd) + goto fdblocks_enospc; + if (delta > counter->res_avail) { + if (ctr == XC_FREE_BLOCKS) + xfs_warn_once(mp, +"Reserve blocks depleted! Consider increasing reserve pool size."); + goto fdblocks_enospc; + } + counter->res_avail -= delta; + trace_xfs_freecounter_reserved(mp, ctr, delta, _RET_IP_); spin_unlock(&mp->m_sb_lock); - return 0; } - xfs_warn_once(mp, -"Reserve blocks depleted! Consider increasing reserve pool size."); + + /* we had space! */ + return 0; fdblocks_enospc: + trace_xfs_freecounter_enospc(mp, ctr, delta, _RET_IP_); spin_unlock(&mp->m_sb_lock); return -ENOSPC; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index db9dade7d22a..e5192c12e7ac 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -98,11 +98,41 @@ struct xfs_groups { uint8_t blklog; /* + * Zoned devices can have gaps beyond the usable capacity of a zone and + * the end in the LBA/daddr address space. In other words, the hardware + * equivalent to the RT groups already takes care of the power of 2 + * alignment for us. In this case the sparse FSB/RTB address space maps + * 1:1 to the device address space. + */ + bool has_daddr_gaps; + + /* * Mask to extract the group-relative block number from a FSB. * For a pre-rtgroups filesystem we pretend to have one very large * rtgroup, so this mask must be 64-bit. */ uint64_t blkmask; + + /* + * Start of the first group in the device. This is used to support a + * RT device following the data device on the same block device for + * SMR hard drives. + */ + xfs_fsblock_t start_fsb; +}; + +struct xfs_freecounter { + /* free blocks for general use: */ + struct percpu_counter count; + + /* total reserved blocks: */ + uint64_t res_total; + + /* available reserved blocks: */ + uint64_t res_avail; + + /* reserved blks @ remount,ro: */ + uint64_t res_saved; }; /* @@ -158,13 +188,20 @@ typedef struct xfs_mount { uint m_bmap_dmnr[2]; /* min bmap btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ + uint m_rtrmap_mxr[2]; /* max rtrmap btree records */ + uint m_rtrmap_mnr[2]; /* min rtrmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ + uint m_rtrefc_mxr[2]; /* max rtrefc btree records */ + uint m_rtrefc_mnr[2]; /* min rtrefc btree records */ uint m_alloc_maxlevels; /* max alloc btree levels */ uint m_bm_maxlevels[2]; /* max bmap btree levels */ uint m_rmap_maxlevels; /* max rmap btree levels */ + uint m_rtrmap_maxlevels; /* max rtrmap btree level */ uint m_refc_maxlevels; /* max refcount btree level */ + uint m_rtrefc_maxlevels; /* max rtrefc btree level */ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */ + unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ uint m_alloc_set_aside; /* space we can't use */ uint m_ag_max_usable; /* max space per AG */ @@ -191,6 +228,8 @@ typedef struct xfs_mount { bool m_fail_unmount; bool m_finobt_nores; /* no per-AG finobt resv. */ bool m_update_sb; /* sb needs update in mount */ + unsigned int m_max_open_zones; + unsigned int m_zonegc_low_space; /* * Bitsets of per-fs metadata that have been checked and/or are sick. @@ -215,8 +254,8 @@ typedef struct xfs_mount { spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */ struct percpu_counter m_icount; /* allocated inodes counter */ struct percpu_counter m_ifree; /* free inodes counter */ - struct percpu_counter m_fdblocks; /* free block counter */ - struct percpu_counter m_frextents; /* free rt extent counter */ + + struct xfs_freecounter m_free[XC_FREE_NR]; /* * Count of data device blocks reserved for delayed allocations, @@ -238,10 +277,8 @@ typedef struct xfs_mount { atomic64_t m_allocbt_blks; struct xfs_groups m_groups[XG_TYPE_MAX]; - uint64_t m_resblks; /* total reserved blocks */ - uint64_t m_resblks_avail;/* available reserved blocks */ - uint64_t m_resblks_save; /* reserved blks @ remount,ro */ struct delayed_work m_reclaim_work; /* background inode reclaim */ + struct xfs_zone_info *m_zone_info; /* zone allocator information */ struct dentry *m_debugfs; /* debugfs parent */ struct xfs_kobj m_kobj; struct xfs_kobj m_error_kobj; @@ -251,10 +288,16 @@ typedef struct xfs_mount { #ifdef CONFIG_XFS_ONLINE_SCRUB_STATS struct xchk_stats *m_scrub_stats; #endif + struct xfs_kobj m_zoned_kobj; xfs_agnumber_t m_agfrotor; /* last ag where space found */ atomic_t m_agirotor; /* last ag dir inode alloced */ atomic_t m_rtgrotor; /* last rtgroup rtpicked */ + struct mutex m_metafile_resv_lock; + uint64_t m_metafile_resv_target; + uint64_t m_metafile_resv_used; + uint64_t m_metafile_resv_avail; + /* Memory shrinker to throttle and reprioritize inodegc */ struct shrinker *m_inodegc_shrinker; /* @@ -329,8 +372,10 @@ typedef struct xfs_mount { #define XFS_FEAT_NREXT64 (1ULL << 26) /* large extent counters */ #define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */ #define XFS_FEAT_METADIR (1ULL << 28) /* metadata directory tree */ +#define XFS_FEAT_ZONED (1ULL << 29) /* zoned RT device */ /* Mount features */ +#define XFS_FEAT_NOLIFETIME (1ULL << 47) /* disable lifetime hints */ #define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */ #define XFS_FEAT_NOALIGN (1ULL << 49) /* ignore alignment */ #define XFS_FEAT_ALLOCSIZE (1ULL << 50) /* user specified allocation size */ @@ -350,7 +395,7 @@ typedef struct xfs_mount { #define XFS_FEAT_NOUUID (1ULL << 63) /* ignore uuid during mount */ #define __XFS_HAS_FEAT(name, NAME) \ -static inline bool xfs_has_ ## name (struct xfs_mount *mp) \ +static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \ { \ return mp->m_features & XFS_FEAT_ ## NAME; \ } @@ -385,17 +430,38 @@ __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR) __XFS_HAS_FEAT(large_extent_counts, NREXT64) __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE) __XFS_HAS_FEAT(metadir, METADIR) +__XFS_HAS_FEAT(zoned, ZONED) +__XFS_HAS_FEAT(nolifetime, NOLIFETIME) -static inline bool xfs_has_rtgroups(struct xfs_mount *mp) +static inline bool xfs_has_rtgroups(const struct xfs_mount *mp) { /* all metadir file systems also allow rtgroups */ return xfs_has_metadir(mp); } -static inline bool xfs_has_rtsb(struct xfs_mount *mp) +static inline bool xfs_has_rtsb(const struct xfs_mount *mp) { /* all rtgroups filesystems with an rt section have an rtsb */ - return xfs_has_rtgroups(mp) && xfs_has_realtime(mp); + return xfs_has_rtgroups(mp) && + xfs_has_realtime(mp) && + !xfs_has_zoned(mp); +} + +static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp) +{ + return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && + xfs_has_rmapbt(mp); +} + +static inline bool xfs_has_rtreflink(const struct xfs_mount *mp) +{ + return xfs_has_metadir(mp) && xfs_has_realtime(mp) && + xfs_has_reflink(mp); +} + +static inline bool xfs_has_nonzoned(const struct xfs_mount *mp) +{ + return !xfs_has_zoned(mp); } /* @@ -501,6 +567,10 @@ __XFS_HAS_FEAT(nouuid, NOUUID) #define XFS_OPSTATE_WARNED_METADIR 17 /* Filesystem should use qflags to determine quotaon status */ #define XFS_OPSTATE_RESUMING_QUOTAON 18 +/* Kernel has logged a warning about zoned RT device being used on this fs. */ +#define XFS_OPSTATE_WARNED_ZONED 19 +/* (Zoned) GC is in progress */ +#define XFS_OPSTATE_ZONEGC_RUNNING 20 #define __XFS_IS_OPSTATE(name, NAME) \ static inline bool xfs_is_ ## name (struct xfs_mount *mp) \ @@ -545,6 +615,7 @@ static inline bool xfs_clear_resuming_quotaon(struct xfs_mount *mp) #endif /* CONFIG_XFS_QUOTA */ __XFS_IS_OPSTATE(done_with_log_incompat, UNSET_LOG_INCOMPAT) __XFS_IS_OPSTATE(using_logged_xattrs, USE_LARP) +__XFS_IS_OPSTATE(zonegc_running, ZONEGC_RUNNING) static inline bool xfs_should_warn(struct xfs_mount *mp, long nr) @@ -614,7 +685,8 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) } extern void xfs_uuid_table_free(void); -extern uint64_t xfs_default_resblks(xfs_mount_t *mp); +uint64_t xfs_default_resblks(struct xfs_mount *mp, + enum xfs_free_counter ctr); extern int xfs_mountfs(xfs_mount_t *mp); extern void xfs_unmountfs(xfs_mount_t *); @@ -627,45 +699,74 @@ extern void xfs_unmountfs(xfs_mount_t *); */ #define XFS_FDBLOCKS_BATCH 1024 +uint64_t xfs_freecounter_unavailable(struct xfs_mount *mp, + enum xfs_free_counter ctr); + /* - * Estimate the amount of free space that is not available to userspace and is - * not explicitly reserved from the incore fdblocks. This includes: - * - * - The minimum number of blocks needed to support splitting a bmap btree - * - The blocks currently in use by the freespace btrees because they record - * the actual blocks that will fill per-AG metadata space reservations + * Sum up the freecount, but never return negative values. */ -static inline uint64_t -xfs_fdblocks_unavailable( - struct xfs_mount *mp) +static inline s64 xfs_sum_freecounter(struct xfs_mount *mp, + enum xfs_free_counter ctr) { - return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); + return percpu_counter_sum_positive(&mp->m_free[ctr].count); } -int xfs_dec_freecounter(struct xfs_mount *mp, struct percpu_counter *counter, +/* + * Same as above, but does return negative values. Mostly useful for + * special cases like repair and tracing. + */ +static inline s64 xfs_sum_freecounter_raw(struct xfs_mount *mp, + enum xfs_free_counter ctr) +{ + return percpu_counter_sum(&mp->m_free[ctr].count); +} + +/* + * This just provides and estimate without the cpu-local updates, use + * xfs_sum_freecounter for the exact value. + */ +static inline s64 xfs_estimate_freecounter(struct xfs_mount *mp, + enum xfs_free_counter ctr) +{ + return percpu_counter_read_positive(&mp->m_free[ctr].count); +} + +static inline int xfs_compare_freecounter(struct xfs_mount *mp, + enum xfs_free_counter ctr, s64 rhs, s32 batch) +{ + return __percpu_counter_compare(&mp->m_free[ctr].count, rhs, batch); +} + +static inline void xfs_set_freecounter(struct xfs_mount *mp, + enum xfs_free_counter ctr, uint64_t val) +{ + percpu_counter_set(&mp->m_free[ctr].count, val); +} + +int xfs_dec_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t delta, bool rsvd); -void xfs_add_freecounter(struct xfs_mount *mp, struct percpu_counter *counter, +void xfs_add_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t delta); static inline int xfs_dec_fdblocks(struct xfs_mount *mp, uint64_t delta, bool reserved) { - return xfs_dec_freecounter(mp, &mp->m_fdblocks, delta, reserved); + return xfs_dec_freecounter(mp, XC_FREE_BLOCKS, delta, reserved); } static inline void xfs_add_fdblocks(struct xfs_mount *mp, uint64_t delta) { - xfs_add_freecounter(mp, &mp->m_fdblocks, delta); + xfs_add_freecounter(mp, XC_FREE_BLOCKS, delta); } static inline int xfs_dec_frextents(struct xfs_mount *mp, uint64_t delta) { - return xfs_dec_freecounter(mp, &mp->m_frextents, delta, false); + return xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, delta, false); } static inline void xfs_add_frextents(struct xfs_mount *mp, uint64_t delta) { - xfs_add_freecounter(mp, &mp->m_frextents, delta); + xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, delta); } extern int xfs_readsb(xfs_mount_t *, int); @@ -687,5 +788,9 @@ int xfs_add_incompat_log_feature(struct xfs_mount *mp, uint32_t feature); bool xfs_clear_incompat_log_features(struct xfs_mount *mp); void xfs_mod_delalloc(struct xfs_inode *ip, int64_t data_delta, int64_t ind_delta); +static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta) +{ + percpu_counter_add(&mp->m_delalloc_blks, delta); +} #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 0b0b0f31aca2..ed8d8ed42f0a 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -19,6 +19,9 @@ #include "xfs_rtalloc.h" #include "xfs_trans.h" #include "xfs_ag.h" +#include "xfs_notify_failure.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include <linux/mm.h> #include <linux/dax.h> @@ -227,23 +230,42 @@ xfs_dax_notify_logdev_failure( } static int -xfs_dax_notify_ddev_failure( +xfs_dax_notify_dev_failure( struct xfs_mount *mp, - xfs_daddr_t daddr, - xfs_daddr_t bblen, - int mf_flags) + u64 offset, + u64 len, + int mf_flags, + enum xfs_group_type type) { struct xfs_failure_info notify = { .mf_flags = mf_flags }; struct xfs_trans *tp = NULL; struct xfs_btree_cur *cur = NULL; - struct xfs_buf *agf_bp = NULL; int error = 0; bool kernel_frozen = false; - xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); - xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, - daddr + bblen - 1); - xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + uint32_t start_gno, end_gno; + xfs_fsblock_t start_bno, end_bno; + xfs_daddr_t daddr; + uint64_t bblen; + struct xfs_group *xg = NULL; + + if (!xfs_has_rmapbt(mp)) { + xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + error = xfs_dax_translate_range(type == XG_TYPE_RTG ? + mp->m_rtdev_targp : mp->m_ddev_targp, + offset, len, &daddr, &bblen); + if (error) + return error; + + if (type == XG_TYPE_RTG) { + start_bno = xfs_daddr_to_rtb(mp, daddr); + end_bno = xfs_daddr_to_rtb(mp, daddr + bblen - 1); + } else { + start_bno = XFS_DADDR_TO_FSB(mp, daddr); + end_bno = XFS_DADDR_TO_FSB(mp, daddr + bblen - 1); + } if (mf_flags & MF_MEM_PRE_REMOVE) { xfs_info(mp, "Device is about to be removed!"); @@ -262,46 +284,58 @@ xfs_dax_notify_ddev_failure( if (error) goto out; - for (; agno <= end_agno; agno++) { + start_gno = xfs_fsb_to_gno(mp, start_bno, type); + end_gno = xfs_fsb_to_gno(mp, end_bno, type); + while ((xg = xfs_group_next_range(mp, xg, start_gno, end_gno, type))) { + struct xfs_buf *agf_bp = NULL; + struct xfs_rtgroup *rtg = NULL; struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; - struct xfs_agf *agf; - struct xfs_perag *pag; - xfs_agblock_t range_agend; - pag = xfs_perag_get(mp, agno); - error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); - if (error) { - xfs_perag_put(pag); - break; - } + if (type == XG_TYPE_AG) { + struct xfs_perag *pag = to_perag(xg); - cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); + if (error) { + xfs_perag_put(pag); + break; + } + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + } else { + rtg = to_rtg(xg); + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + } /* * Set the rmap range from ri_low to ri_high, which represents * a [start, end] where we looking for the files or metadata. */ memset(&ri_high, 0xFF, sizeof(ri_high)); - ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); - if (agno == end_agno) - ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + if (xg->xg_gno == start_gno) + ri_low.rm_startblock = + xfs_fsb_to_gbno(mp, start_bno, type); + if (xg->xg_gno == end_gno) + ri_high.rm_startblock = + xfs_fsb_to_gbno(mp, end_bno, type); - agf = agf_bp->b_addr; - range_agend = min(be32_to_cpu(agf->agf_length) - 1, - ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = range_agend + 1 - ri_low.rm_startblock; + notify.blockcount = min(xg->xg_block_count, + ri_high.rm_startblock + 1) - + ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agf_bp); - xfs_perag_put(pag); - if (error) + if (agf_bp) + xfs_trans_brelse(tp, agf_bp); + if (rtg) + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + if (error) { + xfs_group_put(xg); break; - - fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } } xfs_trans_cancel(tp); @@ -336,37 +370,20 @@ xfs_dax_notify_failure( int mf_flags) { struct xfs_mount *mp = dax_holder(dax_dev); - xfs_daddr_t daddr; - uint64_t bblen; - int error; if (!(mp->m_super->s_flags & SB_BORN)) { xfs_warn(mp, "filesystem is not ready for notify_failure()!"); return -EIO; } - if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { - xfs_debug(mp, - "notify_failure() not supported on realtime device!"); - return -EOPNOTSUPP; - } - - if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && - mp->m_logdev_targp != mp->m_ddev_targp) { + if (mp->m_logdev_targp != mp->m_ddev_targp && + mp->m_logdev_targp->bt_daxdev == dax_dev) { return xfs_dax_notify_logdev_failure(mp, offset, len, mf_flags); } - if (!xfs_has_rmapbt(mp)) { - xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); - return -EOPNOTSUPP; - } - - error = xfs_dax_translate_range(mp->m_ddev_targp, offset, len, &daddr, - &bblen); - if (error) - return error; - - return xfs_dax_notify_ddev_failure(mp, daddr, bblen, mf_flags); + return xfs_dax_notify_dev_failure(mp, offset, len, mf_flags, + (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) ? + XG_TYPE_RTG : XG_TYPE_AG); } const struct dax_holder_operations xfs_dax_holder_operations = { diff --git a/fs/xfs/xfs_notify_failure.h b/fs/xfs/xfs_notify_failure.h new file mode 100644 index 000000000000..8d08ec29dd29 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_NOTIFY_FAILURE_H__ +#define __XFS_NOTIFY_FAILURE_H__ + +extern const struct dax_holder_operations xfs_dax_holder_operations; + +#endif /* __XFS_NOTIFY_FAILURE_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index dc8b1010d4d3..417439b58785 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -230,10 +230,10 @@ xfs_qm_unmount_rt( if (!rtg) return; - if (rtg->rtg_inodes[XFS_RTGI_BITMAP]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_BITMAP]); - if (rtg->rtg_inodes[XFS_RTGI_SUMMARY]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + if (rtg_bitmap(rtg)) + xfs_qm_dqdetach(rtg_bitmap(rtg)); + if (rtg_summary(rtg)) + xfs_qm_dqdetach(rtg_summary(rtg)); xfs_rtgroup_rele(rtg); } @@ -428,6 +428,8 @@ void xfs_qm_dqdetach( xfs_inode_t *ip) { + if (xfs_is_metadir_inode(ip)) + return; if (!(ip->i_udquot || ip->i_gdquot || ip->i_pdquot)) return; @@ -1709,7 +1711,8 @@ xfs_qm_mount_quotas( * immediately. We only support rtquota if rtgroups are enabled to * avoid problems with older kernels. */ - if (mp->m_sb.sb_rextents && !xfs_has_rtgroups(mp)) { + if (mp->m_sb.sb_rextents && + (!xfs_has_rtgroups(mp) || xfs_has_zoned(mp))) { xfs_notice(mp, "Cannot turn on quotas for realtime filesystem"); mp->m_qflags = 0; goto write_changes; diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index db5b8afd9d1b..245d754f382a 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -40,7 +40,6 @@ xfs_fill_statvfs_from_dquot( statp->f_blocks = min(statp->f_blocks, limit); statp->f_bfree = min(statp->f_bfree, remaining); - statp->f_bavail = min(statp->f_bavail, remaining); } limit = dqp->q_ino.softlimit ? @@ -79,6 +78,28 @@ xfs_qm_statvfs( } } +STATIC int +xfs_qm_validate_state_change( + struct xfs_mount *mp, + uint uqd, + uint gqd, + uint pqd) +{ + int state; + + /* Is quota state changing? */ + state = ((uqd && !XFS_IS_UQUOTA_ON(mp)) || + (!uqd && XFS_IS_UQUOTA_ON(mp)) || + (gqd && !XFS_IS_GQUOTA_ON(mp)) || + (!gqd && XFS_IS_GQUOTA_ON(mp)) || + (pqd && !XFS_IS_PQUOTA_ON(mp)) || + (!pqd && XFS_IS_PQUOTA_ON(mp))); + + return state && + (xfs_dev_is_read_only(mp, "changing quota state") || + xfs_has_norecovery(mp)); +} + int xfs_qm_newmount( xfs_mount_t *mp, @@ -98,24 +119,25 @@ xfs_qm_newmount( } /* - * If the device itself is read-only, we can't allow - * the user to change the state of quota on the mount - - * this would generate a transaction on the ro device, - * which would lead to an I/O error and shutdown + * If the device itself is read-only and/or in norecovery + * mode, we can't allow the user to change the state of + * quota on the mount - this would generate a transaction + * on the ro device, which would lead to an I/O error and + * shutdown. */ - if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) || - (!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) || - (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) || - (!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) || - (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || - (!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) && - xfs_dev_is_read_only(mp, "changing quota state")) { - xfs_warn(mp, "please mount with%s%s%s%s.", - (!quotaondisk ? "out quota" : ""), - (uquotaondisk ? " usrquota" : ""), - (gquotaondisk ? " grpquota" : ""), - (pquotaondisk ? " prjquota" : "")); + if (xfs_qm_validate_state_change(mp, uquotaondisk, + gquotaondisk, pquotaondisk)) { + + if (xfs_has_metadir(mp)) + xfs_warn(mp, + "metadir enabled, please mount without any quota mount options"); + else + xfs_warn(mp, "please mount with%s%s%s%s.", + (!quotaondisk ? "out quota" : ""), + (uquotaondisk ? " usrquota" : ""), + (gquotaondisk ? " grpquota" : ""), + (pquotaondisk ? " prjquota" : "")); return -EPERM; } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index d7565462af3d..105e6eb57620 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -29,11 +29,6 @@ struct xfs_buf; (XFS_IS_GQUOTA_ON(mp) && (ip)->i_gdquot == NULL) || \ (XFS_IS_PQUOTA_ON(mp) && (ip)->i_pdquot == NULL)) -#define XFS_IS_DQDETACHED(ip) \ - ((ip)->i_udquot == NULL && \ - (ip)->i_gdquot == NULL && \ - (ip)->i_pdquot == NULL) - #define XFS_QM_NEED_QUOTACHECK(mp) \ ((XFS_IS_UQUOTA_ON(mp) && \ (mp->m_sb.sb_qflags & XFS_UQUOTA_CHKD) == 0) || \ diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index bede1c96c330..fe2d7aab8554 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_cui_cache; struct kmem_cache *xfs_cud_cache; @@ -94,8 +95,9 @@ xfs_cui_item_format( ASSERT(atomic_read(&cuip->cui_next_extent) == cuip->cui_format.cui_nextents); + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); - cuip->cui_format.cui_type = XFS_LI_CUI; + cuip->cui_format.cui_type = lip->li_type; cuip->cui_format.cui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUI_FORMAT, &cuip->cui_format, @@ -138,12 +140,14 @@ xfs_cui_item_release( STATIC struct xfs_cui_log_item * xfs_cui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) - { struct xfs_cui_log_item *cuip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_CUI || item_type == XFS_LI_CUI_RT); + if (nextents > XFS_CUI_MAX_FAST_EXTENTS) cuip = kzalloc(xfs_cui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -151,7 +155,7 @@ xfs_cui_init( cuip = kmem_cache_zalloc(xfs_cui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); + xfs_log_item_init(mp, &cuip->cui_item, item_type, &xfs_cui_item_ops); cuip->cui_format.cui_nextents = nextents; cuip->cui_format.cui_id = (uintptr_t)(void *)cuip; atomic_set(&cuip->cui_next_extent, 0); @@ -190,7 +194,9 @@ xfs_cud_item_format( struct xfs_cud_log_item *cudp = CUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - cudp->cud_format.cud_type = XFS_LI_CUD; + ASSERT(lip->li_type == XFS_LI_CUD || lip->li_type == XFS_LI_CUD_RT); + + cudp->cud_format.cud_type = lip->li_type; cudp->cud_format.cud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUD_FORMAT, &cudp->cud_format, @@ -234,6 +240,14 @@ static inline struct xfs_refcount_intent *ci_entry(const struct list_head *e) return list_entry(e, struct xfs_refcount_intent, ri_list); } +static inline bool +xfs_cui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); + + return lip->li_type == XFS_LI_CUI_RT; +} + /* Sort refcount intents by AG. */ static int xfs_refcount_update_diff_items( @@ -282,18 +296,20 @@ xfs_refcount_update_log_item( } static struct xfs_log_item * -xfs_refcount_update_create_intent( +__xfs_refcount_update_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, - bool sort) + bool sort, + unsigned short item_type) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_cui_log_item *cuip = xfs_cui_init(mp, count); + struct xfs_cui_log_item *cuip; struct xfs_refcount_intent *ri; ASSERT(count > 0); + cuip = xfs_cui_init(mp, item_type, count); if (sort) list_sort(mp, items, xfs_refcount_update_diff_items); list_for_each_entry(ri, items, ri_list) @@ -301,6 +317,23 @@ xfs_refcount_update_create_intent( return &cuip->cui_item; } +static struct xfs_log_item * +xfs_refcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI); +} + +static inline unsigned short +xfs_cud_type_from_cui(const struct xfs_cui_log_item *cuip) +{ + return xfs_cui_item_isrt(&cuip->cui_item) ? XFS_LI_CUD_RT : XFS_LI_CUD; +} + /* Get an CUD so we can process all the deferred refcount updates. */ static struct xfs_log_item * xfs_refcount_update_create_done( @@ -312,8 +345,8 @@ xfs_refcount_update_create_done( struct xfs_cud_log_item *cudp; cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD, - &xfs_cud_item_ops); + xfs_log_item_init(tp->t_mountp, &cudp->cud_item, + xfs_cud_type_from_cui(cuip), &xfs_cud_item_ops); cudp->cud_cuip = cuip; cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id; @@ -328,10 +361,20 @@ xfs_refcount_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_refcount_defer(mp, ri); + /* + * Deferred refcount updates for the realtime and data sections must + * use separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ + ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); - ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type); + trace_xfs_refcount_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrefcount_update_defer_type : + &xfs_refcount_update_defer_type); } /* Cancel a deferred refcount update. */ @@ -381,7 +424,7 @@ xfs_refcount_finish_one_cleanup( return; agbp = rcur->bc_ag.agbp; xfs_btree_del_cursor(rcur, error); - if (error) + if (error && agbp) xfs_trans_brelse(tp, agbp); } @@ -397,6 +440,7 @@ xfs_refcount_update_abort_intent( static inline bool xfs_cui_validate_phys( struct xfs_mount *mp, + bool isrt, struct xfs_phys_extent *pmap) { if (!xfs_has_reflink(mp)) @@ -415,6 +459,9 @@ xfs_cui_validate_phys( return false; } + if (isrt) + return xfs_verify_rtbext(mp, pmap->pe_startblock, pmap->pe_len); + return xfs_verify_fsbext(mp, pmap->pe_startblock, pmap->pe_len); } @@ -422,6 +469,7 @@ static inline void xfs_cui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, struct xfs_phys_extent *pmap) { struct xfs_refcount_intent *ri; @@ -432,7 +480,8 @@ xfs_cui_recover_work( ri->ri_startblock = pmap->pe_startblock; ri->ri_blockcount = pmap->pe_len; ri->ri_group = xfs_group_intent_get(mp, pmap->pe_startblock, - XG_TYPE_AG); + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -451,6 +500,7 @@ xfs_refcount_recover_work( struct xfs_cui_log_item *cuip = CUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_cui_item_isrt(lip); int i; int error = 0; @@ -460,7 +510,7 @@ xfs_refcount_recover_work( * just toss the CUI. */ for (i = 0; i < cuip->cui_format.cui_nextents; i++) { - if (!xfs_cui_validate_phys(mp, + if (!xfs_cui_validate_phys(mp, isrt, &cuip->cui_format.cui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &cuip->cui_format, @@ -468,7 +518,8 @@ xfs_refcount_recover_work( return -EFSCORRUPTED; } - xfs_cui_recover_work(mp, dfp, &cuip->cui_format.cui_extents[i]); + xfs_cui_recover_work(mp, dfp, isrt, + &cuip->cui_format.cui_extents[i]); } /* @@ -515,10 +566,13 @@ xfs_refcount_relog_intent( struct xfs_phys_extent *pmap; unsigned int count; + ASSERT(intent->li_type == XFS_LI_CUI || + intent->li_type == XFS_LI_CUI_RT); + count = CUI_ITEM(intent)->cui_format.cui_nextents; pmap = CUI_ITEM(intent)->cui_format.cui_extents; - cuip = xfs_cui_init(tp->t_mountp, count); + cuip = xfs_cui_init(tp->t_mountp, intent->li_type, count); memcpy(cuip->cui_format.cui_extents, pmap, count * sizeof(*pmap)); atomic_set(&cuip->cui_next_extent, count); @@ -538,6 +592,71 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = { .relog_intent = xfs_refcount_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrefcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI_RT); +} + +/* Process a deferred realtime refcount update. */ +STATIC int +xfs_rtrefcount_update_finish_item( + struct xfs_trans *tp, + struct xfs_log_item *done, + struct list_head *item, + struct xfs_btree_cur **state) +{ + struct xfs_refcount_intent *ri = ci_entry(item); + int error; + + error = xfs_rtrefcount_finish_one(tp, ri, state); + + /* Did we run out of reservation? Requeue what we didn't finish. */ + if (!error && ri->ri_blockcount > 0) { + ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE || + ri->ri_type == XFS_REFCOUNT_DECREASE); + return -EAGAIN; + } + + xfs_refcount_update_cancel_item(item); + return error; +} + +/* Clean up after calling xfs_rtrefcount_finish_one. */ +STATIC void +xfs_rtrefcount_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", + .max_items = XFS_CUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrefcount_update_create_intent, + .abort_intent = xfs_refcount_update_abort_intent, + .create_done = xfs_refcount_update_create_done, + .finish_item = xfs_rtrefcount_update_finish_item, + .finish_cleanup = xfs_rtrefcount_finish_one_cleanup, + .cancel_item = xfs_refcount_update_cancel_item, + .recover_work = xfs_refcount_recover_work, + .relog_intent = xfs_refcount_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", +}; +#endif /* CONFIG_XFS_RT */ + STATIC bool xfs_cui_item_match( struct xfs_log_item *lip, @@ -603,7 +722,7 @@ xlog_recover_cui_commit_pass2( return -EFSCORRUPTED; } - cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); xfs_cui_copy_format(&cuip->cui_format, cui_formatp); atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); @@ -617,6 +736,61 @@ const struct xlog_recover_item_ops xlog_cui_item_ops = { .commit_pass2 = xlog_recover_cui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_cui_log_item *cuip; + struct xfs_cui_log_format *cui_formatp; + size_t len; + + cui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); + xfs_cui_copy_format(&cuip->cui_format, cui_formatp); + atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); + + xlog_recover_intent_item(log, &cuip->cui_item, lsn, + &xfs_rtrefcount_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtcui_item_ops = { + .item_type = XFS_LI_CUI_RT, + .commit_pass2 = xlog_recover_rtcui_commit_pass2, +}; + /* * This routine is called when an CUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding CUI if it @@ -648,3 +822,33 @@ const struct xlog_recover_item_ops xlog_cud_item_ops = { .item_type = XFS_LI_CUD, .commit_pass2 = xlog_recover_cud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_cud_log_format *cud_formatp; + + cud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_CUI_RT, + cud_formatp->cud_cui_id); + return 0; +} +#else +# define xlog_recover_rtcud_commit_pass2 xlog_recover_rtcui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtcud_item_ops = { + .item_type = XFS_LI_CUD_RT, + .commit_pass2 = xlog_recover_rtcud_commit_pass2, +}; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index b11769c009ef..cc3b4df88110 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -30,6 +30,10 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_health.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" /* * Copy on Write of Shared Blocks @@ -120,38 +124,93 @@ */ /* - * Given an AG extent, find the lowest-numbered run of shared blocks - * within that range and return the range in fbno/flen. If - * find_end_of_shared is true, return the longest contiguous extent of - * shared blocks. If there are no shared extents, fbno and flen will - * be set to NULLAGBLOCK and 0, respectively. + * Given a file mapping for the data device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; */ static int xfs_reflink_find_shared( - struct xfs_perag *pag, + struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agblock_t agbno, - xfs_extlen_t aglen, - xfs_agblock_t *fbno, - xfs_extlen_t *flen, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, bool find_end_of_shared) { struct xfs_buf *agbp; + struct xfs_perag *pag; struct xfs_btree_cur *cur; int error; + xfs_agblock_t orig_bno, found_bno; + + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); + orig_bno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) - return error; + goto out; - cur = xfs_refcountbt_init_cursor(pag_mount(pag), tp, agbp, pag); + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agbp); - error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen, - find_end_of_shared); + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; +out: + xfs_perag_put(pag); + return error; +} +/* + * Given a file mapping for the rt device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; + */ +static int +xfs_reflink_find_rtshared( + struct xfs_mount *mp, + struct xfs_trans *tp, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, + bool find_end_of_shared) +{ + struct xfs_rtgroup *rtg; + struct xfs_btree_cur *cur; + xfs_rgblock_t orig_bno; + xfs_agblock_t found_bno; + int error; + + BUILD_BUG_ON(NULLRGBLOCK != NULLAGBLOCK); + + /* + * Note: this uses the not quite correct xfs_agblock_t type because + * xfs_refcount_find_shared is shared between the RT and data device + * refcount code. + */ + orig_bno = xfs_rtb_to_rgbno(mp, irec->br_startblock); + rtg = xfs_rtgroup_get(mp, xfs_rtb_to_rgno(mp, irec->br_startblock)); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, rtg); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_put(rtg); - xfs_trans_brelse(tp, agbp); + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; return error; } @@ -172,56 +231,48 @@ xfs_reflink_trim_around_shared( bool *shared) { struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t shared_offset, shared_len; int error = 0; /* Holes, unwritten, and delalloc extents cannot be shared */ - if (!xfs_is_cow_inode(ip) || !xfs_bmap_is_written_extent(irec)) { + if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_written_extent(irec)) { *shared = false; return 0; } trace_xfs_reflink_trim_around_shared(ip, irec); - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); - aglen = irec->br_blockcount; - - error = xfs_reflink_find_shared(pag, NULL, agbno, aglen, &fbno, &flen, - true); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, NULL, irec, + &shared_offset, &shared_len, true); + else + error = xfs_reflink_find_shared(mp, NULL, irec, + &shared_offset, &shared_len, true); if (error) return error; - *shared = false; - if (fbno == NULLAGBLOCK) { + if (!shared_len) { /* No shared blocks at all. */ - return 0; - } - - if (fbno == agbno) { + *shared = false; + } else if (!shared_offset) { /* - * The start of this extent is shared. Truncate the - * mapping at the end of the shared region so that a - * subsequent iteration starts at the start of the - * unshared region. + * The start of this mapping points to shared space. Truncate + * the mapping at the end of the shared region so that a + * subsequent iteration starts at the start of the unshared + * region. */ - irec->br_blockcount = flen; + irec->br_blockcount = shared_len; *shared = true; - return 0; + } else { + /* + * There's a shared region that doesn't start at the beginning + * of the mapping. Truncate the mapping at the start of the + * shared extent so that a subsequent iteration starts at the + * start of the shared region. + */ + irec->br_blockcount = shared_offset; + *shared = false; } - - /* - * There's a shared extent midway through this extent. - * Truncate the mapping at the start of the shared - * extent so that a subsequent iteration starts at the - * start of the shared region. - */ - irec->br_blockcount = fbno - agbno; return 0; } @@ -389,20 +440,26 @@ xfs_reflink_fill_cow_hole( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_filblks_t resaligned; - xfs_extlen_t resblks; + unsigned int dblocks = 0, rblocks = 0; int nimaps; int error; bool found; resaligned = xfs_aligned_fsb_count(imap->br_startoff, imap->br_blockcount, xfs_get_cowextsz_hint(ip)); - resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resaligned; + } else { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + rblocks = 0; + } xfs_iunlock(ip, *lockmode); *lockmode = 0; - error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, - false, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, + rblocks, false, &tp); if (error) return error; @@ -571,6 +628,7 @@ xfs_reflink_cancel_cow_blocks( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error = 0; if (!xfs_inode_has_cow_data(ip)) @@ -593,17 +651,18 @@ xfs_reflink_cancel_cow_blocks( if (isnullstartblock(del.br_startblock)) { xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &icur, &got, - &del); + &del, 0); } else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) { ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER); /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(*tpp, del.br_startblock, - del.br_blockcount); + xfs_refcount_free_cow_extent(*tpp, isrt, + del.br_startblock, del.br_blockcount); error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) break; @@ -687,6 +746,35 @@ out: return error; } +#ifdef CONFIG_XFS_QUOTA +/* + * Update quota accounting for a remapping operation. When we're remapping + * something from the CoW fork to the data fork, we must update the quota + * accounting for delayed allocations. For remapping from the data fork to the + * data fork, use regular block accounting. + */ +static inline void +xfs_reflink_update_quota( + struct xfs_trans *tp, + struct xfs_inode *ip, + bool is_cow, + int64_t blocks) +{ + unsigned int qflag; + + if (XFS_IS_REALTIME_INODE(ip)) { + qflag = is_cow ? XFS_TRANS_DQ_DELRTBCOUNT : + XFS_TRANS_DQ_RTBCOUNT; + } else { + qflag = is_cow ? XFS_TRANS_DQ_DELBCOUNT : + XFS_TRANS_DQ_BCOUNT; + } + xfs_trans_mod_dquot_byino(tp, ip, qflag, blocks); +} +#else +# define xfs_reflink_update_quota(tp, ip, is_cow, blocks) ((void)0) +#endif + /* * Remap part of the CoW fork into the data fork. * @@ -710,6 +798,7 @@ xfs_reflink_end_cow_extent( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); unsigned int resblks; int nmaps; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error; resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); @@ -779,9 +868,8 @@ xfs_reflink_end_cow_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data); - xfs_refcount_decrease_extent(tp, &data); - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, - -data.br_blockcount); + xfs_refcount_decrease_extent(tp, isrt, &data); + xfs_reflink_update_quota(tp, ip, false, -data.br_blockcount); } else if (data.br_startblock == DELAYSTARTBLOCK) { int done; @@ -799,14 +887,14 @@ xfs_reflink_end_cow_extent( } /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(tp, del.br_startblock, del.br_blockcount); + xfs_refcount_free_cow_extent(tp, isrt, del.br_startblock, + del.br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &del); /* Charge this new data fork mapping to the on-disk quota. */ - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT, - (long)del.br_blockcount); + xfs_reflink_update_quota(tp, ip, true, del.br_blockcount); /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); @@ -895,20 +983,29 @@ xfs_reflink_recover_cow( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error = 0; if (!xfs_has_reflink(mp)) return 0; while ((pag = xfs_perag_next(mp, pag))) { - error = xfs_refcount_recover_cow_leftovers(mp, pag); + error = xfs_refcount_recover_cow_leftovers(pag_group(pag)); if (error) { xfs_perag_rele(pag); - break; + return error; } } - return error; + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + error = xfs_refcount_recover_cow_leftovers(rtg_group(rtg)); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; } /* @@ -1100,14 +1197,22 @@ out_error: static int xfs_reflink_ag_has_free_space( struct xfs_mount *mp, - xfs_agnumber_t agno) + struct xfs_inode *ip, + xfs_fsblock_t fsb) { struct xfs_perag *pag; + xfs_agnumber_t agno; int error = 0; if (!xfs_has_rmapbt(mp)) return 0; + if (XFS_IS_REALTIME_INODE(ip)) { + if (xfs_metafile_resv_critical(mp)) + return -ENOSPC; + return 0; + } + agno = XFS_FSB_TO_AGNO(mp, fsb); pag = xfs_perag_get(mp, agno); if (xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) || xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA)) @@ -1131,10 +1236,11 @@ xfs_reflink_remap_extent( struct xfs_trans *tp; xfs_off_t newlen; int64_t qdelta = 0; - unsigned int resblks; + unsigned int dblocks, rblocks, resblks; bool quota_reserved = true; bool smap_real; bool dmap_written = xfs_bmap_is_written_extent(dmap); + bool isrt = XFS_IS_REALTIME_INODE(ip); int iext_delta = 0; int nimaps; int error; @@ -1161,8 +1267,15 @@ xfs_reflink_remap_extent( * we're remapping. */ resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = resblks; + rblocks = dmap->br_blockcount; + } else { + dblocks = resblks + dmap->br_blockcount; + rblocks = 0; + } error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, - resblks + dmap->br_blockcount, 0, false, &tp); + dblocks, rblocks, false, &tp); if (error == -EDQUOT || error == -ENOSPC) { quota_reserved = false; error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, @@ -1213,8 +1326,8 @@ xfs_reflink_remap_extent( /* No reflinking if the AG of the dest mapping is low on space. */ if (dmap_written) { - error = xfs_reflink_ag_has_free_space(mp, - XFS_FSB_TO_AGNO(mp, dmap->br_startblock)); + error = xfs_reflink_ag_has_free_space(mp, ip, + dmap->br_startblock); if (error) goto out_cancel; } @@ -1242,8 +1355,15 @@ xfs_reflink_remap_extent( * done. */ if (!quota_reserved && !smap_real && dmap_written) { - error = xfs_trans_reserve_quota_nblks(tp, ip, - dmap->br_blockcount, 0, false); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = 0; + rblocks = dmap->br_blockcount; + } else { + dblocks = dmap->br_blockcount; + rblocks = 0; + } + error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, + false); if (error) goto out_cancel; } @@ -1264,7 +1384,7 @@ xfs_reflink_remap_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &smap); - xfs_refcount_decrease_extent(tp, &smap); + xfs_refcount_decrease_extent(tp, isrt, &smap); qdelta -= smap.br_blockcount; } else if (smap.br_startblock == DELAYSTARTBLOCK) { int done; @@ -1287,12 +1407,12 @@ xfs_reflink_remap_extent( * its refcount and map it into the file. */ if (dmap_written) { - xfs_refcount_increase_extent(tp, dmap); + xfs_refcount_increase_extent(tp, isrt, dmap); xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, dmap); qdelta += dmap->br_blockcount; } - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, qdelta); + xfs_reflink_update_quota(tp, ip, false, qdelta); /* Update dest isize if needed. */ newlen = XFS_FSB_TO_B(mp, dmap->br_startoff + dmap->br_blockcount); @@ -1412,7 +1532,7 @@ xfs_reflink_zero_posteof( return 0; trace_xfs_zero_eof(ip, isize, pos - isize); - return xfs_zero_range(ip, isize, pos - isize, NULL); + return xfs_zero_range(ip, isize, pos - isize, NULL, NULL); } /* @@ -1466,8 +1586,8 @@ xfs_reflink_remap_prep( /* Check file eligibility and prepare for block sharing. */ ret = -EINVAL; - /* Don't reflink realtime inodes */ - if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) + /* Can't reflink between data and rt volumes */ + if (XFS_IS_REALTIME_INODE(src) != XFS_IS_REALTIME_INODE(dest)) goto out_unlock; /* Don't share DAX file data with non-DAX file. */ @@ -1547,27 +1667,23 @@ xfs_reflink_inode_has_shared_extents( *has_shared = false; found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got); while (found) { - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t rbno; - xfs_extlen_t rlen; + xfs_extlen_t shared_offset, shared_len; if (isnullstartblock(got.br_startblock) || got.br_state != XFS_EXT_NORM) goto next; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, got.br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock); - aglen = got.br_blockcount; - error = xfs_reflink_find_shared(pag, tp, agbno, aglen, - &rbno, &rlen, false); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, tp, &got, + &shared_offset, &shared_len, false); + else + error = xfs_reflink_find_shared(mp, tp, &got, + &shared_offset, &shared_len, false); if (error) return error; /* Is there still a shared block here? */ - if (rbno != NULLAGBLOCK) { + if (shared_len) { *has_shared = true; return 0; } @@ -1700,3 +1816,28 @@ out: trace_xfs_reflink_unshare_error(ip, error, _RET_IP_); return error; } + +/* + * Can we use reflink with this realtime extent size? Note that we don't check + * for rblocks > 0 here because this can be called as part of attaching a new + * rt section. + */ +bool +xfs_reflink_supports_rextsize( + struct xfs_mount *mp, + unsigned int rextsize) +{ + /* reflink on the realtime device requires rtgroups */ + if (!xfs_has_rtgroups(mp)) + return false; + + /* + * Reflink doesn't support rt extent size larger than a single fsblock + * because we would have to perform CoW-around for unaligned write + * requests to guarantee that we always remap entire rt extents. + */ + if (rextsize != 1) + return false; + + return true; +} diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 4a58e4533671..cc4e92278279 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -25,7 +25,7 @@ xfs_can_free_cowblocks(struct xfs_inode *ip) return true; } -extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, +int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared); int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared); @@ -62,4 +62,6 @@ extern int xfs_reflink_remap_blocks(struct xfs_inode *src, loff_t pos_in, extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen, xfs_extlen_t cowextsize, unsigned int remap_flags); +bool xfs_reflink_supports_rextsize(struct xfs_mount *mp, unsigned int rextsize); + #endif /* __XFS_REFLINK_H */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 76b3c0ed3b4f..89decffe76c8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_rui_cache; struct kmem_cache *xfs_rud_cache; @@ -94,7 +95,9 @@ xfs_rui_item_format( ASSERT(atomic_read(&ruip->rui_next_extent) == ruip->rui_format.rui_nextents); - ruip->rui_format.rui_type = XFS_LI_RUI; + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + ruip->rui_format.rui_type = lip->li_type; ruip->rui_format.rui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format, @@ -137,12 +140,15 @@ xfs_rui_item_release( STATIC struct xfs_rui_log_item * xfs_rui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) { struct xfs_rui_log_item *ruip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT); + if (nextents > XFS_RUI_MAX_FAST_EXTENTS) ruip = kzalloc(xfs_rui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -150,7 +156,7 @@ xfs_rui_init( ruip = kmem_cache_zalloc(xfs_rui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); + xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops); ruip->rui_format.rui_nextents = nextents; ruip->rui_format.rui_id = (uintptr_t)(void *)ruip; atomic_set(&ruip->rui_next_extent, 0); @@ -189,7 +195,9 @@ xfs_rud_item_format( struct xfs_rud_log_item *rudp = RUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - rudp->rud_format.rud_type = XFS_LI_RUD; + ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT); + + rudp->rud_format.rud_type = lip->li_type; rudp->rud_format.rud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format, @@ -233,6 +241,14 @@ static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e) return list_entry(e, struct xfs_rmap_intent, ri_list); } +static inline bool +xfs_rui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + return lip->li_type == XFS_LI_RUI_RT; +} + /* Sort rmap intents by AG. */ static int xfs_rmap_update_diff_items( @@ -305,18 +321,20 @@ xfs_rmap_update_log_item( } static struct xfs_log_item * -xfs_rmap_update_create_intent( +__xfs_rmap_update_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, - bool sort) + bool sort, + unsigned short item_type) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count); + struct xfs_rui_log_item *ruip; struct xfs_rmap_intent *ri; ASSERT(count > 0); + ruip = xfs_rui_init(mp, item_type, count); if (sort) list_sort(mp, items, xfs_rmap_update_diff_items); list_for_each_entry(ri, items, ri_list) @@ -324,6 +342,23 @@ xfs_rmap_update_create_intent( return &ruip->rui_item; } +static struct xfs_log_item * +xfs_rmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI); +} + +static inline unsigned short +xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip) +{ + return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD; +} + /* Get an RUD so we can process all the deferred rmap updates. */ static struct xfs_log_item * xfs_rmap_update_create_done( @@ -335,8 +370,8 @@ xfs_rmap_update_create_done( struct xfs_rud_log_item *rudp; rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD, - &xfs_rud_item_ops); + xfs_log_item_init(tp->t_mountp, &rudp->rud_item, + xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops); rudp->rud_ruip = ruip; rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id; @@ -351,11 +386,20 @@ xfs_rmap_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_rmap_defer(mp, ri); - + /* + * Deferred rmap updates for the realtime and data sections must use + * separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock, - XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type); + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); + + trace_xfs_rmap_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrmap_update_defer_type : + &xfs_rmap_update_defer_type); } /* Cancel a deferred rmap update. */ @@ -415,6 +459,7 @@ xfs_rmap_update_abort_intent( static inline bool xfs_rui_validate_map( struct xfs_mount *mp, + bool isrt, struct xfs_map_extent *map) { if (!xfs_has_rmapbt(mp)) @@ -444,6 +489,9 @@ xfs_rui_validate_map( if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len)) return false; + if (isrt) + return xfs_verify_rtbext(mp, map->me_startblock, map->me_len); + return xfs_verify_fsbext(mp, map->me_startblock, map->me_len); } @@ -451,6 +499,7 @@ static inline void xfs_rui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, const struct xfs_map_extent *map) { struct xfs_rmap_intent *ri; @@ -495,7 +544,9 @@ xfs_rui_recover_work( ri->ri_bmap.br_blockcount = map->me_len; ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM; - ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, XG_TYPE_AG); + ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -514,6 +565,7 @@ xfs_rmap_recover_work( struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_rui_item_isrt(lip); int i; int error = 0; @@ -523,7 +575,7 @@ xfs_rmap_recover_work( * just toss the RUI. */ for (i = 0; i < ruip->rui_format.rui_nextents; i++) { - if (!xfs_rui_validate_map(mp, + if (!xfs_rui_validate_map(mp, isrt, &ruip->rui_format.rui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &ruip->rui_format, @@ -531,7 +583,8 @@ xfs_rmap_recover_work( return -EFSCORRUPTED; } - xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]); + xfs_rui_recover_work(mp, dfp, isrt, + &ruip->rui_format.rui_extents[i]); } resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); @@ -566,10 +619,13 @@ xfs_rmap_relog_intent( struct xfs_map_extent *map; unsigned int count; + ASSERT(intent->li_type == XFS_LI_RUI || + intent->li_type == XFS_LI_RUI_RT); + count = RUI_ITEM(intent)->rui_format.rui_nextents; map = RUI_ITEM(intent)->rui_format.rui_extents; - ruip = xfs_rui_init(tp->t_mountp, count); + ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count); memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map)); atomic_set(&ruip->rui_next_extent, count); @@ -589,6 +645,47 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = { .relog_intent = xfs_rmap_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI_RT); +} + +/* Clean up after calling xfs_rmap_finish_one. */ +STATIC void +xfs_rtrmap_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", + .max_items = XFS_RUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrmap_update_create_intent, + .abort_intent = xfs_rmap_update_abort_intent, + .create_done = xfs_rmap_update_create_done, + .finish_item = xfs_rmap_update_finish_item, + .finish_cleanup = xfs_rtrmap_finish_one_cleanup, + .cancel_item = xfs_rmap_update_cancel_item, + .recover_work = xfs_rmap_recover_work, + .relog_intent = xfs_rmap_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", +}; +#endif + STATIC bool xfs_rui_item_match( struct xfs_log_item *lip, @@ -654,7 +751,7 @@ xlog_recover_rui_commit_pass2( return -EFSCORRUPTED; } - ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); xfs_rui_copy_format(&ruip->rui_format, rui_formatp); atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); @@ -668,6 +765,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = { .commit_pass2 = xlog_recover_rui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_rui_log_item *ruip; + struct xfs_rui_log_format *rui_formatp; + size_t len; + + rui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); + xfs_rui_copy_format(&ruip->rui_format, rui_formatp); + atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); + + xlog_recover_intent_item(log, &ruip->rui_item, lsn, + &xfs_rtrmap_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtrui_item_ops = { + .item_type = XFS_LI_RUI_RT, + .commit_pass2 = xlog_recover_rtrui_commit_pass2, +}; + /* * This routine is called when an RUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding RUI if it @@ -699,3 +851,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = { .item_type = XFS_LI_RUD, .commit_pass2 = xlog_recover_rud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_rud_log_format *rud_formatp; + + rud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + rud_formatp, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_RUI_RT, + rud_formatp->rud_rui_id); + return 0; +} +#else +# define xlog_recover_rtrud_commit_pass2 xlog_recover_rtrui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtrud_item_ops = { + .item_type = XFS_LI_RUD_RT, + .commit_pass2 = xlog_recover_rtrud_commit_pass2, +}; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index fcfa6e0eb3ad..6484c596ecea 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -22,6 +22,7 @@ #include "xfs_rtalloc.h" #include "xfs_sb.h" #include "xfs_rtbitmap.h" +#include "xfs_rtrmap_btree.h" #include "xfs_quota.h" #include "xfs_log_priv.h" #include "xfs_health.h" @@ -30,6 +31,9 @@ #include "xfs_rtgroup.h" #include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_reflink.h" +#include "xfs_zone_alloc.h" /* * Return whether there are any free extents in the size range given @@ -592,7 +596,7 @@ xfs_rtalloc_sumlevel( * specified. If we don't get maxlen then use prod to trim * the length, if given. The lengths are all in rtextents. */ -STATIC int +static int xfs_rtallocate_extent_size( struct xfs_rtalloc_args *args, xfs_rtxlen_t minlen, /* minimum length to allocate */ @@ -660,7 +664,8 @@ xfs_rtunmount_rtg( for (i = 0; i < XFS_RTGI_MAX; i++) xfs_rtginode_irele(&rtg->rtg_inodes[i]); - kvfree(rtg->rtg_rsum_cache); + if (!xfs_has_zoned(rtg_mount(rtg))) + kvfree(rtg->rtg_rsum_cache); } static int @@ -834,7 +839,7 @@ xfs_growfs_rt_init_rtsb( return 0; error = xfs_buf_get_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, 1), - 0, &rtsb_bp); + &rtsb_bp); if (error) return error; @@ -845,6 +850,91 @@ xfs_growfs_rt_init_rtsb( mp->m_rtsb_bp = rtsb_bp; error = xfs_bwrite(rtsb_bp); xfs_buf_unlock(rtsb_bp); + if (error) + return error; + + /* Initialize the rtrmap to reflect the rtsb. */ + if (rtg_rmap(args->rtg) != NULL) + error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp); + + return error; +} + +static void +xfs_growfs_rt_sb_fields( + struct xfs_trans *tp, + const struct xfs_mount *nmp) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSIZE, + nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize); + if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS, + nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks); + if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBLOCKS, + nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks); + if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTENTS, + nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents); + if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG, + nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog); + if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RGCOUNT, + nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount); +} + +static int +xfs_growfs_rt_zoned( + struct xfs_rtgroup *rtg, + xfs_rfsblock_t nrblocks) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_mount *nmp; + struct xfs_trans *tp; + xfs_rtbxlen_t freed_rtx; + int error; + + /* + * Calculate new sb and mount fields for this round. Also ensure the + * rtg_extents value is uptodate as the rtbitmap code relies on it. + */ + nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, + mp->m_sb.sb_rextsize); + if (!nmp) + return -ENOMEM; + freed_rtx = nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents; + + xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg), + nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents); + + error = xfs_trans_alloc(mp, &M_RES(nmp)->tr_growrtfree, 0, 0, 0, &tp); + if (error) + goto out_free; + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + + xfs_growfs_rt_sb_fields(tp, nmp); + xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, freed_rtx); + + error = xfs_trans_commit(tp); + if (error) + goto out_free; + + /* + * Ensure the mount RT feature flag is now set, and compute new + * maxlevels for rt btrees. + */ + mp->m_features |= XFS_FEAT_REALTIME; + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); + xfs_zoned_add_available(mp, freed_rtx); +out_free: + kfree(nmp); return error; } @@ -856,8 +946,8 @@ xfs_growfs_rt_bmblock( xfs_fileoff_t bmbno) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xfs_rtalloc_args args = { .mp = mp, .rtg = rtg, @@ -893,8 +983,9 @@ xfs_growfs_rt_bmblock( goto out_free; nargs.tp = args.tp; - xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP); - xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP); + xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(args.tp, args.rtg, + XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); /* * Update the bitmap inode's size ondisk and incore. We need to update @@ -932,24 +1023,7 @@ xfs_growfs_rt_bmblock( /* * Update superblock fields. */ - if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSIZE, - nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize); - if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBMBLOCKS, - nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks); - if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBLOCKS, - nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks); - if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTENTS, - nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents); - if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSLOG, - nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog); - if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount) - xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RGCOUNT, - nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount); + xfs_growfs_rt_sb_fields(args.tp, nmp); /* * Free the new extent. @@ -980,9 +1054,12 @@ xfs_growfs_rt_bmblock( goto out_free; /* - * Ensure the mount RT feature flag is now set. + * Ensure the mount RT feature flag is now set, and compute new + * maxlevels for rt btrees. */ mp->m_features |= XFS_FEAT_REALTIME; + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); kfree(nmp); return 0; @@ -1041,8 +1118,8 @@ xfs_growfs_rt_alloc_blocks( xfs_extlen_t *nrbmblocks) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); xfs_extlen_t orbmblocks = 0; xfs_extlen_t orsumblocks = 0; struct xfs_mount *nmp; @@ -1113,6 +1190,11 @@ xfs_growfs_rtg( goto out_rele; } + if (xfs_has_zoned(mp)) { + error = xfs_growfs_rt_zoned(rtg, nrblocks); + goto out_rele; + } + error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks); if (error) goto out_rele; @@ -1130,10 +1212,8 @@ xfs_growfs_rtg( goto out_error; } - if (old_rsum_cache) - kvfree(old_rsum_cache); - xfs_rtgroup_rele(rtg); - return 0; + kvfree(old_rsum_cache); + goto out_rele; out_error: /* @@ -1150,29 +1230,54 @@ out_rele: return error; } -static int +int xfs_growfs_check_rtgeom( const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, xfs_extlen_t rextsize) { + xfs_extlen_t min_logfsbs; struct xfs_mount *nmp; - int error = 0; nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize); if (!nmp) return -ENOMEM; + nmp->m_sb.sb_dblocks = dblocks; + + xfs_rtrmapbt_compute_maxlevels(nmp); + xfs_rtrefcountbt_compute_maxlevels(nmp); + xfs_trans_resv_calc(nmp, M_RES(nmp)); /* * New summary size can't be more than half the size of the log. This * prevents us from getting a log overflow, since we'll log basically * the whole summary file at once. */ - if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1)) - error = -EINVAL; + min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp), + nmp->m_rsumblocks * 2); kfree(nmp); - return error; + + if (min_logfsbs > mp->m_sb.sb_logblocks) + return -EINVAL; + + if (xfs_has_zoned(mp)) { + uint32_t gblocks = mp->m_groups[XG_TYPE_RTG].blocks; + uint32_t rem; + + if (rextsize != 1) + return -EINVAL; + div_u64_rem(mp->m_sb.sb_rblocks, gblocks, &rem); + if (rem) { + xfs_warn(mp, +"new RT volume size (%lld) not aligned to RT group size (%d)", + mp->m_sb.sb_rblocks, gblocks); + return -EINVAL; + } + } + + return 0; } /* @@ -1226,6 +1331,35 @@ xfs_grow_last_rtg( } /* + * Read in the last block of the RT device to make sure it is accessible. + */ +static int +xfs_rt_check_size( + struct xfs_mount *mp, + xfs_rfsblock_t last_block) +{ + xfs_daddr_t daddr = XFS_FSB_TO_BB(mp, last_block); + struct xfs_buf *bp; + int error; + + if (XFS_BB_TO_FSB(mp, daddr) != last_block) { + xfs_warn(mp, "RT device size overflow: %llu != %llu", + XFS_BB_TO_FSB(mp, daddr), last_block); + return -EFBIG; + } + + error = xfs_buf_read_uncached(mp->m_rtdev_targp, + XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart) + daddr, + XFS_FSB_TO_BB(mp, 1), &bp, NULL); + if (error) + xfs_warn(mp, "cannot read last RT device sector (%lld)", + last_block); + else + xfs_buf_relse(bp); + return error; +} + +/* * Grow the realtime area of the filesystem. */ int @@ -1236,7 +1370,6 @@ xfs_growfs_rt( xfs_rgnumber_t old_rgcount = mp->m_sb.sb_rgcount; xfs_rgnumber_t new_rgcount = 1; xfs_rgnumber_t rgno; - struct xfs_buf *bp; xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize; int error; @@ -1263,25 +1396,26 @@ xfs_growfs_rt( XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) goto out_unlock; - /* Unsupported realtime features. */ + /* Check for features supported only on rtgroups filesystems. */ error = -EOPNOTSUPP; - if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp)) - goto out_unlock; - if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp)) + if (!xfs_has_rtgroups(mp)) { + if (xfs_has_rmapbt(mp)) + goto out_unlock; + if (xfs_has_quota(mp)) + goto out_unlock; + if (xfs_has_reflink(mp)) + goto out_unlock; + } else if (xfs_has_reflink(mp) && + !xfs_reflink_supports_rextsize(mp, in->extsize)) goto out_unlock; error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks); if (error) goto out_unlock; - /* - * Read in the last block of the device, make sure it exists. - */ - error = xfs_buf_read_uncached(mp->m_rtdev_targp, - XFS_FSB_TO_BB(mp, in->newblocks - 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); + + error = xfs_rt_check_size(mp, in->newblocks - 1); if (error) goto out_unlock; - xfs_buf_relse(bp); /* * Calculate new parameters. These are the final values to be reached. @@ -1291,7 +1425,8 @@ xfs_growfs_rt( goto out_unlock; /* Make sure the new fs size won't cause problems with the log. */ - error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize); + error = xfs_growfs_check_rtgeom(mp, mp->m_sb.sb_dblocks, in->newblocks, + in->extsize); if (error) goto out_unlock; @@ -1344,6 +1479,11 @@ xfs_growfs_rt( if (!error) error = error2; + + /* Reset the rt metadata btree space reservations. */ + error2 = xfs_metafile_resv_init(mp); + if (error2 && error2 != -ENOSPC) + error = error2; } out_unlock: @@ -1371,7 +1511,7 @@ xfs_rtmount_readsb( /* m_blkbb_log is not set up yet */ error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR, - mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp, + mp->m_sb.sb_blocksize >> BBSHIFT, &bp, &xfs_rtsb_buf_ops); if (error) { xfs_warn(mp, "rt sb validate failed with error %d.", error); @@ -1408,10 +1548,6 @@ int /* error */ xfs_rtmount_init( struct xfs_mount *mp) /* file system mount structure */ { - struct xfs_buf *bp; /* buffer for last block of subvolume */ - xfs_daddr_t d; /* address of last block of subvolume */ - int error; - if (mp->m_sb.sb_rblocks == 0) return 0; if (mp->m_rtdev_targp == NULL) { @@ -1422,25 +1558,7 @@ xfs_rtmount_init( mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, &mp->m_rsumlevels); - /* - * Check that the realtime section is an ok size. - */ - d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); - if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_rblocks) { - xfs_warn(mp, "realtime mount -- %llu != %llu", - (unsigned long long) XFS_BB_TO_FSB(mp, d), - (unsigned long long) mp->m_sb.sb_rblocks); - return -EFBIG; - } - error = xfs_buf_read_uncached(mp->m_rtdev_targp, - d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); - if (error) { - xfs_warn(mp, "realtime device size check failed"); - return error; - } - xfs_buf_relse(bp); - return 0; + return xfs_rt_check_size(mp, mp->m_sb.sb_rblocks - 1); } static int @@ -1483,7 +1601,7 @@ xfs_rtalloc_reinit_frextents( spin_lock(&mp->m_sb_lock); mp->m_sb.sb_frextents = val; spin_unlock(&mp->m_sb_lock); - percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents); + xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, mp->m_sb.sb_frextents); return 0; } @@ -1537,6 +1655,8 @@ xfs_rtmount_rtg( } } + if (xfs_has_zoned(mp)) + return 0; return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks); } @@ -1601,7 +1721,7 @@ xfs_rtpick_extent( xfs_rtxlen_t len) /* allocation length (rtextents) */ { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t b = 0; /* result rtext */ int log2; /* log of sequence number */ uint64_t resid; /* residual after log removed */ @@ -1885,7 +2005,7 @@ out_unlock: goto out_release; } -static int +int xfs_rtallocate_rtgs( struct xfs_trans *tp, xfs_fsblock_t bno_hint, @@ -1950,7 +2070,10 @@ xfs_rtallocate_align( if (*noalign) { align = mp->m_sb.sb_rextsize; } else { - align = xfs_get_extsz_hint(ap->ip); + if (ap->flags & XFS_BMAPI_COWFORK) + align = xfs_get_cowextsz_hint(ap->ip); + else + align = xfs_get_extsz_hint(ap->ip); if (!align) align = 1; if (align == mp->m_sb.sb_rextsize) @@ -2018,6 +2141,8 @@ xfs_bmap_rtalloc( ap->datatype & XFS_ALLOC_INITIAL_USER_DATA; int error; + ASSERT(!xfs_has_zoned(ap->tp->t_mountp)); + retry: error = xfs_rtallocate_align(ap, &ralen, &raminlen, &prod, &noalign); if (error) diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 8e2a07b8174b..78a690b489ed 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -43,6 +43,8 @@ xfs_growfs_rt( xfs_growfs_rt_t *in); /* user supplied growfs struct */ int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp); +int xfs_growfs_check_rtgeom(const struct xfs_mount *mp, xfs_rfsblock_t dblocks, + xfs_rfsblock_t rblocks, xfs_agblock_t rextsize); #else # define xfs_growfs_rt(mp,in) (-ENOSYS) # define xfs_rtalloc_reinit_frextents(m) (0) @@ -60,6 +62,19 @@ xfs_rtmount_init( } # define xfs_rtmount_inodes(m) (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS)) # define xfs_rtunmount_inodes(m) + +static inline int +xfs_growfs_check_rtgeom(const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, + xfs_extlen_t rextsize) +{ + return 0; +} #endif /* CONFIG_XFS_RT */ +int xfs_rtallocate_rtgs(struct xfs_trans *tp, xfs_fsblock_t bno_hint, + xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod, + bool wasdel, bool initial_user_data, xfs_rtblock_t *bno, + xfs_extlen_t *blen); + #endif /* __XFS_RTALLOC_H__ */ diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index ffb52725c2a8..35c7fb3ba324 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -52,7 +52,10 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { "rmapbt", xfsstats_offset(xs_refcbt_2) }, { "refcntbt", xfsstats_offset(xs_rmap_mem_2) }, { "rmapbt_mem", xfsstats_offset(xs_rcbag_2) }, - { "rcbagbt", xfsstats_offset(xs_qm_dqreclaims)}, + { "rcbagbt", xfsstats_offset(xs_rtrmap_2) }, + { "rtrmapbt", xfsstats_offset(xs_rtrmap_mem_2)}, + { "rtrmapbt_mem", xfsstats_offset(xs_rtrefcbt_2) }, + { "rtrefcntbt", xfsstats_offset(xs_qm_dqreclaims)}, /* we print both series of quota information together */ { "qm", xfsstats_offset(xs_xstrat_bytes)}, }; diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index a61fb56ed2e6..15ba1abcf253 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -127,6 +127,9 @@ struct __xfsstats { uint32_t xs_refcbt_2[__XBTS_MAX]; uint32_t xs_rmap_mem_2[__XBTS_MAX]; uint32_t xs_rcbag_2[__XBTS_MAX]; + uint32_t xs_rtrmap_2[__XBTS_MAX]; + uint32_t xs_rtrmap_mem_2[__XBTS_MAX]; + uint32_t xs_rtrefcbt_2[__XBTS_MAX]; uint32_t xs_qm_dqreclaims; uint32_t xs_qm_dqreclaim_misses; uint32_t xs_qm_dquot_dups; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 394fdf3bb535..4a11ddccc563 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -46,6 +46,7 @@ #include "xfs_exchmaps_item.h" #include "xfs_parent.h" #include "xfs_rtalloc.h" +#include "xfs_zone_alloc.h" #include "scrub/stats.h" #include "scrub/rcbag_btree.h" @@ -109,7 +110,8 @@ enum { Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota, Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce, - Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, + Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, Opt_max_open_zones, + Opt_lifetime, Opt_nolifetime, }; static const struct fs_parameter_spec xfs_fs_parameters[] = { @@ -154,6 +156,9 @@ static const struct fs_parameter_spec xfs_fs_parameters[] = { fsparam_flag("nodiscard", Opt_nodiscard), fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, dax_param_enums), + fsparam_u32("max_open_zones", Opt_max_open_zones), + fsparam_flag("lifetime", Opt_lifetime), + fsparam_flag("nolifetime", Opt_nolifetime), {} }; @@ -182,6 +187,7 @@ xfs_fs_show_options( { XFS_FEAT_LARGE_IOSIZE, ",largeio" }, { XFS_FEAT_DAX_ALWAYS, ",dax=always" }, { XFS_FEAT_DAX_NEVER, ",dax=never" }, + { XFS_FEAT_NOLIFETIME, ",nolifetime" }, { 0, NULL } }; struct xfs_mount *mp = XFS_M(root->d_sb); @@ -233,6 +239,9 @@ xfs_fs_show_options( if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT)) seq_puts(m, ",noquota"); + if (mp->m_max_open_zones) + seq_printf(m, ",max_open_zones=%u", mp->m_max_open_zones); + return 0; } @@ -533,7 +542,15 @@ xfs_setup_devices( if (error) return error; } - if (mp->m_rtdev_targp) { + + if (mp->m_sb.sb_rtstart) { + if (mp->m_rtdev_targp) { + xfs_warn(mp, + "can't use internal and external rtdev at the same time"); + return -EINVAL; + } + mp->m_rtdev_targp = mp->m_ddev_targp; + } else if (mp->m_rtname) { error = xfs_setsize_buftarg(mp->m_rtdev_targp, mp->m_sb.sb_sectsize); if (error) @@ -751,13 +768,24 @@ xfs_fs_drop_inode( return generic_drop_inode(inode); } +STATIC void +xfs_fs_evict_inode( + struct inode *inode) +{ + if (IS_DAX(inode)) + dax_break_layout_final(inode); + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); +} + static void xfs_mount_free( struct xfs_mount *mp) { if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_logdev_targp); - if (mp->m_rtdev_targp) + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_rtdev_targp); if (mp->m_ddev_targp) xfs_free_buftarg(mp->m_ddev_targp); @@ -814,25 +842,85 @@ xfs_fs_sync_fs( if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) { xfs_inodegc_stop(mp); xfs_blockgc_stop(mp); + xfs_zone_gc_stop(mp); } return 0; } +static xfs_extlen_t +xfs_internal_log_size( + struct xfs_mount *mp) +{ + if (!mp->m_sb.sb_logstart) + return 0; + return mp->m_sb.sb_logblocks; +} + +static void +xfs_statfs_data( + struct xfs_mount *mp, + struct kstatfs *st) +{ + int64_t fdblocks = + xfs_sum_freecounter(mp, XC_FREE_BLOCKS); + + /* make sure st->f_bfree does not underflow */ + st->f_bfree = max(0LL, + fdblocks - xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS)); + + /* + * sb_dblocks can change during growfs, but nothing cares about reporting + * the old or new value during growfs. + */ + st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp); +} + +/* + * When stat(v)fs is called on a file with the realtime bit set or a directory + * with the rtinherit bit, report freespace information for the RT device + * instead of the main data device. + */ +static void +xfs_statfs_rt( + struct xfs_mount *mp, + struct kstatfs *st) +{ + st->f_bfree = xfs_rtbxlen_to_blen(mp, + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); + st->f_blocks = mp->m_sb.sb_rblocks - xfs_rtbxlen_to_blen(mp, + mp->m_free[XC_FREE_RTEXTENTS].res_total); +} + +static void +xfs_statfs_inodes( + struct xfs_mount *mp, + struct kstatfs *st) +{ + uint64_t icount = percpu_counter_sum(&mp->m_icount); + uint64_t ifree = percpu_counter_sum(&mp->m_ifree); + uint64_t fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree); + + st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); + if (M_IGEO(mp)->maxicount) + st->f_files = min_t(typeof(st->f_files), st->f_files, + M_IGEO(mp)->maxicount); + + /* If sb_icount overshot maxicount, report actual allocation */ + st->f_files = max_t(typeof(st->f_files), st->f_files, + mp->m_sb.sb_icount); + + /* Make sure st->f_ffree does not underflow */ + st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree)); +} + STATIC int xfs_fs_statfs( struct dentry *dentry, - struct kstatfs *statp) + struct kstatfs *st) { struct xfs_mount *mp = XFS_M(dentry->d_sb); - xfs_sb_t *sbp = &mp->m_sb; struct xfs_inode *ip = XFS_I(d_inode(dentry)); - uint64_t fakeinos, id; - uint64_t icount; - uint64_t ifree; - uint64_t fdblocks; - xfs_extlen_t lsize; - int64_t ffree; /* * Expedite background inodegc but don't wait. We do not want to block @@ -840,80 +928,58 @@ xfs_fs_statfs( */ xfs_inodegc_push(mp); - statp->f_type = XFS_SUPER_MAGIC; - statp->f_namelen = MAXNAMELEN - 1; - - id = huge_encode_dev(mp->m_ddev_targp->bt_dev); - statp->f_fsid = u64_to_fsid(id); - - icount = percpu_counter_sum(&mp->m_icount); - ifree = percpu_counter_sum(&mp->m_ifree); - fdblocks = percpu_counter_sum(&mp->m_fdblocks); + st->f_type = XFS_SUPER_MAGIC; + st->f_namelen = MAXNAMELEN - 1; + st->f_bsize = mp->m_sb.sb_blocksize; + st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev)); - spin_lock(&mp->m_sb_lock); - statp->f_bsize = sbp->sb_blocksize; - lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0; - statp->f_blocks = sbp->sb_dblocks - lsize; - spin_unlock(&mp->m_sb_lock); - - /* make sure statp->f_bfree does not underflow */ - statp->f_bfree = max_t(int64_t, 0, - fdblocks - xfs_fdblocks_unavailable(mp)); - statp->f_bavail = statp->f_bfree; - - fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); - statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); - if (M_IGEO(mp)->maxicount) - statp->f_files = min_t(typeof(statp->f_files), - statp->f_files, - M_IGEO(mp)->maxicount); - - /* If sb_icount overshot maxicount, report actual allocation */ - statp->f_files = max_t(typeof(statp->f_files), - statp->f_files, - sbp->sb_icount); - - /* make sure statp->f_ffree does not underflow */ - ffree = statp->f_files - (icount - ifree); - statp->f_ffree = max_t(int64_t, ffree, 0); + xfs_statfs_data(mp, st); + xfs_statfs_inodes(mp, st); if (XFS_IS_REALTIME_MOUNT(mp) && - (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) { - s64 freertx; - - statp->f_blocks = sbp->sb_rblocks; - freertx = percpu_counter_sum_positive(&mp->m_frextents); - statp->f_bavail = statp->f_bfree = - xfs_rtbxlen_to_blen(mp, freertx); - } + (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) + xfs_statfs_rt(mp, st); if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD)) - xfs_qm_statvfs(ip, statp); + xfs_qm_statvfs(ip, st); + /* + * XFS does not distinguish between blocks available to privileged and + * unprivileged users. + */ + st->f_bavail = st->f_bfree; return 0; } STATIC void -xfs_save_resvblks(struct xfs_mount *mp) +xfs_save_resvblks( + struct xfs_mount *mp) { - mp->m_resblks_save = mp->m_resblks; - xfs_reserve_blocks(mp, 0); + enum xfs_free_counter i; + + for (i = 0; i < XC_FREE_NR; i++) { + mp->m_free[i].res_saved = mp->m_free[i].res_total; + xfs_reserve_blocks(mp, i, 0); + } } STATIC void -xfs_restore_resvblks(struct xfs_mount *mp) +xfs_restore_resvblks( + struct xfs_mount *mp) { - uint64_t resblks; + uint64_t resblks; + enum xfs_free_counter i; - if (mp->m_resblks_save) { - resblks = mp->m_resblks_save; - mp->m_resblks_save = 0; - } else - resblks = xfs_default_resblks(mp); - - xfs_reserve_blocks(mp, resblks); + for (i = 0; i < XC_FREE_NR; i++) { + if (mp->m_free[i].res_saved) { + resblks = mp->m_free[i].res_saved; + mp->m_free[i].res_saved = 0; + } else + resblks = xfs_default_resblks(mp, i); + xfs_reserve_blocks(mp, i, resblks); + } } /* @@ -950,6 +1016,7 @@ xfs_fs_freeze( if (ret && !xfs_is_readonly(mp)) { xfs_blockgc_start(mp); xfs_inodegc_start(mp); + xfs_zone_gc_start(mp); } return ret; @@ -971,6 +1038,7 @@ xfs_fs_unfreeze( * filesystem. */ if (!xfs_is_readonly(mp)) { + xfs_zone_gc_start(mp); xfs_blockgc_start(mp); xfs_inodegc_start(mp); } @@ -1032,6 +1100,19 @@ xfs_finish_flags( return -EINVAL; } + if (!xfs_has_zoned(mp)) { + if (mp->m_max_open_zones) { + xfs_warn(mp, +"max_open_zones mount option only supported on zoned file systems."); + return -EINVAL; + } + if (mp->m_features & XFS_FEAT_NOLIFETIME) { + xfs_warn(mp, +"nolifetime mount option only supported on zoned file systems."); + return -EINVAL; + } + } + return 0; } @@ -1039,7 +1120,8 @@ static int xfs_init_percpu_counters( struct xfs_mount *mp) { - int error; + int error; + int i; error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL); if (error) @@ -1049,30 +1131,29 @@ xfs_init_percpu_counters( if (error) goto free_icount; - error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL); - if (error) - goto free_ifree; - error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL); if (error) - goto free_fdblocks; + goto free_ifree; error = percpu_counter_init(&mp->m_delalloc_rtextents, 0, GFP_KERNEL); if (error) goto free_delalloc; - error = percpu_counter_init(&mp->m_frextents, 0, GFP_KERNEL); - if (error) - goto free_delalloc_rt; + for (i = 0; i < XC_FREE_NR; i++) { + error = percpu_counter_init(&mp->m_free[i].count, 0, + GFP_KERNEL); + if (error) + goto free_freecounters; + } return 0; -free_delalloc_rt: +free_freecounters: + while (--i >= 0) + percpu_counter_destroy(&mp->m_free[i].count); percpu_counter_destroy(&mp->m_delalloc_rtextents); free_delalloc: percpu_counter_destroy(&mp->m_delalloc_blks); -free_fdblocks: - percpu_counter_destroy(&mp->m_fdblocks); free_ifree: percpu_counter_destroy(&mp->m_ifree); free_icount: @@ -1086,24 +1167,28 @@ xfs_reinit_percpu_counters( { percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount); percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree); - percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks); - percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents); + xfs_set_freecounter(mp, XC_FREE_BLOCKS, mp->m_sb.sb_fdblocks); + if (!xfs_has_zoned(mp)) + xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, + mp->m_sb.sb_frextents); } static void xfs_destroy_percpu_counters( struct xfs_mount *mp) { + enum xfs_free_counter i; + + for (i = 0; i < XC_FREE_NR; i++) + percpu_counter_destroy(&mp->m_free[i].count); percpu_counter_destroy(&mp->m_icount); percpu_counter_destroy(&mp->m_ifree); - percpu_counter_destroy(&mp->m_fdblocks); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_rtextents) == 0); percpu_counter_destroy(&mp->m_delalloc_rtextents); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_blks) == 0); percpu_counter_destroy(&mp->m_delalloc_blks); - percpu_counter_destroy(&mp->m_frextents); } static int @@ -1184,11 +1269,24 @@ xfs_fs_shutdown( xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED); } +static int +xfs_fs_show_stats( + struct seq_file *m, + struct dentry *root) +{ + struct xfs_mount *mp = XFS_M(root->d_sb); + + if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT)) + xfs_zoned_show_stats(m, mp); + return 0; +} + static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, .dirty_inode = xfs_fs_dirty_inode, .drop_inode = xfs_fs_drop_inode, + .evict_inode = xfs_fs_evict_inode, .put_super = xfs_fs_put_super, .sync_fs = xfs_fs_sync_fs, .freeze_fs = xfs_fs_freeze, @@ -1198,6 +1296,7 @@ static const struct super_operations xfs_super_operations = { .nr_cached_objects = xfs_fs_nr_cached_objects, .free_cached_objects = xfs_fs_free_cached_objects, .shutdown = xfs_fs_shutdown, + .show_stats = xfs_fs_show_stats, }; static int @@ -1410,6 +1509,15 @@ xfs_fs_parse_param( xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true); parsing_mp->m_features |= XFS_FEAT_NOATTR2; return 0; + case Opt_max_open_zones: + parsing_mp->m_max_open_zones = result.uint_32; + return 0; + case Opt_lifetime: + parsing_mp->m_features &= ~XFS_FEAT_NOLIFETIME; + return 0; + case Opt_nolifetime: + parsing_mp->m_features |= XFS_FEAT_NOLIFETIME; + return 0; default: xfs_warn(parsing_mp, "unknown mount option [%s].", param->key); return -EINVAL; @@ -1635,8 +1743,12 @@ xfs_fs_fill_super( #endif } - /* Filesystem claims it needs repair, so refuse the mount. */ - if (xfs_has_needsrepair(mp)) { + /* + * Filesystem claims it needs repair, so refuse the mount unless + * norecovery is also specified, in which case the filesystem can + * be mounted with no risk of further damage. + */ + if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; @@ -1730,7 +1842,7 @@ xfs_fs_fill_super( sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); @@ -1750,13 +1862,31 @@ xfs_fs_fill_super( mp->m_features &= ~XFS_FEAT_DISCARD; } - if (xfs_has_metadir(mp)) + if (xfs_has_zoned(mp)) { + if (!xfs_has_metadir(mp)) { + xfs_alert(mp, + "metadir feature required for zoned realtime devices."); + error = -EINVAL; + goto out_filestream_unmount; + } + xfs_warn_experimental(mp, XFS_EXPERIMENTAL_ZONED); + } else if (xfs_has_metadir(mp)) { xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR); + } if (xfs_has_reflink(mp)) { - if (mp->m_sb.sb_rblocks) { + if (xfs_has_realtime(mp) && + !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) { + xfs_alert(mp, + "reflink not compatible with realtime extent size %u!", + mp->m_sb.sb_rextsize); + error = -EINVAL; + goto out_filestream_unmount; + } + + if (xfs_has_zoned(mp)) { xfs_alert(mp, - "reflink not compatible with realtime device!"); + "reflink not compatible with zoned RT device!"); error = -EINVAL; goto out_filestream_unmount; } @@ -1767,12 +1897,6 @@ xfs_fs_fill_super( } } - if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) { - xfs_alert(mp, - "reverse mapping btree not compatible with realtime device!"); - error = -EINVAL; - goto out_filestream_unmount; - } if (xfs_has_exchange_range(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE); @@ -1891,6 +2015,9 @@ xfs_remount_rw( /* Re-enable the background inode inactivation worker. */ xfs_inodegc_start(mp); + /* Restart zone reclaim */ + xfs_zone_gc_start(mp); + return 0; } @@ -1935,6 +2062,9 @@ xfs_remount_ro( */ xfs_inodegc_stop(mp); + /* Stop zone reclaim */ + xfs_zone_gc_stop(mp); + /* Free the per-AG metadata reservation pool. */ xfs_fs_unreserve_ag_blocks(mp); @@ -1984,6 +2114,21 @@ xfs_fs_reconfigure( if (error) return error; + /* attr2 -> noattr2 */ + if (xfs_has_noattr2(new_mp)) { + if (xfs_has_crc(mp)) { + xfs_warn(mp, + "attr2 is always enabled for a V5 filesystem - can't be changed."); + return -EINVAL; + } + mp->m_features &= ~XFS_FEAT_ATTR2; + mp->m_features |= XFS_FEAT_NOATTR2; + } else if (xfs_has_attr2(new_mp)) { + /* noattr2 -> attr2 */ + mp->m_features &= ~XFS_FEAT_NOATTR2; + mp->m_features |= XFS_FEAT_ATTR2; + } + /* inode32 -> inode64 */ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) { mp->m_features &= ~XFS_FEAT_SMALL_INUMS; @@ -1996,6 +2141,17 @@ xfs_fs_reconfigure( mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } + /* + * Now that mp has been modified according to the remount options, we + * do a final option validation with xfs_finish_flags() just like it is + * just like it is done during mount. We cannot use + * done during mount. We cannot use xfs_finish_flags() on new_mp as it + * contains only the user given options. + */ + error = xfs_finish_flags(mp); + if (error) + return error; + /* ro -> rw */ if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) { error = xfs_remount_rw(mp); @@ -2056,6 +2212,7 @@ xfs_init_fs_context( for (i = 0; i < XG_TYPE_MAX; i++) xa_init(&mp->m_groups[i].xa); mutex_init(&mp->m_growlock); + mutex_init(&mp->m_metafile_resv_lock); INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); mp->m_kobj.kobject.kset = xfs_kset; @@ -2096,7 +2253,8 @@ static struct file_system_type xfs_fs_type = { .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = xfs_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME | + FS_LBS, }; MODULE_ALIAS_FS("xfs"); diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 302e6e5d6c7e..c0e85c1e42f2 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,7 +92,6 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; -extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index c84df23b494d..751dc74a3067 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax( return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static struct ctl_table xfs_table[] = { +static const struct ctl_table xfs_table[] = { { .procname = "irix_sgid_inherit", .data = &xfs_params.sgid_inherit.val, diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 60cb5318fdae..7a5c5ef2db92 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -13,6 +13,7 @@ #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_mount.h" +#include "xfs_zones.h" struct xfs_sysfs_attr { struct attribute attr; @@ -69,7 +70,7 @@ static struct attribute *xfs_mp_attrs[] = { }; ATTRIBUTE_GROUPS(xfs_mp); -const struct kobj_type xfs_mp_ktype = { +static const struct kobj_type xfs_mp_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, .default_groups = xfs_mp_groups, @@ -568,8 +569,8 @@ retry_timeout_seconds_store( if (val == -1) cfg->retry_timeout = XFS_ERR_RETRY_FOREVER; else { - cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC); - ASSERT(msecs_to_jiffies(val * MSEC_PER_SEC) < LONG_MAX); + cfg->retry_timeout = secs_to_jiffies(val); + ASSERT(secs_to_jiffies(val) < LONG_MAX); } return count; } @@ -686,8 +687,8 @@ xfs_error_sysfs_init_class( if (init[i].retry_timeout == XFS_ERR_RETRY_FOREVER) cfg->retry_timeout = XFS_ERR_RETRY_FOREVER; else - cfg->retry_timeout = msecs_to_jiffies( - init[i].retry_timeout * MSEC_PER_SEC); + cfg->retry_timeout = + secs_to_jiffies(init[i].retry_timeout); } return 0; @@ -701,45 +702,135 @@ out_error: return error; } +static inline struct xfs_mount *zoned_to_mp(struct kobject *kobj) +{ + return container_of(to_kobj(kobj), struct xfs_mount, m_zoned_kobj); +} + +static ssize_t +max_open_zones_show( + struct kobject *kobj, + char *buf) +{ + /* only report the open zones available for user data */ + return sysfs_emit(buf, "%u\n", + zoned_to_mp(kobj)->m_max_open_zones - XFS_OPEN_GC_ZONES); +} +XFS_SYSFS_ATTR_RO(max_open_zones); + +static ssize_t +zonegc_low_space_store( + struct kobject *kobj, + const char *buf, + size_t count) +{ + int ret; + unsigned int val; + + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; + + if (val > 100) + return -EINVAL; + + zoned_to_mp(kobj)->m_zonegc_low_space = val; + + return count; +} + +static ssize_t +zonegc_low_space_show( + struct kobject *kobj, + char *buf) +{ + return sysfs_emit(buf, "%u\n", + zoned_to_mp(kobj)->m_zonegc_low_space); +} +XFS_SYSFS_ATTR_RW(zonegc_low_space); + +static struct attribute *xfs_zoned_attrs[] = { + ATTR_LIST(max_open_zones), + ATTR_LIST(zonegc_low_space), + NULL, +}; +ATTRIBUTE_GROUPS(xfs_zoned); + +static const struct kobj_type xfs_zoned_ktype = { + .release = xfs_sysfs_release, + .sysfs_ops = &xfs_sysfs_ops, + .default_groups = xfs_zoned_groups, +}; + int -xfs_error_sysfs_init( +xfs_mount_sysfs_init( struct xfs_mount *mp) { int error; + super_set_sysfs_name_id(mp->m_super); + + /* .../xfs/<dev>/ */ + error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, + NULL, mp->m_super->s_id); + if (error) + return error; + + /* .../xfs/<dev>/stats/ */ + error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype, + &mp->m_kobj, "stats"); + if (error) + goto out_remove_fsdir; + /* .../xfs/<dev>/error/ */ error = xfs_sysfs_init(&mp->m_error_kobj, &xfs_error_ktype, &mp->m_kobj, "error"); if (error) - return error; + goto out_remove_stats_dir; + /* .../xfs/<dev>/error/fail_at_unmount */ error = sysfs_create_file(&mp->m_error_kobj.kobject, ATTR_LIST(fail_at_unmount)); if (error) - goto out_error; + goto out_remove_error_dir; /* .../xfs/<dev>/error/metadata/ */ error = xfs_error_sysfs_init_class(mp, XFS_ERR_METADATA, "metadata", &mp->m_error_meta_kobj, xfs_error_meta_init); if (error) - goto out_error; + goto out_remove_error_dir; + + if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) { + /* .../xfs/<dev>/zoned/ */ + error = xfs_sysfs_init(&mp->m_zoned_kobj, &xfs_zoned_ktype, + &mp->m_kobj, "zoned"); + if (error) + goto out_remove_error_dir; + } return 0; -out_error: +out_remove_error_dir: xfs_sysfs_del(&mp->m_error_kobj); +out_remove_stats_dir: + xfs_sysfs_del(&mp->m_stats.xs_kobj); +out_remove_fsdir: + xfs_sysfs_del(&mp->m_kobj); return error; } void -xfs_error_sysfs_del( +xfs_mount_sysfs_del( struct xfs_mount *mp) { struct xfs_error_cfg *cfg; int i, j; + if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) + xfs_sysfs_del(&mp->m_zoned_kobj); + for (i = 0; i < XFS_ERR_CLASS_MAX; i++) { for (j = 0; j < XFS_ERR_ERRNO_MAX; j++) { cfg = &mp->m_error_cfg[i][j]; @@ -749,6 +840,8 @@ xfs_error_sysfs_del( } xfs_sysfs_del(&mp->m_error_meta_kobj); xfs_sysfs_del(&mp->m_error_kobj); + xfs_sysfs_del(&mp->m_stats.xs_kobj); + xfs_sysfs_del(&mp->m_kobj); } struct xfs_error_cfg * diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index 148893ebfdef..1622fe80ad3e 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -7,7 +7,6 @@ #ifndef __XFS_SYSFS_H__ #define __XFS_SYSFS_H__ -extern const struct kobj_type xfs_mp_ktype; /* xfs_mount */ extern const struct kobj_type xfs_dbg_ktype; /* debug */ extern const struct kobj_type xfs_log_ktype; /* xlog */ extern const struct kobj_type xfs_stats_ktype; /* stats */ @@ -53,7 +52,7 @@ xfs_sysfs_del( wait_for_completion(&kobj->complete); } -int xfs_error_sysfs_init(struct xfs_mount *mp); -void xfs_error_sysfs_del(struct xfs_mount *mp); +int xfs_mount_sysfs_init(struct xfs_mount *mp); +void xfs_mount_sysfs_del(struct xfs_mount *mp); #endif /* __XFS_SYSFS_H__ */ diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 8f530e69c18a..a60556dbd172 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -49,6 +49,8 @@ #include "xfs_metafile.h" #include "xfs_metadir.h" #include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" /* * We include this last to have the helpers above available for the trace diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7b16cdd72e9d..e56ba1963160 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -14,11 +14,15 @@ * ino: filesystem inode number * * agbno: per-AG block number in fs blocks + * rgbno: per-rtgroup block number in fs blocks * startblock: physical block number for file mappings. This is either a * segmented fsblock for data device mappings, or a rfsblock * for realtime device mappings * fsbcount: number of blocks in an extent, in fs blocks * + * gbno: generic allocation group block number. This is an agbno for + * space in a per-AG or a rgbno for space in a realtime group. + * * daddr: physical block number in 512b blocks * bbcount: number of blocks in a physical extent, in 512b blocks * @@ -98,6 +102,7 @@ struct xfs_rmap_intent; struct xfs_refcount_intent; struct xfs_metadir_update; struct xfs_rtgroup; +struct xfs_open_zone; #define XFS_ATTR_FILTER_FLAGS \ { XFS_ATTR_ROOT, "ROOT" }, \ @@ -261,6 +266,152 @@ DEFINE_GROUP_REF_EVENT(xfs_group_grab); DEFINE_GROUP_REF_EVENT(xfs_group_grab_next_tag); DEFINE_GROUP_REF_EVENT(xfs_group_rele); +#ifdef CONFIG_XFS_RT +DECLARE_EVENT_CLASS(xfs_zone_class, + TP_PROTO(struct xfs_rtgroup *rtg), + TP_ARGS(rtg), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, used) + __field(unsigned int, nr_open) + ), + TP_fast_assign( + struct xfs_mount *mp = rtg_mount(rtg); + + __entry->dev = mp->m_super->s_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->used = rtg_rmap(rtg)->i_used_blocks; + __entry->nr_open = mp->m_zone_info->zi_nr_open_zones; + ), + TP_printk("dev %d:%d rgno 0x%x used 0x%x nr_open %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->used, + __entry->nr_open) +); + +#define DEFINE_ZONE_EVENT(name) \ +DEFINE_EVENT(xfs_zone_class, name, \ + TP_PROTO(struct xfs_rtgroup *rtg), \ + TP_ARGS(rtg)) +DEFINE_ZONE_EVENT(xfs_zone_emptied); +DEFINE_ZONE_EVENT(xfs_zone_full); +DEFINE_ZONE_EVENT(xfs_zone_opened); +DEFINE_ZONE_EVENT(xfs_zone_reset); +DEFINE_ZONE_EVENT(xfs_zone_gc_target_opened); + +TRACE_EVENT(xfs_zone_free_blocks, + TP_PROTO(struct xfs_rtgroup *rtg, xfs_rgblock_t rgbno, + xfs_extlen_t len), + TP_ARGS(rtg, rgbno, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, used) + __field(xfs_rgblock_t, rgbno) + __field(xfs_extlen_t, len) + ), + TP_fast_assign( + __entry->dev = rtg_mount(rtg)->m_super->s_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->used = rtg_rmap(rtg)->i_used_blocks; + __entry->rgbno = rgbno; + __entry->len = len; + ), + TP_printk("dev %d:%d rgno 0x%x used 0x%x rgbno 0x%x len 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->used, + __entry->rgbno, + __entry->len) +); + +DECLARE_EVENT_CLASS(xfs_zone_alloc_class, + TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno, + xfs_extlen_t len), + TP_ARGS(oz, rgbno, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, used) + __field(xfs_rgblock_t, written) + __field(xfs_rgblock_t, write_pointer) + __field(xfs_rgblock_t, rgbno) + __field(xfs_extlen_t, len) + ), + TP_fast_assign( + __entry->dev = rtg_mount(oz->oz_rtg)->m_super->s_dev; + __entry->rgno = rtg_rgno(oz->oz_rtg); + __entry->used = rtg_rmap(oz->oz_rtg)->i_used_blocks; + __entry->written = oz->oz_written; + __entry->write_pointer = oz->oz_write_pointer; + __entry->rgbno = rgbno; + __entry->len = len; + ), + TP_printk("dev %d:%d rgno 0x%x used 0x%x written 0x%x wp 0x%x rgbno 0x%x len 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->used, + __entry->written, + __entry->write_pointer, + __entry->rgbno, + __entry->len) +); + +#define DEFINE_ZONE_ALLOC_EVENT(name) \ +DEFINE_EVENT(xfs_zone_alloc_class, name, \ + TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno, \ + xfs_extlen_t len), \ + TP_ARGS(oz, rgbno, len)) +DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks); +DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks); + +TRACE_EVENT(xfs_zone_gc_select_victim, + TP_PROTO(struct xfs_rtgroup *rtg, unsigned int bucket), + TP_ARGS(rtg, bucket), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, used) + __field(unsigned int, bucket) + ), + TP_fast_assign( + __entry->dev = rtg_mount(rtg)->m_super->s_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->used = rtg_rmap(rtg)->i_used_blocks; + __entry->bucket = bucket; + ), + TP_printk("dev %d:%d rgno 0x%x used 0x%x bucket %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->used, + __entry->bucket) +); + +TRACE_EVENT(xfs_zones_mount, + TP_PROTO(struct xfs_mount *mp), + TP_ARGS(mp), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgcount) + __field(uint32_t, blocks) + __field(unsigned int, max_open_zones) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rgcount = mp->m_sb.sb_rgcount; + __entry->blocks = mp->m_groups[XG_TYPE_RTG].blocks; + __entry->max_open_zones = mp->m_max_open_zones; + ), + TP_printk("dev %d:%d zoned %u blocks_per_zone %u, max_open %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgcount, + __entry->blocks, + __entry->max_open_zones) +); +#endif /* CONFIG_XFS_RT */ + TRACE_EVENT(xfs_inodegc_worker, TP_PROTO(struct xfs_mount *mp, unsigned int shrinker_hits), TP_ARGS(mp, shrinker_hits), @@ -494,7 +645,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -541,6 +692,10 @@ DEFINE_BUF_EVENT(xfs_buf_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); DEFINE_BUF_EVENT(xfs_buf_drain_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); +DEFINE_BUF_EVENT(xfs_buf_backing_folio); +DEFINE_BUF_EVENT(xfs_buf_backing_kmem); +DEFINE_BUF_EVENT(xfs_buf_backing_vmalloc); +DEFINE_BUF_EVENT(xfs_buf_backing_fallback); /* not really buffer traces, but the buf provides useful information */ DEFINE_BUF_EVENT(xfs_btree_corrupt); @@ -565,7 +720,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; __entry->flags = flags; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->caller_ip = caller_ip; @@ -589,6 +744,7 @@ DEFINE_EVENT(xfs_buf_flags_class, name, \ DEFINE_BUF_FLAGS_EVENT(xfs_buf_find); DEFINE_BUF_FLAGS_EVENT(xfs_buf_get); DEFINE_BUF_FLAGS_EVENT(xfs_buf_read); +DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead); TRACE_EVENT(xfs_buf_ioerror, TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip), @@ -608,7 +764,7 @@ TRACE_EVENT(xfs_buf_ioerror, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->error = error; @@ -652,7 +808,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class, __entry->buf_bno = xfs_buf_daddr(bip->bli_buf); __entry->buf_len = bip->bli_buf->b_length; __entry->buf_flags = bip->bli_buf->b_flags; - __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); + __entry->buf_hold = bip->bli_buf->b_hold; __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); __entry->buf_lockval = bip->bli_buf->b_sema.count; __entry->li_flags = bip->bli_item.li_flags; @@ -1591,6 +1747,7 @@ 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); DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read); +DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), @@ -2295,6 +2452,7 @@ 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), @@ -2918,13 +3076,14 @@ DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item); /* rmap tracepoints */ DECLARE_EVENT_CLASS(xfs_rmap_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, const struct xfs_owner_info *oinfo), - TP_ARGS(cur, agbno, len, unwritten, oinfo), + TP_ARGS(cur, gbno, len, unwritten, oinfo), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -2932,8 +3091,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = oinfo->oi_owner; __entry->offset = oinfo->oi_offset; @@ -2941,10 +3101,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, if (unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -2953,9 +3114,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, #define DEFINE_RMAP_EVENT(name) \ DEFINE_EVENT(xfs_rmap_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, \ + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, \ const struct xfs_owner_info *oinfo), \ - TP_ARGS(cur, agbno, len, unwritten, oinfo)) + TP_ARGS(cur, gbno, len, unwritten, oinfo)) /* btree cursor error/%ip tracepoint class */ DECLARE_EVENT_CLASS(xfs_btree_error_class, @@ -3018,47 +3179,36 @@ TRACE_EVENT(xfs_rmap_convert_state, TP_ARGS(cur, state, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_ino_t, ino) __field(int, state) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; - switch (cur->bc_ops->type) { - case XFS_BTREE_TYPE_INODE: - __entry->agno = 0; - __entry->ino = cur->bc_ino.ip->i_ino; - break; - case XFS_BTREE_TYPE_AG: - __entry->agno = cur->bc_group->xg_gno; - __entry->ino = 0; - break; - case XFS_BTREE_TYPE_MEM: - __entry->agno = 0; - __entry->ino = 0; - break; - } + __entry->type = cur->bc_group->xg_type; + __entry->agno = cur->bc_group->xg_gno; __entry->state = state; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d agno 0x%x ino 0x%llx state %d caller %pS", + TP_printk("dev %d:%d %sno 0x%x state %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->ino, __entry->state, (char *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_rmapbt_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, + xfs_agblock_t gbno, xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags), - TP_ARGS(cur, agbno, len, owner, offset, flags), + TP_ARGS(cur, gbno, len, owner, offset, flags), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -3066,17 +3216,19 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = owner; __entry->offset = offset; __entry->flags = flags; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -3085,9 +3237,9 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, #define DEFINE_RMAPBT_EVENT(name) \ DEFINE_EVENT(xfs_rmapbt_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, \ + xfs_agblock_t gbno, xfs_extlen_t len, \ uint64_t owner, uint64_t offset, unsigned int flags), \ - TP_ARGS(cur, agbno, len, owner, offset, flags)) + TP_ARGS(cur, gbno, len, owner, offset, flags)) TRACE_DEFINE_ENUM(XFS_RMAP_MAP); TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED); @@ -3104,8 +3256,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, owner) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(int, whichfork) __field(xfs_fileoff_t, l_loff) __field(xfs_filblks_t, l_len) @@ -3114,9 +3267,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock); - __entry->agbno = XFS_FSB_TO_AGBNO(mp, - ri->ri_bmap.br_startblock); + __entry->type = ri->ri_group->xg_type; + __entry->agno = ri->ri_group->xg_gno; + __entry->gbno = xfs_fsb_to_gbno(mp, + ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); __entry->owner = ri->ri_owner; __entry->whichfork = ri->ri_whichfork; __entry->l_loff = ri->ri_bmap.br_startoff; @@ -3124,11 +3279,12 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, __entry->l_state = ri->ri_bmap.br_state; __entry->op = ri->ri_type; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_RMAP_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->owner, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->l_loff, @@ -3302,56 +3458,62 @@ TRACE_EVENT(xfs_ag_resv_init_error, /* refcount tracepoint classes */ DECLARE_EVENT_CLASS(xfs_refcount_class, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len), - TP_ARGS(cur, agbno, len), + TP_ARGS(cur, gbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_class, name, \ - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, \ + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, \ xfs_extlen_t len), \ - TP_ARGS(cur, agbno, len)) + TP_ARGS(cur, gbno, len)) TRACE_DEFINE_ENUM(XFS_LOOKUP_EQi); TRACE_DEFINE_ENUM(XFS_LOOKUP_LEi); TRACE_DEFINE_ENUM(XFS_LOOKUP_GEi); TRACE_EVENT(xfs_refcount_lookup, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_lookup_t dir), - TP_ARGS(cur, agbno, dir), + TP_ARGS(cur, gbno, dir), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_lookup_t, dir) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->dir = dir; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x cmp %s(%d)", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x cmp %s(%d)", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __print_symbolic(__entry->dir, XFS_AG_BTREE_CMP_FORMAT_STR), __entry->dir) ) @@ -3362,6 +3524,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_ARGS(cur, irec), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) @@ -3370,14 +3533,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, @@ -3393,49 +3558,53 @@ DEFINE_EVENT(xfs_refcount_extent_class, name, \ /* single-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, - xfs_agblock_t agbno), - TP_ARGS(cur, irec, agbno), + xfs_agblock_t gbno), + TP_ARGS(cur, irec, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, \ - xfs_agblock_t agbno), \ - TP_ARGS(cur, irec, agbno)) + xfs_agblock_t gbno), \ + TP_ARGS(cur, irec, gbno)) /* double-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2), + struct xfs_refcount_irec *i2), TP_ARGS(cur, i1, i2), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3448,6 +3617,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3458,9 +3628,10 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3481,10 +3652,11 @@ DEFINE_EVENT(xfs_refcount_double_extent_class, name, \ /* double-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), - TP_ARGS(cur, i1, i2, agbno), + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), + TP_ARGS(cur, i1, i2, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3494,10 +3666,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3507,11 +3680,12 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3521,14 +3695,14 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_double_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), \ - TP_ARGS(cur, i1, i2, agbno)) + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), \ + TP_ARGS(cur, i1, i2, gbno)) /* triple-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, @@ -3537,6 +3711,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_ARGS(cur, i1, i2, i3), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3553,6 +3728,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3567,10 +3743,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3638,23 +3815,27 @@ DECLARE_EVENT_CLASS(xfs_refcount_deferred_class, TP_ARGS(mp, refc), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, op) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, refc->ri_startblock); + __entry->type = refc->ri_group->xg_type; + __entry->agno = refc->ri_group->xg_gno; __entry->op = refc->ri_type; - __entry->agbno = XFS_FSB_TO_AGBNO(mp, refc->ri_startblock); + __entry->gbno = xfs_fsb_to_gbno(mp, refc->ri_startblock, + refc->ri_group->xg_type); __entry->len = refc->ri_blockcount; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_REFCOUNT_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_DEFERRED_EVENT(name) \ @@ -3954,6 +4135,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_from); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_to); +DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_skip); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); @@ -3993,7 +4175,7 @@ TRACE_EVENT(xfs_fsmap_mapping, __entry->offset = frec->offset; __entry->flags = frec->rm_flags; ), - TP_printk("dev %d:%d keydev %d:%d agno 0x%x rmapbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d keydev %d:%d agno 0x%x gbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, @@ -4950,7 +5132,7 @@ DECLARE_EVENT_CLASS(xfbtree_buf_class, __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -5574,6 +5756,107 @@ DEFINE_EVENT(xfs_metadir_class, name, \ TP_ARGS(dp, name, ino)) DEFINE_METADIR_EVENT(xfs_metadir_lookup); +/* metadata inode space reservations */ + +DECLARE_EVENT_CLASS(xfs_metafile_resv_class, + TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), + TP_ARGS(mp, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned long long, freeblks) + __field(unsigned long long, reserved) + __field(unsigned long long, asked) + __field(unsigned long long, used) + __field(unsigned long long, len) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->freeblks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS); + __entry->reserved = mp->m_metafile_resv_avail; + __entry->asked = mp->m_metafile_resv_target; + __entry->used = mp->m_metafile_resv_used; + __entry->len = len; + ), + TP_printk("dev %d:%d freeblks %llu resv %llu ask %llu used %llu len %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->freeblks, + __entry->reserved, + __entry->asked, + __entry->used, + __entry->len) +) +#define DEFINE_METAFILE_RESV_EVENT(name) \ +DEFINE_EVENT(xfs_metafile_resv_class, name, \ + TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), \ + TP_ARGS(mp, len)) +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init_error); + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xfs_growfs_check_rtgeom, + TP_PROTO(const struct xfs_mount *mp, unsigned int min_logfsbs), + TP_ARGS(mp, min_logfsbs), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, logblocks) + __field(unsigned int, min_logfsbs) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->logblocks = mp->m_sb.sb_logblocks; + __entry->min_logfsbs = min_logfsbs; + ), + TP_printk("dev %d:%d logblocks %u min_logfsbs %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->logblocks, + __entry->min_logfsbs) +); +#endif /* CONFIG_XFS_RT */ + +TRACE_DEFINE_ENUM(XC_FREE_BLOCKS); +TRACE_DEFINE_ENUM(XC_FREE_RTEXTENTS); +TRACE_DEFINE_ENUM(XC_FREE_RTAVAILABLE); + +DECLARE_EVENT_CLASS(xfs_freeblocks_resv_class, + TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, + uint64_t delta, unsigned long caller_ip), + TP_ARGS(mp, ctr, delta, caller_ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(enum xfs_free_counter, ctr) + __field(uint64_t, delta) + __field(uint64_t, avail) + __field(uint64_t, total) + __field(unsigned long, caller_ip) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->ctr = ctr; + __entry->delta = delta; + __entry->avail = mp->m_free[ctr].res_avail; + __entry->total = mp->m_free[ctr].res_total; + __entry->caller_ip = caller_ip; + ), + TP_printk("dev %d:%d ctr %s delta %llu avail %llu total %llu caller %pS", + MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->ctr, XFS_FREECOUNTER_STR), + __entry->delta, + __entry->avail, + __entry->total, + (char *)__entry->caller_ip) +) +#define DEFINE_FREEBLOCKS_RESV_EVENT(name) \ +DEFINE_EVENT(xfs_freeblocks_resv_class, name, \ + TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, \ + uint64_t delta, unsigned long caller_ip), \ + TP_ARGS(mp, ctr, delta, caller_ip)) +DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_reserved); +DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_enospc); + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 4cd25717c9d1..c6657072361a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -100,7 +100,6 @@ xfs_trans_dup( /* * Initialize the new transaction structure. */ - ntp->t_magic = XFS_TRANS_HEADER_MAGIC; ntp->t_mountp = tp->t_mountp; INIT_LIST_HEAD(&ntp->t_items); INIT_LIST_HEAD(&ntp->t_busy); @@ -275,7 +274,6 @@ retry: ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) || xfs_has_lazysbcount(mp)); - tp->t_magic = XFS_TRANS_HEADER_MAGIC; tp->t_flags = flags; tp->t_mountp = mp; INIT_LIST_HEAD(&tp->t_items); @@ -1266,6 +1264,9 @@ retry: xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + if (xfs_is_metadir_inode(ip)) + goto out; + error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ @@ -1334,6 +1335,7 @@ retry: goto out_cancel; } +out: *tpp = tp; return 0; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 71c2e82e4dad..2b366851e9a4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -122,7 +122,6 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, * This is the structure maintained for every active transaction. */ typedef struct xfs_trans { - unsigned int t_magic; /* magic number */ unsigned int t_log_res; /* amt of log space resvd */ unsigned int t_log_count; /* count for perm log res */ unsigned int t_blk_res; /* # of blocks resvd */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index f56d62dced97..67c328d23e4a 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -315,7 +315,7 @@ xfs_ail_splice( } /* - * Delete the given item from the AIL. Return a pointer to the item. + * Delete the given item from the AIL. */ static void xfs_ail_delete( @@ -359,13 +359,8 @@ xfsaild_resubmit_item( } /* protected by ail_lock */ - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (bp->b_flags & (_XBF_INODES | _XBF_DQUOTS)) - clear_bit(XFS_LI_FAILED, &lip->li_flags); - else - xfs_clear_li_failed(lip); - } - + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) + clear_bit(XFS_LI_FAILED, &lip->li_flags); xfs_buf_unlock(bp); return XFS_ITEM_SUCCESS; } @@ -782,26 +777,28 @@ xfs_ail_update_finish( } /* - * xfs_trans_ail_update - bulk AIL insertion operation. + * xfs_trans_ail_update_bulk - bulk AIL insertion operation. * - * @xfs_trans_ail_update takes an array of log items that all need to be + * @xfs_trans_ail_update_bulk takes an array of log items that all need to be * positioned at the same LSN in the AIL. If an item is not in the AIL, it will - * be added. Otherwise, it will be repositioned by removing it and re-adding - * it to the AIL. If we move the first item in the AIL, update the log tail to - * match the new minimum LSN in the AIL. + * be added. Otherwise, it will be repositioned by removing it and re-adding + * it to the AIL. + * + * If we move the first item in the AIL, update the log tail to match the new + * minimum LSN in the AIL. * - * This function takes the AIL lock once to execute the update operations on - * all the items in the array, and as such should not be called with the AIL - * lock held. As a result, once we have the AIL lock, we need to check each log - * item LSN to confirm it needs to be moved forward in the AIL. + * This function should be called with the AIL lock held. * - * To optimise the insert operation, we delete all the items from the AIL in - * the first pass, moving them into a temporary list, then splice the temporary - * list into the correct position in the AIL. This avoids needing to do an - * insert operation on every item. + * To optimise the insert operation, we add all items to a temporary list, then + * splice this list into the correct position in the AIL. * - * This function must be called with the AIL lock held. The lock is dropped - * before returning. + * Items that are already in the AIL are first deleted from their current + * location before being added to the temporary list. + * + * This avoids needing to do an insert operation on every item. + * + * The AIL lock is dropped by xfs_ail_update_finish() before returning to + * the caller. */ void xfs_trans_ail_update_bulk( @@ -914,10 +911,9 @@ xfs_trans_ail_delete( return; } - /* xfs_ail_update_finish() drops the AIL lock */ - xfs_clear_li_failed(lip); + clear_bit(XFS_LI_FAILED, &lip->li_flags); tail_lsn = xfs_ail_delete_one(ailp, lip); - xfs_ail_update_finish(ailp, tail_lsn); + xfs_ail_update_finish(ailp, tail_lsn); /* drops the AIL lock */ } int diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8e886ecfd69a..53af546c0b23 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -659,7 +659,7 @@ xfs_trans_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -684,7 +684,7 @@ xfs_trans_stale_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_STALE_INODE; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -709,7 +709,7 @@ xfs_trans_inode_alloc_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -820,6 +820,6 @@ xfs_trans_dquot_buf( break; } - bp->b_flags |= _XBF_DQUOTS; + bp->b_iodone = xfs_buf_dquot_iodone; xfs_trans_buf_set_type(tp, bp, type); } diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 713b6d243e56..765456bf3428 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -156,7 +156,8 @@ xfs_trans_mod_ino_dquot( unsigned int field, int64_t delta) { - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); + if (xfs_is_metadir_inode(ip)) + return; xfs_trans_mod_dquot(tp, dqp, field, delta); @@ -246,11 +247,10 @@ xfs_trans_mod_dquot_byino( xfs_mount_t *mp = tp->t_mountp; if (!XFS_IS_QUOTA_ON(mp) || - xfs_is_quota_inode(&mp->m_sb, ip->i_ino)) + xfs_is_quota_inode(&mp->m_sb, ip->i_ino) || + xfs_is_metadir_inode(ip)) return; - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); - if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot) xfs_trans_mod_ino_dquot(tp, ip, ip->i_udquot, field, delta); if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot) diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index bd841df93021..f945f0450b16 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -167,32 +167,4 @@ xfs_trans_ail_copy_lsn( } #endif -static inline void -xfs_clear_li_failed( - struct xfs_log_item *lip) -{ - struct xfs_buf *bp = lip->li_buf; - - ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags)); - lockdep_assert_held(&lip->li_ailp->ail_lock); - - if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) { - lip->li_buf = NULL; - xfs_buf_rele(bp); - } -} - -static inline void -xfs_set_li_failed( - struct xfs_log_item *lip, - struct xfs_buf *bp) -{ - lockdep_assert_held(&lip->li_ailp->ail_lock); - - if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) { - xfs_buf_hold(bp); - lip->li_buf = bp; - } -} - #endif /* __XFS_TRANS_PRIV_H__ */ diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c new file mode 100644 index 000000000000..d509e49b2aaa --- /dev/null +++ b/fs/xfs/xfs_zone_alloc.c @@ -0,0 +1,1227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_error.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_iomap.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_bmap.h" +#include "xfs_bmap_btree.h" +#include "xfs_trans_space.h" +#include "xfs_refcount.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" +#include "xfs_zones.h" +#include "xfs_trace.h" + +void +xfs_open_zone_put( + struct xfs_open_zone *oz) +{ + if (atomic_dec_and_test(&oz->oz_ref)) { + xfs_rtgroup_rele(oz->oz_rtg); + kfree(oz); + } +} + +static inline uint32_t +xfs_zone_bucket( + struct xfs_mount *mp, + uint32_t used_blocks) +{ + return XFS_ZONE_USED_BUCKETS * used_blocks / + mp->m_groups[XG_TYPE_RTG].blocks; +} + +static inline void +xfs_zone_add_to_bucket( + struct xfs_zone_info *zi, + xfs_rgnumber_t rgno, + uint32_t to_bucket) +{ + __set_bit(rgno, zi->zi_used_bucket_bitmap[to_bucket]); + zi->zi_used_bucket_entries[to_bucket]++; +} + +static inline void +xfs_zone_remove_from_bucket( + struct xfs_zone_info *zi, + xfs_rgnumber_t rgno, + uint32_t from_bucket) +{ + __clear_bit(rgno, zi->zi_used_bucket_bitmap[from_bucket]); + zi->zi_used_bucket_entries[from_bucket]--; +} + +static void +xfs_zone_account_reclaimable( + struct xfs_rtgroup *rtg, + uint32_t freed) +{ + struct xfs_group *xg = &rtg->rtg_group; + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_zone_info *zi = mp->m_zone_info; + uint32_t used = rtg_rmap(rtg)->i_used_blocks; + xfs_rgnumber_t rgno = rtg_rgno(rtg); + uint32_t from_bucket = xfs_zone_bucket(mp, used + freed); + uint32_t to_bucket = xfs_zone_bucket(mp, used); + bool was_full = (used + freed == rtg_blocks(rtg)); + + /* + * This can be called from log recovery, where the zone_info structure + * hasn't been allocated yet. Skip all work as xfs_mount_zones will + * add the zones to the right buckets before the file systems becomes + * active. + */ + if (!zi) + return; + + if (!used) { + /* + * The zone is now empty, remove it from the bottom bucket and + * trigger a reset. + */ + trace_xfs_zone_emptied(rtg); + + if (!was_full) + xfs_group_clear_mark(xg, XFS_RTG_RECLAIMABLE); + + spin_lock(&zi->zi_used_buckets_lock); + if (!was_full) + xfs_zone_remove_from_bucket(zi, rgno, from_bucket); + spin_unlock(&zi->zi_used_buckets_lock); + + spin_lock(&zi->zi_reset_list_lock); + xg->xg_next_reset = zi->zi_reset_list; + zi->zi_reset_list = xg; + spin_unlock(&zi->zi_reset_list_lock); + + if (zi->zi_gc_thread) + wake_up_process(zi->zi_gc_thread); + } else if (was_full) { + /* + * The zone transitioned from full, mark it up as reclaimable + * and wake up GC which might be waiting for zones to reclaim. + */ + spin_lock(&zi->zi_used_buckets_lock); + xfs_zone_add_to_bucket(zi, rgno, to_bucket); + spin_unlock(&zi->zi_used_buckets_lock); + + xfs_group_set_mark(xg, XFS_RTG_RECLAIMABLE); + if (zi->zi_gc_thread && xfs_zoned_need_gc(mp)) + wake_up_process(zi->zi_gc_thread); + } else if (to_bucket != from_bucket) { + /* + * Move the zone to a new bucket if it dropped below the + * threshold. + */ + spin_lock(&zi->zi_used_buckets_lock); + xfs_zone_add_to_bucket(zi, rgno, to_bucket); + xfs_zone_remove_from_bucket(zi, rgno, from_bucket); + spin_unlock(&zi->zi_used_buckets_lock); + } +} + +static void +xfs_open_zone_mark_full( + struct xfs_open_zone *oz) +{ + struct xfs_rtgroup *rtg = oz->oz_rtg; + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_zone_info *zi = mp->m_zone_info; + uint32_t used = rtg_rmap(rtg)->i_used_blocks; + + trace_xfs_zone_full(rtg); + + WRITE_ONCE(rtg->rtg_open_zone, NULL); + + spin_lock(&zi->zi_open_zones_lock); + if (oz->oz_is_gc) { + ASSERT(current == zi->zi_gc_thread); + zi->zi_open_gc_zone = NULL; + } else { + zi->zi_nr_open_zones--; + list_del_init(&oz->oz_entry); + } + spin_unlock(&zi->zi_open_zones_lock); + xfs_open_zone_put(oz); + + wake_up_all(&zi->zi_zone_wait); + if (used < rtg_blocks(rtg)) + xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used); +} + +static void +xfs_zone_record_blocks( + struct xfs_trans *tp, + xfs_fsblock_t fsbno, + xfs_filblks_t len, + struct xfs_open_zone *oz, + bool used) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = oz->oz_rtg; + struct xfs_inode *rmapip = rtg_rmap(rtg); + + trace_xfs_zone_record_blocks(oz, xfs_rtb_to_rgbno(mp, fsbno), len); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + if (used) { + rmapip->i_used_blocks += len; + ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); + } else { + xfs_add_frextents(mp, len); + } + oz->oz_written += len; + if (oz->oz_written == rtg_blocks(rtg)) + xfs_open_zone_mark_full(oz); + xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE); +} + +static int +xfs_zoned_map_extent( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct xfs_bmbt_irec *new, + struct xfs_open_zone *oz, + xfs_fsblock_t old_startblock) +{ + struct xfs_bmbt_irec data; + int nmaps = 1; + int error; + + /* Grab the corresponding mapping in the data fork. */ + error = xfs_bmapi_read(ip, new->br_startoff, new->br_blockcount, &data, + &nmaps, 0); + if (error) + return error; + + /* + * Cap the update to the existing extent in the data fork because we can + * only overwrite one extent at a time. + */ + ASSERT(new->br_blockcount >= data.br_blockcount); + new->br_blockcount = data.br_blockcount; + + /* + * If a data write raced with this GC write, keep the existing data in + * the data fork, mark our newly written GC extent as reclaimable, then + * move on to the next extent. + */ + if (old_startblock != NULLFSBLOCK && + old_startblock != data.br_startblock) + goto skip; + + trace_xfs_reflink_cow_remap_from(ip, new); + trace_xfs_reflink_cow_remap_to(ip, &data); + + error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, + XFS_IEXT_REFLINK_END_COW_CNT); + if (error) + return error; + + if (data.br_startblock != HOLESTARTBLOCK) { + ASSERT(data.br_startblock != DELAYSTARTBLOCK); + ASSERT(!isnullstartblock(data.br_startblock)); + + xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data); + if (xfs_is_reflink_inode(ip)) { + xfs_refcount_decrease_extent(tp, true, &data); + } else { + error = xfs_free_extent_later(tp, data.br_startblock, + data.br_blockcount, NULL, + XFS_AG_RESV_NONE, + XFS_FREE_EXTENT_REALTIME); + if (error) + return error; + } + } + + xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, + true); + + /* Map the new blocks into the data fork. */ + xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new); + return 0; + +skip: + trace_xfs_reflink_cow_remap_skip(ip, new); + xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, + false); + return 0; +} + +int +xfs_zoned_end_io( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t count, + xfs_daddr_t daddr, + struct xfs_open_zone *oz, + xfs_fsblock_t old_startblock) +{ + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); + struct xfs_bmbt_irec new = { + .br_startoff = XFS_B_TO_FSBT(mp, offset), + .br_startblock = xfs_daddr_to_rtb(mp, daddr), + .br_state = XFS_EXT_NORM, + }; + unsigned int resblks = + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + struct xfs_trans *tp; + int error; + + if (xfs_is_shutdown(mp)) + return -EIO; + + while (new.br_startoff < end_fsb) { + new.br_blockcount = end_fsb - new.br_startoff; + + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, + XFS_TRANS_RESERVE | XFS_TRANS_RES_FDBLKS, &tp); + if (error) + return error; + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); + + error = xfs_zoned_map_extent(tp, ip, &new, oz, old_startblock); + if (error) + xfs_trans_cancel(tp); + else + error = xfs_trans_commit(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + if (error) + return error; + + new.br_startoff += new.br_blockcount; + new.br_startblock += new.br_blockcount; + if (old_startblock != NULLFSBLOCK) + old_startblock += new.br_blockcount; + } + + return 0; +} + +/* + * "Free" blocks allocated in a zone. + * + * Just decrement the used blocks counter and report the space as freed. + */ +int +xfs_zone_free_blocks( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg, + xfs_fsblock_t fsbno, + xfs_filblks_t len) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *rmapip = rtg_rmap(rtg); + + xfs_assert_ilocked(rmapip, XFS_ILOCK_EXCL); + + if (len > rmapip->i_used_blocks) { + xfs_err(mp, +"trying to free more blocks (%lld) than used counter (%u).", + len, rmapip->i_used_blocks); + ASSERT(len <= rmapip->i_used_blocks); + xfs_rtginode_mark_sick(rtg, XFS_RTGI_RMAP); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return -EFSCORRUPTED; + } + + trace_xfs_zone_free_blocks(rtg, xfs_rtb_to_rgbno(mp, fsbno), len); + + rmapip->i_used_blocks -= len; + /* + * Don't add open zones to the reclaimable buckets. The I/O completion + * for writing the last block will take care of accounting for already + * unused blocks instead. + */ + if (!READ_ONCE(rtg->rtg_open_zone)) + xfs_zone_account_reclaimable(rtg, len); + xfs_add_frextents(mp, len); + xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE); + return 0; +} + +/* + * Check if the zone containing the data just before the offset we are + * writing to is still open and has space. + */ +static struct xfs_open_zone * +xfs_last_used_zone( + struct iomap_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset); + struct xfs_rtgroup *rtg = NULL; + struct xfs_open_zone *oz = NULL; + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec got; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb, + &icur, &got)) { + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return NULL; + } + xfs_iunlock(ip, XFS_ILOCK_SHARED); + + rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock)); + if (!rtg) + return NULL; + + xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED); + oz = READ_ONCE(rtg->rtg_open_zone); + if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref))) + oz = NULL; + xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED); + + xfs_rtgroup_rele(rtg); + return oz; +} + +static struct xfs_group * +xfs_find_free_zone( + struct xfs_mount *mp, + unsigned long start, + unsigned long end) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + XA_STATE (xas, &mp->m_groups[XG_TYPE_RTG].xa, start); + struct xfs_group *xg; + + xas_lock(&xas); + xas_for_each_marked(&xas, xg, end, XFS_RTG_FREE) + if (atomic_inc_not_zero(&xg->xg_active_ref)) + goto found; + xas_unlock(&xas); + return NULL; + +found: + xas_clear_mark(&xas, XFS_RTG_FREE); + atomic_dec(&zi->zi_nr_free_zones); + zi->zi_free_zone_cursor = xg->xg_gno; + xas_unlock(&xas); + return xg; +} + +static struct xfs_open_zone * +xfs_init_open_zone( + struct xfs_rtgroup *rtg, + xfs_rgblock_t write_pointer, + enum rw_hint write_hint, + bool is_gc) +{ + struct xfs_open_zone *oz; + + oz = kzalloc(sizeof(*oz), GFP_NOFS | __GFP_NOFAIL); + spin_lock_init(&oz->oz_alloc_lock); + atomic_set(&oz->oz_ref, 1); + oz->oz_rtg = rtg; + oz->oz_write_pointer = write_pointer; + oz->oz_written = write_pointer; + oz->oz_write_hint = write_hint; + oz->oz_is_gc = is_gc; + + /* + * All dereferences of rtg->rtg_open_zone hold the ILOCK for the rmap + * inode, but we don't really want to take that here because we are + * under the zone_list_lock. Ensure the pointer is only set for a fully + * initialized open zone structure so that a racy lookup finding it is + * fine. + */ + WRITE_ONCE(rtg->rtg_open_zone, oz); + return oz; +} + +/* + * Find a completely free zone, open it, and return a reference. + */ +struct xfs_open_zone * +xfs_open_zone( + struct xfs_mount *mp, + enum rw_hint write_hint, + bool is_gc) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_group *xg; + + xg = xfs_find_free_zone(mp, zi->zi_free_zone_cursor, ULONG_MAX); + if (!xg) + xg = xfs_find_free_zone(mp, 0, zi->zi_free_zone_cursor); + if (!xg) + return NULL; + + set_current_state(TASK_RUNNING); + return xfs_init_open_zone(to_rtg(xg), 0, write_hint, is_gc); +} + +static struct xfs_open_zone * +xfs_try_open_zone( + struct xfs_mount *mp, + enum rw_hint write_hint) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_open_zone *oz; + + if (zi->zi_nr_open_zones >= mp->m_max_open_zones - XFS_OPEN_GC_ZONES) + return NULL; + if (atomic_read(&zi->zi_nr_free_zones) < + XFS_GC_ZONES - XFS_OPEN_GC_ZONES) + return NULL; + + /* + * Increment the open zone count to reserve our slot before dropping + * zi_open_zones_lock. + */ + zi->zi_nr_open_zones++; + spin_unlock(&zi->zi_open_zones_lock); + oz = xfs_open_zone(mp, write_hint, false); + spin_lock(&zi->zi_open_zones_lock); + if (!oz) { + zi->zi_nr_open_zones--; + return NULL; + } + + atomic_inc(&oz->oz_ref); + list_add_tail(&oz->oz_entry, &zi->zi_open_zones); + + /* + * If this was the last free zone, other waiters might be waiting + * on us to write to it as well. + */ + wake_up_all(&zi->zi_zone_wait); + + if (xfs_zoned_need_gc(mp)) + wake_up_process(zi->zi_gc_thread); + + trace_xfs_zone_opened(oz->oz_rtg); + return oz; +} + +/* + * For data with short or medium lifetime, try to colocated it into an + * already open zone with a matching temperature. + */ +static bool +xfs_colocate_eagerly( + enum rw_hint file_hint) +{ + switch (file_hint) { + case WRITE_LIFE_MEDIUM: + case WRITE_LIFE_SHORT: + case WRITE_LIFE_NONE: + return true; + default: + return false; + } +} + +static bool +xfs_good_hint_match( + struct xfs_open_zone *oz, + enum rw_hint file_hint) +{ + switch (oz->oz_write_hint) { + case WRITE_LIFE_LONG: + case WRITE_LIFE_EXTREME: + /* colocate long and extreme */ + if (file_hint == WRITE_LIFE_LONG || + file_hint == WRITE_LIFE_EXTREME) + return true; + break; + case WRITE_LIFE_MEDIUM: + /* colocate medium with medium */ + if (file_hint == WRITE_LIFE_MEDIUM) + return true; + break; + case WRITE_LIFE_SHORT: + case WRITE_LIFE_NONE: + case WRITE_LIFE_NOT_SET: + /* colocate short and none */ + if (file_hint <= WRITE_LIFE_SHORT) + return true; + break; + } + return false; +} + +static bool +xfs_try_use_zone( + struct xfs_zone_info *zi, + enum rw_hint file_hint, + struct xfs_open_zone *oz, + bool lowspace) +{ + if (oz->oz_write_pointer == rtg_blocks(oz->oz_rtg)) + return false; + if (!lowspace && !xfs_good_hint_match(oz, file_hint)) + return false; + if (!atomic_inc_not_zero(&oz->oz_ref)) + return false; + + /* + * If we have a hint set for the data, use that for the zone even if + * some data was written already without any hint set, but don't change + * the temperature after that as that would make little sense without + * tracking per-temperature class written block counts, which is + * probably overkill anyway. + */ + if (file_hint != WRITE_LIFE_NOT_SET && + oz->oz_write_hint == WRITE_LIFE_NOT_SET) + oz->oz_write_hint = file_hint; + + /* + * If we couldn't match by inode or life time we just pick the first + * zone with enough space above. For that we want the least busy zone + * for some definition of "least" busy. For now this simple LRU + * algorithm that rotates every zone to the end of the list will do it, + * even if it isn't exactly cache friendly. + */ + if (!list_is_last(&oz->oz_entry, &zi->zi_open_zones)) + list_move_tail(&oz->oz_entry, &zi->zi_open_zones); + return true; +} + +static struct xfs_open_zone * +xfs_select_open_zone_lru( + struct xfs_zone_info *zi, + enum rw_hint file_hint, + bool lowspace) +{ + struct xfs_open_zone *oz; + + lockdep_assert_held(&zi->zi_open_zones_lock); + + list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) + if (xfs_try_use_zone(zi, file_hint, oz, lowspace)) + return oz; + + cond_resched_lock(&zi->zi_open_zones_lock); + return NULL; +} + +static struct xfs_open_zone * +xfs_select_open_zone_mru( + struct xfs_zone_info *zi, + enum rw_hint file_hint) +{ + struct xfs_open_zone *oz; + + lockdep_assert_held(&zi->zi_open_zones_lock); + + list_for_each_entry_reverse(oz, &zi->zi_open_zones, oz_entry) + if (xfs_try_use_zone(zi, file_hint, oz, false)) + return oz; + + cond_resched_lock(&zi->zi_open_zones_lock); + return NULL; +} + +static inline enum rw_hint xfs_inode_write_hint(struct xfs_inode *ip) +{ + if (xfs_has_nolifetime(ip->i_mount)) + return WRITE_LIFE_NOT_SET; + return VFS_I(ip)->i_write_hint; +} + +/* + * Try to pack inodes that are written back after they were closed tight instead + * of trying to open new zones for them or spread them to the least recently + * used zone. This optimizes the data layout for workloads that untar or copy + * a lot of small files. Right now this does not separate multiple such + * streams. + */ +static inline bool xfs_zoned_pack_tight(struct xfs_inode *ip) +{ + return !inode_is_open_for_write(VFS_I(ip)) && + !(ip->i_diflags & XFS_DIFLAG_APPEND); +} + +/* + * Pick a new zone for writes. + * + * If we aren't using up our budget of open zones just open a new one from the + * freelist. Else try to find one that matches the expected data lifetime. If + * we don't find one that is good pick any zone that is available. + */ +static struct xfs_open_zone * +xfs_select_zone_nowait( + struct xfs_mount *mp, + enum rw_hint write_hint, + bool pack_tight) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_open_zone *oz = NULL; + + if (xfs_is_shutdown(mp)) + return NULL; + + /* + * Try to fill up open zones with matching temperature if available. It + * is better to try to co-locate data when this is favorable, so we can + * activate empty zones when it is statistically better to separate + * data. + */ + spin_lock(&zi->zi_open_zones_lock); + if (xfs_colocate_eagerly(write_hint)) + oz = xfs_select_open_zone_lru(zi, write_hint, false); + else if (pack_tight) + oz = xfs_select_open_zone_mru(zi, write_hint); + if (oz) + goto out_unlock; + + /* + * See if we can open a new zone and use that. + */ + oz = xfs_try_open_zone(mp, write_hint); + if (oz) + goto out_unlock; + + /* + * Try to colocate cold data with other cold data if we failed to open a + * new zone for it. + */ + if (write_hint != WRITE_LIFE_NOT_SET && + !xfs_colocate_eagerly(write_hint)) + oz = xfs_select_open_zone_lru(zi, write_hint, false); + if (!oz) + oz = xfs_select_open_zone_lru(zi, WRITE_LIFE_NOT_SET, false); + if (!oz) + oz = xfs_select_open_zone_lru(zi, WRITE_LIFE_NOT_SET, true); +out_unlock: + spin_unlock(&zi->zi_open_zones_lock); + return oz; +} + +static struct xfs_open_zone * +xfs_select_zone( + struct xfs_mount *mp, + enum rw_hint write_hint, + bool pack_tight) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + DEFINE_WAIT (wait); + struct xfs_open_zone *oz; + + oz = xfs_select_zone_nowait(mp, write_hint, pack_tight); + if (oz) + return oz; + + for (;;) { + prepare_to_wait(&zi->zi_zone_wait, &wait, TASK_UNINTERRUPTIBLE); + oz = xfs_select_zone_nowait(mp, write_hint, pack_tight); + if (oz) + break; + schedule(); + } + finish_wait(&zi->zi_zone_wait, &wait); + return oz; +} + +static unsigned int +xfs_zone_alloc_blocks( + struct xfs_open_zone *oz, + xfs_filblks_t count_fsb, + sector_t *sector, + bool *is_seq) +{ + struct xfs_rtgroup *rtg = oz->oz_rtg; + struct xfs_mount *mp = rtg_mount(rtg); + xfs_rgblock_t rgbno; + + spin_lock(&oz->oz_alloc_lock); + count_fsb = min3(count_fsb, XFS_MAX_BMBT_EXTLEN, + (xfs_filblks_t)rtg_blocks(rtg) - oz->oz_write_pointer); + if (!count_fsb) { + spin_unlock(&oz->oz_alloc_lock); + return 0; + } + rgbno = oz->oz_write_pointer; + oz->oz_write_pointer += count_fsb; + spin_unlock(&oz->oz_alloc_lock); + + trace_xfs_zone_alloc_blocks(oz, rgbno, count_fsb); + + *sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0); + *is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector); + if (!*is_seq) + *sector += XFS_FSB_TO_BB(mp, rgbno); + return XFS_FSB_TO_B(mp, count_fsb); +} + +void +xfs_mark_rtg_boundary( + struct iomap_ioend *ioend) +{ + struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount; + sector_t sector = ioend->io_bio.bi_iter.bi_sector; + + if (xfs_rtb_to_rgbno(mp, xfs_daddr_to_rtb(mp, sector)) == 0) + ioend->io_flags |= IOMAP_IOEND_BOUNDARY; +} + +static void +xfs_submit_zoned_bio( + struct iomap_ioend *ioend, + struct xfs_open_zone *oz, + bool is_seq) +{ + ioend->io_bio.bi_iter.bi_sector = ioend->io_sector; + ioend->io_private = oz; + atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */ + + if (is_seq) { + ioend->io_bio.bi_opf &= ~REQ_OP_WRITE; + ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND; + } else { + xfs_mark_rtg_boundary(ioend); + } + + submit_bio(&ioend->io_bio); +} + +void +xfs_zone_alloc_and_submit( + struct iomap_ioend *ioend, + struct xfs_open_zone **oz) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + enum rw_hint write_hint = xfs_inode_write_hint(ip); + bool pack_tight = xfs_zoned_pack_tight(ip); + unsigned int alloc_len; + struct iomap_ioend *split; + bool is_seq; + + if (xfs_is_shutdown(mp)) + goto out_error; + + /* + * If we don't have a cached zone in this write context, see if the + * last extent before the one we are writing to points to an active + * zone. If so, just continue writing to it. + */ + if (!*oz && ioend->io_offset) + *oz = xfs_last_used_zone(ioend); + if (!*oz) { +select_zone: + *oz = xfs_select_zone(mp, write_hint, pack_tight); + if (!*oz) + goto out_error; + } + + alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), + &ioend->io_sector, &is_seq); + if (!alloc_len) { + xfs_open_zone_put(*oz); + goto select_zone; + } + + while ((split = iomap_split_ioend(ioend, alloc_len, is_seq))) { + if (IS_ERR(split)) + goto out_split_error; + alloc_len -= split->io_bio.bi_iter.bi_size; + xfs_submit_zoned_bio(split, *oz, is_seq); + if (!alloc_len) { + xfs_open_zone_put(*oz); + goto select_zone; + } + } + + xfs_submit_zoned_bio(ioend, *oz, is_seq); + return; + +out_split_error: + ioend->io_bio.bi_status = errno_to_blk_status(PTR_ERR(split)); +out_error: + bio_io_error(&ioend->io_bio); +} + +/* + * Wake up all threads waiting for a zoned space allocation when the file system + * is shut down. + */ +void +xfs_zoned_wake_all( + struct xfs_mount *mp) +{ + /* + * Don't wake up if there is no m_zone_info. This is complicated by the + * fact that unmount can't atomically clear m_zone_info and thus we need + * to check SB_ACTIVE for that, but mount temporarily enables SB_ACTIVE + * during log recovery so we can't entirely rely on that either. + */ + if ((mp->m_super->s_flags & SB_ACTIVE) && mp->m_zone_info) + wake_up_all(&mp->m_zone_info->zi_zone_wait); +} + +/* + * Check if @rgbno in @rgb is a potentially valid block. It might still be + * unused, but that information is only found in the rmap. + */ +bool +xfs_zone_rgbno_is_valid( + struct xfs_rtgroup *rtg, + xfs_rgnumber_t rgbno) +{ + lockdep_assert_held(&rtg_rmap(rtg)->i_lock); + + if (rtg->rtg_open_zone) + return rgbno < rtg->rtg_open_zone->oz_write_pointer; + return !xa_get_mark(&rtg_mount(rtg)->m_groups[XG_TYPE_RTG].xa, + rtg_rgno(rtg), XFS_RTG_FREE); +} + +static void +xfs_free_open_zones( + struct xfs_zone_info *zi) +{ + struct xfs_open_zone *oz; + + spin_lock(&zi->zi_open_zones_lock); + while ((oz = list_first_entry_or_null(&zi->zi_open_zones, + struct xfs_open_zone, oz_entry))) { + list_del(&oz->oz_entry); + xfs_open_zone_put(oz); + } + spin_unlock(&zi->zi_open_zones_lock); +} + +struct xfs_init_zones { + struct xfs_mount *mp; + uint64_t available; + uint64_t reclaimable; +}; + +static int +xfs_init_zone( + struct xfs_init_zones *iz, + struct xfs_rtgroup *rtg, + struct blk_zone *zone) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_zone_info *zi = mp->m_zone_info; + uint64_t used = rtg_rmap(rtg)->i_used_blocks; + xfs_rgblock_t write_pointer, highest_rgbno; + int error; + + if (zone && !xfs_zone_validate(zone, rtg, &write_pointer)) + return -EFSCORRUPTED; + + /* + * For sequential write required zones we retrieved the hardware write + * pointer above. + * + * For conventional zones or conventional devices we don't have that + * luxury. Instead query the rmap to find the highest recorded block + * and set the write pointer to the block after that. In case of a + * power loss this misses blocks where the data I/O has completed but + * not recorded in the rmap yet, and it also rewrites blocks if the most + * recently written ones got deleted again before unmount, but this is + * the best we can do without hardware support. + */ + if (!zone || zone->cond == BLK_ZONE_COND_NOT_WP) { + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + highest_rgbno = xfs_rtrmap_highest_rgbno(rtg); + if (highest_rgbno == NULLRGBLOCK) + write_pointer = 0; + else + write_pointer = highest_rgbno + 1; + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + } + + /* + * If there are no used blocks, but the zone is not in empty state yet + * we lost power before the zoned reset. In that case finish the work + * here. + */ + if (write_pointer == rtg_blocks(rtg) && used == 0) { + error = xfs_zone_gc_reset_sync(rtg); + if (error) + return error; + write_pointer = 0; + } + + if (write_pointer == 0) { + /* zone is empty */ + atomic_inc(&zi->zi_nr_free_zones); + xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE); + iz->available += rtg_blocks(rtg); + } else if (write_pointer < rtg_blocks(rtg)) { + /* zone is open */ + struct xfs_open_zone *oz; + + atomic_inc(&rtg_group(rtg)->xg_active_ref); + oz = xfs_init_open_zone(rtg, write_pointer, WRITE_LIFE_NOT_SET, + false); + list_add_tail(&oz->oz_entry, &zi->zi_open_zones); + zi->zi_nr_open_zones++; + + iz->available += (rtg_blocks(rtg) - write_pointer); + iz->reclaimable += write_pointer - used; + } else if (used < rtg_blocks(rtg)) { + /* zone fully written, but has freed blocks */ + xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used); + iz->reclaimable += (rtg_blocks(rtg) - used); + } + + return 0; +} + +static int +xfs_get_zone_info_cb( + struct blk_zone *zone, + unsigned int idx, + void *data) +{ + struct xfs_init_zones *iz = data; + struct xfs_mount *mp = iz->mp; + xfs_fsblock_t zsbno = xfs_daddr_to_rtb(mp, zone->start); + xfs_rgnumber_t rgno; + struct xfs_rtgroup *rtg; + int error; + + if (xfs_rtb_to_rgbno(mp, zsbno) != 0) { + xfs_warn(mp, "mismatched zone start 0x%llx.", zsbno); + return -EFSCORRUPTED; + } + + rgno = xfs_rtb_to_rgno(mp, zsbno); + rtg = xfs_rtgroup_grab(mp, rgno); + if (!rtg) { + xfs_warn(mp, "realtime group not found for zone %u.", rgno); + return -EFSCORRUPTED; + } + error = xfs_init_zone(iz, rtg, zone); + xfs_rtgroup_rele(rtg); + return error; +} + +/* + * Calculate the max open zone limit based on the of number of + * backing zones available + */ +static inline uint32_t +xfs_max_open_zones( + struct xfs_mount *mp) +{ + unsigned int max_open, max_open_data_zones; + /* + * We need two zones for every open data zone, + * one in reserve as we don't reclaim open zones. One data zone + * and its spare is included in XFS_MIN_ZONES. + */ + max_open_data_zones = (mp->m_sb.sb_rgcount - XFS_MIN_ZONES) / 2 + 1; + max_open = max_open_data_zones + XFS_OPEN_GC_ZONES; + + /* + * Cap the max open limit to 1/4 of available space + */ + max_open = min(max_open, mp->m_sb.sb_rgcount / 4); + + return max(XFS_MIN_OPEN_ZONES, max_open); +} + +/* + * Normally we use the open zone limit that the device reports. If there is + * none let the user pick one from the command line. + * + * If the device doesn't report an open zone limit and there is no override, + * allow to hold about a quarter of the zones open. In theory we could allow + * all to be open, but at that point we run into GC deadlocks because we can't + * reclaim open zones. + * + * When used on conventional SSDs a lower open limit is advisable as we'll + * otherwise overwhelm the FTL just as much as a conventional block allocator. + * + * Note: To debug the open zone management code, force max_open to 1 here. + */ +static int +xfs_calc_open_zones( + struct xfs_mount *mp) +{ + struct block_device *bdev = mp->m_rtdev_targp->bt_bdev; + unsigned int bdev_open_zones = bdev_max_open_zones(bdev); + + if (!mp->m_max_open_zones) { + if (bdev_open_zones) + mp->m_max_open_zones = bdev_open_zones; + else + mp->m_max_open_zones = xfs_max_open_zones(mp); + } + + if (mp->m_max_open_zones < XFS_MIN_OPEN_ZONES) { + xfs_notice(mp, "need at least %u open zones.", + XFS_MIN_OPEN_ZONES); + return -EIO; + } + + if (bdev_open_zones && bdev_open_zones < mp->m_max_open_zones) { + mp->m_max_open_zones = bdev_open_zones; + xfs_info(mp, "limiting open zones to %u due to hardware limit.\n", + bdev_open_zones); + } + + if (mp->m_max_open_zones > xfs_max_open_zones(mp)) { + mp->m_max_open_zones = xfs_max_open_zones(mp); + xfs_info(mp, +"limiting open zones to %u due to total zone count (%u)", + mp->m_max_open_zones, mp->m_sb.sb_rgcount); + } + + return 0; +} + +static unsigned long * +xfs_alloc_bucket_bitmap( + struct xfs_mount *mp) +{ + return kvmalloc_array(BITS_TO_LONGS(mp->m_sb.sb_rgcount), + sizeof(unsigned long), GFP_KERNEL | __GFP_ZERO); +} + +static struct xfs_zone_info * +xfs_alloc_zone_info( + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi; + int i; + + zi = kzalloc(sizeof(*zi), GFP_KERNEL); + if (!zi) + return NULL; + INIT_LIST_HEAD(&zi->zi_open_zones); + INIT_LIST_HEAD(&zi->zi_reclaim_reservations); + spin_lock_init(&zi->zi_reset_list_lock); + spin_lock_init(&zi->zi_open_zones_lock); + spin_lock_init(&zi->zi_reservation_lock); + init_waitqueue_head(&zi->zi_zone_wait); + spin_lock_init(&zi->zi_used_buckets_lock); + for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) { + zi->zi_used_bucket_bitmap[i] = xfs_alloc_bucket_bitmap(mp); + if (!zi->zi_used_bucket_bitmap[i]) + goto out_free_bitmaps; + } + return zi; + +out_free_bitmaps: + while (--i > 0) + kvfree(zi->zi_used_bucket_bitmap[i]); + kfree(zi); + return NULL; +} + +static void +xfs_free_zone_info( + struct xfs_zone_info *zi) +{ + int i; + + xfs_free_open_zones(zi); + for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) + kvfree(zi->zi_used_bucket_bitmap[i]); + kfree(zi); +} + +int +xfs_mount_zones( + struct xfs_mount *mp) +{ + struct xfs_init_zones iz = { + .mp = mp, + }; + struct xfs_buftarg *bt = mp->m_rtdev_targp; + int error; + + if (!bt) { + xfs_notice(mp, "RT device missing."); + return -EINVAL; + } + + if (!xfs_has_rtgroups(mp) || !xfs_has_rmapbt(mp)) { + xfs_notice(mp, "invalid flag combination."); + return -EFSCORRUPTED; + } + if (mp->m_sb.sb_rextsize != 1) { + xfs_notice(mp, "zoned file systems do not support rextsize."); + return -EFSCORRUPTED; + } + if (mp->m_sb.sb_rgcount < XFS_MIN_ZONES) { + xfs_notice(mp, +"zoned file systems need to have at least %u zones.", XFS_MIN_ZONES); + return -EFSCORRUPTED; + } + + error = xfs_calc_open_zones(mp); + if (error) + return error; + + mp->m_zone_info = xfs_alloc_zone_info(mp); + if (!mp->m_zone_info) + return -ENOMEM; + + xfs_info(mp, "%u zones of %u blocks size (%u max open)", + mp->m_sb.sb_rgcount, mp->m_groups[XG_TYPE_RTG].blocks, + mp->m_max_open_zones); + trace_xfs_zones_mount(mp); + + if (bdev_is_zoned(bt->bt_bdev)) { + error = blkdev_report_zones(bt->bt_bdev, + XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart), + mp->m_sb.sb_rgcount, xfs_get_zone_info_cb, &iz); + if (error < 0) + goto out_free_zone_info; + } else { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + error = xfs_init_zone(&iz, rtg, NULL); + if (error) + goto out_free_zone_info; + } + } + + xfs_set_freecounter(mp, XC_FREE_RTAVAILABLE, iz.available); + xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, + iz.available + iz.reclaimable); + + /* + * The user may configure GC to free up a percentage of unused blocks. + * By default this is 0. GC will always trigger at the minimum level + * for keeping max_open_zones available for data placement. + */ + mp->m_zonegc_low_space = 0; + + error = xfs_zone_gc_mount(mp); + if (error) + goto out_free_zone_info; + return 0; + +out_free_zone_info: + xfs_free_zone_info(mp->m_zone_info); + return error; +} + +void +xfs_unmount_zones( + struct xfs_mount *mp) +{ + xfs_zone_gc_unmount(mp); + xfs_free_zone_info(mp->m_zone_info); +} diff --git a/fs/xfs/xfs_zone_alloc.h b/fs/xfs/xfs_zone_alloc.h new file mode 100644 index 000000000000..ecf39106704c --- /dev/null +++ b/fs/xfs/xfs_zone_alloc.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XFS_ZONE_ALLOC_H +#define _XFS_ZONE_ALLOC_H + +struct iomap_ioend; +struct xfs_open_zone; + +struct xfs_zone_alloc_ctx { + struct xfs_open_zone *open_zone; + xfs_filblks_t reserved_blocks; +}; + +/* + * Grab any available space, even if it is less than what the caller asked for. + */ +#define XFS_ZR_GREEDY (1U << 0) +/* + * Only grab instantly available space, don't wait or GC. + */ +#define XFS_ZR_NOWAIT (1U << 1) +/* + * Dip into the reserved pool. + */ +#define XFS_ZR_RESERVED (1U << 2) + +int xfs_zoned_space_reserve(struct xfs_inode *ip, xfs_filblks_t count_fsb, + unsigned int flags, struct xfs_zone_alloc_ctx *ac); +void xfs_zoned_space_unreserve(struct xfs_inode *ip, + struct xfs_zone_alloc_ctx *ac); +void xfs_zoned_add_available(struct xfs_mount *mp, xfs_filblks_t count_fsb); + +void xfs_zone_alloc_and_submit(struct iomap_ioend *ioend, + struct xfs_open_zone **oz); +int xfs_zone_free_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg, + xfs_fsblock_t fsbno, xfs_filblks_t len); +int xfs_zoned_end_io(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count, + xfs_daddr_t daddr, struct xfs_open_zone *oz, + xfs_fsblock_t old_startblock); +void xfs_open_zone_put(struct xfs_open_zone *oz); + +void xfs_zoned_wake_all(struct xfs_mount *mp); +bool xfs_zone_rgbno_is_valid(struct xfs_rtgroup *rtg, xfs_rgnumber_t rgbno); +void xfs_mark_rtg_boundary(struct iomap_ioend *ioend); + +uint64_t xfs_zoned_default_resblks(struct xfs_mount *mp, + enum xfs_free_counter ctr); +void xfs_zoned_show_stats(struct seq_file *m, struct xfs_mount *mp); + +#ifdef CONFIG_XFS_RT +int xfs_mount_zones(struct xfs_mount *mp); +void xfs_unmount_zones(struct xfs_mount *mp); +void xfs_zone_gc_start(struct xfs_mount *mp); +void xfs_zone_gc_stop(struct xfs_mount *mp); +#else +static inline int xfs_mount_zones(struct xfs_mount *mp) +{ + return -EIO; +} +static inline void xfs_unmount_zones(struct xfs_mount *mp) +{ +} +static inline void xfs_zone_gc_start(struct xfs_mount *mp) +{ +} +static inline void xfs_zone_gc_stop(struct xfs_mount *mp) +{ +} +#endif /* CONFIG_XFS_RT */ + +#endif /* _XFS_ZONE_ALLOC_H */ diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c new file mode 100644 index 000000000000..d613a4094db6 --- /dev/null +++ b/fs/xfs/xfs_zone_gc.c @@ -0,0 +1,1184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_btree.h" +#include "xfs_trans.h" +#include "xfs_icache.h" +#include "xfs_rmap.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" +#include "xfs_zones.h" +#include "xfs_trace.h" + +/* + * Implement Garbage Collection (GC) of partially used zoned. + * + * To support the purely sequential writes in each zone, zoned XFS needs to be + * able to move data remaining in a zone out of it to reset the zone to prepare + * for writing to it again. + * + * This is done by the GC thread implemented in this file. To support that a + * number of zones (XFS_GC_ZONES) is reserved from the user visible capacity to + * write the garbage collected data into. + * + * Whenever the available space is below the chosen threshold, the GC thread + * looks for potential non-empty but not fully used zones that are worth + * reclaiming. Once found the rmap for the victim zone is queried, and after + * a bit of sorting to reduce fragmentation, the still live extents are read + * into memory and written to the GC target zone, and the bmap btree of the + * files is updated to point to the new location. To avoid taking the IOLOCK + * and MMAPLOCK for the entire GC process and thus affecting the latency of + * user reads and writes to the files, the GC writes are speculative and the + * I/O completion checks that no other writes happened for the affected regions + * before remapping. + * + * Once a zone does not contain any valid data, be that through GC or user + * block removal, it is queued for for a zone reset. The reset operation + * carefully ensures that the RT device cache is flushed and all transactions + * referencing the rmap have been committed to disk. + */ + +/* + * Size of each GC scratch pad. This is also the upper bound for each + * GC I/O, which helps to keep latency down. + */ +#define XFS_GC_CHUNK_SIZE SZ_1M + +/* + * Scratchpad data to read GCed data into. + * + * The offset member tracks where the next allocation starts, and freed tracks + * the amount of space that is not used anymore. + */ +#define XFS_ZONE_GC_NR_SCRATCH 2 +struct xfs_zone_scratch { + struct folio *folio; + unsigned int offset; + unsigned int freed; +}; + +/* + * Chunk that is read and written for each GC operation. + * + * Note that for writes to actual zoned devices, the chunk can be split when + * reaching the hardware limit. + */ +struct xfs_gc_bio { + struct xfs_zone_gc_data *data; + + /* + * Entry into the reading/writing/resetting list. Only accessed from + * the GC thread, so no locking needed. + */ + struct list_head entry; + + /* + * State of this gc_bio. Done means the current I/O completed. + * Set from the bio end I/O handler, read from the GC thread. + */ + enum { + XFS_GC_BIO_NEW, + XFS_GC_BIO_DONE, + } state; + + /* + * Pointer to the inode and byte range in the inode that this + * GC chunk is operating on. + */ + struct xfs_inode *ip; + loff_t offset; + unsigned int len; + + /* + * Existing startblock (in the zone to be freed) and newly assigned + * daddr in the zone GCed into. + */ + xfs_fsblock_t old_startblock; + xfs_daddr_t new_daddr; + struct xfs_zone_scratch *scratch; + + /* Are we writing to a sequential write required zone? */ + bool is_seq; + + /* Open Zone being written to */ + struct xfs_open_zone *oz; + + /* Bio used for reads and writes, including the bvec used by it */ + struct bio_vec bv; + struct bio bio; /* must be last */ +}; + +#define XFS_ZONE_GC_RECS 1024 + +/* iterator, needs to be reinitialized for each victim zone */ +struct xfs_zone_gc_iter { + struct xfs_rtgroup *victim_rtg; + unsigned int rec_count; + unsigned int rec_idx; + xfs_agblock_t next_startblock; + struct xfs_rmap_irec *recs; +}; + +/* + * Per-mount GC state. + */ +struct xfs_zone_gc_data { + struct xfs_mount *mp; + + /* bioset used to allocate the gc_bios */ + struct bio_set bio_set; + + /* + * Scratchpad used, and index to indicated which one is used. + */ + struct xfs_zone_scratch scratch[XFS_ZONE_GC_NR_SCRATCH]; + unsigned int scratch_idx; + + /* + * List of bios currently being read, written and reset. + * These lists are only accessed by the GC thread itself, and must only + * be processed in order. + */ + struct list_head reading; + struct list_head writing; + struct list_head resetting; + + /* + * Iterator for the victim zone. + */ + struct xfs_zone_gc_iter iter; +}; + +/* + * We aim to keep enough zones free in stock to fully use the open zone limit + * for data placement purposes. Additionally, the m_zonegc_low_space tunable + * can be set to make sure a fraction of the unused blocks are available for + * writing. + */ +bool +xfs_zoned_need_gc( + struct xfs_mount *mp) +{ + s64 available, free, threshold; + s32 remainder; + + if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE)) + return false; + + available = xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE); + + if (available < + mp->m_groups[XG_TYPE_RTG].blocks * + (mp->m_max_open_zones - XFS_OPEN_GC_ZONES)) + return true; + + free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS); + + threshold = div_s64_rem(free, 100, &remainder); + threshold = threshold * mp->m_zonegc_low_space + + remainder * div_s64(mp->m_zonegc_low_space, 100); + + if (available < threshold) + return true; + + return false; +} + +static struct xfs_zone_gc_data * +xfs_zone_gc_data_alloc( + struct xfs_mount *mp) +{ + struct xfs_zone_gc_data *data; + int i; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return NULL; + data->iter.recs = kcalloc(XFS_ZONE_GC_RECS, sizeof(*data->iter.recs), + GFP_KERNEL); + if (!data->iter.recs) + goto out_free_data; + + /* + * We actually only need a single bio_vec. It would be nice to have + * a flag that only allocates the inline bvecs and not the separate + * bvec pool. + */ + if (bioset_init(&data->bio_set, 16, offsetof(struct xfs_gc_bio, bio), + BIOSET_NEED_BVECS)) + goto out_free_recs; + for (i = 0; i < XFS_ZONE_GC_NR_SCRATCH; i++) { + data->scratch[i].folio = + folio_alloc(GFP_KERNEL, get_order(XFS_GC_CHUNK_SIZE)); + if (!data->scratch[i].folio) + goto out_free_scratch; + } + INIT_LIST_HEAD(&data->reading); + INIT_LIST_HEAD(&data->writing); + INIT_LIST_HEAD(&data->resetting); + data->mp = mp; + return data; + +out_free_scratch: + while (--i >= 0) + folio_put(data->scratch[i].folio); + bioset_exit(&data->bio_set); +out_free_recs: + kfree(data->iter.recs); +out_free_data: + kfree(data); + return NULL; +} + +static void +xfs_zone_gc_data_free( + struct xfs_zone_gc_data *data) +{ + int i; + + for (i = 0; i < XFS_ZONE_GC_NR_SCRATCH; i++) + folio_put(data->scratch[i].folio); + bioset_exit(&data->bio_set); + kfree(data->iter.recs); + kfree(data); +} + +static void +xfs_zone_gc_iter_init( + struct xfs_zone_gc_iter *iter, + struct xfs_rtgroup *victim_rtg) + +{ + iter->next_startblock = 0; + iter->rec_count = 0; + iter->rec_idx = 0; + iter->victim_rtg = victim_rtg; +} + +/* + * Query the rmap of the victim zone to gather the records to evacuate. + */ +static int +xfs_zone_gc_query_cb( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *irec, + void *private) +{ + struct xfs_zone_gc_iter *iter = private; + + ASSERT(!XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)); + ASSERT(!xfs_is_sb_inum(cur->bc_mp, irec->rm_owner)); + ASSERT(!(irec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))); + + iter->recs[iter->rec_count] = *irec; + if (++iter->rec_count == XFS_ZONE_GC_RECS) { + iter->next_startblock = + irec->rm_startblock + irec->rm_blockcount; + return 1; + } + return 0; +} + +#define cmp_int(l, r) ((l > r) - (l < r)) + +static int +xfs_zone_gc_rmap_rec_cmp( + const void *a, + const void *b) +{ + const struct xfs_rmap_irec *reca = a; + const struct xfs_rmap_irec *recb = b; + int diff; + + diff = cmp_int(reca->rm_owner, recb->rm_owner); + if (diff) + return diff; + return cmp_int(reca->rm_offset, recb->rm_offset); +} + +static int +xfs_zone_gc_query( + struct xfs_mount *mp, + struct xfs_zone_gc_iter *iter) +{ + struct xfs_rtgroup *rtg = iter->victim_rtg; + struct xfs_rmap_irec ri_low = { }; + struct xfs_rmap_irec ri_high; + struct xfs_btree_cur *cur; + struct xfs_trans *tp; + int error; + + ASSERT(iter->next_startblock <= rtg_blocks(rtg)); + if (iter->next_startblock == rtg_blocks(rtg)) + goto done; + + ASSERT(iter->next_startblock < rtg_blocks(rtg)); + ri_low.rm_startblock = iter->next_startblock; + memset(&ri_high, 0xFF, sizeof(ri_high)); + + iter->rec_idx = 0; + iter->rec_count = 0; + + error = xfs_trans_alloc_empty(mp, &tp); + if (error) + return error; + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + error = xfs_rmap_query_range(cur, &ri_low, &ri_high, + xfs_zone_gc_query_cb, iter); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + xfs_btree_del_cursor(cur, error < 0 ? error : 0); + xfs_trans_cancel(tp); + + if (error < 0) + return error; + + /* + * Sort the rmap records by inode number and increasing offset to + * defragment the mappings. + * + * This could be further enhanced by an even bigger look ahead window, + * but that's better left until we have better detection of changes to + * inode mapping to avoid the potential of GCing already dead data. + */ + sort(iter->recs, iter->rec_count, sizeof(iter->recs[0]), + xfs_zone_gc_rmap_rec_cmp, NULL); + + if (error == 0) { + /* + * We finished iterating through the zone. + */ + iter->next_startblock = rtg_blocks(rtg); + if (iter->rec_count == 0) + goto done; + } + + return 0; +done: + xfs_rtgroup_rele(iter->victim_rtg); + iter->victim_rtg = NULL; + return 0; +} + +static bool +xfs_zone_gc_iter_next( + struct xfs_mount *mp, + struct xfs_zone_gc_iter *iter, + struct xfs_rmap_irec *chunk_rec, + struct xfs_inode **ipp) +{ + struct xfs_rmap_irec *irec; + int error; + + if (!iter->victim_rtg) + return false; + +retry: + if (iter->rec_idx == iter->rec_count) { + error = xfs_zone_gc_query(mp, iter); + if (error) + goto fail; + if (!iter->victim_rtg) + return false; + } + + irec = &iter->recs[iter->rec_idx]; + error = xfs_iget(mp, NULL, irec->rm_owner, + XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, ipp); + if (error) { + /* + * If the inode was already deleted, skip over it. + */ + if (error == -ENOENT) { + iter->rec_idx++; + goto retry; + } + goto fail; + } + + if (!S_ISREG(VFS_I(*ipp)->i_mode) || !XFS_IS_REALTIME_INODE(*ipp)) { + iter->rec_idx++; + xfs_irele(*ipp); + goto retry; + } + + *chunk_rec = *irec; + return true; + +fail: + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + return false; +} + +static void +xfs_zone_gc_iter_advance( + struct xfs_zone_gc_iter *iter, + xfs_extlen_t count_fsb) +{ + struct xfs_rmap_irec *irec = &iter->recs[iter->rec_idx]; + + irec->rm_offset += count_fsb; + irec->rm_startblock += count_fsb; + irec->rm_blockcount -= count_fsb; + if (!irec->rm_blockcount) + iter->rec_idx++; +} + +static struct xfs_rtgroup * +xfs_zone_gc_pick_victim_from( + struct xfs_mount *mp, + uint32_t bucket) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + uint32_t victim_used = U32_MAX; + struct xfs_rtgroup *victim_rtg = NULL; + uint32_t bit; + + if (!zi->zi_used_bucket_entries[bucket]) + return NULL; + + for_each_set_bit(bit, zi->zi_used_bucket_bitmap[bucket], + mp->m_sb.sb_rgcount) { + struct xfs_rtgroup *rtg = xfs_rtgroup_grab(mp, bit); + + if (!rtg) + continue; + + /* skip zones that are just waiting for a reset */ + if (rtg_rmap(rtg)->i_used_blocks == 0 || + rtg_rmap(rtg)->i_used_blocks >= victim_used) { + xfs_rtgroup_rele(rtg); + continue; + } + + if (victim_rtg) + xfs_rtgroup_rele(victim_rtg); + victim_rtg = rtg; + victim_used = rtg_rmap(rtg)->i_used_blocks; + + /* + * Any zone that is less than 1 percent used is fair game for + * instant reclaim. All of these zones are in the last + * bucket, so avoid the expensive division for the zones + * in the other buckets. + */ + if (bucket == 0 && + rtg_rmap(rtg)->i_used_blocks < rtg_blocks(rtg) / 100) + break; + } + + return victim_rtg; +} + +/* + * Iterate through all zones marked as reclaimable and find a candidate to + * reclaim. + */ +static bool +xfs_zone_gc_select_victim( + struct xfs_zone_gc_data *data) +{ + struct xfs_zone_gc_iter *iter = &data->iter; + struct xfs_mount *mp = data->mp; + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_rtgroup *victim_rtg = NULL; + unsigned int bucket; + + if (xfs_is_shutdown(mp)) + return false; + + if (iter->victim_rtg) + return true; + + /* + * Don't start new work if we are asked to stop or park. + */ + if (kthread_should_stop() || kthread_should_park()) + return false; + + if (!xfs_zoned_need_gc(mp)) + return false; + + spin_lock(&zi->zi_used_buckets_lock); + for (bucket = 0; bucket < XFS_ZONE_USED_BUCKETS; bucket++) { + victim_rtg = xfs_zone_gc_pick_victim_from(mp, bucket); + if (victim_rtg) + break; + } + spin_unlock(&zi->zi_used_buckets_lock); + + if (!victim_rtg) + return false; + + trace_xfs_zone_gc_select_victim(victim_rtg, bucket); + xfs_zone_gc_iter_init(iter, victim_rtg); + return true; +} + +static struct xfs_open_zone * +xfs_zone_gc_steal_open( + struct xfs_zone_info *zi) +{ + struct xfs_open_zone *oz, *found = NULL; + + spin_lock(&zi->zi_open_zones_lock); + list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) { + if (!found || + oz->oz_write_pointer < found->oz_write_pointer) + found = oz; + } + + if (found) { + found->oz_is_gc = true; + list_del_init(&found->oz_entry); + zi->zi_nr_open_zones--; + } + + spin_unlock(&zi->zi_open_zones_lock); + return found; +} + +static struct xfs_open_zone * +xfs_zone_gc_select_target( + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_open_zone *oz = zi->zi_open_gc_zone; + + /* + * We need to wait for pending writes to finish. + */ + if (oz && oz->oz_written < rtg_blocks(oz->oz_rtg)) + return NULL; + + ASSERT(zi->zi_nr_open_zones <= + mp->m_max_open_zones - XFS_OPEN_GC_ZONES); + oz = xfs_open_zone(mp, WRITE_LIFE_NOT_SET, true); + if (oz) + trace_xfs_zone_gc_target_opened(oz->oz_rtg); + spin_lock(&zi->zi_open_zones_lock); + zi->zi_open_gc_zone = oz; + spin_unlock(&zi->zi_open_zones_lock); + return oz; +} + +/* + * Ensure we have a valid open zone to write the GC data to. + * + * If the current target zone has space keep writing to it, else first wait for + * all pending writes and then pick a new one. + */ +static struct xfs_open_zone * +xfs_zone_gc_ensure_target( + struct xfs_mount *mp) +{ + struct xfs_open_zone *oz = mp->m_zone_info->zi_open_gc_zone; + + if (!oz || oz->oz_write_pointer == rtg_blocks(oz->oz_rtg)) + return xfs_zone_gc_select_target(mp); + return oz; +} + +static unsigned int +xfs_zone_gc_scratch_available( + struct xfs_zone_gc_data *data) +{ + return XFS_GC_CHUNK_SIZE - data->scratch[data->scratch_idx].offset; +} + +static bool +xfs_zone_gc_space_available( + struct xfs_zone_gc_data *data) +{ + struct xfs_open_zone *oz; + + oz = xfs_zone_gc_ensure_target(data->mp); + if (!oz) + return false; + return oz->oz_write_pointer < rtg_blocks(oz->oz_rtg) && + xfs_zone_gc_scratch_available(data); +} + +static void +xfs_zone_gc_end_io( + struct bio *bio) +{ + struct xfs_gc_bio *chunk = + container_of(bio, struct xfs_gc_bio, bio); + struct xfs_zone_gc_data *data = chunk->data; + + WRITE_ONCE(chunk->state, XFS_GC_BIO_DONE); + wake_up_process(data->mp->m_zone_info->zi_gc_thread); +} + +static struct xfs_open_zone * +xfs_zone_gc_alloc_blocks( + struct xfs_zone_gc_data *data, + xfs_extlen_t *count_fsb, + xfs_daddr_t *daddr, + bool *is_seq) +{ + struct xfs_mount *mp = data->mp; + struct xfs_open_zone *oz; + + oz = xfs_zone_gc_ensure_target(mp); + if (!oz) + return NULL; + + *count_fsb = min(*count_fsb, + XFS_B_TO_FSB(mp, xfs_zone_gc_scratch_available(data))); + + /* + * Directly allocate GC blocks from the reserved pool. + * + * If we'd take them from the normal pool we could be stealing blocks + * from a regular writer, which would then have to wait for GC and + * deadlock. + */ + spin_lock(&mp->m_sb_lock); + *count_fsb = min(*count_fsb, + rtg_blocks(oz->oz_rtg) - oz->oz_write_pointer); + *count_fsb = min3(*count_fsb, + mp->m_free[XC_FREE_RTEXTENTS].res_avail, + mp->m_free[XC_FREE_RTAVAILABLE].res_avail); + mp->m_free[XC_FREE_RTEXTENTS].res_avail -= *count_fsb; + mp->m_free[XC_FREE_RTAVAILABLE].res_avail -= *count_fsb; + spin_unlock(&mp->m_sb_lock); + + if (!*count_fsb) + return NULL; + + *daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0); + *is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr); + if (!*is_seq) + *daddr += XFS_FSB_TO_BB(mp, oz->oz_write_pointer); + oz->oz_write_pointer += *count_fsb; + atomic_inc(&oz->oz_ref); + return oz; +} + +static bool +xfs_zone_gc_start_chunk( + struct xfs_zone_gc_data *data) +{ + struct xfs_zone_gc_iter *iter = &data->iter; + struct xfs_mount *mp = data->mp; + struct block_device *bdev = mp->m_rtdev_targp->bt_bdev; + struct xfs_open_zone *oz; + struct xfs_rmap_irec irec; + struct xfs_gc_bio *chunk; + struct xfs_inode *ip; + struct bio *bio; + xfs_daddr_t daddr; + bool is_seq; + + if (xfs_is_shutdown(mp)) + return false; + + if (!xfs_zone_gc_iter_next(mp, iter, &irec, &ip)) + return false; + oz = xfs_zone_gc_alloc_blocks(data, &irec.rm_blockcount, &daddr, + &is_seq); + if (!oz) { + xfs_irele(ip); + return false; + } + + bio = bio_alloc_bioset(bdev, 1, REQ_OP_READ, GFP_NOFS, &data->bio_set); + + chunk = container_of(bio, struct xfs_gc_bio, bio); + chunk->ip = ip; + chunk->offset = XFS_FSB_TO_B(mp, irec.rm_offset); + chunk->len = XFS_FSB_TO_B(mp, irec.rm_blockcount); + chunk->old_startblock = + xfs_rgbno_to_rtb(iter->victim_rtg, irec.rm_startblock); + chunk->new_daddr = daddr; + chunk->is_seq = is_seq; + chunk->scratch = &data->scratch[data->scratch_idx]; + chunk->data = data; + chunk->oz = oz; + + bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock); + bio->bi_end_io = xfs_zone_gc_end_io; + bio_add_folio_nofail(bio, chunk->scratch->folio, chunk->len, + chunk->scratch->offset); + chunk->scratch->offset += chunk->len; + if (chunk->scratch->offset == XFS_GC_CHUNK_SIZE) { + data->scratch_idx = + (data->scratch_idx + 1) % XFS_ZONE_GC_NR_SCRATCH; + } + WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); + list_add_tail(&chunk->entry, &data->reading); + xfs_zone_gc_iter_advance(iter, irec.rm_blockcount); + + submit_bio(bio); + return true; +} + +static void +xfs_zone_gc_free_chunk( + struct xfs_gc_bio *chunk) +{ + list_del(&chunk->entry); + xfs_open_zone_put(chunk->oz); + xfs_irele(chunk->ip); + bio_put(&chunk->bio); +} + +static void +xfs_zone_gc_submit_write( + struct xfs_zone_gc_data *data, + struct xfs_gc_bio *chunk) +{ + if (chunk->is_seq) { + chunk->bio.bi_opf &= ~REQ_OP_WRITE; + chunk->bio.bi_opf |= REQ_OP_ZONE_APPEND; + } + chunk->bio.bi_iter.bi_sector = chunk->new_daddr; + chunk->bio.bi_end_io = xfs_zone_gc_end_io; + submit_bio(&chunk->bio); +} + +static struct xfs_gc_bio * +xfs_zone_gc_split_write( + struct xfs_zone_gc_data *data, + struct xfs_gc_bio *chunk) +{ + struct queue_limits *lim = + &bdev_get_queue(chunk->bio.bi_bdev)->limits; + struct xfs_gc_bio *split_chunk; + int split_sectors; + unsigned int split_len; + struct bio *split; + unsigned int nsegs; + + if (!chunk->is_seq) + return NULL; + + split_sectors = bio_split_rw_at(&chunk->bio, lim, &nsegs, + lim->max_zone_append_sectors << SECTOR_SHIFT); + if (!split_sectors) + return NULL; + + /* ensure the split chunk is still block size aligned */ + split_sectors = ALIGN_DOWN(split_sectors << SECTOR_SHIFT, + data->mp->m_sb.sb_blocksize) >> SECTOR_SHIFT; + split_len = split_sectors << SECTOR_SHIFT; + + split = bio_split(&chunk->bio, split_sectors, GFP_NOFS, &data->bio_set); + split_chunk = container_of(split, struct xfs_gc_bio, bio); + split_chunk->data = data; + ihold(VFS_I(chunk->ip)); + split_chunk->ip = chunk->ip; + split_chunk->is_seq = chunk->is_seq; + split_chunk->scratch = chunk->scratch; + split_chunk->offset = chunk->offset; + split_chunk->len = split_len; + split_chunk->old_startblock = chunk->old_startblock; + split_chunk->new_daddr = chunk->new_daddr; + split_chunk->oz = chunk->oz; + atomic_inc(&chunk->oz->oz_ref); + + chunk->offset += split_len; + chunk->len -= split_len; + chunk->old_startblock += XFS_B_TO_FSB(data->mp, split_len); + + /* add right before the original chunk */ + WRITE_ONCE(split_chunk->state, XFS_GC_BIO_NEW); + list_add_tail(&split_chunk->entry, &chunk->entry); + return split_chunk; +} + +static void +xfs_zone_gc_write_chunk( + struct xfs_gc_bio *chunk) +{ + struct xfs_zone_gc_data *data = chunk->data; + struct xfs_mount *mp = chunk->ip->i_mount; + phys_addr_t bvec_paddr = + bvec_phys(bio_first_bvec_all(&chunk->bio)); + struct xfs_gc_bio *split_chunk; + + if (chunk->bio.bi_status) + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + if (xfs_is_shutdown(mp)) { + xfs_zone_gc_free_chunk(chunk); + return; + } + + WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); + list_move_tail(&chunk->entry, &data->writing); + + bio_reset(&chunk->bio, mp->m_rtdev_targp->bt_bdev, REQ_OP_WRITE); + bio_add_folio_nofail(&chunk->bio, chunk->scratch->folio, chunk->len, + offset_in_folio(chunk->scratch->folio, bvec_paddr)); + + while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) + xfs_zone_gc_submit_write(data, split_chunk); + xfs_zone_gc_submit_write(data, chunk); +} + +static void +xfs_zone_gc_finish_chunk( + struct xfs_gc_bio *chunk) +{ + uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; + struct xfs_inode *ip = chunk->ip; + struct xfs_mount *mp = ip->i_mount; + int error; + + if (chunk->bio.bi_status) + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + if (xfs_is_shutdown(mp)) { + xfs_zone_gc_free_chunk(chunk); + return; + } + + chunk->scratch->freed += chunk->len; + if (chunk->scratch->freed == chunk->scratch->offset) { + chunk->scratch->offset = 0; + chunk->scratch->freed = 0; + } + + /* + * Cycle through the iolock and wait for direct I/O and layouts to + * ensure no one is reading from the old mapping before it goes away. + * + * Note that xfs_zoned_end_io() below checks that no other writer raced + * with us to update the mapping by checking that the old startblock + * didn't change. + */ + xfs_ilock(ip, iolock); + error = xfs_break_layouts(VFS_I(ip), &iolock, BREAK_UNMAP); + if (!error) + inode_dio_wait(VFS_I(ip)); + xfs_iunlock(ip, iolock); + if (error) + goto free; + + if (chunk->is_seq) + chunk->new_daddr = chunk->bio.bi_iter.bi_sector; + error = xfs_zoned_end_io(ip, chunk->offset, chunk->len, + chunk->new_daddr, chunk->oz, chunk->old_startblock); +free: + if (error) + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + xfs_zone_gc_free_chunk(chunk); +} + +static void +xfs_zone_gc_finish_reset( + struct xfs_gc_bio *chunk) +{ + struct xfs_rtgroup *rtg = chunk->bio.bi_private; + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_zone_info *zi = mp->m_zone_info; + + if (chunk->bio.bi_status) { + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + goto out; + } + + xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE); + atomic_inc(&zi->zi_nr_free_zones); + + xfs_zoned_add_available(mp, rtg_blocks(rtg)); + + wake_up_all(&zi->zi_zone_wait); +out: + list_del(&chunk->entry); + bio_put(&chunk->bio); +} + +static bool +xfs_zone_gc_prepare_reset( + struct bio *bio, + struct xfs_rtgroup *rtg) +{ + trace_xfs_zone_reset(rtg); + + ASSERT(rtg_rmap(rtg)->i_used_blocks == 0); + bio->bi_iter.bi_sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0); + if (!bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) { + if (!bdev_max_discard_sectors(bio->bi_bdev)) + return false; + bio->bi_opf = REQ_OP_DISCARD | REQ_SYNC; + bio->bi_iter.bi_size = + XFS_FSB_TO_B(rtg_mount(rtg), rtg_blocks(rtg)); + } + + return true; +} + +int +xfs_zone_gc_reset_sync( + struct xfs_rtgroup *rtg) +{ + int error = 0; + struct bio bio; + + bio_init(&bio, rtg_mount(rtg)->m_rtdev_targp->bt_bdev, NULL, 0, + REQ_OP_ZONE_RESET); + if (xfs_zone_gc_prepare_reset(&bio, rtg)) + error = submit_bio_wait(&bio); + bio_uninit(&bio); + + return error; +} + +static void +xfs_zone_gc_reset_zones( + struct xfs_zone_gc_data *data, + struct xfs_group *reset_list) +{ + struct xfs_group *next = reset_list; + + if (blkdev_issue_flush(data->mp->m_rtdev_targp->bt_bdev) < 0) { + xfs_force_shutdown(data->mp, SHUTDOWN_META_IO_ERROR); + return; + } + + do { + struct xfs_rtgroup *rtg = to_rtg(next); + struct xfs_gc_bio *chunk; + struct bio *bio; + + xfs_log_force_inode(rtg_rmap(rtg)); + + next = rtg_group(rtg)->xg_next_reset; + rtg_group(rtg)->xg_next_reset = NULL; + + bio = bio_alloc_bioset(rtg_mount(rtg)->m_rtdev_targp->bt_bdev, + 0, REQ_OP_ZONE_RESET, GFP_NOFS, &data->bio_set); + bio->bi_private = rtg; + bio->bi_end_io = xfs_zone_gc_end_io; + + chunk = container_of(bio, struct xfs_gc_bio, bio); + chunk->data = data; + WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); + list_add_tail(&chunk->entry, &data->resetting); + + /* + * Also use the bio to drive the state machine when neither + * zone reset nor discard is supported to keep things simple. + */ + if (xfs_zone_gc_prepare_reset(bio, rtg)) + submit_bio(bio); + else + bio_endio(bio); + } while (next); +} + +/* + * Handle the work to read and write data for GC and to reset the zones, + * including handling all completions. + * + * Note that the order of the chunks is preserved so that we don't undo the + * optimal order established by xfs_zone_gc_query(). + */ +static bool +xfs_zone_gc_handle_work( + struct xfs_zone_gc_data *data) +{ + struct xfs_zone_info *zi = data->mp->m_zone_info; + struct xfs_gc_bio *chunk, *next; + struct xfs_group *reset_list; + struct blk_plug plug; + + spin_lock(&zi->zi_reset_list_lock); + reset_list = zi->zi_reset_list; + zi->zi_reset_list = NULL; + spin_unlock(&zi->zi_reset_list_lock); + + if (!xfs_zone_gc_select_victim(data) || + !xfs_zone_gc_space_available(data)) { + if (list_empty(&data->reading) && + list_empty(&data->writing) && + list_empty(&data->resetting) && + !reset_list) + return false; + } + + __set_current_state(TASK_RUNNING); + try_to_freeze(); + + if (reset_list) + xfs_zone_gc_reset_zones(data, reset_list); + + list_for_each_entry_safe(chunk, next, &data->resetting, entry) { + if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) + break; + xfs_zone_gc_finish_reset(chunk); + } + + list_for_each_entry_safe(chunk, next, &data->writing, entry) { + if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) + break; + xfs_zone_gc_finish_chunk(chunk); + } + + blk_start_plug(&plug); + list_for_each_entry_safe(chunk, next, &data->reading, entry) { + if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) + break; + xfs_zone_gc_write_chunk(chunk); + } + blk_finish_plug(&plug); + + blk_start_plug(&plug); + while (xfs_zone_gc_start_chunk(data)) + ; + blk_finish_plug(&plug); + return true; +} + +/* + * Note that the current GC algorithm would break reflinks and thus duplicate + * data that was shared by multiple owners before. Because of that reflinks + * are currently not supported on zoned file systems and can't be created or + * mounted. + */ +static int +xfs_zoned_gcd( + void *private) +{ + struct xfs_zone_gc_data *data = private; + struct xfs_mount *mp = data->mp; + struct xfs_zone_info *zi = mp->m_zone_info; + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); + set_freezable(); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE | TASK_FREEZABLE); + xfs_set_zonegc_running(mp); + if (xfs_zone_gc_handle_work(data)) + continue; + + if (list_empty(&data->reading) && + list_empty(&data->writing) && + list_empty(&data->resetting) && + !zi->zi_reset_list) { + xfs_clear_zonegc_running(mp); + xfs_zoned_resv_wake_all(mp); + + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); + break; + } + + if (kthread_should_park()) { + __set_current_state(TASK_RUNNING); + kthread_parkme(); + continue; + } + } + + schedule(); + } + xfs_clear_zonegc_running(mp); + + if (data->iter.victim_rtg) + xfs_rtgroup_rele(data->iter.victim_rtg); + + memalloc_nofs_restore(nofs_flag); + xfs_zone_gc_data_free(data); + return 0; +} + +void +xfs_zone_gc_start( + struct xfs_mount *mp) +{ + if (xfs_has_zoned(mp)) + kthread_unpark(mp->m_zone_info->zi_gc_thread); +} + +void +xfs_zone_gc_stop( + struct xfs_mount *mp) +{ + if (xfs_has_zoned(mp)) + kthread_park(mp->m_zone_info->zi_gc_thread); +} + +int +xfs_zone_gc_mount( + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_zone_gc_data *data; + struct xfs_open_zone *oz; + int error; + + /* + * If there are no free zones available for GC, pick the open zone with + * the least used space to GC into. This should only happen after an + * unclean shutdown near ENOSPC while GC was ongoing. + * + * We also need to do this for the first gc zone allocation if we + * unmounted while at the open limit. + */ + if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_FREE) || + zi->zi_nr_open_zones == mp->m_max_open_zones) + oz = xfs_zone_gc_steal_open(zi); + else + oz = xfs_open_zone(mp, WRITE_LIFE_NOT_SET, true); + if (!oz) { + xfs_warn(mp, "unable to allocate a zone for gc"); + error = -EIO; + goto out; + } + + trace_xfs_zone_gc_target_opened(oz->oz_rtg); + zi->zi_open_gc_zone = oz; + + data = xfs_zone_gc_data_alloc(mp); + if (!data) { + error = -ENOMEM; + goto out_put_gc_zone; + } + + mp->m_zone_info->zi_gc_thread = kthread_create(xfs_zoned_gcd, data, + "xfs-zone-gc/%s", mp->m_super->s_id); + if (IS_ERR(mp->m_zone_info->zi_gc_thread)) { + xfs_warn(mp, "unable to create zone gc thread"); + error = PTR_ERR(mp->m_zone_info->zi_gc_thread); + goto out_free_gc_data; + } + + /* xfs_zone_gc_start will unpark for rw mounts */ + kthread_park(mp->m_zone_info->zi_gc_thread); + return 0; + +out_free_gc_data: + kfree(data); +out_put_gc_zone: + xfs_open_zone_put(zi->zi_open_gc_zone); +out: + return error; +} + +void +xfs_zone_gc_unmount( + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + + kthread_stop(zi->zi_gc_thread); + if (zi->zi_open_gc_zone) + xfs_open_zone_put(zi->zi_open_gc_zone); +} diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c new file mode 100644 index 000000000000..733bcc2f8645 --- /dev/null +++ b/fs/xfs/xfs_zone_info.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" + +static const char xfs_write_hint_shorthand[6][16] = { + "NOT_SET", "NONE", "SHORT", "MEDIUM", "LONG", "EXTREME"}; + +static inline const char * +xfs_write_hint_to_str( + uint8_t write_hint) +{ + if (write_hint > WRITE_LIFE_EXTREME) + return "UNKNOWN"; + return xfs_write_hint_shorthand[write_hint]; +} + +static void +xfs_show_open_zone( + struct seq_file *m, + struct xfs_open_zone *oz) +{ + seq_printf(m, "\t zone %d, wp %u, written %u, used %u, hint %s\n", + rtg_rgno(oz->oz_rtg), + oz->oz_write_pointer, oz->oz_written, + rtg_rmap(oz->oz_rtg)->i_used_blocks, + xfs_write_hint_to_str(oz->oz_write_hint)); +} + +static void +xfs_show_full_zone_used_distribution( + struct seq_file *m, + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + unsigned int reclaimable = 0, full, i; + + spin_lock(&zi->zi_used_buckets_lock); + for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) { + unsigned int entries = zi->zi_used_bucket_entries[i]; + + seq_printf(m, "\t %2u..%2u%%: %u\n", + i * (100 / XFS_ZONE_USED_BUCKETS), + (i + 1) * (100 / XFS_ZONE_USED_BUCKETS) - 1, + entries); + reclaimable += entries; + } + spin_unlock(&zi->zi_used_buckets_lock); + + full = mp->m_sb.sb_rgcount; + if (zi->zi_open_gc_zone) + full--; + full -= zi->zi_nr_open_zones; + full -= atomic_read(&zi->zi_nr_free_zones); + full -= reclaimable; + + seq_printf(m, "\t 100%%: %u\n", full); +} + +void +xfs_zoned_show_stats( + struct seq_file *m, + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_open_zone *oz; + + seq_puts(m, "\n"); + + seq_printf(m, "\tuser free RT blocks: %lld\n", + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); + seq_printf(m, "\treserved free RT blocks: %lld\n", + mp->m_free[XC_FREE_RTEXTENTS].res_avail); + seq_printf(m, "\tuser available RT blocks: %lld\n", + xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE)); + seq_printf(m, "\treserved available RT blocks: %lld\n", + mp->m_free[XC_FREE_RTAVAILABLE].res_avail); + seq_printf(m, "\tRT reservations required: %d\n", + !list_empty_careful(&zi->zi_reclaim_reservations)); + seq_printf(m, "\tRT GC required: %d\n", + xfs_zoned_need_gc(mp)); + + seq_printf(m, "\tfree zones: %d\n", atomic_read(&zi->zi_nr_free_zones)); + seq_puts(m, "\topen zones:\n"); + spin_lock(&zi->zi_open_zones_lock); + list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) + xfs_show_open_zone(m, oz); + if (zi->zi_open_gc_zone) { + seq_puts(m, "\topen gc zone:\n"); + xfs_show_open_zone(m, zi->zi_open_gc_zone); + } + spin_unlock(&zi->zi_open_zones_lock); + seq_puts(m, "\tused blocks distribution (fully written zones):\n"); + xfs_show_full_zone_used_distribution(m, mp); +} diff --git a/fs/xfs/xfs_zone_priv.h b/fs/xfs/xfs_zone_priv.h new file mode 100644 index 000000000000..ab696975a993 --- /dev/null +++ b/fs/xfs/xfs_zone_priv.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XFS_ZONE_PRIV_H +#define _XFS_ZONE_PRIV_H + +struct xfs_open_zone { + /* + * Entry in the open zone list and refcount. Protected by + * zi_open_zones_lock in struct xfs_zone_info. + */ + struct list_head oz_entry; + atomic_t oz_ref; + + /* + * oz_write_pointer is the write pointer at which space is handed out + * for conventional zones, or simple the count of blocks handed out + * so far for sequential write required zones and is protected by + * oz_alloc_lock/ + */ + spinlock_t oz_alloc_lock; + xfs_rgblock_t oz_write_pointer; + + /* + * oz_written is the number of blocks for which we've received a + * write completion. oz_written must always be <= oz_write_pointer + * and is protected by the ILOCK of the rmap inode. + */ + xfs_rgblock_t oz_written; + + /* + * Write hint (data temperature) assigned to this zone, or + * WRITE_LIFE_NOT_SET if none was set. + */ + enum rw_hint oz_write_hint; + + /* + * Is this open zone used for garbage collection? There can only be a + * single open GC zone, which is pointed to by zi_open_gc_zone in + * struct xfs_zone_info. Constant over the life time of an open zone. + */ + bool oz_is_gc; + + /* + * Pointer to the RT groups structure for this open zone. Constant over + * the life time of an open zone. + */ + struct xfs_rtgroup *oz_rtg; +}; + +/* + * Number of bitmap buckets to track reclaimable zones. There are 10 buckets + * so that each 10% of the usable capacity get their own bucket and GC can + * only has to walk the bitmaps of the lesser used zones if there are any. + */ +#define XFS_ZONE_USED_BUCKETS 10u + +struct xfs_zone_info { + /* + * List of pending space reservations: + */ + spinlock_t zi_reservation_lock; + struct list_head zi_reclaim_reservations; + + /* + * List and number of open zones: + */ + spinlock_t zi_open_zones_lock; + struct list_head zi_open_zones; + unsigned int zi_nr_open_zones; + + /* + * Free zone search cursor and number of free zones: + */ + unsigned long zi_free_zone_cursor; + atomic_t zi_nr_free_zones; + + /* + * Wait queue to wait for free zones or open zone resources to become + * available: + */ + wait_queue_head_t zi_zone_wait; + + /* + * Pointer to the GC thread, and the current open zone used by GC + * (if any). + * + * zi_open_gc_zone is mostly private to the GC thread, but can be read + * for debugging from other threads, in which case zi_open_zones_lock + * must be taken to access it. + */ + struct task_struct *zi_gc_thread; + struct xfs_open_zone *zi_open_gc_zone; + + /* + * List of zones that need a reset: + */ + spinlock_t zi_reset_list_lock; + struct xfs_group *zi_reset_list; + + /* + * A set of bitmaps to bucket-sort reclaimable zones by used blocks to help + * garbage collection to quickly find the best candidate for reclaim. + */ + spinlock_t zi_used_buckets_lock; + unsigned int zi_used_bucket_entries[XFS_ZONE_USED_BUCKETS]; + unsigned long *zi_used_bucket_bitmap[XFS_ZONE_USED_BUCKETS]; + +}; + +struct xfs_open_zone *xfs_open_zone(struct xfs_mount *mp, + enum rw_hint write_hint, bool is_gc); + +int xfs_zone_gc_reset_sync(struct xfs_rtgroup *rtg); +bool xfs_zoned_need_gc(struct xfs_mount *mp); +int xfs_zone_gc_mount(struct xfs_mount *mp); +void xfs_zone_gc_unmount(struct xfs_mount *mp); + +void xfs_zoned_resv_wake_all(struct xfs_mount *mp); + +#endif /* _XFS_ZONE_PRIV_H */ diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c new file mode 100644 index 000000000000..93c9a7721139 --- /dev/null +++ b/fs/xfs/xfs_zone_space_resv.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_rtbitmap.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" +#include "xfs_zones.h" + +/* + * Note: the zoned allocator does not support a rtextsize > 1, so this code and + * the allocator itself uses file system blocks interchangeable with realtime + * extents without doing the otherwise required conversions. + */ + +/* + * Per-task space reservation. + * + * Tasks that need to wait for GC to free up space allocate one of these + * on-stack and adds it to the per-mount zi_reclaim_reservations lists. + * The GC thread will then wake the tasks in order when space becomes available. + */ +struct xfs_zone_reservation { + struct list_head entry; + struct task_struct *task; + xfs_filblks_t count_fsb; +}; + +/* + * Calculate the number of reserved blocks. + * + * XC_FREE_RTEXTENTS counts the user available capacity, to which the file + * system can be filled, while XC_FREE_RTAVAILABLE counts the blocks instantly + * available for writes without waiting for GC. + * + * For XC_FREE_RTAVAILABLE only the smaller reservation required for GC and + * block zeroing is excluded from the user capacity, while XC_FREE_RTEXTENTS + * is further restricted by at least one zone as well as the optional + * persistently reserved blocks. This allows the allocator to run more + * smoothly by not always triggering GC. + */ +uint64_t +xfs_zoned_default_resblks( + struct xfs_mount *mp, + enum xfs_free_counter ctr) +{ + switch (ctr) { + case XC_FREE_RTEXTENTS: + return (uint64_t)XFS_RESERVED_ZONES * + mp->m_groups[XG_TYPE_RTG].blocks + + mp->m_sb.sb_rtreserved; + case XC_FREE_RTAVAILABLE: + return (uint64_t)XFS_GC_ZONES * + mp->m_groups[XG_TYPE_RTG].blocks; + default: + ASSERT(0); + return 0; + } +} + +void +xfs_zoned_resv_wake_all( + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_zone_reservation *reservation; + + spin_lock(&zi->zi_reservation_lock); + list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry) + wake_up_process(reservation->task); + spin_unlock(&zi->zi_reservation_lock); +} + +void +xfs_zoned_add_available( + struct xfs_mount *mp, + xfs_filblks_t count_fsb) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_zone_reservation *reservation; + + if (list_empty_careful(&zi->zi_reclaim_reservations)) { + xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + return; + } + + spin_lock(&zi->zi_reservation_lock); + xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + count_fsb = xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE); + list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry) { + if (reservation->count_fsb > count_fsb) + break; + wake_up_process(reservation->task); + count_fsb -= reservation->count_fsb; + + } + spin_unlock(&zi->zi_reservation_lock); +} + +static int +xfs_zoned_space_wait_error( + struct xfs_mount *mp) +{ + if (xfs_is_shutdown(mp)) + return -EIO; + if (fatal_signal_pending(current)) + return -EINTR; + return 0; +} + +static int +xfs_zoned_reserve_available( + struct xfs_inode *ip, + xfs_filblks_t count_fsb, + unsigned int flags) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_zone_reservation reservation = { + .task = current, + .count_fsb = count_fsb, + }; + int error; + + /* + * If there are no waiters, try to directly grab the available blocks + * from the percpu counter. + * + * If the caller wants to dip into the reserved pool also bypass the + * wait list. This relies on the fact that we have a very graciously + * sized reserved pool that always has enough space. If the reserved + * allocations fail we're in trouble. + */ + if (likely(list_empty_careful(&zi->zi_reclaim_reservations) || + (flags & XFS_ZR_RESERVED))) { + error = xfs_dec_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb, + flags & XFS_ZR_RESERVED); + if (error != -ENOSPC) + return error; + } + + if (flags & XFS_ZR_NOWAIT) + return -EAGAIN; + + spin_lock(&zi->zi_reservation_lock); + list_add_tail(&reservation.entry, &zi->zi_reclaim_reservations); + while ((error = xfs_zoned_space_wait_error(mp)) == 0) { + set_current_state(TASK_KILLABLE); + + error = xfs_dec_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb, + flags & XFS_ZR_RESERVED); + if (error != -ENOSPC) + break; + + /* + * Make sure to start GC if it is not running already. As we + * check the rtavailable count when filling up zones, GC is + * normally already running at this point, but in some setups + * with very few zones we may completely run out of non- + * reserved blocks in between filling zones. + */ + if (!xfs_is_zonegc_running(mp)) + wake_up_process(zi->zi_gc_thread); + + /* + * If there is no reclaimable group left and we aren't still + * processing a pending GC request give up as we're fully out + * of space. + */ + if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE) && + !xfs_is_zonegc_running(mp)) + break; + + spin_unlock(&zi->zi_reservation_lock); + schedule(); + spin_lock(&zi->zi_reservation_lock); + } + list_del(&reservation.entry); + spin_unlock(&zi->zi_reservation_lock); + + __set_current_state(TASK_RUNNING); + return error; +} + +/* + * Implement greedy space allocation for short writes by trying to grab all + * that is left after locking out other threads from trying to do the same. + * + * This isn't exactly optimal and can hopefully be replaced by a proper + * percpu_counter primitive one day. + */ +static int +xfs_zoned_reserve_extents_greedy( + struct xfs_inode *ip, + xfs_filblks_t *count_fsb, + unsigned int flags) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_zone_info *zi = mp->m_zone_info; + s64 len = *count_fsb; + int error = -ENOSPC; + + spin_lock(&zi->zi_reservation_lock); + len = min(len, xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); + if (len > 0) { + *count_fsb = len; + error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, *count_fsb, + flags & XFS_ZR_RESERVED); + } + spin_unlock(&zi->zi_reservation_lock); + return error; +} + +int +xfs_zoned_space_reserve( + struct xfs_inode *ip, + xfs_filblks_t count_fsb, + unsigned int flags, + struct xfs_zone_alloc_ctx *ac) +{ + struct xfs_mount *mp = ip->i_mount; + int error; + + ASSERT(ac->reserved_blocks == 0); + ASSERT(ac->open_zone == NULL); + + error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb, + flags & XFS_ZR_RESERVED); + if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1) + error = xfs_zoned_reserve_extents_greedy(ip, &count_fsb, flags); + if (error) + return error; + + error = xfs_zoned_reserve_available(ip, count_fsb, flags); + if (error) { + xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb); + return error; + } + ac->reserved_blocks = count_fsb; + return 0; +} + +void +xfs_zoned_space_unreserve( + struct xfs_inode *ip, + struct xfs_zone_alloc_ctx *ac) +{ + if (ac->reserved_blocks > 0) { + struct xfs_mount *mp = ip->i_mount; + + xfs_zoned_add_available(mp, ac->reserved_blocks); + xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, ac->reserved_blocks); + } + if (ac->open_zone) + xfs_open_zone_put(ac->open_zone); +} |