diff options
Diffstat (limited to 'fs/xfs')
64 files changed, 2050 insertions, 1281 deletions
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 7cb9f064ac64..0c623d3c1036 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2474,6 +2474,47 @@ xfs_defer_agfl_block( xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list); } +#ifdef DEBUG +/* + * Check if an AGF has a free extent record whose length is equal to + * args->minlen. + */ +STATIC int +xfs_exact_minlen_extent_available( + struct xfs_alloc_arg *args, + struct xfs_buf *agbp, + int *stat) +{ + struct xfs_btree_cur *cnt_cur; + xfs_agblock_t fbno; + xfs_extlen_t flen; + int error = 0; + + cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, agbp, + args->agno, XFS_BTNUM_CNT); + error = xfs_alloc_lookup_ge(cnt_cur, 0, args->minlen, stat); + if (error) + goto out; + + if (*stat == 0) { + error = -EFSCORRUPTED; + goto out; + } + + error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, stat); + if (error) + goto out; + + if (*stat == 1 && flen != args->minlen) + *stat = 0; + +out: + xfs_btree_del_cursor(cnt_cur, error); + + return error; +} +#endif + /* * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size. @@ -2545,6 +2586,15 @@ xfs_alloc_fix_freelist( if (!xfs_alloc_space_available(args, need, flags)) goto out_agbp_relse; +#ifdef DEBUG + if (args->alloc_minlen_only) { + int stat; + + error = xfs_exact_minlen_extent_available(args, agbp, &stat); + if (error || !stat) + goto out_agbp_relse; + } +#endif /* * Make the freelist shorter if it's too long. * diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 6c22b12176b8..a4427c5775c2 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -75,6 +75,9 @@ typedef struct xfs_alloc_arg { char wasfromfl; /* set if allocation is from freelist */ struct xfs_owner_info oinfo; /* owner of blocks being allocated */ enum xfs_ag_resv_type resv; /* block reservation to use */ +#ifdef DEBUG + bool alloc_minlen_only; /* allocate exact minlen extent */ +#endif } xfs_alloc_arg_t; /* diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index fd8e6418a0d3..472b3039eabb 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -396,6 +396,7 @@ xfs_attr_set( struct xfs_trans_res tres; bool rsvd = (args->attr_filter & XFS_ATTR_ROOT); int error, local; + int rmt_blks = 0; unsigned int total; if (XFS_FORCED_SHUTDOWN(dp->i_mount)) @@ -442,34 +443,33 @@ xfs_attr_set( tres.tr_logcount = XFS_ATTRSET_LOG_COUNT; tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; total = args->total; + + if (!local) + rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen); } else { XFS_STATS_INC(mp, xs_attr_remove); tres = M_RES(mp)->tr_attrrm; total = XFS_ATTRRM_SPACE_RES(mp); + rmt_blks = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX); } /* * Root fork attributes can use reserved data blocks for this * operation if necessary */ - error = xfs_trans_alloc(mp, &tres, total, 0, - rsvd ? XFS_TRANS_RESERVE : 0, &args->trans); + error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans); if (error) return error; - xfs_ilock(dp, XFS_ILOCK_EXCL); - xfs_trans_ijoin(args->trans, dp, 0); - if (args->value) { - unsigned int quota_flags = XFS_QMOPT_RES_REGBLKS; - - if (rsvd) - quota_flags |= XFS_QMOPT_FORCE_RES; - error = xfs_trans_reserve_quota_nblks(args->trans, dp, - args->total, 0, quota_flags); + if (args->value || xfs_inode_hasattr(dp)) { + error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK, + XFS_IEXT_ATTR_MANIP_CNT(rmt_blks)); if (error) goto out_trans_cancel; + } + if (args->value) { error = xfs_has_attr(args); if (error == -EEXIST && (args->attr_flags & XATTR_CREATE)) goto out_trans_cancel; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index bc446418e227..e0905ad171f0 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1079,21 +1079,13 @@ xfs_bmap_add_attrfork( blks = XFS_ADDAFORK_SPACE_RES(mp); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0, - rsvd ? XFS_TRANS_RESERVE : 0, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0, + rsvd, &tp); if (error) return error; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ? - XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : - XFS_QMOPT_RES_REGBLKS); - if (error) - goto trans_cancel; if (XFS_IFORK_Q(ip)) goto trans_cancel; - xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_bmap_set_attrforkoff(ip, size, &version); if (error) @@ -3463,34 +3455,16 @@ xfs_bmap_btalloc_accounting( args->len); } -STATIC int -xfs_bmap_btalloc( - struct xfs_bmalloca *ap) /* bmap alloc argument struct */ +static int +xfs_bmap_compute_alignments( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) { - xfs_mount_t *mp; /* mount point structure */ - xfs_alloctype_t atype = 0; /* type for allocation routines */ - xfs_extlen_t align = 0; /* minimum allocation alignment */ - xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ - xfs_agnumber_t ag; - xfs_alloc_arg_t args; - xfs_fileoff_t orig_offset; - xfs_extlen_t orig_length; - xfs_extlen_t blen; - xfs_extlen_t nextminlen = 0; - int nullfb; /* true if ap->firstblock isn't set */ - int isaligned; - int tryagain; - int error; - int stripe_align; - - ASSERT(ap->length); - orig_offset = ap->offset; - orig_length = ap->length; - - mp = ap->ip->i_mount; + struct xfs_mount *mp = args->mp; + xfs_extlen_t align = 0; /* minimum allocation alignment */ + int stripe_align = 0; /* stripe alignment for allocation is determined by mount parameters */ - stripe_align = 0; if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) stripe_align = mp->m_swidth; else if (mp->m_dalign) @@ -3501,13 +3475,171 @@ xfs_bmap_btalloc( else if (ap->datatype & XFS_ALLOC_USERDATA) align = xfs_get_extsz_hint(ap->ip); if (align) { - error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, - align, 0, ap->eof, 0, ap->conv, - &ap->offset, &ap->length); - ASSERT(!error); + if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, + ap->eof, 0, ap->conv, &ap->offset, + &ap->length)) + ASSERT(0); ASSERT(ap->length); } + /* apply extent size hints if obtained earlier */ + if (align) { + args->prod = align; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { + args->prod = 1; + args->mod = 0; + } else { + args->prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } + + return stripe_align; +} + +static void +xfs_bmap_process_allocated_extent( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_fileoff_t orig_offset, + xfs_extlen_t orig_length) +{ + int nullfb; + + nullfb = ap->tp->t_firstblock == NULLFSBLOCK; + + /* + * check the allocation happened at the same or higher AG than + * the first block that was allocated. + */ + ASSERT(nullfb || + XFS_FSB_TO_AGNO(args->mp, ap->tp->t_firstblock) <= + XFS_FSB_TO_AGNO(args->mp, args->fsbno)); + + ap->blkno = args->fsbno; + if (nullfb) + ap->tp->t_firstblock = args->fsbno; + ap->length = args->len; + /* + * If the extent size hint is active, we tried to round the + * caller's allocation request offset down to extsz and the + * length up to another extsz boundary. If we found a free + * extent we mapped it in starting at this new offset. If the + * newly mapped space isn't long enough to cover any of the + * range of offsets that was originally requested, move the + * mapping up so that we can fill as much of the caller's + * original request as possible. Free space is apparently + * very fragmented so we're unlikely to be able to satisfy the + * hints anyway. + */ + if (ap->length <= orig_length) + ap->offset = orig_offset; + else if (ap->offset + ap->length < orig_offset + orig_length) + ap->offset = orig_offset + orig_length - ap->length; + xfs_bmap_btalloc_accounting(ap, args); +} + +#ifdef DEBUG +static int +xfs_bmap_exact_minlen_extent_alloc( + struct xfs_bmalloca *ap) +{ + struct xfs_mount *mp = ap->ip->i_mount; + struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; + xfs_fileoff_t orig_offset; + xfs_extlen_t orig_length; + int error; + + ASSERT(ap->length); + + if (ap->minlen != 1) { + ap->blkno = NULLFSBLOCK; + ap->length = 0; + return 0; + } + + orig_offset = ap->offset; + orig_length = ap->length; + + args.alloc_minlen_only = 1; + + xfs_bmap_compute_alignments(ap, &args); + + if (ap->tp->t_firstblock == NULLFSBLOCK) { + /* + * Unlike the longest extent available in an AG, we don't track + * the length of an AG's shortest extent. + * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and + * hence we can afford to start traversing from the 0th AG since + * we need not be concerned about a drop in performance in + * "debug only" code paths. + */ + ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0); + } else { + ap->blkno = ap->tp->t_firstblock; + } + + args.fsbno = ap->blkno; + args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; + args.type = XFS_ALLOCTYPE_FIRST_AG; + args.total = args.minlen = args.maxlen = ap->minlen; + + args.alignment = 1; + args.minalignslop = 0; + + args.minleft = ap->minleft; + args.wasdel = ap->wasdel; + args.resv = XFS_AG_RESV_NONE; + args.datatype = ap->datatype; + + error = xfs_alloc_vextent(&args); + if (error) + return error; + + if (args.fsbno != NULLFSBLOCK) { + xfs_bmap_process_allocated_extent(ap, &args, orig_offset, + orig_length); + } else { + ap->blkno = NULLFSBLOCK; + ap->length = 0; + } + + return 0; +} +#else + +#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED) + +#endif + +STATIC int +xfs_bmap_btalloc( + struct xfs_bmalloca *ap) +{ + struct xfs_mount *mp = ap->ip->i_mount; + struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; + xfs_alloctype_t atype = 0; + xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ + xfs_agnumber_t ag; + xfs_fileoff_t orig_offset; + xfs_extlen_t orig_length; + xfs_extlen_t blen; + xfs_extlen_t nextminlen = 0; + int nullfb; /* true if ap->firstblock isn't set */ + int isaligned; + int tryagain; + int error; + int stripe_align; + + ASSERT(ap->length); + orig_offset = ap->offset; + orig_length = ap->length; + + stripe_align = xfs_bmap_compute_alignments(ap, &args); nullfb = ap->tp->t_firstblock == NULLFSBLOCK; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, @@ -3538,9 +3670,6 @@ xfs_bmap_btalloc( * Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned = 0; - memset(&args, 0, sizeof(args)); - args.tp = ap->tp; - args.mp = mp; args.fsbno = ap->blkno; args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; @@ -3571,21 +3700,7 @@ xfs_bmap_btalloc( args.total = ap->total; args.minlen = ap->minlen; } - /* apply extent size hints if obtained earlier */ - if (align) { - args.prod = align; - div_u64_rem(ap->offset, args.prod, &args.mod); - if (args.mod) - args.mod = args.prod - args.mod; - } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { - args.prod = 1; - args.mod = 0; - } else { - args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; - div_u64_rem(ap->offset, args.prod, &args.mod); - if (args.mod) - args.mod = args.prod - args.mod; - } + /* * If we are not low on available data blocks, and the underlying * logical volume manager is a stripe, and the file offset is zero then @@ -3687,37 +3802,10 @@ xfs_bmap_btalloc( return error; ap->tp->t_flags |= XFS_TRANS_LOWMODE; } + if (args.fsbno != NULLFSBLOCK) { - /* - * check the allocation happened at the same or higher AG than - * the first block that was allocated. - */ - ASSERT(ap->tp->t_firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <= - XFS_FSB_TO_AGNO(mp, args.fsbno)); - - ap->blkno = args.fsbno; - if (ap->tp->t_firstblock == NULLFSBLOCK) - ap->tp->t_firstblock = args.fsbno; - ASSERT(nullfb || fb_agno <= args.agno); - ap->length = args.len; - /* - * If the extent size hint is active, we tried to round the - * caller's allocation request offset down to extsz and the - * length up to another extsz boundary. If we found a free - * extent we mapped it in starting at this new offset. If the - * newly mapped space isn't long enough to cover any of the - * range of offsets that was originally requested, move the - * mapping up so that we can fill as much of the caller's - * original request as possible. Free space is apparently - * very fragmented so we're unlikely to be able to satisfy the - * hints anyway. - */ - if (ap->length <= orig_length) - ap->offset = orig_offset; - else if (ap->offset + ap->length < orig_offset + orig_length) - ap->offset = orig_offset + orig_length - ap->length; - xfs_bmap_btalloc_accounting(ap, &args); + xfs_bmap_process_allocated_extent(ap, &args, orig_offset, + orig_length); } else { ap->blkno = NULLFSBLOCK; ap->length = 0; @@ -4001,8 +4089,7 @@ xfs_bmapi_reserve_delalloc( * blocks. This number gets adjusted later. We return if we haven't * allocated blocks already inside this loop. */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, (long)alen, 0, - XFS_QMOPT_RES_REGBLKS); + error = xfs_quota_reserve_blkres(ip, alen); if (error) return error; @@ -4048,8 +4135,7 @@ out_unreserve_blocks: xfs_mod_fdblocks(mp, alen, false); out_unreserve_quota: if (XFS_IS_QUOTA_ON(mp)) - xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, - XFS_QMOPT_RES_REGBLKS); + xfs_quota_unreserve_blkres(ip, alen); return error; } @@ -4083,6 +4169,10 @@ xfs_bmap_alloc_userdata( return xfs_bmap_rtalloc(bma); } + if (unlikely(XFS_TEST_ERROR(false, mp, + XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) + return xfs_bmap_exact_minlen_extent_alloc(bma); + return xfs_bmap_btalloc(bma); } @@ -4119,10 +4209,15 @@ xfs_bmapi_allocate( else bma->minlen = 1; - if (bma->flags & XFS_BMAPI_METADATA) - error = xfs_bmap_btalloc(bma); - else + if (bma->flags & XFS_BMAPI_METADATA) { + if (unlikely(XFS_TEST_ERROR(false, mp, + XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) + error = xfs_bmap_exact_minlen_extent_alloc(bma); + else + error = xfs_bmap_btalloc(bma); + } else { error = xfs_bmap_alloc_userdata(bma); + } if (error || bma->blkno == NULLFSBLOCK) return error; @@ -4527,6 +4622,12 @@ xfs_bmapi_convert_delalloc( return error; xfs_ilock(ip, XFS_ILOCK_EXCL); + + error = xfs_iext_count_may_overflow(ip, whichfork, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + xfs_trans_ijoin(tp, ip, 0); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) || @@ -4826,9 +4927,8 @@ xfs_bmap_del_extent_delay( * sb counters as we might have to borrow some blocks for the * indirect block accounting. */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, - -((long)del->br_blockcount), 0, - isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + ASSERT(!isrt); + error = xfs_quota_unreserve_blkres(ip, del->br_blockcount); if (error) return error; ip->i_delayed_blks -= del->br_blockcount; @@ -5145,6 +5245,27 @@ xfs_bmap_del_extent_real( /* * Deleting the middle of the extent. */ + + /* + * For directories, -ENOSPC is returned since a directory entry + * remove operation must not fail due to low extent count + * availability. -ENOSPC will be handled by higher layers of XFS + * by letting the corresponding empty Data/Free blocks to linger + * until a future remove operation. Dabtree blocks would be + * swapped with the last block in the leaf space and then the + * new last block will be unmapped. + * + * The above logic also applies to the source directory entry of + * a rename operation. + */ + error = xfs_iext_count_may_overflow(ip, whichfork, 1); + if (error) { + ASSERT(S_ISDIR(VFS_I(ip)->i_mode) && + whichfork == XFS_DATA_FORK); + error = -ENOSPC; + goto done; + } + old = got; got.br_blockcount = del->br_startoff - got.br_startoff; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index c4d7a9241dc3..5b6fcb9b44e2 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -353,20 +353,17 @@ xfs_btree_free_block( */ void xfs_btree_del_cursor( - xfs_btree_cur_t *cur, /* btree cursor */ - int error) /* del because of error */ + struct xfs_btree_cur *cur, /* btree cursor */ + int error) /* del because of error */ { - int i; /* btree level */ + int i; /* btree level */ /* - * Clear the buffer pointers, and release the buffers. - * If we're doing this in the face of an error, we - * need to make sure to inspect all of the entries - * in the bc_bufs array for buffers to be unlocked. - * This is because some of the btree code works from - * level n down to 0, and if we get an error along - * the way we won't have initialized all the entries - * down to 0. + * Clear the buffer pointers and release the buffers. If we're doing + * this because of an error, inspect all of the entries in the bc_bufs + * array for buffers to be unlocked. This is because some of the btree + * code works from level n down to 0, and if we get an error along the + * way we won't have initialized all the entries down to 0. */ for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_bufs[i]) @@ -374,17 +371,11 @@ xfs_btree_del_cursor( else if (!error) break; } - /* - * Can't free a bmap cursor without having dealt with the - * allocated indirect blocks' accounting. - */ - ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || - cur->bc_ino.allocated == 0); - /* - * Free the cursor. - */ + + ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || cur->bc_ino.allocated == 0 || + XFS_FORCED_SHUTDOWN(cur->bc_mp)); if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) - kmem_free((void *)cur->bc_ops); + kmem_free(cur->bc_ops); kmem_cache_free(xfs_btree_cur_zone, cur); } @@ -2814,7 +2805,7 @@ xfs_btree_split_worker( struct xfs_btree_split_args *args = container_of(work, struct xfs_btree_split_args, work); unsigned long pflags; - unsigned long new_pflags = PF_MEMALLOC_NOFS; + unsigned long new_pflags = 0; /* * we are in a transaction context here, but may also be doing work @@ -2826,12 +2817,20 @@ xfs_btree_split_worker( new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; current_set_flags_nested(&pflags, new_pflags); + xfs_trans_set_context(args->cur->bc_tp); args->result = __xfs_btree_split(args->cur, args->level, args->ptrp, args->key, args->curp, args->stat); - complete(args->done); + xfs_trans_clear_context(args->cur->bc_tp); current_restore_flags_nested(&pflags, new_pflags); + + /* + * Do not access args after complete() has run here. We don't own args + * and the owner may run and free args before we return here. + */ + complete(args->done); + } /* diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index e55378640b05..d03e6098ded9 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -47,8 +47,6 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t tot); -extern bool xfs_dir2_sf_replace_needblock(struct xfs_inode *dp, - xfs_ino_t inum); extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t inum, xfs_extlen_t tot); diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 2463b5d73447..8c4f76bba88b 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -1018,7 +1018,7 @@ xfs_dir2_sf_removename( /* * Check whether the sf dir replace operation need more blocks. */ -bool +static bool xfs_dir2_sf_replace_needblock( struct xfs_inode *dp, xfs_ino_t inum) diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 53b305dea381..6ca9084b6934 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -56,7 +56,9 @@ #define XFS_ERRTAG_FORCE_SUMMARY_RECALC 33 #define XFS_ERRTAG_IUNLINK_FALLBACK 34 #define XFS_ERRTAG_BUF_IOERROR 35 -#define XFS_ERRTAG_MAX 36 +#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36 +#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37 +#define XFS_ERRTAG_MAX 38 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -97,5 +99,7 @@ #define XFS_RANDOM_FORCE_SUMMARY_RECALC 1 #define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10) #define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT +#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1 +#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1 #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 2a2e3cfd94f0..6fad140d4c8e 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -250,6 +250,7 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_RMAPBT (1 << 19) /* reverse mapping btree */ #define XFS_FSOP_GEOM_FLAGS_REFLINK (1 << 20) /* files can share blocks */ #define XFS_FSOP_GEOM_FLAGS_BIGTIME (1 << 21) /* 64-bit nsec timestamps */ +#define XFS_FSOP_GEOM_FLAGS_INOBTCNT (1 << 22) /* inobt btree counter */ /* * Minimum and maximum sizes need for growth checks. diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 7575de5cecb1..e080d7e07643 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -23,6 +23,8 @@ #include "xfs_da_btree.h" #include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" +#include "xfs_types.h" +#include "xfs_errortag.h" kmem_zone_t *xfs_ifork_zone; @@ -728,3 +730,28 @@ xfs_ifork_verify_local_attr( return 0; } + +int +xfs_iext_count_may_overflow( + struct xfs_inode *ip, + int whichfork, + int nr_to_add) +{ + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + uint64_t max_exts; + uint64_t nr_exts; + + if (whichfork == XFS_COW_FORK) + return 0; + + max_exts = (whichfork == XFS_ATTR_FORK) ? MAXAEXTNUM : MAXEXTNUM; + + if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) + max_exts = 10; + + nr_exts = ifp->if_nextents + nr_to_add; + if (nr_exts < ifp->if_nextents || nr_exts > max_exts) + return -EFBIG; + + return 0; +} diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index a4953e95c4f3..9e2137cd7372 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -35,6 +35,67 @@ struct xfs_ifork { #define XFS_IFBROOT 0x04 /* i_broot points to the bmap b-tree root */ /* + * Worst-case increase in the fork extent count when we're adding a single + * extent to a fork and there's no possibility of splitting an existing mapping. + */ +#define XFS_IEXT_ADD_NOSPLIT_CNT (1) + +/* + * Punching out an extent from the middle of an existing extent can cause the + * extent count to increase by 1. + * i.e. | Old extent | Hole | Old extent | + */ +#define XFS_IEXT_PUNCH_HOLE_CNT (1) + +/* + * Directory entry addition can cause the following, + * 1. Data block can be added/removed. + * A new extent can cause extent count to increase by 1. + * 2. Free disk block can be added/removed. + * Same behaviour as described above for Data block. + * 3. Dabtree blocks. + * XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new + * extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH. + */ +#define XFS_IEXT_DIR_MANIP_CNT(mp) \ + ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount) + +/* + * Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to + * be added. One extra extent for dabtree in case a local attr is + * large enough to cause a double split. It can also cause extent + * count to increase proportional to the size of a remote xattr's + * value. + */ +#define XFS_IEXT_ATTR_MANIP_CNT(rmt_blks) \ + (XFS_DA_NODE_MAXDEPTH + max(1, rmt_blks)) + +/* + * A write to a sub-interval of an existing unwritten extent causes the original + * extent to be split into 3 extents + * i.e. | Unwritten | Real | Unwritten | + * Hence extent count can increase by 2. + */ +#define XFS_IEXT_WRITE_UNWRITTEN_CNT (2) + + +/* + * Moving an extent to data fork can cause a sub-interval of an existing extent + * to be unmapped. This will increase extent count by 1. Mapping in the new + * extent can increase the extent count by 1 again i.e. + * | Old extent | New extent | Old extent | + * Hence number of extents increases by 2. + */ +#define XFS_IEXT_REFLINK_END_COW_CNT (2) + +/* + * Removing an initial range of source/donor file's extent and adding a new + * extent (from donor/source file) in its place will cause extent count to + * increase by 1. + */ +#define XFS_IEXT_SWAP_RMAP_CNT (1) + +/* * Fork handling. */ @@ -172,5 +233,7 @@ extern void xfs_ifork_init_cow(struct xfs_inode *ip); int xfs_ifork_verify_local_data(struct xfs_inode *ip); int xfs_ifork_verify_local_attr(struct xfs_inode *ip); +int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork, + int nr_to_add); #endif /* __XFS_INODE_FORK_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index bbda117e5d85..60e6d255e5e2 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1138,6 +1138,8 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK; if (xfs_sb_version_hasbigtime(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME; + if (xfs_sb_version_hasinobtcounts(sbp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT; if (xfs_sb_version_hassector(sbp)) geo->logsectsize = sbp->sb_logsectsize; else diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 8ea6d4aa3f55..53456f3de881 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -888,7 +888,7 @@ xchk_stop_reaping( struct xfs_scrub *sc) { sc->flags |= XCHK_REAPING_DISABLED; - xfs_stop_block_reaping(sc->mp); + xfs_blockgc_stop(sc->mp); } /* Restart background reaping of resources. */ @@ -896,6 +896,6 @@ void xchk_start_reaping( struct xfs_scrub *sc) { - xfs_start_block_reaping(sc->mp); + xfs_blockgc_start(sc->mp); sc->flags &= ~XCHK_REAPING_DISABLED; } diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 779cb73b3d00..d02bef24b32b 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -238,7 +238,8 @@ xfs_acl_set_mode( } int -xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { umode_t mode; bool set_mode = false; @@ -252,7 +253,7 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); if (error) return error; set_mode = true; diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index c042c0868016..7bdb3a4ed798 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -11,7 +11,8 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); -extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); void xfs_forget_acl(struct inode *inode, const char *name); #else diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4304c6416fbb..b4186d666157 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -62,7 +62,7 @@ xfs_setfilesize_trans_alloc( * We hand off the transaction to the completion thread now, so * clear the flag here. */ - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + xfs_trans_clear_context(tp); return 0; } @@ -125,7 +125,7 @@ xfs_setfilesize_ioend( * thus we need to mark ourselves as being in a transaction manually. * Similarly for freeze protection. */ - current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + xfs_trans_set_context(tp); __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS); /* we abort the update if there was an IO error */ @@ -568,6 +568,12 @@ xfs_vm_writepage( { struct xfs_writepage_ctx wpc = { }; + if (WARN_ON_ONCE(current->journal_info)) { + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; + } + return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops); } @@ -578,6 +584,13 @@ xfs_vm_writepages( { struct xfs_writepage_ctx wpc = { }; + /* + * Writing back data in a transaction context can result in recursive + * transactions. This is bad, so issue a warning and get out of here. + */ + if (WARN_ON_ONCE(current->journal_info)) + return 0; + xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); } diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c index e2148f2d5d6b..17f36db2f792 100644 --- a/fs/xfs/xfs_bio_io.c +++ b/fs/xfs/xfs_bio_io.c @@ -6,7 +6,7 @@ static inline unsigned int bio_max_vecs(unsigned int count) { - return min_t(unsigned, howmany(count, PAGE_SIZE), BIO_MAX_PAGES); + return bio_max_segs(howmany(count, PAGE_SIZE)); } int diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 93e4d8ae6e92..2344757ede63 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -471,6 +471,7 @@ xfs_bui_item_recover( xfs_exntst_t state; unsigned int bui_type; int whichfork; + int iext_delta; int error = 0; if (!xfs_bui_validate(mp, buip)) { @@ -508,6 +509,15 @@ xfs_bui_item_recover( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + if (bui_type == XFS_BMAP_MAP) + iext_delta = XFS_IEXT_ADD_NOSPLIT_CNT; + else + iext_delta = XFS_IEXT_PUNCH_HOLE_CNT; + + error = xfs_iext_count_may_overflow(ip, whichfork, iext_delta); + if (error) + goto err_cancel; + count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip, whichfork, bmap->me_startoff, bmap->me_startblock, diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 7371a7f7c652..e7d68318e6a5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -727,11 +727,9 @@ xfs_alloc_file_space( xfs_fileoff_t startoffset_fsb; xfs_fileoff_t endoffset_fsb; int nimaps; - int quota_flag; int rt; xfs_trans_t *tp; xfs_bmbt_irec_t imaps[1], *imapp; - uint qblocks, resblks, resrtextents; int error; trace_xfs_alloc_file_space(ip); @@ -761,6 +759,7 @@ xfs_alloc_file_space( */ while (allocatesize_fsb && !error) { xfs_fileoff_t s, e; + unsigned int dblocks, rblocks, resblks; /* * Determine space reservations for data/realtime. @@ -790,45 +789,31 @@ xfs_alloc_file_space( */ resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps)); if (unlikely(rt)) { - resrtextents = qblocks = resblks; - resrtextents /= mp->m_sb.sb_rextsize; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); - quota_flag = XFS_QMOPT_RES_RTBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resblks; } else { - resrtextents = 0; - resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks); - quota_flag = XFS_QMOPT_RES_REGBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks); + rblocks = 0; } /* * Allocate and setup the transaction. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, - resrtextents, 0, &tp); - - /* - * Check for running out of space - */ - if (error) { - /* - * Free the transaction structure. - */ - ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp)); - break; - } - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, - 0, quota_flag); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + dblocks, rblocks, false, &tp); if (error) - goto error1; + break; - xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto error; error = xfs_bmapi_write(tp, ip, startoffset_fsb, allocatesize_fsb, alloc_type, 0, imapp, &nimaps); if (error) - goto error0; + goto error; /* * Complete the transaction @@ -851,10 +836,7 @@ xfs_alloc_file_space( return error; -error0: /* unlock inode, unreserve quota blocks, cancel trans */ - xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); - -error1: /* Just cancel transaction */ +error: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; @@ -872,20 +854,16 @@ xfs_unmap_extent( uint resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); int error; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); - if (error) { - ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp)); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, + false, &tp); + if (error) return error; - } - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, ip->i_gdquot, - ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_PUNCH_HOLE_CNT); if (error) goto out_trans_cancel; - xfs_trans_ijoin(tp, ip, 0); - error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done); if (error) goto out_trans_cancel; @@ -1163,6 +1141,11 @@ xfs_insert_file_space( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_PUNCH_HOLE_CNT); + if (error) + goto out_trans_cancel; + /* * The extent shifting code works on extent granularity. So, if stop_fsb * is not the starting block of extent, we need to split the extent at @@ -1384,6 +1367,22 @@ xfs_swap_extent_rmap( irec.br_blockcount); trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec); + if (xfs_bmap_is_real_extent(&uirec)) { + error = xfs_iext_count_may_overflow(ip, + XFS_DATA_FORK, + XFS_IEXT_SWAP_RMAP_CNT); + if (error) + goto out; + } + + if (xfs_bmap_is_real_extent(&irec)) { + error = xfs_iext_count_may_overflow(tip, + XFS_DATA_FORK, + XFS_IEXT_SWAP_RMAP_CNT); + if (error) + goto out; + } + /* Remove the mapping from the donor file. */ xfs_bmap_unmap_extent(tp, tip, &uirec); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f8400bbd6473..37a1d12762d8 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -43,7 +43,7 @@ static kmem_zone_t *xfs_buf_zone; * pag_buf_lock * lru_lock * - * xfs_buftarg_wait_rele + * xfs_buftarg_drain_rele * lru_lock * b_lock (trylock due to inversion) * @@ -88,7 +88,7 @@ xfs_buf_vmap_len( * 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_wait_buftarg()), so all we really need is a count of + * 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 @@ -1480,7 +1480,7 @@ xfs_buf_ioapply_map( int op) { int page_index; - int total_nr_pages = bp->b_page_count; + unsigned int total_nr_pages = bp->b_page_count; int nr_pages; struct bio *bio; sector_t sector = bp->b_maps[map].bm_bn; @@ -1505,7 +1505,7 @@ xfs_buf_ioapply_map( next_chunk: atomic_inc(&bp->b_io_remaining); - nr_pages = min(total_nr_pages, BIO_MAX_PAGES); + nr_pages = bio_max_segs(total_nr_pages); bio = bio_alloc(GFP_NOIO, nr_pages); bio_set_dev(bio, bp->b_target->bt_bdev); @@ -1786,7 +1786,7 @@ __xfs_buf_mark_corrupt( * while freeing all the buffers only held by the LRU. */ static enum lru_status -xfs_buftarg_wait_rele( +xfs_buftarg_drain_rele( struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, @@ -1798,7 +1798,7 @@ xfs_buftarg_wait_rele( if (atomic_read(&bp->b_hold) > 1) { /* need to wait, so skip it this pass */ - trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + trace_xfs_buf_drain_buftarg(bp, _RET_IP_); return LRU_SKIP; } if (!spin_trylock(&bp->b_lock)) @@ -1815,14 +1815,13 @@ xfs_buftarg_wait_rele( return LRU_REMOVED; } +/* + * Wait for outstanding I/O on the buftarg to complete. + */ void -xfs_wait_buftarg( +xfs_buftarg_wait( struct xfs_buftarg *btp) { - LIST_HEAD(dispose); - int loop = 0; - bool write_fail = false; - /* * 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 @@ -1838,10 +1837,21 @@ xfs_wait_buftarg( while (percpu_counter_sum(&btp->bt_io_count)) delay(100); flush_workqueue(btp->bt_mount->m_buf_workqueue); +} + +void +xfs_buftarg_drain( + struct xfs_buftarg *btp) +{ + LIST_HEAD(dispose); + int loop = 0; + bool write_fail = false; + + xfs_buftarg_wait(btp); /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { - list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, + list_lru_walk(&btp->bt_lru, xfs_buftarg_drain_rele, &dispose, LONG_MAX); while (!list_empty(&dispose)) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 5d91a31298a4..459ca34f26f5 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -152,7 +152,7 @@ struct xfs_buf { struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ struct xfs_mount *b_mount; - xfs_buftarg_t *b_target; /* buffer target (device) */ + struct xfs_buftarg *b_target; /* buffer target (device) */ void *b_addr; /* virtual address of buffer */ struct work_struct b_ioend_work; struct completion b_iowait; /* queue for I/O waiters */ @@ -344,11 +344,12 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) /* * Handling of buftargs. */ -extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *, - struct block_device *, struct dax_device *); +extern struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *, + struct block_device *, struct dax_device *); extern void xfs_free_buftarg(struct xfs_buftarg *); -extern void xfs_wait_buftarg(xfs_buftarg_t *); -extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int); +extern void xfs_buftarg_wait(struct xfs_buftarg *); +extern void xfs_buftarg_drain(struct xfs_buftarg *); +extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int); #define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 1d95ed387d66..bd8379b98374 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -314,8 +314,14 @@ xfs_dquot_disk_alloc( return -ESRCH; } - /* Create the block mapping. */ xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL); + + error = xfs_iext_count_may_overflow(quotip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + return error; + + /* Create the block mapping. */ error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0, &map, &nmaps); @@ -500,6 +506,42 @@ xfs_dquot_alloc( return dqp; } +/* Check the ondisk dquot's id and type match what the incore dquot expects. */ +static bool +xfs_dquot_check_type( + struct xfs_dquot *dqp, + struct xfs_disk_dquot *ddqp) +{ + uint8_t ddqp_type; + uint8_t dqp_type; + + ddqp_type = ddqp->d_type & XFS_DQTYPE_REC_MASK; + dqp_type = xfs_dquot_type(dqp); + + if (be32_to_cpu(ddqp->d_id) != dqp->q_id) + return false; + + /* + * V5 filesystems always expect an exact type match. V4 filesystems + * expect an exact match for user dquots and for non-root group and + * project dquots. + */ + if (xfs_sb_version_hascrc(&dqp->q_mount->m_sb) || + dqp_type == XFS_DQTYPE_USER || dqp->q_id != 0) + return ddqp_type == dqp_type; + + /* + * V4 filesystems support either group or project quotas, but not both + * at the same time. The non-user quota file can be switched between + * group and project quota uses depending on the mount options, which + * means that we can encounter the other type when we try to load quota + * defaults. Quotacheck will soon reset the the entire quota file + * (including the root dquot) anyway, but don't log scary corruption + * reports to dmesg. + */ + return ddqp_type == XFS_DQTYPE_GROUP || ddqp_type == XFS_DQTYPE_PROJ; +} + /* Copy the in-core quota fields in from the on-disk buffer. */ STATIC int xfs_dquot_from_disk( @@ -512,8 +554,7 @@ xfs_dquot_from_disk( * Ensure that we got the type and ID we were looking for. * Everything else was checked by the dquot buffer verifier. */ - if ((ddqp->d_type & XFS_DQTYPE_REC_MASK) != xfs_dquot_type(dqp) || - be32_to_cpu(ddqp->d_id) != dqp->q_id) { + if (!xfs_dquot_check_type(dqp, ddqp)) { xfs_alert_tag(bp->b_mount, XFS_PTAG_VERIFIER_ERROR, "Metadata corruption detected at %pS, quota %u", __this_address, dqp->q_id); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 7f6e20899473..185b4915b7bf 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -54,6 +54,8 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_FORCE_SUMMARY_RECALC, XFS_RANDOM_IUNLINK_FALLBACK, XFS_RANDOM_BUF_IOERROR, + XFS_RANDOM_REDUCE_MAX_IEXTENTS, + XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT, }; struct xfs_errortag_attr { @@ -164,6 +166,8 @@ XFS_ERRORTAG_ATTR_RW(force_repair, XFS_ERRTAG_FORCE_SCRUB_REPAIR); XFS_ERRORTAG_ATTR_RW(bad_summary, XFS_ERRTAG_FORCE_SUMMARY_RECALC); XFS_ERRORTAG_ATTR_RW(iunlink_fallback, XFS_ERRTAG_IUNLINK_FALLBACK); XFS_ERRORTAG_ATTR_RW(buf_ioerror, XFS_ERRTAG_BUF_IOERROR); +XFS_ERRORTAG_ATTR_RW(reduce_max_iextents, XFS_ERRTAG_REDUCE_MAX_IEXTENTS); +XFS_ERRORTAG_ATTR_RW(bmap_alloc_minlen_extent, XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT); static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(noerror), @@ -202,6 +206,8 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(bad_summary), XFS_ERRORTAG_ATTR_LIST(iunlink_fallback), XFS_ERRORTAG_ATTR_LIST(buf_ioerror), + XFS_ERRORTAG_ATTR_LIST(reduce_max_iextents), + XFS_ERRORTAG_ATTR_LIST(bmap_alloc_minlen_extent), NULL, }; diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 3991e59cfd18..ef17c1f6db32 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -344,7 +344,6 @@ xfs_extent_busy_trim( ASSERT(*len > 0); spin_lock(&args->pag->pagb_lock); -restart: fbno = *bno; flen = *len; rbp = args->pag->pagb_tree.rb_node; @@ -363,19 +362,6 @@ restart: continue; } - /* - * If this is a metadata allocation, try to reuse the busy - * extent instead of trimming the allocation. - */ - if (!(args->datatype & XFS_ALLOC_USERDATA) && - !(busyp->flags & XFS_EXTENT_BUSY_DISCARDED)) { - if (!xfs_extent_busy_update_extent(args->mp, args->pag, - busyp, fbno, flen, - false)) - goto restart; - continue; - } - if (bbno <= fbno) { /* start overlap */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5b0f93f73837..a007ca0711d9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -29,6 +29,7 @@ #include <linux/backing-dev.h> #include <linux/mman.h> #include <linux/fadvise.h> +#include <linux/mount.h> static const struct vm_operations_struct xfs_file_vm_ops; @@ -118,6 +119,54 @@ xfs_dir_fsync( return xfs_log_force_inode(ip); } +static xfs_lsn_t +xfs_fsync_lsn( + struct xfs_inode *ip, + bool datasync) +{ + if (!xfs_ipincount(ip)) + return 0; + if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) + return 0; + return ip->i_itemp->ili_last_lsn; +} + +/* + * All metadata updates are logged, which means that we just have to flush the + * log up to the latest LSN that touched the inode. + * + * If we have concurrent fsync/fdatasync() calls, we need them to all block on + * the log force before we clear the ili_fsync_fields field. This ensures that + * we don't get a racing sync operation that does not wait for the metadata to + * hit the journal before returning. If we race with clearing ili_fsync_fields, + * then all that will happen is the log force will do nothing as the lsn will + * already be on disk. We can't race with setting ili_fsync_fields because that + * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock + * shared until after the ili_fsync_fields is cleared. + */ +static int +xfs_fsync_flush_log( + struct xfs_inode *ip, + bool datasync, + int *log_flushed) +{ + int error = 0; + xfs_lsn_t lsn; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + lsn = xfs_fsync_lsn(ip, datasync); + if (lsn) { + error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, + log_flushed); + + spin_lock(&ip->i_itemp->ili_lock); + ip->i_itemp->ili_fsync_fields = 0; + spin_unlock(&ip->i_itemp->ili_lock); + } + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return error; +} + STATIC int xfs_file_fsync( struct file *file, @@ -125,13 +174,10 @@ xfs_file_fsync( loff_t end, int datasync) { - struct inode *inode = file->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_inode *ip = XFS_I(file->f_mapping->host); struct xfs_mount *mp = ip->i_mount; int error = 0; int log_flushed = 0; - xfs_lsn_t lsn = 0; trace_xfs_file_fsync(ip); @@ -156,32 +202,13 @@ xfs_file_fsync( xfs_blkdev_issue_flush(mp->m_ddev_targp); /* - * All metadata updates are logged, which means that we just have to - * flush the log up to the latest LSN that touched the inode. If we have - * concurrent fsync/fdatasync() calls, we need them to all block on the - * log force before we clear the ili_fsync_fields field. This ensures - * that we don't get a racing sync operation that does not wait for the - * metadata to hit the journal before returning. If we race with - * clearing the ili_fsync_fields, then all that will happen is the log - * force will do nothing as the lsn will already be on disk. We can't - * race with setting ili_fsync_fields because that is done under - * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared - * until after the ili_fsync_fields is cleared. + * Any inode that has dirty modifications in the log is pinned. The + * racy check here for a pinned inode while not catch modifications + * that happen concurrently to the fsync call, but fsync semantics + * only require to sync previously completed I/O. */ - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) { - if (!datasync || - (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) - lsn = iip->ili_last_lsn; - } - - if (lsn) { - error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed); - spin_lock(&iip->ili_lock); - iip->ili_fsync_fields = 0; - spin_unlock(&iip->ili_lock); - } - xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (xfs_ipincount(ip)) + error = xfs_fsync_flush_log(ip, datasync, &log_flushed); /* * If we only have a single device, and the log force about was @@ -197,30 +224,42 @@ xfs_file_fsync( return error; } +static int +xfs_ilock_iocb( + struct kiocb *iocb, + unsigned int lock_mode) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, lock_mode)) + return -EAGAIN; + } else { + xfs_ilock(ip, lock_mode); + } + + return 0; +} + STATIC ssize_t -xfs_file_dio_aio_read( +xfs_file_dio_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); - size_t count = iov_iter_count(to); ssize_t ret; - trace_xfs_file_direct_read(ip, count, iocb->ki_pos); + trace_xfs_file_direct_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ file_accessed(iocb->ki_filp); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, - is_sync_kiocb(iocb)); + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; + ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -232,21 +271,16 @@ xfs_file_dax_read( struct iov_iter *to) { struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host); - size_t count = iov_iter_count(to); ssize_t ret = 0; - trace_xfs_file_dax_read(ip, count, iocb->ki_pos); + trace_xfs_file_dax_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = dax_iomap_rw(iocb, to, &xfs_read_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -255,21 +289,18 @@ xfs_file_dax_read( } STATIC ssize_t -xfs_file_buffered_aio_read( +xfs_file_buffered_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); ssize_t ret; - trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); + trace_xfs_file_buffered_read(iocb, to); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = generic_file_read_iter(iocb, to); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -293,9 +324,9 @@ xfs_file_read_iter( if (IS_DAX(inode)) ret = xfs_file_dax_read(iocb, to); else if (iocb->ki_flags & IOCB_DIRECT) - ret = xfs_file_dio_aio_read(iocb, to); + ret = xfs_file_dio_read(iocb, to); else - ret = xfs_file_buffered_aio_read(iocb, to); + ret = xfs_file_buffered_read(iocb, to); if (ret > 0) XFS_STATS_ADD(mp, xs_read_bytes, ret); @@ -310,7 +341,7 @@ xfs_file_read_iter( * if called for a direct write beyond i_size. */ STATIC ssize_t -xfs_file_aio_write_checks( +xfs_file_write_checks( struct kiocb *iocb, struct iov_iter *from, int *iolock) @@ -328,7 +359,14 @@ restart: if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + if (iocb->ki_flags & IOCB_NOWAIT) { + error = break_layout(inode, false); + if (error == -EWOULDBLOCK) + error = -EAGAIN; + } else { + error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + } + if (error) return error; @@ -339,7 +377,11 @@ restart: if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) { xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_ilock(ip, *iolock); + error = xfs_ilock_iocb(iocb, *iolock); + if (error) { + *iolock = 0; + return error; + } goto restart; } /* @@ -361,6 +403,10 @@ restart: isize = i_size_read(inode); if (iocb->ki_pos > isize) { spin_unlock(&ip->i_flags_lock); + + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_iunlock(ip, *iolock); @@ -389,12 +435,6 @@ restart: } else spin_unlock(&ip->i_flags_lock); - /* - * Updating the timestamps will grab the ilock again from - * xfs_fs_dirty_inode, so we have to call it after dropping the - * lock above. Eventually we should look into a way to avoid - * the pointless lock roundtrip. - */ return file_modified(file); } @@ -480,122 +520,149 @@ static const struct iomap_dio_ops xfs_dio_write_ops = { }; /* - * xfs_file_dio_aio_write - handle direct IO writes - * - * Lock the inode appropriately to prepare for and issue a direct IO write. - * By separating it from the buffered write path we remove all the tricky to - * follow locking changes and looping. - * - * If there are cached pages or we're extending the file, we need IOLOCK_EXCL - * until we're sure the bytes at the new EOF have been zeroed and/or the cached - * pages are flushed out. - * - * In most cases the direct IO writes will be done holding IOLOCK_SHARED - * allowing them to be done in parallel with reads and other direct IO writes. - * However, if the IO is not aligned to filesystem blocks, the direct IO layer - * needs to do sub-block zeroing and that requires serialisation against other - * direct IOs to the same block. In this case we need to serialise the - * submission of the unaligned IOs so that we don't get racing block zeroing in - * the dio layer. To avoid the problem with aio, we also need to wait for - * outstanding IOs to complete so that unwritten extent conversion is completed - * before we try to map the overlapping block. This is currently implemented by - * hitting it with a big hammer (i.e. inode_dio_wait()). - * - * Returns with locks held indicated by @iolock and errors indicated by - * negative return values. + * Handle block aligned direct I/O writes */ -STATIC ssize_t -xfs_file_dio_aio_write( +static noinline ssize_t +xfs_file_dio_write_aligned( + struct xfs_inode *ip, struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - ssize_t ret = 0; - int unaligned_io = 0; - int iolock; - size_t count = iov_iter_count(from); - struct xfs_buftarg *target = xfs_inode_buftarg(ip); + int iolock = XFS_IOLOCK_SHARED; + ssize_t ret; - /* DIO must be aligned to device logical sector size */ - if ((iocb->ki_pos | count) & target->bt_logical_sectormask) - return -EINVAL; + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; /* - * Don't take the exclusive iolock here unless the I/O is unaligned to - * the file system block size. We don't need to consider the EOF - * extension case here because xfs_file_aio_write_checks() will relock - * the inode as necessary for EOF zeroing cases and fill out the new - * inode size as appropriate. + * We don't need to hold the IOLOCK exclusively across the IO, so demote + * the iolock back to shared if we had to take the exclusive lock in + * xfs_file_write_checks() for other reasons. */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) { - unaligned_io = 1; - - /* - * We can't properly handle unaligned direct I/O to reflink - * files yet, as we can't unshare a partial block. - */ - if (xfs_is_cow_inode(ip)) { - trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count); - return -ENOTBLK; - } - iolock = XFS_IOLOCK_EXCL; - } else { + if (iolock == XFS_IOLOCK_EXCL) { + xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); 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); +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); + return ret; +} - if (iocb->ki_flags & IOCB_NOWAIT) { - /* unaligned dio always waits, bail */ - if (unaligned_io) - return -EAGAIN; - if (!xfs_ilock_nowait(ip, iolock)) +/* + * Handle block unaligned direct I/O writes + * + * In most cases direct I/O writes will be done holding IOLOCK_SHARED, allowing + * them to be done in parallel with reads and other direct I/O writes. However, + * if the I/O is not aligned to filesystem blocks, the direct I/O layer may need + * to do sub-block zeroing and that requires serialisation against other direct + * I/O to the same block. In this case we need to serialise the submission of + * the unaligned I/O so that we don't get racing block zeroing in the dio layer. + * In the case where sub-block zeroing is not required, we can do concurrent + * sub-block dios to the same block successfully. + * + * Optimistically submit the I/O using the shared lock first, but use the + * IOMAP_DIO_OVERWRITE_ONLY flag to tell the lower layers to return -EAGAIN + * if block allocation or partial block zeroing would be required. In that case + * we try again with the exclusive lock. + */ +static noinline ssize_t +xfs_file_dio_write_unaligned( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from) +{ + size_t isize = i_size_read(VFS_I(ip)); + size_t count = iov_iter_count(from); + int iolock = XFS_IOLOCK_SHARED; + unsigned int flags = IOMAP_DIO_OVERWRITE_ONLY; + ssize_t ret; + + /* + * Extending writes need exclusivity because of the sub-block zeroing + * that the DIO code always does for partial tail blocks beyond EOF, so + * don't even bother trying the fast path in this case. + */ + if (iocb->ki_pos > isize || iocb->ki_pos + count >= isize) { +retry_exclusive: + if (iocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; - } else { - xfs_ilock(ip, iolock); + iolock = XFS_IOLOCK_EXCL; + flags = IOMAP_DIO_FORCE_WAIT; } - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); if (ret) - goto out; - count = iov_iter_count(from); + return ret; /* - * If we are doing unaligned IO, we can't allow any other overlapping IO - * in-flight at the same time or we risk data corruption. Wait for all - * other IO to drain before we submit. If the IO is aligned, demote the - * iolock if we had to take the exclusive lock in - * xfs_file_aio_write_checks() for other reasons. + * We can't properly handle unaligned direct I/O to reflink files yet, + * as we can't unshare a partial block. */ - if (unaligned_io) { - inode_dio_wait(inode); - } else if (iolock == XFS_IOLOCK_EXCL) { - xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); - iolock = XFS_IOLOCK_SHARED; + if (xfs_is_cow_inode(ip)) { + trace_xfs_reflink_bounce_dio_write(iocb, from); + ret = -ENOTBLK; + goto out_unlock; } - trace_xfs_file_direct_write(ip, count, iocb->ki_pos); + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; + /* - * If unaligned, this is the only IO in-flight. Wait on it before we - * release the iolock to prevent subsequent overlapping IO. + * If we are doing exclusive unaligned I/O, this must be the only I/O + * in-flight. Otherwise we risk data corruption due to unwritten extent + * conversions from the AIO end_io handler. Wait for all other I/O to + * drain first. */ + if (flags & IOMAP_DIO_FORCE_WAIT) + inode_dio_wait(VFS_I(ip)); + + trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, - is_sync_kiocb(iocb) || unaligned_io); -out: - xfs_iunlock(ip, iolock); + &xfs_dio_write_ops, flags); /* - * No fallback to buffered IO after short writes for XFS, direct I/O - * will either complete fully or return an error. + * Retry unaligned I/O with exclusive blocking semantics if the DIO + * layer rejected it for mapping or locking reasons. If we are doing + * nonblocking user I/O, propagate the error. */ - ASSERT(ret < 0 || ret == count); + if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT)) { + ASSERT(flags & IOMAP_DIO_OVERWRITE_ONLY); + xfs_iunlock(ip, iolock); + goto retry_exclusive; + } + +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); return ret; } +static ssize_t +xfs_file_dio_write( + struct kiocb *iocb, + struct iov_iter *from) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + size_t count = iov_iter_count(from); + + /* 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) + return xfs_file_dio_write_unaligned(ip, iocb, from); + return xfs_file_dio_write_aligned(ip, iocb, from); +} + static noinline ssize_t xfs_file_dax_write( struct kiocb *iocb, @@ -605,31 +672,26 @@ xfs_file_dax_write( struct xfs_inode *ip = XFS_I(inode); int iolock = XFS_IOLOCK_EXCL; ssize_t ret, error = 0; - size_t count; loff_t pos; - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, iolock)) - return -EAGAIN; - } else { - xfs_ilock(ip, iolock); - } - - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; pos = iocb->ki_pos; - count = iov_iter_count(from); - trace_xfs_file_dax_write(ip, count, pos); + trace_xfs_file_dax_write(iocb, from); ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); } out: - xfs_iunlock(ip, iolock); + if (iolock) + xfs_iunlock(ip, iolock); if (error) return error; @@ -643,7 +705,7 @@ out: } STATIC ssize_t -xfs_file_buffered_aio_write( +xfs_file_buffered_write( struct kiocb *iocb, struct iov_iter *from) { @@ -652,7 +714,7 @@ xfs_file_buffered_aio_write( struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t ret; - int enospc = 0; + bool cleared_space = false; int iolock; if (iocb->ki_flags & IOCB_NOWAIT) @@ -662,14 +724,14 @@ write_retry: iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos); + trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, &xfs_buffered_write_iomap_ops); if (likely(ret >= 0)) @@ -682,27 +744,23 @@ write_retry: * metadata space. This reduces the chances that the eofblocks scan * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this * also behaves as a filter to prevent too many eofblocks scans from - * running at the same time. + * running at the same time. Use a synchronous scan to increase the + * effectiveness of the scan. */ - if (ret == -EDQUOT && !enospc) { + if (ret == -EDQUOT && !cleared_space) { xfs_iunlock(ip, iolock); - enospc = xfs_inode_free_quota_eofblocks(ip); - if (enospc) - goto write_retry; - enospc = xfs_inode_free_quota_cowblocks(ip); - if (enospc) - goto write_retry; - iolock = 0; - } else if (ret == -ENOSPC && !enospc) { + xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC); + cleared_space = true; + goto write_retry; + } else if (ret == -ENOSPC && !cleared_space) { struct xfs_eofblocks eofb = {0}; - enospc = 1; + cleared_space = true; xfs_flush_inodes(ip->i_mount); xfs_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; - xfs_icache_free_eofblocks(ip->i_mount, &eofb); - xfs_icache_free_cowblocks(ip->i_mount, &eofb); + xfs_blockgc_free_space(ip->i_mount, &eofb); goto write_retry; } @@ -749,12 +807,12 @@ xfs_file_write_iter( * CoW. In all other directio scenarios we do not * allow an operation to fall back to buffered mode. */ - ret = xfs_file_dio_aio_write(iocb, from); + ret = xfs_file_dio_write(iocb, from); if (ret != -ENOTBLK) return ret; } - return xfs_file_buffered_aio_write(iocb, from); + return xfs_file_buffered_write(iocb, from); } static void @@ -994,7 +1052,8 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_vn_setattr_size(file_dentry(file), &iattr); + error = xfs_vn_setattr_size(file_mnt_user_ns(file), + file_dentry(file), &iattr); if (error) goto out_unlock; } @@ -1319,17 +1378,19 @@ xfs_filemap_pfn_mkwrite( return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } -static void +static vm_fault_t xfs_filemap_map_pages( struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct inode *inode = file_inode(vmf->vma->vm_file); + vm_fault_t ret; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - filemap_map_pages(vmf, start_pgoff, end_pgoff); + ret = filemap_map_pages(vmf, start_pgoff, end_pgoff); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + return ret; } static const struct vm_operations_struct xfs_file_vm_ops = { diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 959ce91a3755..a2a407039227 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -25,17 +25,17 @@ */ static int xfs_growfs_data_private( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_growfs_data_t *in) /* growfs data input struct */ + struct xfs_mount *mp, /* mount point for filesystem */ + struct xfs_growfs_data *in) /* growfs data input struct */ { struct xfs_buf *bp; int error; xfs_agnumber_t nagcount; xfs_agnumber_t nagimax = 0; - xfs_rfsblock_t nb, nb_mod; - xfs_rfsblock_t new; + xfs_rfsblock_t nb, nb_div, nb_mod; + xfs_rfsblock_t delta; xfs_agnumber_t oagcount; - xfs_trans_t *tp; + struct xfs_trans *tp; struct aghdr_init_data id = {}; nb = in->newblocks; @@ -50,16 +50,16 @@ xfs_growfs_data_private( return error; xfs_buf_relse(bp); - new = nb; /* use new as a temporary here */ - nb_mod = do_div(new, mp->m_sb.sb_agblocks); - nagcount = new + (nb_mod != 0); + nb_div = nb; + nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); + nagcount = nb_div + (nb_mod != 0); if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) { nagcount--; nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks; if (nb < mp->m_sb.sb_dblocks) return -EINVAL; } - new = nb - mp->m_sb.sb_dblocks; + delta = nb - mp->m_sb.sb_dblocks; oagcount = mp->m_sb.sb_agcount; /* allocate the new per-ag structures */ @@ -89,7 +89,7 @@ xfs_growfs_data_private( INIT_LIST_HEAD(&id.buffer_list); for (id.agno = nagcount - 1; id.agno >= oagcount; - id.agno--, new -= id.agsize) { + id.agno--, delta -= id.agsize) { if (id.agno == nagcount - 1) id.agsize = nb - @@ -110,8 +110,8 @@ xfs_growfs_data_private( xfs_trans_agblocks_delta(tp, id.nfree); /* If there are new blocks in the old last AG, extend it. */ - if (new) { - error = xfs_ag_extend_space(mp, tp, &id, new); + if (delta) { + error = xfs_ag_extend_space(mp, tp, &id, delta); if (error) goto out_trans_cancel; } @@ -143,7 +143,7 @@ xfs_growfs_data_private( * If we expanded the last AG, free the per-AG reservation * so we can reinitialize it with the new size. */ - if (new) { + if (delta) { struct xfs_perag *pag; pag = xfs_perag_get(mp, id.agno); @@ -170,8 +170,8 @@ out_trans_cancel: static int xfs_growfs_log_private( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_growfs_log_t *in) /* growfs log input struct */ + struct xfs_mount *mp, /* mount point for filesystem */ + struct xfs_growfs_log *in) /* growfs log input struct */ { xfs_extlen_t nb; @@ -268,7 +268,7 @@ out_error: int xfs_growfs_log( xfs_mount_t *mp, - xfs_growfs_log_t *in) + struct xfs_growfs_log *in) { int error; diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index 92869f6ec8d3..2cffe51a31e8 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -6,8 +6,8 @@ #ifndef __XFS_FSOPS_H__ #define __XFS_FSOPS_H__ -extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in); -extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in); +extern int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in); +extern int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in); extern void xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval, xfs_fsop_resblks_t *outval); diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c index fa55ab8b8d80..f62fa652c2fd 100644 --- a/fs/xfs/xfs_globals.c +++ b/fs/xfs/xfs_globals.c @@ -8,8 +8,8 @@ /* * Tunable XFS parameters. xfs_params is required even when CONFIG_SYSCTL=n, * other XFS code uses these values. Times are measured in centisecs (i.e. - * 100ths of a second) with the exception of eofb_timer and cowb_timer, which - * are measured in seconds. + * 100ths of a second) with the exception of blockgc_timer, which is measured + * in seconds. */ xfs_param_t xfs_params = { /* MIN DFLT MAX */ @@ -28,8 +28,7 @@ xfs_param_t xfs_params = { .rotorstep = { 1, 1, 255 }, .inherit_nodfrg = { 0, 1, 1 }, .fstrm_timer = { 1, 30*100, 3600*100}, - .eofb_timer = { 1, 300, 3600*24}, - .cowb_timer = { 1, 1800, 3600*24}, + .blockgc_timer = { 1, 300, 3600*24}, }; struct xfs_globals xfs_globals = { diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index deb99300d171..1d7720a0c068 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -916,69 +916,6 @@ xfs_inode_walk( } /* - * Background scanning to trim post-EOF preallocated space. This is queued - * based on the 'speculative_prealloc_lifetime' tunable (5m by default). - */ -void -xfs_queue_eofblocks( - struct xfs_mount *mp) -{ - rcu_read_lock(); - if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_EOFBLOCKS_TAG)) - queue_delayed_work(mp->m_eofblocks_workqueue, - &mp->m_eofblocks_work, - msecs_to_jiffies(xfs_eofb_secs * 1000)); - rcu_read_unlock(); -} - -void -xfs_eofblocks_worker( - struct work_struct *work) -{ - struct xfs_mount *mp = container_of(to_delayed_work(work), - struct xfs_mount, m_eofblocks_work); - - if (!sb_start_write_trylock(mp->m_super)) - return; - xfs_icache_free_eofblocks(mp, NULL); - sb_end_write(mp->m_super); - - xfs_queue_eofblocks(mp); -} - -/* - * Background scanning to trim preallocated CoW space. This is queued - * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default). - * (We'll just piggyback on the post-EOF prealloc space workqueue.) - */ -void -xfs_queue_cowblocks( - struct xfs_mount *mp) -{ - rcu_read_lock(); - if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_COWBLOCKS_TAG)) - queue_delayed_work(mp->m_eofblocks_workqueue, - &mp->m_cowblocks_work, - msecs_to_jiffies(xfs_cowb_secs * 1000)); - rcu_read_unlock(); -} - -void -xfs_cowblocks_worker( - struct work_struct *work) -{ - struct xfs_mount *mp = container_of(to_delayed_work(work), - struct xfs_mount, m_cowblocks_work); - - if (!sb_start_write_trylock(mp->m_super)) - return; - xfs_icache_free_cowblocks(mp, NULL); - sb_end_write(mp->m_super); - - xfs_queue_cowblocks(mp); -} - -/* * Grab the inode for reclaim exclusively. * * We have found this inode via a lookup under RCU, so the inode may have @@ -1346,14 +1283,17 @@ xfs_reclaim_worker( STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, - void *args) + void *args, + unsigned int *lockflags) { struct xfs_eofblocks *eofb = args; bool wait; - int ret; wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC); + if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS)) + return 0; + if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); @@ -1380,130 +1320,68 @@ xfs_inode_free_eofblocks( return -EAGAIN; return 0; } + *lockflags |= XFS_IOLOCK_EXCL; - ret = xfs_free_eofblocks(ip); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - - return ret; -} - -int -xfs_icache_free_eofblocks( - struct xfs_mount *mp, - struct xfs_eofblocks *eofb) -{ - return xfs_inode_walk(mp, 0, xfs_inode_free_eofblocks, eofb, - XFS_ICI_EOFBLOCKS_TAG); + return xfs_free_eofblocks(ip); } /* - * Run eofblocks scans on the quotas applicable to the inode. For inodes with - * multiple quotas, we don't know exactly which quota caused an allocation - * failure. We make a best effort by including each quota under low free space - * conditions (less than 1% free space) in the scan. + * Background scanning to trim preallocated space. This is queued based on the + * 'speculative_prealloc_lifetime' tunable (5m by default). */ -static int -__xfs_inode_free_quota_eofblocks( - struct xfs_inode *ip, - int (*execute)(struct xfs_mount *mp, - struct xfs_eofblocks *eofb)) -{ - int scan = 0; - struct xfs_eofblocks eofb = {0}; - struct xfs_dquot *dq; - - /* - * Run a sync scan to increase effectiveness and use the union filter to - * cover all applicable quotas in a single scan. - */ - eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC; - - if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) { - dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER); - if (dq && xfs_dquot_lowsp(dq)) { - eofb.eof_uid = VFS_I(ip)->i_uid; - eofb.eof_flags |= XFS_EOF_FLAGS_UID; - scan = 1; - } - } - - if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) { - dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP); - if (dq && xfs_dquot_lowsp(dq)) { - eofb.eof_gid = VFS_I(ip)->i_gid; - eofb.eof_flags |= XFS_EOF_FLAGS_GID; - scan = 1; - } - } - - if (scan) - execute(ip->i_mount, &eofb); - - return scan; -} - -int -xfs_inode_free_quota_eofblocks( - struct xfs_inode *ip) -{ - return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks); -} - -static inline unsigned long -xfs_iflag_for_tag( - int tag) +static inline void +xfs_blockgc_queue( + struct xfs_perag *pag) { - switch (tag) { - case XFS_ICI_EOFBLOCKS_TAG: - return XFS_IEOFBLOCKS; - case XFS_ICI_COWBLOCKS_TAG: - return XFS_ICOWBLOCKS; - default: - ASSERT(0); - return 0; - } + rcu_read_lock(); + if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) + queue_delayed_work(pag->pag_mount->m_blockgc_workqueue, + &pag->pag_blockgc_work, + msecs_to_jiffies(xfs_blockgc_secs * 1000)); + rcu_read_unlock(); } static void -__xfs_inode_set_blocks_tag( - xfs_inode_t *ip, - void (*execute)(struct xfs_mount *mp), - void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, - int error, unsigned long caller_ip), - int tag) +xfs_blockgc_set_iflag( + struct xfs_inode *ip, + unsigned long iflag) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - int tagged; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; + int tagged; + + ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); /* * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ - if (ip->i_flags & xfs_iflag_for_tag(tag)) + if (ip->i_flags & iflag) return; spin_lock(&ip->i_flags_lock); - ip->i_flags |= xfs_iflag_for_tag(tag); + ip->i_flags |= iflag; spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); - tagged = radix_tree_tagged(&pag->pag_ici_root, tag); + tagged = radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG); radix_tree_tag_set(&pag->pag_ici_root, - XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag); + XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), + XFS_ICI_BLOCKGC_TAG); if (!tagged) { - /* propagate the eofblocks tag up into the perag radix tree */ + /* propagate the blockgc tag up into the perag radix tree */ spin_lock(&ip->i_mount->m_perag_lock); radix_tree_tag_set(&ip->i_mount->m_perag_tree, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), - tag); + XFS_ICI_BLOCKGC_TAG); spin_unlock(&ip->i_mount->m_perag_lock); /* kick off background trimming */ - execute(ip->i_mount); + xfs_blockgc_queue(pag); - set_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_); + trace_xfs_perag_set_blockgc(ip->i_mount, pag->pag_agno, -1, + _RET_IP_); } spin_unlock(&pag->pag_ici_lock); @@ -1515,38 +1393,43 @@ xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); - return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks, - trace_xfs_perag_set_eofblocks, - XFS_ICI_EOFBLOCKS_TAG); + return xfs_blockgc_set_iflag(ip, XFS_IEOFBLOCKS); } static void -__xfs_inode_clear_blocks_tag( - xfs_inode_t *ip, - void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, - int error, unsigned long caller_ip), - int tag) +xfs_blockgc_clear_iflag( + struct xfs_inode *ip, + unsigned long iflag) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; + bool clear_tag; + + ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~xfs_iflag_for_tag(tag); + ip->i_flags &= ~iflag; + clear_tag = (ip->i_flags & (XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0; spin_unlock(&ip->i_flags_lock); + if (!clear_tag) + return; + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); radix_tree_tag_clear(&pag->pag_ici_root, - XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag); - if (!radix_tree_tagged(&pag->pag_ici_root, tag)) { - /* clear the eofblocks tag from the perag radix tree */ + XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), + XFS_ICI_BLOCKGC_TAG); + if (!radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) { + /* clear the blockgc tag from the perag radix tree */ spin_lock(&ip->i_mount->m_perag_lock); radix_tree_tag_clear(&ip->i_mount->m_perag_tree, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), - tag); + XFS_ICI_BLOCKGC_TAG); spin_unlock(&ip->i_mount->m_perag_lock); - clear_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_); + trace_xfs_perag_clear_blockgc(ip->i_mount, pag->pag_agno, -1, + _RET_IP_); } spin_unlock(&pag->pag_ici_lock); @@ -1558,8 +1441,7 @@ xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); - return __xfs_inode_clear_blocks_tag(ip, - trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG); + return xfs_blockgc_clear_iflag(ip, XFS_IEOFBLOCKS); } /* @@ -1609,20 +1491,42 @@ xfs_prep_free_cowblocks( STATIC int xfs_inode_free_cowblocks( struct xfs_inode *ip, - void *args) + void *args, + unsigned int *lockflags) { struct xfs_eofblocks *eofb = args; + bool wait; int ret = 0; + wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC); + + if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS)) + return 0; + if (!xfs_prep_free_cowblocks(ip)) return 0; if (!xfs_inode_matches_eofb(ip, eofb)) return 0; - /* Free the CoW blocks */ - xfs_ilock(ip, XFS_IOLOCK_EXCL); - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + /* + * If the caller is waiting, return -EAGAIN to keep the background + * scanner moving and revisit the inode in a subsequent pass. + */ + if (!(*lockflags & XFS_IOLOCK_EXCL) && + !xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + if (wait) + return -EAGAIN; + return 0; + } + *lockflags |= XFS_IOLOCK_EXCL; + + if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) { + if (wait) + return -EAGAIN; + return 0; + } + *lockflags |= XFS_MMAPLOCK_EXCL; /* * Check again, nobody else should be able to dirty blocks or change @@ -1630,37 +1534,15 @@ xfs_inode_free_cowblocks( */ if (xfs_prep_free_cowblocks(ip)) ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); - - xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; } -int -xfs_icache_free_cowblocks( - struct xfs_mount *mp, - struct xfs_eofblocks *eofb) -{ - return xfs_inode_walk(mp, 0, xfs_inode_free_cowblocks, eofb, - XFS_ICI_COWBLOCKS_TAG); -} - -int -xfs_inode_free_quota_cowblocks( - struct xfs_inode *ip) -{ - return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_cowblocks); -} - void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); - return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks, - trace_xfs_perag_set_cowblocks, - XFS_ICI_COWBLOCKS_TAG); + return xfs_blockgc_set_iflag(ip, XFS_ICOWBLOCKS); } void @@ -1668,24 +1550,158 @@ xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); - return __xfs_inode_clear_blocks_tag(ip, - trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); + return xfs_blockgc_clear_iflag(ip, XFS_ICOWBLOCKS); } +#define for_each_perag_tag(mp, next_agno, pag, tag) \ + for ((next_agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \ + (pag) != NULL; \ + (next_agno) = (pag)->pag_agno + 1, \ + xfs_perag_put(pag), \ + (pag) = xfs_perag_get_tag((mp), (next_agno), (tag))) + + /* Disable post-EOF and CoW block auto-reclamation. */ void -xfs_stop_block_reaping( +xfs_blockgc_stop( struct xfs_mount *mp) { - cancel_delayed_work_sync(&mp->m_eofblocks_work); - cancel_delayed_work_sync(&mp->m_cowblocks_work); + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) + cancel_delayed_work_sync(&pag->pag_blockgc_work); } /* Enable post-EOF and CoW block auto-reclamation. */ void -xfs_start_block_reaping( +xfs_blockgc_start( struct xfs_mount *mp) { - xfs_queue_eofblocks(mp); - xfs_queue_cowblocks(mp); + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) + xfs_blockgc_queue(pag); +} + +/* Scan one incore inode for block preallocations that we can remove. */ +static int +xfs_blockgc_scan_inode( + struct xfs_inode *ip, + void *args) +{ + unsigned int lockflags = 0; + int error; + + error = xfs_inode_free_eofblocks(ip, args, &lockflags); + if (error) + goto unlock; + + error = xfs_inode_free_cowblocks(ip, args, &lockflags); +unlock: + if (lockflags) + xfs_iunlock(ip, lockflags); + return error; +} + +/* Background worker that trims preallocated space. */ +void +xfs_blockgc_worker( + struct work_struct *work) +{ + struct xfs_perag *pag = container_of(to_delayed_work(work), + struct xfs_perag, pag_blockgc_work); + struct xfs_mount *mp = pag->pag_mount; + int error; + + if (!sb_start_write_trylock(mp->m_super)) + return; + error = xfs_inode_walk_ag(pag, 0, xfs_blockgc_scan_inode, NULL, + XFS_ICI_BLOCKGC_TAG); + if (error) + xfs_info(mp, "AG %u preallocation gc worker failed, err=%d", + pag->pag_agno, error); + sb_end_write(mp->m_super); + xfs_blockgc_queue(pag); +} + +/* + * Try to free space in the filesystem by purging eofblocks and cowblocks. + */ +int +xfs_blockgc_free_space( + struct xfs_mount *mp, + struct xfs_eofblocks *eofb) +{ + trace_xfs_blockgc_free_space(mp, eofb, _RET_IP_); + + return xfs_inode_walk(mp, 0, xfs_blockgc_scan_inode, eofb, + XFS_ICI_BLOCKGC_TAG); +} + +/* + * Run cow/eofblocks scans on the supplied dquots. We don't know exactly which + * quota caused an allocation failure, so we make a best effort by including + * each quota under low free space conditions (less than 1% free space) in the + * scan. + * + * Callers must not hold any inode's ILOCK. If requesting a synchronous scan + * (XFS_EOF_FLAGS_SYNC), the caller also must not hold any inode's IOLOCK or + * MMAPLOCK. + */ +int +xfs_blockgc_free_dquots( + struct xfs_mount *mp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + unsigned int eof_flags) +{ + struct xfs_eofblocks eofb = {0}; + bool do_work = false; + + if (!udqp && !gdqp && !pdqp) + return 0; + + /* + * Run a scan to free blocks using the union filter to cover all + * applicable quotas in a single scan. + */ + eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags; + + if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) { + eofb.eof_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id); + eofb.eof_flags |= XFS_EOF_FLAGS_UID; + do_work = true; + } + + if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) { + eofb.eof_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id); + eofb.eof_flags |= XFS_EOF_FLAGS_GID; + do_work = true; + } + + if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) { + eofb.eof_prid = pdqp->q_id; + eofb.eof_flags |= XFS_EOF_FLAGS_PRID; + do_work = true; + } + + if (!do_work) + return 0; + + return xfs_blockgc_free_space(mp, &eofb); +} + +/* Run cow/eofblocks scans on the quotas attached to the inode. */ +int +xfs_blockgc_free_quota( + struct xfs_inode *ip, + unsigned int eof_flags) +{ + return xfs_blockgc_free_dquots(ip->i_mount, + xfs_inode_dquot(ip, XFS_DQTYPE_USER), + xfs_inode_dquot(ip, XFS_DQTYPE_GROUP), + xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), eof_flags); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 3a4c8b382cd0..d1fddb152420 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -23,8 +23,8 @@ struct xfs_eofblocks { #define XFS_ICI_NO_TAG (-1) /* special flag for an untagged lookup in xfs_inode_walk */ #define XFS_ICI_RECLAIM_TAG 0 /* inode is to be reclaimed */ -#define XFS_ICI_EOFBLOCKS_TAG 1 /* inode has blocks beyond EOF */ -#define XFS_ICI_COWBLOCKS_TAG 2 /* inode can have cow blocks to gc */ +/* Inode has speculative preallocations (posteof or cow) to clean. */ +#define XFS_ICI_BLOCKGC_TAG 1 /* * Flags for xfs_iget() @@ -54,19 +54,19 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); +int xfs_blockgc_free_dquots(struct xfs_mount *mp, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, + unsigned int eof_flags); +int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags); +int xfs_blockgc_free_space(struct xfs_mount *mp, struct xfs_eofblocks *eofb); + void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip); void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip); -int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *); -int xfs_inode_free_quota_eofblocks(struct xfs_inode *ip); -void xfs_eofblocks_worker(struct work_struct *); -void xfs_queue_eofblocks(struct xfs_mount *); void xfs_inode_set_cowblocks_tag(struct xfs_inode *ip); void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip); -int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *); -int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip); -void xfs_cowblocks_worker(struct work_struct *); -void xfs_queue_cowblocks(struct xfs_mount *); + +void xfs_blockgc_worker(struct work_struct *work); int xfs_inode_walk(struct xfs_mount *mp, int iter_flags, int (*execute)(struct xfs_inode *ip, void *args), @@ -75,7 +75,7 @@ int xfs_inode_walk(struct xfs_mount *mp, int iter_flags, int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, bool *inuse); -void xfs_stop_block_reaping(struct xfs_mount *mp); -void xfs_start_block_reaping(struct xfs_mount *mp); +void xfs_blockgc_stop(struct xfs_mount *mp); +void xfs_blockgc_start(struct xfs_mount *mp); #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index b7352bc4c815..46a861d55e48 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -766,6 +766,7 @@ xfs_inode_inherit_flags2( */ static int xfs_init_new_inode( + struct user_namespace *mnt_userns, struct xfs_trans *tp, struct xfs_inode *pip, xfs_ino_t ino, @@ -775,6 +776,7 @@ xfs_init_new_inode( prid_t prid, struct xfs_inode **ipp) { + struct inode *dir = pip ? VFS_I(pip) : NULL; struct xfs_mount *mp = tp->t_mountp; struct xfs_inode *ip; unsigned int flags; @@ -804,18 +806,17 @@ xfs_init_new_inode( ASSERT(ip != NULL); inode = VFS_I(ip); - inode->i_mode = mode; set_nlink(inode, nlink); - inode->i_uid = current_fsuid(); inode->i_rdev = rdev; ip->i_d.di_projid = prid; - if (pip && XFS_INHERIT_GID(pip)) { - inode->i_gid = VFS_I(pip)->i_gid; - if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) - inode->i_mode |= S_ISGID; + if (dir && !(dir->i_mode & S_ISGID) && + (mp->m_flags & XFS_MOUNT_GRPID)) { + inode->i_uid = fsuid_into_mnt(mnt_userns); + inode->i_gid = dir->i_gid; + inode->i_mode = mode; } else { - inode->i_gid = current_fsgid(); + inode_init_owner(mnt_userns, inode, dir, mode); } /* @@ -824,7 +825,8 @@ xfs_init_new_inode( * (and only if the irix_sgid_inherit compatibility variable is set). */ if (irix_sgid_inherit && - (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid)) + (inode->i_mode & S_ISGID) && + !in_group_p(i_gid_into_mnt(mnt_userns, inode))) inode->i_mode &= ~S_ISGID; ip->i_d.di_size = 0; @@ -901,6 +903,7 @@ xfs_init_new_inode( */ int xfs_dir_ialloc( + struct user_namespace *mnt_userns, struct xfs_trans **tpp, struct xfs_inode *dp, umode_t mode, @@ -933,7 +936,8 @@ xfs_dir_ialloc( return error; ASSERT(ino != NULLFSINO); - return xfs_init_new_inode(*tpp, dp, ino, mode, nlink, rdev, prid, ipp); + return xfs_init_new_inode(mnt_userns, *tpp, dp, ino, mode, nlink, rdev, + prid, ipp); } /* @@ -973,6 +977,7 @@ xfs_bumplink( int xfs_create( + struct user_namespace *mnt_userns, xfs_inode_t *dp, struct xfs_name *name, umode_t mode, @@ -1022,23 +1027,22 @@ xfs_create( * the case we'll drop the one we have and get a more * appropriate transaction later. */ - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error == -ENOSPC) { /* flush outstanding delalloc blocks and retry */ xfs_flush_inodes(mp); - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, + resblks, &tp); } if (error) - goto out_release_inode; + goto out_release_dquots; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; - /* - * Reserve disk quota and the inode. - */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); if (error) goto out_trans_cancel; @@ -1047,7 +1051,8 @@ xfs_create( * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip); + error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, is_dir ? 2 : 1, rdev, + prid, &ip); if (error) goto out_trans_cancel; @@ -1116,7 +1121,7 @@ xfs_create( xfs_finish_inode_setup(ip); xfs_irele(ip); } - + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1128,6 +1133,7 @@ xfs_create( int xfs_create_tmpfile( + struct user_namespace *mnt_userns, struct xfs_inode *dp, umode_t mode, struct xfs_inode **ipp) @@ -1160,16 +1166,12 @@ xfs_create_tmpfile( resblks = XFS_IALLOC_SPACE_RES(mp); tres = &M_RES(mp)->tr_create_tmpfile; - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error) - goto out_release_inode; - - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error) - goto out_trans_cancel; + goto out_release_dquots; - error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip); + error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid, &ip); if (error) goto out_trans_cancel; @@ -1210,7 +1212,7 @@ xfs_create_tmpfile( xfs_finish_inode_setup(ip); xfs_irele(ip); } - + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1258,6 +1260,11 @@ xfs_link( xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL); + error = xfs_iext_count_may_overflow(tdp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); + if (error) + goto error_return; + /* * If we are using project inheritance, we only allow hard link * creation in our tree when the project IDs are the same; else @@ -2977,13 +2984,15 @@ out_trans_abort: */ static int xfs_rename_alloc_whiteout( + struct user_namespace *mnt_userns, struct xfs_inode *dp, struct xfs_inode **wip) { struct xfs_inode *tmpfile; int error; - error = xfs_create_tmpfile(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile); + error = xfs_create_tmpfile(mnt_userns, dp, S_IFCHR | WHITEOUT_MODE, + &tmpfile); if (error) return error; @@ -3005,6 +3014,7 @@ xfs_rename_alloc_whiteout( */ int xfs_rename( + struct user_namespace *mnt_userns, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, @@ -3017,7 +3027,7 @@ xfs_rename( struct xfs_trans *tp; struct xfs_inode *wip = NULL; /* whiteout inode */ struct xfs_inode *inodes[__XFS_SORT_INODES]; - struct xfs_buf *agibp; + int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); @@ -3036,7 +3046,7 @@ xfs_rename( */ if (flags & RENAME_WHITEOUT) { ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); - error = xfs_rename_alloc_whiteout(target_dp, &wip); + error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip); if (error) return error; @@ -3106,6 +3116,35 @@ xfs_rename( /* * Check for expected errors before we dirty the transaction * so we can return an error without a transaction abort. + * + * Extent count overflow check: + * + * From the perspective of src_dp, a rename operation is essentially a + * directory entry remove operation. Hence the only place where we check + * for extent count overflow for src_dp is in + * xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns + * -ENOSPC when it detects a possible extent count overflow and in + * response, the higher layers of directory handling code do the + * following: + * 1. Data/Free blocks: XFS lets these blocks linger until a + * future remove operation removes them. + * 2. Dabtree blocks: XFS swaps the blocks with the last block in the + * Leaf space and unmaps the last block. + * + * For target_dp, there are two cases depending on whether the + * destination directory entry exists or not. + * + * When destination directory entry does not exist (i.e. target_ip == + * NULL), extent count overflow check is performed only when transaction + * has a non-zero sized space reservation associated with it. With a + * zero-sized space reservation, XFS allows a rename operation to + * continue only when the directory has sufficient free space in its + * data/leaf/free space blocks to hold the new entry. + * + * When destination directory entry exists (i.e. target_ip != NULL), all + * we need to do is change the inode number associated with the already + * existing entry. Hence there is no need to perform an extent count + * overflow check. */ if (target_ip == NULL) { /* @@ -3116,6 +3155,12 @@ xfs_rename( error = xfs_dir_canenter(tp, target_dp, target_name); if (error) goto out_trans_cancel; + } else { + error = xfs_iext_count_may_overflow(target_dp, + XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); + if (error) + goto out_trans_cancel; } } else { /* @@ -3131,6 +3176,30 @@ xfs_rename( } /* + * Lock the AGI buffers we need to handle bumping the nlink of the + * whiteout inode off the unlinked list and to handle dropping the + * nlink of the target inode. Per locking order rules, do this in + * increasing AG order and before directory block allocation tries to + * grab AGFs because we grab AGIs before AGFs. + * + * The (vfs) caller must ensure that if src is a directory then + * target_ip is either null or an empty directory. + */ + for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { + if (inodes[i] == wip || + (inodes[i] == target_ip && + (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { + struct xfs_buf *bp; + xfs_agnumber_t agno; + + agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino); + error = xfs_read_agi(mp, tp, agno, &bp); + if (error) + goto out_trans_cancel; + } + } + + /* * Directory entry creation below may acquire the AGF. Remove * the whiteout from the unlinked list first to preserve correct * AGI/AGF locking order. This dirties the transaction so failures @@ -3182,22 +3251,6 @@ xfs_rename( * In case there is already an entry with the same * name at the destination directory, remove it first. */ - - /* - * Check whether the replace operation will need to allocate - * blocks. This happens when the shortform directory lacks - * space and we have to convert it to a block format directory. - * When more blocks are necessary, we must lock the AGI first - * to preserve locking order (AGI -> AGF). - */ - if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) { - error = xfs_read_agi(mp, tp, - XFS_INO_TO_AGNO(mp, target_ip->i_ino), - &agibp); - if (error) - goto out_trans_cancel; - } - error = xfs_dir_replace(tp, target_dp, target_name, src_ip->i_ino, spaceres); if (error) @@ -3273,9 +3326,16 @@ xfs_rename( if (wip) { error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino, spaceres); - } else + } else { + /* + * NOTE: We don't need to check for extent count overflow here + * because the dir remove name code will leave the dir block in + * place if the extent count would overflow. + */ error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, spaceres); + } + if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index eca333f5f715..88ee4c3930ae 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -369,15 +369,18 @@ int xfs_release(struct xfs_inode *ip); void xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); -int xfs_create(struct xfs_inode *dp, struct xfs_name *name, +int xfs_create(struct user_namespace *mnt_userns, + struct xfs_inode *dp, struct xfs_name *name, umode_t mode, dev_t rdev, struct xfs_inode **ipp); -int xfs_create_tmpfile(struct xfs_inode *dp, umode_t mode, +int xfs_create_tmpfile(struct user_namespace *mnt_userns, + struct xfs_inode *dp, umode_t mode, struct xfs_inode **ipp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name); -int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name, +int xfs_rename(struct user_namespace *mnt_userns, + struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, struct xfs_inode *target_ip, unsigned int flags); @@ -407,9 +410,10 @@ void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode, xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); -int xfs_dir_ialloc(struct xfs_trans **tpp, struct xfs_inode *dp, umode_t mode, - xfs_nlink_t nlink, dev_t dev, prid_t prid, - struct xfs_inode **ipp); +int xfs_dir_ialloc(struct user_namespace *mnt_userns, + struct xfs_trans **tpp, struct xfs_inode *dp, + umode_t mode, xfs_nlink_t nlink, dev_t dev, + prid_t prid, struct xfs_inode **ipp); static inline int xfs_itruncate_extents( diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3fbd98f61ea5..99dfe89a8d08 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -693,7 +693,8 @@ xfs_ioc_space( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = bf->l_start; - error = xfs_vn_setattr_size(file_dentry(filp), &iattr); + error = xfs_vn_setattr_size(file_mnt_user_ns(filp), file_dentry(filp), + &iattr); if (error) goto out_unlock; @@ -734,13 +735,15 @@ xfs_fsinumbers_fmt( STATIC int xfs_ioc_fsbulkstat( - xfs_mount_t *mp, + struct file *file, unsigned int cmd, void __user *arg) { + struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount; struct xfs_fsop_bulkreq bulkreq; struct xfs_ibulk breq = { .mp = mp, + .mnt_userns = file_mnt_user_ns(file), .ocount = 0, }; xfs_ino_t lastino; @@ -908,13 +911,15 @@ xfs_bulk_ireq_teardown( /* Handle the v5 bulkstat ioctl. */ STATIC int xfs_ioc_bulkstat( - struct xfs_mount *mp, + struct file *file, unsigned int cmd, struct xfs_bulkstat_req __user *arg) { + struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount; struct xfs_bulk_ireq hdr; struct xfs_ibulk breq = { .mp = mp, + .mnt_userns = file_mnt_user_ns(file), }; int error; @@ -1275,24 +1280,24 @@ xfs_ioctl_setattr_prepare_dax( */ static struct xfs_trans * xfs_ioctl_setattr_get_trans( - struct xfs_inode *ip) + struct file *file, + struct xfs_dquot *pdqp) { + struct xfs_inode *ip = XFS_I(file_inode(file)); struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error = -EROFS; if (mp->m_flags & XFS_MOUNT_RDONLY) - goto out_unlock; + goto out_error; error = -EIO; if (XFS_FORCED_SHUTDOWN(mp)) - goto out_unlock; + goto out_error; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, + capable(CAP_FOWNER), &tp); if (error) - goto out_unlock; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + goto out_error; /* * CAP_FOWNER overrides the following restrictions: @@ -1300,7 +1305,7 @@ xfs_ioctl_setattr_get_trans( * The user ID of the calling process must be equal to the file owner * ID, except in cases where the CAP_FSETID capability is applicable. */ - if (!inode_owner_or_capable(VFS_I(ip))) { + if (!inode_owner_or_capable(file_mnt_user_ns(file), VFS_I(ip))) { error = -EPERM; goto out_cancel; } @@ -1312,7 +1317,7 @@ xfs_ioctl_setattr_get_trans( out_cancel: xfs_trans_cancel(tp); -out_unlock: +out_error: return ERR_PTR(error); } @@ -1428,21 +1433,23 @@ xfs_ioctl_setattr_check_projid( STATIC int xfs_ioctl_setattr( - xfs_inode_t *ip, + struct file *file, struct fsxattr *fa) { + struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct xfs_inode *ip = XFS_I(file_inode(file)); struct fsxattr old_fa; struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; - int code; + int error; trace_xfs_ioctl_setattr(ip); - code = xfs_ioctl_setattr_check_projid(ip, fa); - if (code) - return code; + error = xfs_ioctl_setattr_check_projid(ip, fa); + if (error) + return error; /* * If disk quotas is on, we make sure that the dquots do exist on disk, @@ -1453,44 +1460,36 @@ xfs_ioctl_setattr( * because the i_*dquot fields will get updated anyway. */ if (XFS_IS_QUOTA_ON(mp)) { - code = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, + error = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, VFS_I(ip)->i_gid, fa->fsx_projid, XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp); - if (code) - return code; + if (error) + return error; } xfs_ioctl_setattr_prepare_dax(ip, fa); - tp = xfs_ioctl_setattr_get_trans(ip); + tp = xfs_ioctl_setattr_get_trans(file, pdqp); if (IS_ERR(tp)) { - code = PTR_ERR(tp); + error = PTR_ERR(tp); goto error_free_dquots; } - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && - ip->i_d.di_projid != fa->fsx_projid) { - code = xfs_qm_vop_chown_reserve(tp, ip, NULL, NULL, pdqp, - capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); - if (code) /* out of quota */ - goto error_trans_cancel; - } - xfs_fill_fsxattr(ip, false, &old_fa); - code = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa); - if (code) + error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_check_extsize(ip, fa); - if (code) + error = xfs_ioctl_setattr_check_extsize(ip, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_check_cowextsize(ip, fa); - if (code) + error = xfs_ioctl_setattr_check_cowextsize(ip, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_xflags(tp, ip, fa); - if (code) + error = xfs_ioctl_setattr_xflags(tp, ip, fa); + if (error) goto error_trans_cancel; /* @@ -1502,7 +1501,7 @@ xfs_ioctl_setattr( */ if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) && - !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) + !capable_wrt_inode_uidgid(mnt_userns, VFS_I(ip), CAP_FSETID)) VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ @@ -1530,7 +1529,7 @@ xfs_ioctl_setattr( else ip->i_d.di_cowextsize = 0; - code = xfs_trans_commit(tp); + error = xfs_trans_commit(tp); /* * Release any dquot(s) the inode had kept before chown. @@ -1538,18 +1537,17 @@ xfs_ioctl_setattr( xfs_qm_dqrele(olddquot); xfs_qm_dqrele(pdqp); - return code; + return error; error_trans_cancel: xfs_trans_cancel(tp); error_free_dquots: xfs_qm_dqrele(pdqp); - return code; + return error; } STATIC int xfs_ioc_fssetxattr( - xfs_inode_t *ip, struct file *filp, void __user *arg) { @@ -1562,7 +1560,7 @@ xfs_ioc_fssetxattr( error = mnt_want_write_file(filp); if (error) return error; - error = xfs_ioctl_setattr(ip, &fa); + error = xfs_ioctl_setattr(filp, &fa); mnt_drop_write_file(filp); return error; } @@ -1608,7 +1606,7 @@ xfs_ioc_setxflags( xfs_ioctl_setattr_prepare_dax(ip, &fa); - tp = xfs_ioctl_setattr_get_trans(ip); + tp = xfs_ioctl_setattr_get_trans(filp, NULL); if (IS_ERR(tp)) { error = PTR_ERR(tp); goto out_drop_write; @@ -2119,10 +2117,10 @@ xfs_file_ioctl( case XFS_IOC_FSBULKSTAT_SINGLE: case XFS_IOC_FSBULKSTAT: case XFS_IOC_FSINUMBERS: - return xfs_ioc_fsbulkstat(mp, cmd, arg); + return xfs_ioc_fsbulkstat(filp, cmd, arg); case XFS_IOC_BULKSTAT: - return xfs_ioc_bulkstat(mp, cmd, arg); + return xfs_ioc_bulkstat(filp, cmd, arg); case XFS_IOC_INUMBERS: return xfs_ioc_inumbers(mp, cmd, arg); @@ -2144,7 +2142,7 @@ xfs_file_ioctl( case XFS_IOC_FSGETXATTRA: return xfs_ioc_fsgetxattr(ip, 1, arg); case XFS_IOC_FSSETXATTR: - return xfs_ioc_fssetxattr(ip, filp, arg); + return xfs_ioc_fssetxattr(filp, arg); case XFS_IOC_GETXFLAGS: return xfs_ioc_getxflags(ip, arg); case XFS_IOC_SETXFLAGS: @@ -2260,7 +2258,7 @@ xfs_file_ioctl( } case XFS_IOC_FSGROWFSDATA: { - xfs_growfs_data_t in; + struct xfs_growfs_data in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; @@ -2274,7 +2272,7 @@ xfs_file_ioctl( } case XFS_IOC_FSGROWFSLOG: { - xfs_growfs_log_t in; + struct xfs_growfs_log in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; @@ -2348,8 +2346,10 @@ xfs_file_ioctl( if (error) return error; + trace_xfs_ioc_free_eofblocks(mp, &keofb, _RET_IP_); + sb_start_write(mp->m_super); - error = xfs_icache_free_eofblocks(mp, &keofb); + error = xfs_blockgc_free_space(mp, &keofb); sb_end_write(mp->m_super); return error; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index c1771e728117..33c09ec8e6c0 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -209,14 +209,16 @@ xfs_fsbulkstat_one_fmt_compat( /* copied from xfs_ioctl.c */ STATIC int xfs_compat_ioc_fsbulkstat( - xfs_mount_t *mp, + struct file *file, unsigned int cmd, struct compat_xfs_fsop_bulkreq __user *p32) { + struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount; u32 addr; struct xfs_fsop_bulkreq bulkreq; struct xfs_ibulk breq = { .mp = mp, + .mnt_userns = file_mnt_user_ns(file), .ocount = 0, }; xfs_ino_t lastino; @@ -436,7 +438,6 @@ xfs_file_compat_ioctl( { struct inode *inode = file_inode(filp); struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; void __user *arg = compat_ptr(p); int error; @@ -456,7 +457,7 @@ xfs_file_compat_ioctl( return xfs_ioc_space(filp, &bf); } case XFS_IOC_FSGEOMETRY_V1_32: - return xfs_compat_ioc_fsgeometry_v1(mp, arg); + return xfs_compat_ioc_fsgeometry_v1(ip->i_mount, arg); case XFS_IOC_FSGROWFSDATA_32: { struct xfs_growfs_data in; @@ -465,7 +466,7 @@ xfs_file_compat_ioctl( error = mnt_want_write_file(filp); if (error) return error; - error = xfs_growfs_data(mp, &in); + error = xfs_growfs_data(ip->i_mount, &in); mnt_drop_write_file(filp); return error; } @@ -477,7 +478,7 @@ xfs_file_compat_ioctl( error = mnt_want_write_file(filp); if (error) return error; - error = xfs_growfs_rt(mp, &in); + error = xfs_growfs_rt(ip->i_mount, &in); mnt_drop_write_file(filp); return error; } @@ -507,7 +508,7 @@ xfs_file_compat_ioctl( case XFS_IOC_FSBULKSTAT_32: case XFS_IOC_FSBULKSTAT_SINGLE_32: case XFS_IOC_FSINUMBERS_32: - return xfs_compat_ioc_fsbulkstat(mp, cmd, arg); + return xfs_compat_ioc_fsbulkstat(filp, cmd, arg); case XFS_IOC_FD_TO_HANDLE_32: case XFS_IOC_PATH_TO_HANDLE_32: case XFS_IOC_PATH_TO_FSHANDLE_32: { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 7b9ff824e82d..e17ab7f42928 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -194,25 +194,21 @@ xfs_iomap_write_direct( struct xfs_trans *tp; xfs_filblks_t resaligned; int nimaps; - int quota_flag; - uint qblocks, resblks; - unsigned int resrtextents = 0; + unsigned int dblocks, rblocks; + bool force = false; int error; int bmapi_flags = XFS_BMAPI_PREALLOC; - uint tflags = 0; ASSERT(count_fsb > 0); resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, xfs_get_extsz_hint(ip)); if (unlikely(XFS_IS_REALTIME_INODE(ip))) { - resrtextents = qblocks = resaligned; - resrtextents /= mp->m_sb.sb_rextsize; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); - quota_flag = XFS_QMOPT_RES_RTBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resaligned; } else { - resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); - quota_flag = XFS_QMOPT_RES_REGBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + rblocks = 0; } error = xfs_qm_dqattach(ip); @@ -235,23 +231,21 @@ xfs_iomap_write_direct( if (IS_DAX(VFS_I(ip))) { bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO; if (imap->br_state == XFS_EXT_UNWRITTEN) { - tflags |= XFS_TRANS_RESERVE; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1; + force = true; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1; } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, resrtextents, - tflags, &tp); + + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, + rblocks, force, &tp); if (error) return error; - xfs_ilock(ip, XFS_ILOCK_EXCL); - - error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); if (error) goto out_trans_cancel; - xfs_trans_ijoin(tp, ip, 0); - /* * From this point onwards we overwrite the imap pointer that the * caller gave to us. @@ -260,7 +254,7 @@ xfs_iomap_write_direct( error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flags, 0, imap, &nimaps); if (error) - goto out_res_cancel; + goto out_trans_cancel; /* * Complete the transaction @@ -284,8 +278,6 @@ out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; -out_res_cancel: - xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock; @@ -548,16 +540,13 @@ xfs_iomap_write_unwritten( * here as we might be asked to write out the same inode that we * complete here and might deadlock on the iolock. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, - XFS_TRANS_RESERVE, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, + 0, true, &tp); if (error) return error; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - - error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, - XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_WRITE_UNWRITTEN_CNT); if (error) goto error_on_bmapi_transaction; @@ -784,15 +773,28 @@ xfs_direct_write_iomap_begin( goto allocate_blocks; /* - * NOWAIT IO needs to span the entire requested IO with a single map so - * that we avoid partial IO failures due to the rest of the IO range not - * covered by this map triggering an EAGAIN condition when it is - * subsequently mapped and aborting the IO. + * NOWAIT and OVERWRITE I/O needs to span the entire requested I/O with + * a single map so that we avoid partial IO failures due to the rest of + * the I/O range not covered by this map triggering an EAGAIN condition + * when it is subsequently mapped and aborting the I/O. */ - if ((flags & IOMAP_NOWAIT) && - !imap_spans_range(&imap, offset_fsb, end_fsb)) { + if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) { error = -EAGAIN; - goto out_unlock; + if (!imap_spans_range(&imap, offset_fsb, end_fsb)) + goto out_unlock; + } + + /* + * For overwrite only I/O, we cannot convert unwritten extents without + * requiring sub-block zeroing. This can only be done under an + * exclusive IOLOCK, hence return -EAGAIN if this is not a written + * extent to tell the caller to try again. + */ + if (flags & IOMAP_OVERWRITE_ONLY) { + error = -EAGAIN; + if (imap.br_state != XFS_EXT_NORM && + ((offset | length) & mp->m_blockmask)) + goto out_unlock; } xfs_iunlock(ip, lockmode); @@ -801,7 +803,7 @@ xfs_direct_write_iomap_begin( allocate_blocks: error = -EAGAIN; - if (flags & IOMAP_NOWAIT) + if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) goto out_unlock; /* @@ -842,7 +844,8 @@ out_found_cow: return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED); out_unlock: - xfs_iunlock(ip, lockmode); + if (lockmode) + xfs_iunlock(ip, lockmode); return error; } @@ -870,6 +873,9 @@ xfs_buffered_write_iomap_begin( int allocfork = XFS_DATA_FORK; int error = 0; + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + /* 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, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 67c8dc9de8aa..66ebccb5a6ff 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -128,6 +128,7 @@ xfs_cleanup_inode( STATIC int xfs_generic_create( + struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode, @@ -161,9 +162,10 @@ xfs_generic_create( goto out_free_acl; if (!tmpfile) { - error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); + error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev, + &ip); } else { - error = xfs_create_tmpfile(XFS_I(dir), mode, &ip); + error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip); } if (unlikely(error)) goto out_free_acl; @@ -220,31 +222,35 @@ xfs_generic_create( STATIC int xfs_vn_mknod( - struct inode *dir, - struct dentry *dentry, - umode_t mode, - dev_t rdev) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode, + dev_t rdev) { - return xfs_generic_create(dir, dentry, mode, rdev, false); + return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, false); } STATIC int xfs_vn_create( - struct inode *dir, - struct dentry *dentry, - umode_t mode, - bool flags) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode, + bool flags) { - return xfs_generic_create(dir, dentry, mode, 0, false); + return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, false); } STATIC int xfs_vn_mkdir( - struct inode *dir, - struct dentry *dentry, - umode_t mode) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { - return xfs_generic_create(dir, dentry, mode | S_IFDIR, 0, false); + return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0, + false); } STATIC struct dentry * @@ -361,9 +367,10 @@ xfs_vn_unlink( STATIC int xfs_vn_symlink( - struct inode *dir, - struct dentry *dentry, - const char *symname) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + const char *symname) { struct inode *inode; struct xfs_inode *cip = NULL; @@ -377,7 +384,7 @@ xfs_vn_symlink( if (unlikely(error)) goto out; - error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip); + error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip); if (unlikely(error)) goto out; @@ -403,11 +410,12 @@ xfs_vn_symlink( STATIC int xfs_vn_rename( - struct inode *odir, - struct dentry *odentry, - struct inode *ndir, - struct dentry *ndentry, - unsigned int flags) + struct user_namespace *mnt_userns, + struct inode *odir, + struct dentry *odentry, + struct inode *ndir, + struct dentry *ndentry, + unsigned int flags) { struct inode *new_inode = d_inode(ndentry); int omode = 0; @@ -431,8 +439,8 @@ xfs_vn_rename( if (unlikely(error)) return error; - return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)), - XFS_I(ndir), &nname, + return xfs_rename(mnt_userns, XFS_I(odir), &oname, + XFS_I(d_inode(odentry)), XFS_I(ndir), &nname, new_inode ? XFS_I(new_inode) : NULL, flags); } @@ -529,6 +537,7 @@ xfs_stat_blksize( STATIC int xfs_vn_getattr( + struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, @@ -547,8 +556,8 @@ xfs_vn_getattr( stat->dev = inode->i_sb->s_dev; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; - stat->uid = inode->i_uid; - stat->gid = inode->i_gid; + stat->uid = i_uid_into_mnt(mnt_userns, inode); + stat->gid = i_gid_into_mnt(mnt_userns, inode); stat->ino = ip->i_ino; stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; @@ -626,8 +635,9 @@ xfs_setattr_time( static int xfs_vn_change_ok( - struct dentry *dentry, - struct iattr *iattr) + struct user_namespace *mnt_userns, + struct dentry *dentry, + struct iattr *iattr) { struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount; @@ -637,7 +647,7 @@ xfs_vn_change_ok( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - return setattr_prepare(dentry, iattr); + return setattr_prepare(mnt_userns, dentry, iattr); } /* @@ -648,6 +658,7 @@ xfs_vn_change_ok( */ static int xfs_setattr_nonsize( + struct user_namespace *mnt_userns, struct xfs_inode *ip, struct iattr *iattr) { @@ -700,13 +711,11 @@ xfs_setattr_nonsize( return error; } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, + capable(CAP_FOWNER), &tp); if (error) goto out_dqrele; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - /* * Change file ownership. Must be the owner or privileged. */ @@ -723,21 +732,6 @@ xfs_setattr_nonsize( uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid; /* - * Do a quota reservation only if uid/gid is actually - * going to change. - */ - if (XFS_IS_QUOTA_RUNNING(mp) && - ((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) || - (XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) { - ASSERT(tp); - error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, - NULL, capable(CAP_FOWNER) ? - XFS_QMOPT_FORCE_RES : 0); - if (error) /* out of quota */ - goto out_cancel; - } - - /* * CAP_FSETID overrides the following restrictions: * * The set-user-ID and set-group-ID bits of a file will be @@ -786,8 +780,6 @@ xfs_setattr_nonsize( xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - /* * Release any dquot(s) the inode had kept before chown. */ @@ -807,16 +799,13 @@ xfs_setattr_nonsize( * Posix ACL code seems to care about this issue either. */ if (mask & ATTR_MODE) { - error = posix_acl_chmod(inode, inode->i_mode); + error = posix_acl_chmod(mnt_userns, inode, inode->i_mode); if (error) return error; } return 0; -out_cancel: - xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); out_dqrele: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); @@ -831,6 +820,7 @@ out_dqrele: */ STATIC int xfs_setattr_size( + struct user_namespace *mnt_userns, struct xfs_inode *ip, struct iattr *iattr) { @@ -846,7 +836,7 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(inode->i_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ATTR_MTIME_SET|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; @@ -862,7 +852,7 @@ xfs_setattr_size( * Use the regular setattr path to update the timestamps. */ iattr->ia_valid &= ~ATTR_SIZE; - return xfs_setattr_nonsize(ip, iattr); + return xfs_setattr_nonsize(mnt_userns, ip, iattr); } /* @@ -1031,6 +1021,7 @@ out_trans_cancel: int xfs_vn_setattr_size( + struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *iattr) { @@ -1039,14 +1030,15 @@ xfs_vn_setattr_size( trace_xfs_setattr(ip); - error = xfs_vn_change_ok(dentry, iattr); + error = xfs_vn_change_ok(mnt_userns, dentry, iattr); if (error) return error; - return xfs_setattr_size(ip, iattr); + return xfs_setattr_size(mnt_userns, ip, iattr); } STATIC int xfs_vn_setattr( + struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *iattr) { @@ -1066,14 +1058,14 @@ xfs_vn_setattr( return error; } - error = xfs_vn_setattr_size(dentry, iattr); + error = xfs_vn_setattr_size(mnt_userns, dentry, iattr); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); } else { trace_xfs_setattr(ip); - error = xfs_vn_change_ok(dentry, iattr); + error = xfs_vn_change_ok(mnt_userns, dentry, iattr); if (!error) - error = xfs_setattr_nonsize(ip, iattr); + error = xfs_setattr_nonsize(mnt_userns, ip, iattr); } return error; @@ -1144,11 +1136,12 @@ xfs_vn_fiemap( STATIC int xfs_vn_tmpfile( - struct inode *dir, - struct dentry *dentry, - umode_t mode) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { - return xfs_generic_create(dir, dentry, mode, 0, true); + return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, true); } static const struct inode_operations xfs_inode_operations = { diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index 99ca745c1071..278949056048 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -14,6 +14,7 @@ extern const struct file_operations xfs_dir_file_operations; extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); -extern int xfs_vn_setattr_size(struct dentry *dentry, struct iattr *vap); +int xfs_vn_setattr_size(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *vap); #endif /* __XFS_IOPS_H__ */ diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 16ca97a7ff00..ca310a125d1e 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -54,10 +54,12 @@ struct xfs_bstat_chunk { STATIC int xfs_bulkstat_one_int( struct xfs_mount *mp, + struct user_namespace *mnt_userns, struct xfs_trans *tp, xfs_ino_t ino, struct xfs_bstat_chunk *bc) { + struct user_namespace *sb_userns = mp->m_super->s_user_ns; struct xfs_icdinode *dic; /* dinode core info pointer */ struct xfs_inode *ip; /* incore inode pointer */ struct inode *inode; @@ -86,8 +88,8 @@ xfs_bulkstat_one_int( */ buf->bs_projectid = ip->i_d.di_projid; buf->bs_ino = ino; - buf->bs_uid = i_uid_read(inode); - buf->bs_gid = i_gid_read(inode); + buf->bs_uid = from_kuid(sb_userns, i_uid_into_mnt(mnt_userns, inode)); + buf->bs_gid = from_kgid(sb_userns, i_gid_into_mnt(mnt_userns, inode)); buf->bs_size = dic->di_size; buf->bs_nlink = inode->i_nlink; @@ -173,7 +175,8 @@ xfs_bulkstat_one( if (!bc.buf) return -ENOMEM; - error = xfs_bulkstat_one_int(breq->mp, NULL, breq->startino, &bc); + error = xfs_bulkstat_one_int(breq->mp, breq->mnt_userns, NULL, + breq->startino, &bc); kmem_free(bc.buf); @@ -194,9 +197,10 @@ xfs_bulkstat_iwalk( xfs_ino_t ino, void *data) { + struct xfs_bstat_chunk *bc = data; int error; - error = xfs_bulkstat_one_int(mp, tp, ino, data); + error = xfs_bulkstat_one_int(mp, bc->breq->mnt_userns, tp, ino, data); /* bulkstat just skips over missing inodes */ if (error == -ENOENT || error == -EINVAL) return 0; @@ -239,6 +243,11 @@ xfs_bulkstat( }; int error; + if (breq->mnt_userns != &init_user_ns) { + xfs_warn_ratelimited(breq->mp, + "bulkstat not supported inside of idmapped mounts."); + return -EINVAL; + } if (xfs_bulkstat_already_done(breq->mp, breq->startino)) return 0; diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index 96a1e2a9be3f..7078d10c9b12 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -8,6 +8,7 @@ /* In-memory representation of a userspace request for batch inode data. */ struct xfs_ibulk { struct xfs_mount *mp; + struct user_namespace *mnt_userns; void __user *ubuffer; /* user output buffer */ xfs_ino_t startino; /* start with this inode */ unsigned int icount; /* number of elements in ubuffer */ diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index eae3aff9bc97..c4a340f1f1e1 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -618,15 +618,12 @@ xfs_iwalk_threaded( { struct xfs_pwork_ctl pctl; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); - unsigned int nr_threads; int error; ASSERT(agno < mp->m_sb.sb_agcount); ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL)); - nr_threads = xfs_pwork_guess_datadev_parallelism(mp); - error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk", - nr_threads); + error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk"); if (error) return error; diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 5b7a1e201559..af6be9b9ccdf 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -98,8 +98,7 @@ typedef __u32 xfs_nlink_t; #define xfs_rotorstep xfs_params.rotorstep.val #define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val #define xfs_fstrm_centisecs xfs_params.fstrm_timer.val -#define xfs_eofb_secs xfs_params.eofb_timer.val -#define xfs_cowb_secs xfs_params.cowb_timer.val +#define xfs_blockgc_secs xfs_params.blockgc_timer.val #define current_cpu() (raw_smp_processor_id()) #define current_set_flags_nested(sp, f) \ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index fa2d05e65ff1..06041834daa3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -91,6 +91,9 @@ STATIC int xlog_iclogs_empty( struct xlog *log); +static int +xfs_log_cover(struct xfs_mount *); + static void xlog_grant_sub_space( struct xlog *log, @@ -347,6 +350,25 @@ xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type) tic->t_res_num++; } +bool +xfs_log_writable( + struct xfs_mount *mp) +{ + /* + * Never write to the log on norecovery mounts, if the block device is + * read-only, or if the filesystem is shutdown. Read-only mounts still + * allow internal writes for log recovery and unmount purposes, so don't + * restrict that case here. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return false; + if (xfs_readonly_buftarg(mp->m_log->l_targ)) + return false; + if (XFS_FORCED_SHUTDOWN(mp)) + return false; + return true; +} + /* * Replenish the byte reservation required by moving the grant write head. */ @@ -741,7 +763,7 @@ xfs_log_mount_finish( xfs_log_force(mp, XFS_LOG_SYNC); xfs_ail_push_all_sync(mp->m_ail); } - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_drain(mp->m_ddev_targp); if (readonly) mp->m_flags |= XFS_MOUNT_RDONLY; @@ -886,15 +908,8 @@ xfs_log_unmount_write( { struct xlog *log = mp->m_log; - /* - * Don't write out unmount record on norecovery mounts or ro devices. - * Or, if we are doing a forced umount (typically because of IO errors). - */ - if (mp->m_flags & XFS_MOUNT_NORECOVERY || - xfs_readonly_buftarg(log->l_targ)) { - ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); + if (!xfs_log_writable(mp)) return; - } xfs_log_force(mp, XFS_LOG_SYNC); @@ -924,10 +939,9 @@ xfs_log_unmount_write( * To do this, we first need to shut down the background log work so it is not * trying to cover the log as we clean up. We then need to unpin all objects in * the log so we can then flush them out. Once they have completed their IO and - * run the callbacks removing themselves from the AIL, we can write the unmount - * record. + * run the callbacks removing themselves from the AIL, we can cover the log. */ -void +int xfs_log_quiesce( struct xfs_mount *mp) { @@ -936,16 +950,24 @@ xfs_log_quiesce( /* * The superblock buffer is uncached and while xfs_ail_push_all_sync() - * will push it, xfs_wait_buftarg() will not wait for it. Further, + * will push it, xfs_buftarg_wait() will not wait for it. Further, * xfs_buf_iowait() cannot be used because it was pushed with the * XBF_ASYNC flag set, so we need to use a lock/unlock pair to wait for * the IO to complete. */ xfs_ail_push_all_sync(mp->m_ail); - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_wait(mp->m_ddev_targp); xfs_buf_lock(mp->m_sb_bp); xfs_buf_unlock(mp->m_sb_bp); + return xfs_log_cover(mp); +} + +void +xfs_log_clean( + struct xfs_mount *mp) +{ + xfs_log_quiesce(mp); xfs_log_unmount_write(mp); } @@ -960,7 +982,9 @@ void xfs_log_unmount( struct xfs_mount *mp) { - xfs_log_quiesce(mp); + xfs_log_clean(mp); + + xfs_buftarg_drain(mp->m_ddev_targp); xfs_trans_ail_destroy(mp); @@ -1037,17 +1061,15 @@ xfs_log_space_wake( * there's no point in running a dummy transaction at this point because we * can't start trying to idle the log until both the CIL and AIL are empty. */ -static int -xfs_log_need_covered(xfs_mount_t *mp) +static bool +xfs_log_need_covered( + struct xfs_mount *mp) { - struct xlog *log = mp->m_log; - int needed = 0; - - if (!xfs_fs_writable(mp, SB_FREEZE_WRITE)) - return 0; + struct xlog *log = mp->m_log; + bool needed = false; if (!xlog_cil_empty(log)) - return 0; + return false; spin_lock(&log->l_icloglock); switch (log->l_covered_state) { @@ -1062,14 +1084,14 @@ xfs_log_need_covered(xfs_mount_t *mp) if (!xlog_iclogs_empty(log)) break; - needed = 1; + needed = true; if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; else log->l_covered_state = XLOG_STATE_COVER_DONE2; break; default: - needed = 1; + needed = true; break; } spin_unlock(&log->l_icloglock); @@ -1077,6 +1099,60 @@ xfs_log_need_covered(xfs_mount_t *mp) } /* + * Explicitly cover the log. This is similar to background log covering but + * intended for usage in quiesce codepaths. The caller is responsible to ensure + * the log is idle and suitable for covering. The CIL, iclog buffers and AIL + * must all be empty. + */ +static int +xfs_log_cover( + struct xfs_mount *mp) +{ + int error = 0; + bool need_covered; + + ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && + !xfs_ail_min_lsn(mp->m_log->l_ailp)) || + XFS_FORCED_SHUTDOWN(mp)); + + if (!xfs_log_writable(mp)) + return 0; + + /* + * xfs_log_need_covered() is not idempotent because it progresses the + * state machine if the log requires covering. Therefore, we must call + * this function once and use the result until we've issued an sb sync. + * Do so first to make that abundantly clear. + * + * Fall into the covering sequence if the log needs covering or the + * mount has lazy superblock accounting to sync to disk. The sb sync + * used for covering accumulates the in-core counters, so covering + * handles this for us. + */ + need_covered = xfs_log_need_covered(mp); + if (!need_covered && !xfs_sb_version_haslazysbcount(&mp->m_sb)) + return 0; + + /* + * To cover the log, commit the superblock twice (at most) in + * independent checkpoints. The first serves as a reference for the + * tail pointer. The sync transaction and AIL push empties the AIL and + * updates the in-core tail to the LSN of the first checkpoint. The + * second commit updates the on-disk tail with the in-core LSN, + * covering the log. Push the AIL one more time to leave it empty, as + * we found it. + */ + do { + error = xfs_sync_sb(mp, true); + if (error) + break; + xfs_ail_push_all_sync(mp->m_ail); + } while (xfs_log_need_covered(mp)); + + return error; +} + +/* * We may be holding the log iclog lock upon entering this routine. */ xfs_lsn_t @@ -1259,7 +1335,7 @@ xfs_log_worker( struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ - if (xfs_log_need_covered(mp)) { + if (xfs_fs_writable(mp, SB_FREEZE_WRITE) && xfs_log_need_covered(mp)) { /* * Dump a transaction into the log that contains no real change. * This is needed to stamp the current tail LSN into the log @@ -1416,8 +1492,9 @@ xlog_alloc_log( log->l_iclog->ic_prev = prev_iclog; /* re-write 1st prev ptr */ log->l_ioend_workqueue = alloc_workqueue("xfs-log/%s", - WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_HIGHPRI, 0, - mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | + WQ_HIGHPRI), + 0, mp->m_super->s_id); if (!log->l_ioend_workqueue) goto out_free_iclog; @@ -2538,12 +2615,15 @@ xlog_covered_state( int iclogs_changed) { /* - * We usually go to NEED. But we go to NEED2 if the changed indicates we - * are done writing the dummy record. If we are done with the second - * dummy recored (DONE2), then we go to IDLE. + * We go to NEED for any non-covering writes. We go to NEED2 if we just + * wrote the first covering record (DONE). We go to IDLE if we just + * wrote the second covering record (DONE2) and remain in IDLE until a + * non-covering write occurs. */ switch (prev_state) { case XLOG_STATE_COVER_IDLE: + if (iclogs_changed == 1) + return XLOG_STATE_COVER_IDLE; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: break; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 58c3fcbec94a..044e02cb8921 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -127,6 +127,7 @@ int xfs_log_reserve(struct xfs_mount *mp, int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic); void xfs_log_unmount(struct xfs_mount *mp); int xfs_log_force_umount(struct xfs_mount *mp, int logerror); +bool xfs_log_writable(struct xfs_mount *mp); struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket); void xfs_log_ticket_put(struct xlog_ticket *ticket); @@ -137,7 +138,8 @@ void xlog_cil_process_committed(struct list_head *list); bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); void xfs_log_work_queue(struct xfs_mount *mp); -void xfs_log_quiesce(struct xfs_mount *mp); +int xfs_log_quiesce(struct xfs_mount *mp); +void xfs_log_clean(struct xfs_mount *mp); bool xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t); bool xfs_log_in_recovery(struct xfs_mount *); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 7110507a2b6b..52370d0a3f43 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -126,6 +126,7 @@ __xfs_free_perag( { struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); + ASSERT(!delayed_work_pending(&pag->pag_blockgc_work)); ASSERT(atomic_read(&pag->pag_ref) == 0); kmem_free(pag); } @@ -146,6 +147,7 @@ xfs_free_perag( spin_unlock(&mp->m_perag_lock); ASSERT(pag); ASSERT(atomic_read(&pag->pag_ref) == 0); + cancel_delayed_work_sync(&pag->pag_blockgc_work); xfs_iunlink_destroy(pag); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); @@ -201,6 +203,7 @@ xfs_initialize_perag( pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); + INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); error = xfs_buf_hash_init(pag); @@ -946,7 +949,7 @@ xfs_mountfs( */ if ((mp->m_flags & (XFS_MOUNT_RDONLY|XFS_MOUNT_NORECOVERY)) == XFS_MOUNT_RDONLY) { - xfs_quiesce_attr(mp); + xfs_log_clean(mp); } /* @@ -1023,8 +1026,8 @@ xfs_mountfs( xfs_log_mount_cancel(mp); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) - xfs_wait_buftarg(mp->m_logdev_targp); - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_drain(mp->m_logdev_targp); + xfs_buftarg_drain(mp->m_ddev_targp); out_free_perag: xfs_free_perag(mp); out_free_dir: @@ -1054,7 +1057,7 @@ xfs_unmountfs( uint64_t resblks; int error; - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); xfs_rtunmount_inodes(mp); @@ -1124,12 +1127,6 @@ xfs_unmountfs( xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); - error = xfs_log_sbcount(mp); - if (error) - xfs_warn(mp, "Unable to update superblock counters. " - "Freespace may not be correct on next mount."); - - xfs_log_unmount(mp); xfs_da_unmount(mp); xfs_uuid_unmount(mp); @@ -1165,32 +1162,6 @@ xfs_fs_writable( } /* - * xfs_log_sbcount - * - * Sync the superblock counters to disk. - * - * Note this code can be called during the process of freezing, so we use the - * transaction allocator that does not block when the transaction subsystem is - * in its frozen state. - */ -int -xfs_log_sbcount(xfs_mount_t *mp) -{ - /* allow this to proceed during the freeze sequence... */ - if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) - return 0; - - /* - * we don't need to do this if we are updating the superblock - * counters on every modification. - */ - if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) - return 0; - - return xfs_sync_sb(mp, true); -} - -/* * Deltas for the block count can vary from 1 to very large, but lock contention * only occurs on frequent small block count updates such as in the delayed * allocation path for buffered writes (page a time updates). Hence we set diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index dfa429b77ee2..659ad95fe3e0 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -93,7 +93,7 @@ typedef struct xfs_mount { struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_cil_workqueue; struct workqueue_struct *m_reclaim_workqueue; - struct workqueue_struct *m_eofblocks_workqueue; + struct workqueue_struct *m_blockgc_workqueue; struct workqueue_struct *m_sync_workqueue; int m_bsize; /* fs logical block size */ @@ -177,10 +177,6 @@ typedef struct xfs_mount { 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 delayed_work m_eofblocks_work; /* background eof blocks - trimming */ - struct delayed_work m_cowblocks_work; /* background cow blocks - trimming */ struct xfs_kobj m_kobj; struct xfs_kobj m_error_kobj; struct xfs_kobj m_error_meta_kobj; @@ -369,6 +365,9 @@ typedef struct xfs_perag { /* Blocks reserved for the reverse mapping btree. */ struct xfs_ag_resv pag_rmapbt_resv; + /* background prealloc block trimming */ + struct delayed_work pag_blockgc_work; + /* reference count */ uint8_t pagf_refcount_level; @@ -399,7 +398,6 @@ int xfs_buf_hash_init(xfs_perag_t *pag); void xfs_buf_hash_destroy(xfs_perag_t *pag); extern void xfs_uuid_table_free(void); -extern int xfs_log_sbcount(xfs_mount_t *); extern uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern int xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount, diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index a06661dac5be..34c3b16f834f 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -294,7 +294,7 @@ int xfs_mru_cache_init(void) { xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 1); + XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 1); if (!xfs_mru_reap_wq) return -ENOMEM; return 0; diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c index b03333f1c84a..c283b801cc5d 100644 --- a/fs/xfs/xfs_pwork.c +++ b/fs/xfs/xfs_pwork.c @@ -61,16 +61,18 @@ xfs_pwork_init( struct xfs_mount *mp, struct xfs_pwork_ctl *pctl, xfs_pwork_work_fn work_fn, - const char *tag, - unsigned int nr_threads) + const char *tag) { + unsigned int nr_threads = 0; + #ifdef DEBUG if (xfs_globals.pwork_threads >= 0) nr_threads = xfs_globals.pwork_threads; #endif trace_xfs_pwork_init(mp, nr_threads, current->pid); - pctl->wq = alloc_workqueue("%s-%d", WQ_FREEZABLE, nr_threads, tag, + pctl->wq = alloc_workqueue("%s-%d", + WQ_UNBOUND | WQ_SYSFS | WQ_FREEZABLE, nr_threads, tag, current->pid); if (!pctl->wq) return -ENOMEM; @@ -117,20 +119,3 @@ xfs_pwork_poll( atomic_read(&pctl->nr_work) == 0, HZ) == 0) touch_softlockup_watchdog(); } - -/* - * Return the amount of parallelism that the data device can handle, or 0 for - * no limit. - */ -unsigned int -xfs_pwork_guess_datadev_parallelism( - struct xfs_mount *mp) -{ - struct xfs_buftarg *btp = mp->m_ddev_targp; - - /* - * For now we'll go with the most conservative setting possible, - * which is two threads for an SSD and 1 thread everywhere else. - */ - return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1; -} diff --git a/fs/xfs/xfs_pwork.h b/fs/xfs/xfs_pwork.h index 8133124cf3bb..c0ef81fc85dd 100644 --- a/fs/xfs/xfs_pwork.h +++ b/fs/xfs/xfs_pwork.h @@ -51,11 +51,9 @@ xfs_pwork_want_abort( } int xfs_pwork_init(struct xfs_mount *mp, struct xfs_pwork_ctl *pctl, - xfs_pwork_work_fn work_fn, const char *tag, - unsigned int nr_threads); + xfs_pwork_work_fn work_fn, const char *tag); void xfs_pwork_queue(struct xfs_pwork_ctl *pctl, struct xfs_pwork *pwork); int xfs_pwork_destroy(struct xfs_pwork_ctl *pctl); void xfs_pwork_poll(struct xfs_pwork_ctl *pctl); -unsigned int xfs_pwork_guess_datadev_parallelism(struct xfs_mount *mp); #endif /* __XFS_PWORK_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index c134eb4aeaa8..bfa4164990b1 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -787,7 +787,8 @@ xfs_qm_qino_alloc( return error; if (need_alloc) { - error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ipp); + error = xfs_dir_ialloc(&init_user_ns, &tp, NULL, S_IFREG, 1, 0, + 0, ipp); if (error) { xfs_trans_cancel(tp); return error; @@ -1786,105 +1787,35 @@ xfs_qm_vop_chown( xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1); /* - * Take an extra reference, because the inode is going to keep - * this dquot pointer even after the trans_commit. + * Back when we made quota reservations for the chown, we reserved the + * ondisk blocks + delalloc blocks with the new dquot. Now that we've + * switched the dquots, decrease the new dquot's block reservation + * (having already bumped up the real counter) so that we don't have + * any reservation to give back when we commit. */ - *IO_olddq = xfs_qm_dqhold(newdq); + xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_RES_BLKS, + -ip->i_delayed_blks); - return prevdq; -} - -/* - * Quota reservations for setattr(AT_UID|AT_GID|AT_PROJID). - */ -int -xfs_qm_vop_chown_reserve( - struct xfs_trans *tp, - struct xfs_inode *ip, - struct xfs_dquot *udqp, - struct xfs_dquot *gdqp, - struct xfs_dquot *pdqp, - uint flags) -{ - struct xfs_mount *mp = ip->i_mount; - uint64_t delblks; - unsigned int blkflags; - struct xfs_dquot *udq_unres = NULL; - struct xfs_dquot *gdq_unres = NULL; - struct xfs_dquot *pdq_unres = NULL; - struct xfs_dquot *udq_delblks = NULL; - struct xfs_dquot *gdq_delblks = NULL; - struct xfs_dquot *pdq_delblks = NULL; - int error; - - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(XFS_IS_QUOTA_RUNNING(mp)); - - delblks = ip->i_delayed_blks; - blkflags = XFS_IS_REALTIME_INODE(ip) ? - XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS; - - if (XFS_IS_UQUOTA_ON(mp) && udqp && - i_uid_read(VFS_I(ip)) != udqp->q_id) { - udq_delblks = udqp; - /* - * If there are delayed allocation blocks, then we have to - * unreserve those from the old dquot, and add them to the - * new dquot. - */ - if (delblks) { - ASSERT(ip->i_udquot); - udq_unres = ip->i_udquot; - } - } - if (XFS_IS_GQUOTA_ON(ip->i_mount) && gdqp && - i_gid_read(VFS_I(ip)) != gdqp->q_id) { - gdq_delblks = gdqp; - if (delblks) { - ASSERT(ip->i_gdquot); - gdq_unres = ip->i_gdquot; - } - } - - if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp && - ip->i_d.di_projid != pdqp->q_id) { - pdq_delblks = pdqp; - if (delblks) { - ASSERT(ip->i_pdquot); - pdq_unres = ip->i_pdquot; - } - } - - error = xfs_trans_reserve_quota_bydquots(tp, ip->i_mount, - udq_delblks, gdq_delblks, pdq_delblks, - ip->i_d.di_nblocks, 1, flags | blkflags); - if (error) - return error; + /* + * Give the incore reservation for delalloc blocks back to the old + * dquot. We don't normally handle delalloc quota reservations + * transactionally, so just lock the dquot and subtract from the + * reservation. Dirty the transaction because it's too late to turn + * back now. + */ + tp->t_flags |= XFS_TRANS_DIRTY; + xfs_dqlock(prevdq); + ASSERT(prevdq->q_blk.reserved >= ip->i_delayed_blks); + prevdq->q_blk.reserved -= ip->i_delayed_blks; + xfs_dqunlock(prevdq); /* - * Do the delayed blks reservations/unreservations now. Since, these - * are done without the help of a transaction, if a reservation fails - * its previous reservations won't be automatically undone by trans - * code. So, we have to do it manually here. + * Take an extra reference, because the inode is going to keep + * this dquot pointer even after the trans_commit. */ - if (delblks) { - /* - * Do the reservations first. Unreservation can't fail. - */ - ASSERT(udq_delblks || gdq_delblks || pdq_delblks); - ASSERT(udq_unres || gdq_unres || pdq_unres); - error = xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_delblks, gdq_delblks, pdq_delblks, - (xfs_qcnt_t)delblks, 0, flags | blkflags); - if (error) - return error; - xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_unres, gdq_unres, pdq_unres, - -((xfs_qcnt_t)delblks), 0, blkflags); - } + *IO_olddq = xfs_qm_dqhold(newdq); - return 0; + return prevdq; } int diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index 5a62398940d0..d00d01302545 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -81,11 +81,14 @@ extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); -extern int xfs_trans_reserve_quota_nblks(struct xfs_trans *, - struct xfs_inode *, int64_t, long, uint); +int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, + int64_t dblocks, int64_t rblocks, bool force); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint); +int xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, + struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, int64_t dblocks); extern int xfs_qm_vop_dqalloc(struct xfs_inode *, kuid_t, kgid_t, prid_t, uint, struct xfs_dquot **, struct xfs_dquot **, @@ -95,9 +98,6 @@ extern void xfs_qm_vop_create_dqattach(struct xfs_trans *, struct xfs_inode *, extern int xfs_qm_vop_rename_dqattach(struct xfs_inode **); extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *, struct xfs_inode *, struct xfs_dquot **, struct xfs_dquot *); -extern int xfs_qm_vop_chown_reserve(struct xfs_trans *, struct xfs_inode *, - struct xfs_dquot *, struct xfs_dquot *, - struct xfs_dquot *, uint); extern int xfs_qm_dqattach(struct xfs_inode *); extern int xfs_qm_dqattach_locked(struct xfs_inode *ip, bool doalloc); extern void xfs_qm_dqdetach(struct xfs_inode *); @@ -108,6 +108,11 @@ extern void xfs_qm_mount_quotas(struct xfs_mount *); extern void xfs_qm_unmount(struct xfs_mount *); extern void xfs_qm_unmount_quotas(struct xfs_mount *); +static inline int +xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return xfs_trans_reserve_quota_nblks(NULL, ip, blocks, 0, false); +} #else static inline int xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid, @@ -121,11 +126,12 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid, } #define xfs_trans_dup_dqinfo(tp, tp2) #define xfs_trans_free_dqinfo(tp) -#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) +#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) do { } while (0) #define xfs_trans_apply_dquot_deltas(tp) #define xfs_trans_unreserve_and_mod_dquots(tp) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, - struct xfs_inode *ip, int64_t nblks, long ninos, uint flags) + struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, + bool force) { return 0; } @@ -136,26 +142,39 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, { return 0; } + +static inline int +xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return 0; +} + +static inline int +xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, int64_t dblocks) +{ + return 0; +} + #define xfs_qm_vop_create_dqattach(tp, ip, u, g, p) #define xfs_qm_vop_rename_dqattach(it) (0) #define xfs_qm_vop_chown(tp, ip, old, new) (NULL) -#define xfs_qm_vop_chown_reserve(tp, ip, u, g, p, fl) (0) #define xfs_qm_dqattach(ip) (0) #define xfs_qm_dqattach_locked(ip, fl) (0) #define xfs_qm_dqdetach(ip) -#define xfs_qm_dqrele(d) -#define xfs_qm_statvfs(ip, s) +#define xfs_qm_dqrele(d) do { (d) = (d); } while(0) +#define xfs_qm_statvfs(ip, s) do { } while(0) #define xfs_qm_newmount(mp, a, b) (0) #define xfs_qm_mount_quotas(mp) #define xfs_qm_unmount(mp) #define xfs_qm_unmount_quotas(mp) #endif /* CONFIG_XFS_QUOTA */ -#define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \ - xfs_trans_reserve_quota_nblks(tp, ip, -(nblks), -(ninos), flags) -#define xfs_trans_reserve_quota(tp, mp, ud, gd, pd, nb, ni, f) \ - xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, pd, nb, ni, \ - f | XFS_QMOPT_RES_REGBLKS) +static inline int +xfs_quota_unreserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return xfs_quota_reserve_blkres(ip, -blocks); +} extern int xfs_mount_reset_sbqflags(struct xfs_mount *); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6fa05fb78189..725c7d8e4438 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -376,16 +376,14 @@ xfs_reflink_allocate_cow( resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); xfs_iunlock(ip, *lockmode); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); - *lockmode = XFS_ILOCK_EXCL; - xfs_ilock(ip, *lockmode); + *lockmode = 0; + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, + false, &tp); if (error) return error; - error = xfs_qm_dqattach_locked(ip, false); - if (error) - goto out_trans_cancel; + *lockmode = XFS_ILOCK_EXCL; /* * Check for an overlapping extent again now that we dropped the ilock. @@ -398,20 +396,13 @@ xfs_reflink_allocate_cow( goto convert; } - error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, - XFS_QMOPT_RES_REGBLKS); - if (error) - goto out_trans_cancel; - - xfs_trans_ijoin(tp, ip, 0); - /* Allocate the entire reservation as unwritten blocks. */ nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, 0, cmap, &nimaps); if (error) - goto out_unreserve; + goto out_trans_cancel; xfs_inode_set_cowblocks_tag(ip); error = xfs_trans_commit(tp); @@ -436,9 +427,6 @@ convert: trace_xfs_reflink_convert_cow(ip, cmap); return xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb); -out_unreserve: - xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0, - XFS_QMOPT_RES_REGBLKS); out_trans_cancel: xfs_trans_cancel(tp); return error; @@ -508,9 +496,8 @@ xfs_reflink_cancel_cow_blocks( xfs_bmap_del_extent_cow(ip, &icur, &got, &del); /* Remove the quota reservation */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, - -(long)del.br_blockcount, 0, - XFS_QMOPT_RES_REGBLKS); + error = xfs_quota_unreserve_blkres(ip, + del.br_blockcount); if (error) break; } else { @@ -628,6 +615,11 @@ xfs_reflink_end_cow_extent( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_REFLINK_END_COW_CNT); + if (error) + goto out_cancel; + /* * In case of racing, overlapping AIO writes no COW extents might be * left by the time I/O completes for the loser of the race. In that @@ -997,22 +989,47 @@ xfs_reflink_remap_extent( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_off_t newlen; - int64_t qres, qdelta; + int64_t qdelta = 0; unsigned int resblks; + bool quota_reserved = true; bool smap_real; bool dmap_written = xfs_bmap_is_written_extent(dmap); + int iext_delta = 0; int nimaps; int error; - /* Start a rolling transaction to switch the mappings */ + /* + * Start a rolling transaction to switch the mappings. + * + * Adding a written extent to the extent map can cause a bmbt split, + * and removing a mapped extent from the extent can cause a bmbt split. + * The two operations cannot both cause a split since they operate on + * the same index in the bmap btree, so we only need a reservation for + * one bmbt split if either thing is happening. However, we haven't + * locked the inode yet, so we reserve assuming this is the case. + * + * The first allocation call tries to reserve enough space to handle + * mapping dmap into a sparse part of the file plus the bmbt split. We + * haven't locked the inode or read the existing mapping yet, so we do + * not know for sure that we need the space. This should succeed most + * of the time. + * + * If the first attempt fails, try again but reserving only enough + * space to handle a bmbt split. This is the hard minimum requirement, + * and we revisit quota reservations later when we know more about what + * we're remapping. + */ resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + resblks + dmap->br_blockcount, 0, false, &tp); + if (error == -EDQUOT || error == -ENOSPC) { + quota_reserved = false; + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + resblks, 0, false, &tp); + } if (error) goto out; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - /* * Read what's currently mapped in the destination file into smap. * If smap isn't a hole, we will have to remove it before we can add @@ -1060,15 +1077,9 @@ xfs_reflink_remap_extent( } /* - * Compute quota reservation if we think the quota block counter for + * Increase quota reservation if we think the quota block counter for * this file could increase. * - * Adding a written extent to the extent map can cause a bmbt split, - * and removing a mapped extent from the extent can cause a bmbt split. - * The two operations cannot both cause a split since they operate on - * the same index in the bmap btree, so we only need a reservation for - * one bmbt split if either thing is happening. - * * If we are mapping a written extent into the file, we need to have * enough quota block count reservation to handle the blocks in that * extent. We log only the delta to the quota block counts, so if the @@ -1081,19 +1092,29 @@ xfs_reflink_remap_extent( * count. This is suboptimal, but the VFS flushed the dest range * before we started. That should have removed all the delalloc * reservations, but we code defensively. + * + * xfs_trans_alloc_inode above already tried to grab an even larger + * quota reservation, and kicked off a blockgc scan if it couldn't. + * If we can't get a potentially smaller quota reservation now, we're + * done. */ - qres = qdelta = 0; - if (smap_real || dmap_written) - qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - if (!smap_real && dmap_written) - qres += dmap->br_blockcount; - if (qres > 0) { - error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0, - XFS_QMOPT_RES_REGBLKS); + if (!quota_reserved && !smap_real && dmap_written) { + error = xfs_trans_reserve_quota_nblks(tp, ip, + dmap->br_blockcount, 0, false); if (error) goto out_cancel; } + if (smap_real) + ++iext_delta; + + if (dmap_written) + ++iext_delta; + + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, iext_delta); + if (error) + goto out_cancel; + if (smap_real) { /* * If the extent we're unmapping is backed by storage (written diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index b4999fb01ff7..161b0e8992ba 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -804,6 +804,11 @@ xfs_growfs_rt_alloc( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + /* * Allocate blocks to the bitmap file. */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 813be879a5e5..e5e0713bebcd 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -35,6 +35,7 @@ #include "xfs_refcount_item.h" #include "xfs_bmap_item.h" #include "xfs_reflink.h" +#include "xfs_pwork.h" #include <linux/magic.h> #include <linux/fs_context.h> @@ -342,7 +343,7 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS); + blkdev_issue_flush(buftarg->bt_bdev); } STATIC void @@ -495,40 +496,44 @@ xfs_init_mount_workqueues( struct xfs_mount *mp) { mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 1, mp->m_super->s_id); if (!mp->m_buf_workqueue) goto out; mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 0, mp->m_super->s_id); if (!mp->m_unwritten_workqueue) goto out_destroy_buf; mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s", - WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND, + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND), 0, mp->m_super->s_id); if (!mp->m_cil_workqueue) goto out_destroy_unwritten; mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 0, mp->m_super->s_id); if (!mp->m_reclaim_workqueue) goto out_destroy_cil; - mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); - if (!mp->m_eofblocks_workqueue) + mp->m_blockgc_workqueue = alloc_workqueue("xfs-blockgc/%s", + WQ_SYSFS | WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM, + 0, mp->m_super->s_id); + if (!mp->m_blockgc_workqueue) goto out_destroy_reclaim; - mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0, - mp->m_super->s_id); + mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", + XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id); if (!mp->m_sync_workqueue) goto out_destroy_eofb; return 0; out_destroy_eofb: - destroy_workqueue(mp->m_eofblocks_workqueue); + destroy_workqueue(mp->m_blockgc_workqueue); out_destroy_reclaim: destroy_workqueue(mp->m_reclaim_workqueue); out_destroy_cil: @@ -546,7 +551,7 @@ xfs_destroy_mount_workqueues( struct xfs_mount *mp) { destroy_workqueue(mp->m_sync_workqueue); - destroy_workqueue(mp->m_eofblocks_workqueue); + destroy_workqueue(mp->m_blockgc_workqueue); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_cil_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); @@ -868,39 +873,6 @@ xfs_restore_resvblks(struct xfs_mount *mp) } /* - * Trigger writeback of all the dirty metadata in the file system. - * - * This ensures that the metadata is written to their location on disk rather - * than just existing in transactions in the log. This means after a quiesce - * there is no log replay required to write the inodes to disk - this is the - * primary difference between a sync and a quiesce. - * - * We cancel log work early here to ensure all transactions the log worker may - * run have finished before we clean up and log the superblock and write an - * unmount record. The unfreeze process is responsible for restarting the log - * worker correctly. - */ -void -xfs_quiesce_attr( - struct xfs_mount *mp) -{ - int error = 0; - - cancel_delayed_work_sync(&mp->m_log->l_work); - - /* force the log to unpin objects from the now complete transactions */ - xfs_log_force(mp, XFS_LOG_SYNC); - - - /* Push the superblock and write an unmount record */ - error = xfs_log_sbcount(mp); - if (error) - xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. " - "Frozen image may not be consistent."); - xfs_log_quiesce(mp); -} - -/* * Second stage of a freeze. The data is already frozen so we only * need to take care of the metadata. Once that's done sync the superblock * to the log to dirty it in case of a crash while frozen. This ensures that we @@ -920,10 +892,9 @@ xfs_fs_freeze( * set a GFP_NOFS context here to avoid recursion deadlocks. */ flags = memalloc_nofs_save(); - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); xfs_save_resvblks(mp); - xfs_quiesce_attr(mp); - ret = xfs_sync_sb(mp, true); + ret = xfs_log_quiesce(mp); memalloc_nofs_restore(flags); return ret; } @@ -936,7 +907,7 @@ xfs_fs_unfreeze( xfs_restore_resvblks(mp); xfs_log_work_queue(mp); - xfs_start_block_reaping(mp); + xfs_blockgc_start(mp); return 0; } @@ -1720,7 +1691,7 @@ xfs_remount_rw( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } - xfs_start_block_reaping(mp); + xfs_blockgc_start(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1740,10 +1711,10 @@ xfs_remount_ro( * Cancel background eofb scanning so it cannot race with the final * log force+buftarg wait and deadlock the remount. */ - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); /* Get rid of any leftover CoW reservations... */ - error = xfs_icache_free_cowblocks(mp, NULL); + error = xfs_blockgc_free_space(mp, NULL); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; @@ -1765,7 +1736,7 @@ xfs_remount_ro( */ xfs_save_resvblks(mp); - xfs_quiesce_attr(mp); + xfs_log_clean(mp); mp->m_flags |= XFS_MOUNT_RDONLY; return 0; @@ -1872,8 +1843,6 @@ static int xfs_init_fs_context( mutex_init(&mp->m_growlock); INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); - INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker); - INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker); mp->m_kobj.kobject.kset = xfs_kset; /* * We don't create the finobt per-ag space reservation until after log @@ -1912,7 +1881,7 @@ static struct file_system_type xfs_fs_type = { .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("xfs"); @@ -2119,11 +2088,12 @@ xfs_init_workqueues(void) * max_active value for this workqueue. */ xfs_alloc_wq = alloc_workqueue("xfsalloc", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0); + XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 0); if (!xfs_alloc_wq) return -ENOMEM; - xfs_discard_wq = alloc_workqueue("xfsdiscard", WQ_UNBOUND, 0); + xfs_discard_wq = alloc_workqueue("xfsdiscard", XFS_WQFLAGS(WQ_UNBOUND), + 0); if (!xfs_discard_wq) goto out_free_alloc_wq; diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index b552cf6d3379..1ca484b8357f 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -75,6 +75,12 @@ extern void xfs_qm_exit(void); XFS_ASSERT_FATAL_STRING \ XFS_DBG_STRING /* DBG must be last */ +#ifdef DEBUG +# define XFS_WQFLAGS(wqflags) (WQ_SYSFS | (wqflags)) +#else +# define XFS_WQFLAGS(wqflags) (wqflags) +#endif + struct xfs_inode; struct xfs_mount; struct xfs_buftarg; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 1f43fd7f3209..1379013d74b8 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -134,6 +134,7 @@ xfs_readlink( int xfs_symlink( + struct user_namespace *mnt_userns, struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, @@ -197,9 +198,10 @@ xfs_symlink( fs_blocks = xfs_symlink_blocks(mp, pathlen); resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, &M_RES(mp)->tr_symlink, udqp, gdqp, + pdqp, resblks, &tp); if (error) - goto out_release_inode; + goto out_release_dquots; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; @@ -212,19 +214,16 @@ xfs_symlink( goto out_trans_cancel; } - /* - * Reserve disk quota : blocks and inode. - */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); if (error) goto out_trans_cancel; /* * Allocate an inode for the symlink. */ - error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, - prid, &ip); + error = xfs_dir_ialloc(mnt_userns, &tp, dp, S_IFLNK | (mode & ~S_IFMT), + 1, 0, prid, &ip); if (error) goto out_trans_cancel; @@ -300,6 +299,7 @@ xfs_symlink( } ASSERT(pathlen == 0); } + i_size_write(VFS_I(ip), ip->i_d.di_size); /* * Create the directory entry for the symlink. @@ -342,7 +342,7 @@ out_release_inode: xfs_finish_inode_setup(ip); xfs_irele(ip); } - +out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h index b1fa091427e6..2586b7e393f3 100644 --- a/fs/xfs/xfs_symlink.h +++ b/fs/xfs/xfs_symlink.h @@ -7,8 +7,9 @@ /* Kernel only symlink definitions */ -int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name, - const char *target_path, umode_t mode, struct xfs_inode **ipp); +int xfs_symlink(struct user_namespace *mnt_userns, struct xfs_inode *dp, + struct xfs_name *link_name, const char *target_path, + umode_t mode, struct xfs_inode **ipp); int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link); int xfs_readlink(struct xfs_inode *ip, char *link); int xfs_inactive_symlink(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index fac9de7ee6d0..546a6cd96729 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -51,7 +51,7 @@ xfs_panic_mask_proc_handler( #endif /* CONFIG_PROC_FS */ STATIC int -xfs_deprecate_irix_sgid_inherit_proc_handler( +xfs_deprecated_dointvec_minmax( struct ctl_table *ctl, int write, void *buffer, @@ -59,24 +59,8 @@ xfs_deprecate_irix_sgid_inherit_proc_handler( loff_t *ppos) { if (write) { - printk_once(KERN_WARNING - "XFS: " "%s sysctl option is deprecated.\n", - ctl->procname); - } - return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); -} - -STATIC int -xfs_deprecate_irix_symlink_mode_proc_handler( - struct ctl_table *ctl, - int write, - void *buffer, - size_t *lenp, - loff_t *ppos) -{ - if (write) { - printk_once(KERN_WARNING - "XFS: " "%s sysctl option is deprecated.\n", + printk_ratelimited(KERN_WARNING + "XFS: %s sysctl option is deprecated.\n", ctl->procname); } return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); @@ -88,7 +72,7 @@ static struct ctl_table xfs_table[] = { .data = &xfs_params.sgid_inherit.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = xfs_deprecate_irix_sgid_inherit_proc_handler, + .proc_handler = xfs_deprecated_dointvec_minmax, .extra1 = &xfs_params.sgid_inherit.min, .extra2 = &xfs_params.sgid_inherit.max }, @@ -97,7 +81,7 @@ static struct ctl_table xfs_table[] = { .data = &xfs_params.symlink_mode.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = xfs_deprecate_irix_symlink_mode_proc_handler, + .proc_handler = xfs_deprecated_dointvec_minmax, .extra1 = &xfs_params.symlink_mode.min, .extra2 = &xfs_params.symlink_mode.max }, @@ -194,21 +178,21 @@ static struct ctl_table xfs_table[] = { }, { .procname = "speculative_prealloc_lifetime", - .data = &xfs_params.eofb_timer.val, + .data = &xfs_params.blockgc_timer.val, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.eofb_timer.min, - .extra2 = &xfs_params.eofb_timer.max, + .extra1 = &xfs_params.blockgc_timer.min, + .extra2 = &xfs_params.blockgc_timer.max, }, { .procname = "speculative_cow_prealloc_lifetime", - .data = &xfs_params.cowb_timer.val, + .data = &xfs_params.blockgc_timer.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.cowb_timer.min, - .extra2 = &xfs_params.cowb_timer.max, + .proc_handler = xfs_deprecated_dointvec_minmax, + .extra1 = &xfs_params.blockgc_timer.min, + .extra2 = &xfs_params.blockgc_timer.max, }, /* please keep this the last entry */ #ifdef CONFIG_PROC_FS diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h index 8abf4640f1d5..7692e76ead33 100644 --- a/fs/xfs/xfs_sysctl.h +++ b/fs/xfs/xfs_sysctl.h @@ -35,8 +35,7 @@ typedef struct xfs_param { xfs_sysctl_val_t rotorstep; /* inode32 AG rotoring control knob */ xfs_sysctl_val_t inherit_nodfrg;/* Inherit the "nodefrag" inode flag. */ xfs_sysctl_val_t fstrm_timer; /* Filestream dir-AG assoc'n timeout. */ - xfs_sysctl_val_t eofb_timer; /* Interval between eofb scan wakeups */ - xfs_sysctl_val_t cowb_timer; /* Interval between cowb scan wakeups */ + xfs_sysctl_val_t blockgc_timer; /* Interval between blockgc scans */ } xfs_param_t; /* diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 120398a37c2a..9b8d703dc9fd 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -29,6 +29,7 @@ #include "xfs_filestream.h" #include "xfs_fsmap.h" #include "xfs_btree_staging.h" +#include "xfs_icache.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 5a263ae3d4f0..e74bbb648f83 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -37,6 +37,7 @@ struct xfs_trans_res; struct xfs_inobt_rec_incore; union xfs_btree_ptr; struct xfs_dqtrx; +struct xfs_eofblocks; #define XFS_ATTR_FILTER_FLAGS \ { XFS_ATTR_ROOT, "ROOT" }, \ @@ -154,10 +155,8 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag); DEFINE_PERAG_REF_EVENT(xfs_perag_put); DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim); DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim); -DEFINE_PERAG_REF_EVENT(xfs_perag_set_eofblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_clear_eofblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_set_cowblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_clear_cowblocks); +DEFINE_PERAG_REF_EVENT(xfs_perag_set_blockgc); +DEFINE_PERAG_REF_EVENT(xfs_perag_clear_blockgc); DECLARE_EVENT_CLASS(xfs_ag_class, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno), @@ -358,7 +357,7 @@ DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); -DEFINE_BUF_EVENT(xfs_buf_wait_buftarg); +DEFINE_BUF_EVENT(xfs_buf_drain_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); /* not really buffer traces, but the buf provides useful information */ @@ -1287,8 +1286,8 @@ TRACE_EVENT(xfs_log_assign_tail_lsn, ) DECLARE_EVENT_CLASS(xfs_file_class, - TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset), - TP_ARGS(ip, count, offset), + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), + TP_ARGS(iocb, iter), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) @@ -1297,11 +1296,11 @@ DECLARE_EVENT_CLASS(xfs_file_class, __field(size_t, count) ), TP_fast_assign( - __entry->dev = VFS_I(ip)->i_sb->s_dev; - __entry->ino = ip->i_ino; - __entry->size = ip->i_d.di_size; - __entry->offset = offset; - __entry->count = count; + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = XFS_I(file_inode(iocb->ki_filp))->i_ino; + __entry->size = XFS_I(file_inode(iocb->ki_filp))->i_d.di_size; + __entry->offset = iocb->ki_pos; + __entry->count = iov_iter_count(iter); ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx count 0x%zx", MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1313,14 +1312,16 @@ DECLARE_EVENT_CLASS(xfs_file_class, #define DEFINE_RW_EVENT(name) \ DEFINE_EVENT(xfs_file_class, name, \ - TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset), \ - TP_ARGS(ip, count, offset)) + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), \ + TP_ARGS(iocb, iter)) DEFINE_RW_EVENT(xfs_file_buffered_read); DEFINE_RW_EVENT(xfs_file_direct_read); DEFINE_RW_EVENT(xfs_file_dax_read); DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); +DEFINE_RW_EVENT(xfs_reflink_bounce_dio_write); + DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, @@ -3294,8 +3295,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow); -DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write); - 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); @@ -3888,6 +3887,47 @@ DEFINE_EVENT(xfs_timestamp_range_class, name, \ DEFINE_TIMESTAMP_RANGE_EVENT(xfs_inode_timestamp_range); DEFINE_TIMESTAMP_RANGE_EVENT(xfs_quota_expiry_range); +DECLARE_EVENT_CLASS(xfs_eofblocks_class, + TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb, + unsigned long caller_ip), + TP_ARGS(mp, eofb, caller_ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(__u32, flags) + __field(uint32_t, uid) + __field(uint32_t, gid) + __field(prid_t, prid) + __field(__u64, min_file_size) + __field(unsigned long, caller_ip) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->flags = eofb ? eofb->eof_flags : 0; + __entry->uid = eofb ? from_kuid(mp->m_super->s_user_ns, + eofb->eof_uid) : 0; + __entry->gid = eofb ? from_kgid(mp->m_super->s_user_ns, + eofb->eof_gid) : 0; + __entry->prid = eofb ? eofb->eof_prid : 0; + __entry->min_file_size = eofb ? eofb->eof_min_file_size : 0; + __entry->caller_ip = caller_ip; + ), + TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu caller %pS", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->flags, + __entry->uid, + __entry->gid, + __entry->prid, + __entry->min_file_size, + (char *)__entry->caller_ip) +); +#define DEFINE_EOFBLOCKS_EVENT(name) \ +DEFINE_EVENT(xfs_eofblocks_class, name, \ + TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb, \ + unsigned long caller_ip), \ + TP_ARGS(mp, eofb, caller_ip)) +DEFINE_EOFBLOCKS_EVENT(xfs_ioc_free_eofblocks); +DEFINE_EOFBLOCKS_EVENT(xfs_blockgc_free_space); + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index e72730f85af1..b22a09e9daee 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -20,6 +20,10 @@ #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_dquot_item.h" +#include "xfs_dquot.h" +#include "xfs_icache.h" kmem_zone_t *xfs_trans_zone; @@ -68,6 +72,7 @@ xfs_trans_free( xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false); trace_xfs_trans_free(tp, _RET_IP_); + xfs_trans_clear_context(tp); if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT)) sb_end_intwrite(tp->t_mountp->m_super); xfs_trans_free_dqinfo(tp); @@ -119,7 +124,8 @@ xfs_trans_dup( ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used; tp->t_rtx_res = tp->t_rtx_res_used; - ntp->t_pflags = tp->t_pflags; + + xfs_trans_switch_context(tp, ntp); /* move deferred ops over to the new tp */ xfs_defer_move(ntp, tp); @@ -153,9 +159,6 @@ xfs_trans_reserve( int error = 0; bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; - /* Mark this thread as being in a transaction */ - current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - /* * Attempt to reserve the needed disk blocks by decrementing * the number needed from the number available. This will @@ -163,10 +166,8 @@ xfs_trans_reserve( */ if (blocks > 0) { error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd); - if (error != 0) { - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); + if (error != 0) return -ENOSPC; - } tp->t_blk_res += blocks; } @@ -240,9 +241,6 @@ undo_blocks: xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd); tp->t_blk_res = 0; } - - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - return error; } @@ -256,6 +254,7 @@ xfs_trans_alloc( struct xfs_trans **tpp) { struct xfs_trans *tp; + bool want_retry = true; int error; /* @@ -263,9 +262,11 @@ xfs_trans_alloc( * GFP_NOFS allocation context so that we avoid lockdep false positives * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ +retry: tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL); if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); + xfs_trans_set_context(tp); /* * Zero-reservation ("empty") transactions can't modify anything, so @@ -285,6 +286,22 @@ xfs_trans_alloc( tp->t_firstblock = NULLFSBLOCK; error = xfs_trans_reserve(tp, resp, blocks, rtextents); + if (error == -ENOSPC && want_retry) { + xfs_trans_cancel(tp); + + /* + * We weren't able to reserve enough space for the transaction. + * Flush the other speculative space allocations to free space. + * Do not perform a synchronous scan because callers can hold + * other locks. + */ + error = xfs_blockgc_free_space(mp, NULL); + if (error) + return error; + + want_retry = false; + goto retry; + } if (error) { xfs_trans_cancel(tp); return error; @@ -878,7 +895,6 @@ __xfs_trans_commit( xfs_log_commit_cil(mp, tp, &commit_lsn, regrant); - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free(tp); /* @@ -910,7 +926,6 @@ out_unreserve: xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; } - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free_items(tp, !!error); xfs_trans_free(tp); @@ -970,9 +985,6 @@ xfs_trans_cancel( tp->t_ticket = NULL; } - /* mark this thread as no longer being in a transaction */ - current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - xfs_trans_free_items(tp, dirty); xfs_trans_free(tp); } @@ -1024,3 +1036,183 @@ xfs_trans_roll( tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; return xfs_trans_reserve(*tpp, &tres, 0, 0); } + +/* + * Allocate an transaction, lock and join the inode to it, and reserve quota. + * + * The caller must ensure that the on-disk dquots attached to this inode have + * already been allocated and initialized. The caller is responsible for + * releasing ILOCK_EXCL if a new transaction is returned. + */ +int +xfs_trans_alloc_inode( + struct xfs_inode *ip, + struct xfs_trans_res *resv, + unsigned int dblocks, + unsigned int rblocks, + bool force, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + struct xfs_mount *mp = ip->i_mount; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, resv, dblocks, + rblocks / mp->m_sb.sb_rextsize, + force ? XFS_TRANS_RESERVE : 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); + + error = xfs_qm_dqattach_locked(ip, false); + if (error) { + /* Caller should have allocated the dquots! */ + ASSERT(error != -ENOENT); + goto out_cancel; + } + + error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_blockgc_free_quota(ip, 0); + retried = true; + goto retry; + } + if (error) + goto out_cancel; + + *tpp = tp; + return 0; + +out_cancel: + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; +} + +/* + * Allocate an transaction in preparation for inode creation by reserving quota + * against the given dquots. Callers are not required to hold any inode locks. + */ +int +xfs_trans_alloc_icreate( + struct xfs_mount *mp, + struct xfs_trans_res *resv, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + unsigned int dblocks, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp); + if (error) + return error; + + error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); + retried = true; + goto retry; + } + if (error) { + xfs_trans_cancel(tp); + return error; + } + + *tpp = tp; + return 0; +} + +/* + * Allocate an transaction, lock and join the inode to it, and reserve quota + * in preparation for inode attribute changes that include uid, gid, or prid + * changes. + * + * The caller must ensure that the on-disk dquots attached to this inode have + * already been allocated and initialized. The ILOCK will be dropped when the + * transaction is committed or cancelled. + */ +int +xfs_trans_alloc_ichange( + struct xfs_inode *ip, + struct xfs_dquot *new_udqp, + struct xfs_dquot *new_gdqp, + struct xfs_dquot *new_pdqp, + bool force, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + struct xfs_mount *mp = ip->i_mount; + struct xfs_dquot *udqp; + struct xfs_dquot *gdqp; + struct xfs_dquot *pdqp; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + error = xfs_qm_dqattach_locked(ip, false); + if (error) { + /* Caller should have allocated the dquots! */ + ASSERT(error != -ENOENT); + goto out_cancel; + } + + /* + * For each quota type, skip quota reservations if the inode's dquots + * now match the ones that came from the caller, or the caller didn't + * pass one in. The inode's dquots can change if we drop the ILOCK to + * perform a blockgc scan, so we must preserve the caller's arguments. + */ + udqp = (new_udqp != ip->i_udquot) ? new_udqp : NULL; + gdqp = (new_gdqp != ip->i_gdquot) ? new_gdqp : NULL; + pdqp = (new_pdqp != ip->i_pdquot) ? new_pdqp : NULL; + if (udqp || gdqp || pdqp) { + unsigned int qflags = XFS_QMOPT_RES_REGBLKS; + + if (force) + qflags |= XFS_QMOPT_FORCE_RES; + + /* + * Reserve enough quota to handle blocks on disk and reserved + * for a delayed allocation. We'll actually transfer the + * delalloc reservation between dquots at chown time, even + * though that part is only semi-transactional. + */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, + pdqp, ip->i_d.di_nblocks + ip->i_delayed_blks, + 1, qflags); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); + retried = true; + goto retry; + } + if (error) + goto out_cancel; + } + + *tpp = tp; + return 0; + +out_cancel: + xfs_trans_cancel(tp); + return error; +} diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 084658946cc8..9dd745cf77c9 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -268,4 +268,47 @@ xfs_trans_item_relog( return lip->li_ops->iop_relog(lip, tp); } +struct xfs_dquot; + +int xfs_trans_alloc_inode(struct xfs_inode *ip, struct xfs_trans_res *resv, + unsigned int dblocks, unsigned int rblocks, bool force, + struct xfs_trans **tpp); +int xfs_trans_alloc_icreate(struct xfs_mount *mp, struct xfs_trans_res *resv, + struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, unsigned int dblocks, + struct xfs_trans **tpp); +int xfs_trans_alloc_ichange(struct xfs_inode *ip, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, bool force, + struct xfs_trans **tpp); + +static inline void +xfs_trans_set_context( + struct xfs_trans *tp) +{ + ASSERT(current->journal_info == NULL); + tp->t_pflags = memalloc_nofs_save(); + current->journal_info = tp; +} + +static inline void +xfs_trans_clear_context( + struct xfs_trans *tp) +{ + if (current->journal_info == tp) { + memalloc_nofs_restore(tp->t_pflags); + current->journal_info = NULL; + } +} + +static inline void +xfs_trans_switch_context( + struct xfs_trans *old_tp, + struct xfs_trans *new_tp) +{ + ASSERT(current->journal_info == old_tp); + new_tp->t_pflags = old_tp->t_pflags; + old_tp->t_pflags = 0; + current->journal_info = new_tp; +} + #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 28b8ac701919..48e09ea30ee5 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -16,6 +16,7 @@ #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_trace.h" +#include "xfs_error.h" STATIC void xfs_trans_alloc_dqinfo(xfs_trans_t *); @@ -691,9 +692,11 @@ xfs_trans_dqresv( nblks); xfs_trans_mod_dquot(tp, dqp, XFS_TRANS_DQ_RES_INOS, ninos); } - ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); - ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); - ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); + + if (XFS_IS_CORRUPT(mp, dqp->q_blk.reserved < dqp->q_blk.count) || + XFS_IS_CORRUPT(mp, dqp->q_rtb.reserved < dqp->q_rtb.count) || + XFS_IS_CORRUPT(mp, dqp->q_ino.reserved < dqp->q_ino.count)) + goto error_corrupt; xfs_dqunlock(dqp); return 0; @@ -703,6 +706,10 @@ error_return: if (xfs_dquot_type(dqp) == XFS_DQTYPE_PROJ) return -ENOSPC; return -EDQUOT; +error_corrupt: + xfs_dqunlock(dqp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return -EFSCORRUPTED; } @@ -780,28 +787,60 @@ int xfs_trans_reserve_quota_nblks( struct xfs_trans *tp, struct xfs_inode *ip, - int64_t nblks, - long ninos, - uint flags) + int64_t dblocks, + int64_t rblocks, + bool force) { struct xfs_mount *mp = ip->i_mount; + unsigned int qflags = 0; + int error; if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp)) return 0; ASSERT(!xfs_is_quota_inode(&mp->m_sb, ip->i_ino)); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT((flags & ~(XFS_QMOPT_FORCE_RES)) == XFS_TRANS_DQ_RES_RTBLKS || - (flags & ~(XFS_QMOPT_FORCE_RES)) == XFS_TRANS_DQ_RES_BLKS); - /* - * Reserve nblks against these dquots, with trans as the mediator. - */ - return xfs_trans_reserve_quota_bydquots(tp, mp, - ip->i_udquot, ip->i_gdquot, - ip->i_pdquot, - nblks, ninos, flags); + if (force) + qflags |= XFS_QMOPT_FORCE_RES; + + /* Reserve data device quota against the inode's dquots. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, dblocks, 0, + XFS_QMOPT_RES_REGBLKS | qflags); + if (error) + return error; + + /* Do the same but for realtime blocks. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, rblocks, 0, + XFS_QMOPT_RES_RTBLKS | qflags); + if (error) { + xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, -dblocks, 0, + XFS_QMOPT_RES_REGBLKS); + return error; + } + + return 0; +} + +/* Change the quota reservations for an inode creation activity. */ +int +xfs_trans_reserve_quota_icreate( + struct xfs_trans *tp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + int64_t dblocks) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp)) + return 0; + + return xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp, + dblocks, 1, XFS_QMOPT_RES_REGBLKS); } /* diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index bca48b308c02..12be32f66dc1 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -38,9 +38,10 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, } static int -xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused, - struct inode *inode, const char *name, const void *value, - size_t size, int flags) +xfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, + struct inode *inode, const char *name, const void *value, + size_t size, int flags) { struct xfs_da_args args = { .dp = XFS_I(inode), |