From 673e8e597c06eb81954bf21a10f5cce74a1de8f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:04 +0000 Subject: xfs: remove xfs_itruncate_data This wrapper isn't overly useful, not to say rather confusing. Around the call to xfs_itruncate_extents it does: - add tracing - add a few asserts in debug builds - conditionally update the inode size in two places - log the inode Both the tracing and the inode logging can be moved to xfs_itruncate_extents as they are useful for the attribute fork as well - in fact the attr code already does an equivalent xfs_trans_log_inode call just after calling xfs_itruncate_extents. The conditional size updates are a mess, and there was no reason to do them in two places anyway, as the first one was conditional on the inode having extents - but without extents we xfs_itruncate_extents would be a no-op and the placement wouldn't matter anyway. Instead move the size assignments and the asserts that make sense to the callers that want it. As a side effect of this clean up xfs_setattr_size by introducing variables for the old and new inode size, and moving the size updates into a common place. Reviewed-by: Dave Chinner Signed-off-by: Christoph Hellwig Signed-off-by: Ben Myers --- fs/xfs/xfs_inode.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index f0e6b151ba37..440f2acebfa8 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -491,8 +491,6 @@ int xfs_ifree(struct xfs_trans *, xfs_inode_t *, struct xfs_bmap_free *); int xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t); -int xfs_itruncate_data(struct xfs_trans **, struct xfs_inode *, - xfs_fsize_t); int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); void xfs_iext_realloc(xfs_inode_t *, int, int); -- cgit v1.2.3 From 3d2b3129c2c48cf0153e0f2058cf87e4b45ca3ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:06 +0000 Subject: xfs: remove the unused dm_attrs structure .. and the just as dead bhv_desc forward declaration while we're at it. Signed-off-by: Christoph Hellwig Reviewed-by: Alex Elder Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_inode.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 440f2acebfa8..c1574721a191 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -211,7 +211,6 @@ typedef struct xfs_icdinode { #ifdef __KERNEL__ -struct bhv_desc; struct xfs_buf; struct xfs_bmap_free; struct xfs_bmbt_irec; @@ -220,12 +219,6 @@ struct xfs_mount; struct xfs_trans; struct xfs_dquot; -typedef struct dm_attrs_s { - __uint32_t da_dmevmask; /* DMIG event mask */ - __uint16_t da_dmstate; /* DMIG state info */ - __uint16_t da_pad; /* DMIG extra padding */ -} dm_attrs_t; - typedef struct xfs_inode { /* Inode linking and identification information. */ struct xfs_mount *i_mount; /* fs mount struct ptr */ -- cgit v1.2.3 From 8096b1ebb59b94b3bc6abb6b7d121419e83447ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:07 +0000 Subject: xfs: remove the if_ext_max field in struct xfs_ifork We spent a lot of effort to maintain this field, but it always equals to the fork size divided by the constant size of an extent. The prime use of it is to assert that the two stay in sync. Just divide the fork size by the extent size in the few places that we actually use it and remove the overhead of maintaining it. Also introduce a few helpers to consolidate the places where we actually care about the value. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_attr_leaf.c | 9 ----- fs/xfs/xfs_bmap.c | 101 ++++++++++++++++++++++-------------------------- fs/xfs/xfs_dfrag.c | 43 ++++++++++----------- fs/xfs/xfs_iget.c | 2 - fs/xfs/xfs_inode.c | 30 +++++--------- fs/xfs/xfs_inode.h | 4 +- fs/xfs/xfs_inode_item.c | 2 - fs/xfs/xfs_trace.h | 5 +-- 8 files changed, 81 insertions(+), 115 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index c1b55e596551..d25eafd4d28d 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -271,10 +271,6 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff) dp = args->dp; mp = dp->i_mount; dp->i_d.di_forkoff = forkoff; - dp->i_df.if_ext_max = - XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); - dp->i_afp->if_ext_max = - XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); ifp = dp->i_afp; ASSERT(ifp->if_flags & XFS_IFINLINE); @@ -326,7 +322,6 @@ xfs_attr_fork_reset( ASSERT(ip->i_d.di_anextents == 0); ASSERT(ip->i_afp == NULL); - ip->i_df.if_ext_max = XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } @@ -389,10 +384,6 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) (args->op_flags & XFS_DA_OP_ADDNAME) || !(mp->m_flags & XFS_MOUNT_ATTR2) || dp->i_d.di_format == XFS_DINODE_FMT_BTREE); - dp->i_afp->if_ext_max = - XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); - dp->i_df.if_ext_max = - XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index d0ab78837057..7a888ca2f7f6 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -249,7 +249,27 @@ xfs_bmbt_lookup_ge( } /* -* Update the record referred to by cur to the value given + * Check if the inode needs to be converted to btree format. + */ +static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork) +{ + return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_NEXTENTS(ip, whichfork) > + XFS_IFORK_MAXEXT(ip, whichfork); +} + +/* + * Check if the inode should be converted to extent format. + */ +static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork) +{ + return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE && + XFS_IFORK_NEXTENTS(ip, whichfork) <= + XFS_IFORK_MAXEXT(ip, whichfork); +} + +/* + * Update the record referred to by cur to the value given * by [off, bno, len, state]. * This either works (return 0) or gets an EFSCORRUPTED error. */ @@ -683,8 +703,8 @@ xfs_bmap_add_extent_delay_real( goto done; XFS_WANT_CORRUPTED_GOTO(i == 1, done); } - if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && - bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) { + + if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, 1, &tmp_rval, XFS_DATA_FORK); @@ -767,8 +787,8 @@ xfs_bmap_add_extent_delay_real( goto done; XFS_WANT_CORRUPTED_GOTO(i == 1, done); } - if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && - bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) { + + if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, 1, &tmp_rval, XFS_DATA_FORK); @@ -836,8 +856,8 @@ xfs_bmap_add_extent_delay_real( goto done; XFS_WANT_CORRUPTED_GOTO(i == 1, done); } - if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && - bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) { + + if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, 1, &tmp_rval, XFS_DATA_FORK); @@ -884,8 +904,7 @@ xfs_bmap_add_extent_delay_real( } /* convert to a btree if necessary */ - if (XFS_IFORK_FORMAT(bma->ip, XFS_DATA_FORK) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(bma->ip, XFS_DATA_FORK) > ifp->if_ext_max) { + if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { int tmp_logflags; /* partial log flag return val */ ASSERT(bma->cur == NULL); @@ -1421,8 +1440,7 @@ xfs_bmap_add_extent_unwritten_real( } /* convert to a btree if necessary */ - if (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > ifp->if_ext_max) { + if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) { int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); @@ -1812,8 +1830,7 @@ xfs_bmap_add_extent_hole_real( } /* convert to a btree if necessary */ - if (XFS_IFORK_FORMAT(bma->ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(bma->ip, whichfork) > ifp->if_ext_max) { + if (xfs_bmap_needs_btree(bma->ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(bma->cur == NULL); @@ -3037,8 +3054,7 @@ xfs_bmap_extents_to_btree( ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS); - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); + /* * Make space in the inode incore. */ @@ -3184,13 +3200,8 @@ xfs_bmap_forkoff_reset( ip->i_d.di_format != XFS_DINODE_FMT_BTREE) { uint dfl_forkoff = xfs_default_attroffset(ip) >> 3; - if (dfl_forkoff > ip->i_d.di_forkoff) { + if (dfl_forkoff > ip->i_d.di_forkoff) ip->i_d.di_forkoff = dfl_forkoff; - ip->i_df.if_ext_max = - XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t); - ip->i_afp->if_ext_max = - XFS_IFORK_ASIZE(ip) / sizeof(xfs_bmbt_rec_t); - } } } @@ -3430,8 +3441,6 @@ xfs_bmap_add_attrfork( int error; /* error return value */ ASSERT(XFS_IFORK_Q(ip) == 0); - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t)); mp = ip->i_mount; ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); @@ -3486,12 +3495,9 @@ xfs_bmap_add_attrfork( error = XFS_ERROR(EINVAL); goto error1; } - ip->i_df.if_ext_max = - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); + ASSERT(ip->i_afp == NULL); ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP); - ip->i_afp->if_ext_max = - XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); ip->i_afp->if_flags = XFS_IFEXTENTS; logflags = 0; xfs_bmap_init(&flist, &firstblock); @@ -3535,20 +3541,17 @@ xfs_bmap_add_attrfork( } else spin_unlock(&mp->m_sb_lock); } - if ((error = xfs_bmap_finish(&tp, &flist, &committed))) + + error = xfs_bmap_finish(&tp, &flist, &committed); + if (error) goto error2; - error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t)); - return error; + return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); error2: xfs_bmap_cancel(&flist); error1: xfs_iunlock(ip, XFS_ILOCK_EXCL); error0: xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t)); return error; } @@ -4379,8 +4382,6 @@ xfs_bmapi_read( XFS_STATS_INC(xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); if (!(ifp->if_flags & XFS_IFEXTENTS)) { error = xfs_iread_extents(NULL, ip, whichfork); @@ -4871,8 +4872,6 @@ xfs_bmapi_write( return XFS_ERROR(EIO); ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); XFS_STATS_INC(xs_blk_mapw); @@ -4981,8 +4980,7 @@ xfs_bmapi_write( /* * Transform from btree to extents, give it cur. */ - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE && - XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max) { + if (xfs_bmap_wants_extents(ip, whichfork)) { int tmp_logflags = 0; ASSERT(bma.cur); @@ -4992,10 +4990,10 @@ xfs_bmapi_write( if (error) goto error0; } - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); + ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE || - XFS_IFORK_NEXTENTS(ip, whichfork) > ifp->if_ext_max); + XFS_IFORK_NEXTENTS(ip, whichfork) > + XFS_IFORK_MAXEXT(ip, whichfork)); error = 0; error0: /* @@ -5095,8 +5093,7 @@ xfs_bunmapi( ASSERT(len > 0); ASSERT(nexts >= 0); - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); + if (!(ifp->if_flags & XFS_IFEXTENTS) && (error = xfs_iread_extents(tp, ip, whichfork))) return error; @@ -5322,7 +5319,8 @@ xfs_bunmapi( */ if (!wasdel && xfs_trans_get_block_res(tp) == 0 && XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, whichfork) >= ifp->if_ext_max && + XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */ + XFS_IFORK_MAXEXT(ip, whichfork) && del.br_startoff > got.br_startoff && del.br_startoff + del.br_blockcount < got.br_startoff + got.br_blockcount) { @@ -5353,13 +5351,11 @@ nodelete: } } *done = bno == (xfs_fileoff_t)-1 || bno < start || lastx < 0; - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); + /* * Convert to a btree if necessary. */ - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, whichfork) > ifp->if_ext_max) { + if (xfs_bmap_needs_btree(ip, whichfork)) { ASSERT(cur == NULL); error = xfs_bmap_extents_to_btree(tp, ip, firstblock, flist, &cur, 0, &tmp_logflags, whichfork); @@ -5370,8 +5366,7 @@ nodelete: /* * transform from btree to extents, give it cur */ - else if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE && - XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max) { + else if (xfs_bmap_wants_extents(ip, whichfork)) { ASSERT(cur != NULL); error = xfs_bmap_btree_to_extents(tp, ip, cur, &tmp_logflags, whichfork); @@ -5382,8 +5377,6 @@ nodelete: /* * transform from extents to local? */ - ASSERT(ifp->if_ext_max == - XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t)); error = 0; error0: /* diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index 654dc6f05bac..dd974a55c77d 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -163,12 +163,14 @@ xfs_swap_extents_check_format( /* Check temp in extent form to max in target */ if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max) + XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > + XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) return EINVAL; /* Check target in extent form to max in temp */ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max) + XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > + XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK)) return EINVAL; /* @@ -180,18 +182,25 @@ xfs_swap_extents_check_format( * (a common defrag case) which will occur when the temp inode is in * extent format... */ - if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE && - ((XFS_IFORK_BOFF(ip) && - tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip)) || - XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <= ip->i_df.if_ext_max)) - return EINVAL; + if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + if (XFS_IFORK_BOFF(ip) && + tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip)) + return EINVAL; + if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <= + XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) + return EINVAL; + } /* Reciprocal target->temp btree format checks */ - if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE && - ((XFS_IFORK_BOFF(tip) && - ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip)) || - XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <= tip->i_df.if_ext_max)) - return EINVAL; + if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + if (XFS_IFORK_BOFF(tip) && + ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip)) + return EINVAL; + + if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <= + XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK)) + return EINVAL; + } return 0; } @@ -348,16 +357,6 @@ xfs_swap_extents( *ifp = *tifp; /* struct copy */ *tifp = *tempifp; /* struct copy */ - /* - * Fix the in-memory data fork values that are dependent on the fork - * offset in the inode. We can't assume they remain the same as attr2 - * has dynamic fork offsets. - */ - ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) / - (uint)sizeof(xfs_bmbt_rec_t); - tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) / - (uint)sizeof(xfs_bmbt_rec_t); - /* * Fix the on-disk inode values */ diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 3960a066d7ff..f180ce896cd7 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -450,8 +450,6 @@ again: *ipp = ip; - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t)); /* * If we have a real type for an on-disk inode, we can set ops(&unlock) * now. If it's a new inode being created, xfs_ialloc will handle it. diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ccd619a993f6..96b29e3286db 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -299,11 +299,8 @@ xfs_iformat( { xfs_attr_shortform_t *atp; int size; - int error; + int error = 0; xfs_fsize_t di_size; - ip->i_df.if_ext_max = - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); - error = 0; if (unlikely(be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) > @@ -409,10 +406,10 @@ xfs_iformat( } if (!XFS_DFORK_Q(dip)) return 0; + ASSERT(ip->i_afp == NULL); ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP | KM_NOFS); - ip->i_afp->if_ext_max = - XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); + switch (dip->di_aformat) { case XFS_DINODE_FMT_LOCAL: atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip); @@ -604,10 +601,11 @@ xfs_iformat_btree( * or the number of extents is greater than the number of * blocks. */ - if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max - || XFS_BMDR_SPACE_CALC(nrecs) > - XFS_DFORK_SIZE(dip, ip->i_mount, whichfork) - || XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) { + if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <= + XFS_IFORK_MAXEXT(ip, whichfork) || + XFS_BMDR_SPACE_CALC(nrecs) > + XFS_DFORK_SIZE(dip, ip->i_mount, whichfork) || + XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) { xfs_warn(ip->i_mount, "corrupt inode %Lu (btree).", (unsigned long long) ip->i_ino); XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW, @@ -835,12 +833,6 @@ xfs_iread( * with the uninitialized part of it. */ ip->i_d.di_mode = 0; - /* - * Initialize the per-fork minima and maxima for a new - * inode here. xfs_iformat will do it for old inodes. - */ - ip->i_df.if_ext_max = - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); } /* @@ -1740,8 +1732,6 @@ xfs_ifree( ip->i_d.di_flags = 0; ip->i_d.di_dmevmask = 0; ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */ - ip->i_df.if_ext_max = - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS; ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS; /* @@ -2408,7 +2398,7 @@ xfs_iflush( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(!completion_done(&ip->i_flush)); ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || - ip->i_d.di_nextents > ip->i_df.if_ext_max); + ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); iip = ip->i_itemp; mp = ip->i_mount; @@ -2524,7 +2514,7 @@ xfs_iflush_int( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(!completion_done(&ip->i_flush)); ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || - ip->i_d.di_nextents > ip->i_df.if_ext_max); + ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); iip = ip->i_itemp; mp = ip->i_mount; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index c1574721a191..47497e11c111 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -66,7 +66,6 @@ typedef struct xfs_ifork { struct xfs_btree_block *if_broot; /* file's incore btree root */ short if_broot_bytes; /* bytes allocated for root */ unsigned char if_flags; /* per-fork flags */ - unsigned char if_ext_max; /* max # of extent records */ union { xfs_bmbt_rec_host_t *if_extents;/* linear map file exts */ xfs_ext_irec_t *if_ext_irec; /* irec map file exts */ @@ -206,7 +205,8 @@ typedef struct xfs_icdinode { ((w) == XFS_DATA_FORK ? \ ((ip)->i_d.di_nextents = (n)) : \ ((ip)->i_d.di_anextents = (n))) - +#define XFS_IFORK_MAXEXT(ip, w) \ + (XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t)) #ifdef __KERNEL__ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index cfd6c7f8cc3c..2b6b4fcef49e 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -79,8 +79,6 @@ xfs_inode_item_size( break; case XFS_DINODE_FMT_BTREE: - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t)); iip->ili_format.ilf_fields &= ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV | XFS_ILOG_UUID); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 297f9fa6fb64..81efa0416173 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1568,7 +1568,6 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class, __field(xfs_ino_t, ino) __field(int, format) __field(int, nex) - __field(int, max_nex) __field(int, broot_size) __field(int, fork_off) ), @@ -1578,18 +1577,16 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class, __entry->ino = ip->i_ino; __entry->format = ip->i_d.di_format; __entry->nex = ip->i_d.di_nextents; - __entry->max_nex = ip->i_df.if_ext_max; __entry->broot_size = ip->i_df.if_broot_bytes; __entry->fork_off = XFS_IFORK_BOFF(ip); ), TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %d, " - "Max in-fork extents %d, broot size %d, fork offset %d", + "broot size %d, fork offset %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_symbolic(__entry->which, XFS_SWAPEXT_INODES), __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR), __entry->nex, - __entry->max_nex, __entry->broot_size, __entry->fork_off) ) -- cgit v1.2.3 From 49e4c70e52a2bc2090e5a4e003e2888af21d6a2b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:08 +0000 Subject: xfs: make i_flags an unsigned long To be used for bit wakeup i_flags needs to be an unsigned long or we'll run into trouble on big endian systems. Because of the 1-byte i_update field right after it this actually causes a fairly large size increase on its own (4 or 8 bytes), but that increase will be more than offset by the next two patches. Signed-off-by: Christoph Hellwig Reviewed-by: Alex Elder Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_inode.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 47497e11c111..be8dc0c2cf52 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -242,7 +242,7 @@ typedef struct xfs_inode { wait_queue_head_t i_ipin_wait; /* inode pinning wait queue */ spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ - unsigned short i_flags; /* see defined flags below */ + unsigned long i_flags; /* see defined flags below */ unsigned char i_update_core; /* timestamps/size is dirty */ unsigned int i_delayed_blks; /* count of delay alloc blks */ -- cgit v1.2.3 From 474fce067521a40dbacc722e8ba119e81c2d31bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:09 +0000 Subject: xfs: replace i_flock with a sleeping bitlock We almost never block on i_flock, the exception is synchronous inode flushing. Instead of bloating the inode with a 16/24-byte completion that we abuse as a semaphore just implement it as a bitlock that uses a bit waitqueue for the rare sleeping path. This primarily is a tradeoff between a much smaller inode and a faster non-blocking path vs faster wakeups, and we are much better off with the former. A small downside is that we will lose lockdep checking for i_flock, but given that it's always taken inside the ilock that should be acceptable. Note that for example the inode writeback locking is implemented in a very similar way. Signed-off-by: Christoph Hellwig Reviewed-by: Alex Elder Signed-off-by: Ben Myers --- fs/xfs/xfs_iget.c | 20 +++++++++++-- fs/xfs/xfs_inode.c | 4 +-- fs/xfs/xfs_inode.h | 78 +++++++++++++++++++++++++++++++------------------ fs/xfs/xfs_inode_item.c | 4 +-- fs/xfs/xfs_super.c | 7 ----- fs/xfs/xfs_sync.c | 9 +++--- 6 files changed, 76 insertions(+), 46 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index f180ce896cd7..a7cf7139f9ad 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -77,7 +77,7 @@ xfs_inode_alloc( ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(completion_done(&ip->i_flush)); + ASSERT(!xfs_isiflocked(ip)); ASSERT(ip->i_ino == 0); mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino); @@ -150,7 +150,7 @@ xfs_inode_free( /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(completion_done(&ip->i_flush)); + ASSERT(!xfs_isiflocked(ip)); /* * Because we use RCU freeing we need to ensure the inode always @@ -713,3 +713,19 @@ xfs_isilocked( return 0; } #endif + +void +__xfs_iflock( + struct xfs_inode *ip) +{ + wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT); + DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT); + + do { + prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + if (xfs_isiflocked(ip)) + io_schedule(); + } while (!xfs_iflock_nowait(ip)); + + finish_wait(wq, &wait.wait); +} diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 96b29e3286db..eeb60d31b086 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2396,7 +2396,7 @@ xfs_iflush( XFS_STATS_INC(xs_iflush_count); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(!completion_done(&ip->i_flush)); + ASSERT(xfs_isiflocked(ip)); ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); @@ -2512,7 +2512,7 @@ xfs_iflush_int( #endif ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(!completion_done(&ip->i_flush)); + ASSERT(xfs_isiflocked(ip)); ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index be8dc0c2cf52..960d2a89b3ac 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -237,7 +237,6 @@ typedef struct xfs_inode { struct xfs_inode_log_item *i_itemp; /* logging information */ mrlock_t i_lock; /* inode lock */ mrlock_t i_iolock; /* inode IO lock */ - struct completion i_flush; /* inode flush completion q */ atomic_t i_pincount; /* inode pin count */ wait_queue_head_t i_ipin_wait; /* inode pinning wait queue */ spinlock_t i_flags_lock; /* inode i_flags lock */ @@ -324,6 +323,19 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags) return ret; } +static inline int +xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags) +{ + int ret; + + spin_lock(&ip->i_flags_lock); + ret = ip->i_flags & flags; + if (!ret) + ip->i_flags |= flags; + spin_unlock(&ip->i_flags_lock); + return ret; +} + /* * Project quota id helpers (previously projid was 16bit only * and using two 16bit values to hold new 32bit projid was chosen @@ -343,36 +355,18 @@ xfs_set_projid(struct xfs_inode *ip, ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff); } -/* - * Manage the i_flush queue embedded in the inode. This completion - * queue synchronizes processes attempting to flush the in-core - * inode back to disk. - */ -static inline void xfs_iflock(xfs_inode_t *ip) -{ - wait_for_completion(&ip->i_flush); -} - -static inline int xfs_iflock_nowait(xfs_inode_t *ip) -{ - return try_wait_for_completion(&ip->i_flush); -} - -static inline void xfs_ifunlock(xfs_inode_t *ip) -{ - complete(&ip->i_flush); -} - /* * In-core inode flags. */ -#define XFS_IRECLAIM 0x0001 /* started reclaiming this inode */ -#define XFS_ISTALE 0x0002 /* inode has been staled */ -#define XFS_IRECLAIMABLE 0x0004 /* inode can be reclaimed */ -#define XFS_INEW 0x0008 /* inode has just been allocated */ -#define XFS_IFILESTREAM 0x0010 /* inode is in a filestream directory */ -#define XFS_ITRUNCATED 0x0020 /* truncated down so flush-on-close */ -#define XFS_IDIRTY_RELEASE 0x0040 /* dirty release already seen */ +#define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ +#define XFS_ISTALE (1 << 1) /* inode has been staled */ +#define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ +#define XFS_INEW (1 << 3) /* inode has just been allocated */ +#define XFS_IFILESTREAM (1 << 4) /* inode is in a filestream dir. */ +#define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ +#define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ +#define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */ +#define XFS_IFLOCK (1 << __XFS_IFLOCK_BIT) /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during @@ -384,6 +378,34 @@ static inline void xfs_ifunlock(xfs_inode_t *ip) XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \ XFS_IFILESTREAM); +/* + * Synchronize processes attempting to flush the in-core inode back to disk. + */ + +extern void __xfs_iflock(struct xfs_inode *ip); + +static inline int xfs_iflock_nowait(struct xfs_inode *ip) +{ + return !xfs_iflags_test_and_set(ip, XFS_IFLOCK); +} + +static inline void xfs_iflock(struct xfs_inode *ip) +{ + if (!xfs_iflock_nowait(ip)) + __xfs_iflock(ip); +} + +static inline void xfs_ifunlock(struct xfs_inode *ip) +{ + xfs_iflags_clear(ip, XFS_IFLOCK); + wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT); +} + +static inline int xfs_isiflocked(struct xfs_inode *ip) +{ + return xfs_iflags_test(ip, XFS_IFLOCK); +} + /* * Flags for inode locking. * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 2b6b4fcef49e..c8d4ce0efd5a 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -717,7 +717,7 @@ xfs_inode_item_pushbuf( * If a flush is not in progress anymore, chances are that the * inode was taken off the AIL. So, just get out. */ - if (completion_done(&ip->i_flush) || + if (!xfs_isiflocked(ip) || !(lip->li_flags & XFS_LI_IN_AIL)) { xfs_iunlock(ip, XFS_ILOCK_SHARED); return true; @@ -750,7 +750,7 @@ xfs_inode_item_push( struct xfs_inode *ip = iip->ili_inode; ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); - ASSERT(!completion_done(&ip->i_flush)); + ASSERT(xfs_isiflocked(ip)); /* * Since we were able to lock the inode's flush lock and diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 281961c1d81a..6851fa7b1afa 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -829,13 +829,6 @@ xfs_fs_inode_init_once( atomic_set(&ip->i_pincount, 0); spin_lock_init(&ip->i_flags_lock); init_waitqueue_head(&ip->i_ipin_wait); - /* - * Because we want to use a counting completion, complete - * the flush completion once to allow a single access to - * the flush completion without blocking. - */ - init_completion(&ip->i_flush); - complete(&ip->i_flush); mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER, "xfsino", ip->i_ino); diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index 72c01a1c16e7..40b75eecd2b4 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -707,14 +707,13 @@ xfs_reclaim_inode_grab( return 1; /* - * do some unlocked checks first to avoid unnecessary lock traffic. - * The first is a flush lock check, the second is a already in reclaim - * check. Only do these checks if we are not going to block on locks. + * If we are asked for non-blocking operation, do unlocked checks to + * see if the inode already is being flushed or in reclaim to avoid + * lock traffic. */ if ((flags & SYNC_TRYLOCK) && - (!ip->i_flush.done || __xfs_iflags_test(ip, XFS_IRECLAIM))) { + __xfs_iflags_test(ip, XFS_IFLOCK | XFS_IRECLAIM)) return 1; - } /* * The radix tree lock here protects a thread in xfs_iget from racing -- cgit v1.2.3 From f392e6319a4e9a028b0c8b48f000bb01d660ad53 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:10 +0000 Subject: xfs: replace i_pin_wait with a bit waitqueue Replace i_pin_wait, which is only used during synchronous inode flushing with a bit waitqueue. This trades off a much smaller inode against slightly slower wakeup performance, and saves 12 (32-bit) or 20 (64-bit) bytes in the XFS inode. Reviewed-by: Alex Elder Reviewed-by: Dave Chinner Signed-off-by: Christoph Hellwig Signed-off-by: Ben Myers --- fs/xfs/xfs_inode.c | 27 +++++++++++++++++++++------ fs/xfs/xfs_inode.h | 3 ++- fs/xfs/xfs_inode_item.c | 2 +- fs/xfs/xfs_super.c | 1 - 4 files changed, 24 insertions(+), 9 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index eeb60d31b086..62603369b523 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2037,7 +2037,7 @@ xfs_idestroy_fork( * once someone is waiting for it to be unpinned. */ static void -xfs_iunpin_nowait( +xfs_iunpin( struct xfs_inode *ip) { ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); @@ -2049,14 +2049,29 @@ xfs_iunpin_nowait( } +static void +__xfs_iunpin_wait( + struct xfs_inode *ip) +{ + wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IPINNED_BIT); + DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IPINNED_BIT); + + xfs_iunpin(ip); + + do { + prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + if (xfs_ipincount(ip)) + io_schedule(); + } while (xfs_ipincount(ip)); + finish_wait(wq, &wait.wait); +} + void xfs_iunpin_wait( struct xfs_inode *ip) { - if (xfs_ipincount(ip)) { - xfs_iunpin_nowait(ip); - wait_event(ip->i_ipin_wait, (xfs_ipincount(ip) == 0)); - } + if (xfs_ipincount(ip)) + __xfs_iunpin_wait(ip); } /* @@ -2415,7 +2430,7 @@ xfs_iflush( * out for us if they occur after the log force completes. */ if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) { - xfs_iunpin_nowait(ip); + xfs_iunpin(ip); xfs_ifunlock(ip); return EAGAIN; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 960d2a89b3ac..4acbe740be46 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -238,7 +238,6 @@ typedef struct xfs_inode { mrlock_t i_lock; /* inode lock */ mrlock_t i_iolock; /* inode IO lock */ atomic_t i_pincount; /* inode pin count */ - wait_queue_head_t i_ipin_wait; /* inode pinning wait queue */ spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ unsigned long i_flags; /* see defined flags below */ @@ -367,6 +366,8 @@ xfs_set_projid(struct xfs_inode *ip, #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ #define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */ #define XFS_IFLOCK (1 << __XFS_IFLOCK_BIT) +#define __XFS_IPINNED_BIT 8 /* wakeup key for zero pin count */ +#define XFS_IPINNED (1 << __XFS_IPINNED_BIT) /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index c8d4ce0efd5a..91d71dcd4852 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -555,7 +555,7 @@ xfs_inode_item_unpin( trace_xfs_inode_unpin(ip, _RET_IP_); ASSERT(atomic_read(&ip->i_pincount) > 0); if (atomic_dec_and_test(&ip->i_pincount)) - wake_up(&ip->i_ipin_wait); + wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } /* diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 6851fa7b1afa..ee5b695c99a7 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -828,7 +828,6 @@ xfs_fs_inode_init_once( /* xfs inode */ atomic_set(&ip->i_pincount, 0); spin_lock_init(&ip->i_flags_lock); - init_waitqueue_head(&ip->i_ipin_wait); mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER, "xfsino", ip->i_ino); -- cgit v1.2.3 From ce7ae151ddada3dbf67301464343c154903166b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:11 +0000 Subject: xfs: remove the i_size field in struct xfs_inode There is no fundamental need to keep an in-memory inode size copy in the XFS inode. We already have the on-disk value in the dinode, and the separate in-memory copy that we need for regular files only in the XFS inode. Remove the xfs_inode i_size field and change the XFS_ISIZE macro to use the VFS inode i_size field for regular files. Switch code that was directly accessing the i_size field in the xfs_inode to XFS_ISIZE, or in cases where we are limited to regular files direct access of the VFS inode i_size field. This also allows dropping some fairly complicated code in the write path which dealt with keeping the xfs_inode i_size uptodate with the VFS i_size that is getting updated inside ->write_end. Note that we do not bother resetting the VFS i_size when truncating a file that gets freed to zero as there is no point in doing so because the VFS inode is no longer in use at this point. Just relax the assert in xfs_ifree to only check the on-disk size instead. Reviewed-by: Dave Chinner Signed-off-by: Christoph Hellwig Signed-off-by: Ben Myers --- fs/xfs/xfs_aops.c | 2 +- fs/xfs/xfs_bmap.c | 15 ++++++--------- fs/xfs/xfs_file.c | 45 +++++++++++---------------------------------- fs/xfs/xfs_fs_subr.c | 2 +- fs/xfs/xfs_iget.c | 1 - fs/xfs/xfs_inode.c | 8 ++------ fs/xfs/xfs_inode.h | 16 ++++++++++++---- fs/xfs/xfs_iomap.c | 12 ++++++------ fs/xfs/xfs_iops.c | 3 +-- fs/xfs/xfs_qm_syscalls.c | 1 - fs/xfs/xfs_trace.h | 2 +- fs/xfs/xfs_vnodeops.c | 31 +++++++++++++++---------------- 12 files changed, 56 insertions(+), 82 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 574d4ee9b625..4d27ea117e0e 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -111,7 +111,7 @@ xfs_ioend_new_eof( xfs_fsize_t bsize; bsize = ioend->io_offset + ioend->io_size; - isize = MAX(ip->i_size, ip->i_new_size); + isize = MAX(i_size_read(VFS_I(ip)), ip->i_new_size); isize = MIN(isize, bsize); return isize > ip->i_d.di_size ? isize : 0; } diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 7a888ca2f7f6..188ef2fbd628 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -3997,11 +3997,8 @@ xfs_bmap_one_block( xfs_bmbt_irec_t s; /* internal version of extent */ #ifndef DEBUG - if (whichfork == XFS_DATA_FORK) { - return S_ISREG(ip->i_d.di_mode) ? - (ip->i_size == ip->i_mount->m_sb.sb_blocksize) : - (ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize); - } + if (whichfork == XFS_DATA_FORK) + return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize; #endif /* !DEBUG */ if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1) return 0; @@ -4013,7 +4010,7 @@ xfs_bmap_one_block( xfs_bmbt_get_all(ep, &s); rval = s.br_startoff == 0 && s.br_blockcount == 1; if (rval && whichfork == XFS_DATA_FORK) - ASSERT(ip->i_size == ip->i_mount->m_sb.sb_blocksize); + ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize); return rval; } @@ -5427,7 +5424,7 @@ xfs_getbmapx_fix_eof_hole( if (startblock == HOLESTARTBLOCK) { mp = ip->i_mount; out->bmv_block = -1; - fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, ip->i_size)); + fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip))); fixlen -= out->bmv_offset; if (prealloced && out->bmv_offset + out->bmv_length == end) { /* Came to hole at EOF. Trim it. */ @@ -5515,7 +5512,7 @@ xfs_getbmap( fixlen = XFS_MAXIOFFSET(mp); } else { prealloced = 0; - fixlen = ip->i_size; + fixlen = XFS_ISIZE(ip); } } @@ -5544,7 +5541,7 @@ xfs_getbmap( xfs_ilock(ip, XFS_IOLOCK_SHARED); if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) { - if (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size) { + if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) { error = xfs_flush_pages(ip, 0, -1, 0, FI_REMAPF); if (error) goto out_unlock_iolock; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f675f3d9d7b3..86d5dc260464 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -327,7 +327,7 @@ xfs_file_aio_read( mp->m_rtdev_targp : mp->m_ddev_targp; if ((iocb->ki_pos & target->bt_smask) || (size & target->bt_smask)) { - if (iocb->ki_pos == ip->i_size) + if (iocb->ki_pos == i_size_read(inode)) return 0; return -XFS_ERROR(EINVAL); } @@ -412,30 +412,6 @@ xfs_file_splice_read( return ret; } -STATIC void -xfs_aio_write_isize_update( - struct inode *inode, - loff_t *ppos, - ssize_t bytes_written) -{ - struct xfs_inode *ip = XFS_I(inode); - xfs_fsize_t isize = i_size_read(inode); - - if (bytes_written > 0) - XFS_STATS_ADD(xs_write_bytes, bytes_written); - - if (unlikely(bytes_written < 0 && bytes_written != -EFAULT && - *ppos > isize)) - *ppos = isize; - - if (*ppos > ip->i_size) { - xfs_rw_ilock(ip, XFS_ILOCK_EXCL); - if (*ppos > ip->i_size) - ip->i_size = *ppos; - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); - } -} - /* * If this was a direct or synchronous I/O that failed (such as ENOSPC) then * part of the I/O may have been written to disk before the error occurred. In @@ -451,8 +427,8 @@ xfs_aio_write_newsize_update( xfs_rw_ilock(ip, XFS_ILOCK_EXCL); if (new_size == ip->i_new_size) ip->i_new_size = 0; - if (ip->i_d.di_size > ip->i_size) - ip->i_d.di_size = ip->i_size; + if (ip->i_d.di_size > i_size_read(VFS_I(ip))) + ip->i_d.di_size = i_size_read(VFS_I(ip)); xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); } } @@ -492,15 +468,16 @@ xfs_file_splice_write( new_size = *ppos + count; xfs_ilock(ip, XFS_ILOCK_EXCL); - if (new_size > ip->i_size) + if (new_size > i_size_read(inode)) ip->i_new_size = new_size; xfs_iunlock(ip, XFS_ILOCK_EXCL); trace_xfs_file_splice_write(ip, count, *ppos, ioflags); ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags); + if (ret > 0) + XFS_STATS_ADD(xs_write_bytes, ret); - xfs_aio_write_isize_update(inode, ppos, ret); xfs_aio_write_newsize_update(ip, new_size); xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; @@ -728,14 +705,14 @@ restart: * values are still valid. */ if ((ip->i_new_size && *pos > ip->i_new_size) || - (!ip->i_new_size && *pos > ip->i_size)) { + (!ip->i_new_size && *pos > i_size_read(inode))) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock); *iolock = XFS_IOLOCK_EXCL; xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock); goto restart; } - error = -xfs_zero_eof(ip, *pos, ip->i_size); + error = -xfs_zero_eof(ip, *pos, i_size_read(inode)); } /* @@ -744,7 +721,7 @@ restart: * ip->i_new_size if this IO ends beyond any other in-flight writes. */ new_size = *pos + *count; - if (new_size > ip->i_size) { + if (new_size > i_size_read(inode)) { if (new_size > ip->i_new_size) ip->i_new_size = new_size; *new_sizep = new_size; @@ -957,11 +934,11 @@ xfs_file_aio_write( ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos, ocount, &new_size, &iolock); - xfs_aio_write_isize_update(inode, &iocb->ki_pos, ret); - if (ret <= 0) goto out_unlock; + XFS_STATS_ADD(xs_write_bytes, ret); + /* Handle various SYNC-type writes */ if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) { loff_t end = pos + ret - 1; diff --git a/fs/xfs/xfs_fs_subr.c b/fs/xfs/xfs_fs_subr.c index ed88ed16811c..652b875a9d4c 100644 --- a/fs/xfs/xfs_fs_subr.c +++ b/fs/xfs/xfs_fs_subr.c @@ -90,7 +90,7 @@ xfs_wait_on_pages( if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { return -filemap_fdatawait_range(mapping, first, - last == -1 ? ip->i_size - 1 : last); + last == -1 ? XFS_ISIZE(ip) - 1 : last); } return 0; } diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index a7cf7139f9ad..3b5b78aa3b87 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -94,7 +94,6 @@ xfs_inode_alloc( ip->i_update_core = 0; ip->i_delayed_blks = 0; memset(&ip->i_d, 0, sizeof(xfs_icdinode_t)); - ip->i_size = 0; ip->i_new_size = 0; return ip; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 62603369b523..b21022499c2e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -347,7 +347,6 @@ xfs_iformat( return XFS_ERROR(EFSCORRUPTED); } ip->i_d.di_size = 0; - ip->i_size = 0; ip->i_df.if_u2.if_rdev = xfs_dinode_get_rdev(dip); break; @@ -853,7 +852,6 @@ xfs_iread( } ip->i_delayed_blks = 0; - ip->i_size = ip->i_d.di_size; /* * Mark the buffer containing the inode as something to keep @@ -1043,7 +1041,6 @@ xfs_ialloc( } ip->i_d.di_size = 0; - ip->i_size = 0; ip->i_d.di_nextents = 0; ASSERT(ip->i_d.di_nblocks == 0); @@ -1198,7 +1195,7 @@ xfs_itruncate_extents( int done = 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); - ASSERT(new_size <= ip->i_size); + ASSERT(new_size <= XFS_ISIZE(ip)); ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(ip->i_itemp != NULL); ASSERT(ip->i_itemp->ili_lock_flags == 0); @@ -1712,8 +1709,7 @@ xfs_ifree( ASSERT(ip->i_d.di_nlink == 0); ASSERT(ip->i_d.di_nextents == 0); ASSERT(ip->i_d.di_anextents == 0); - ASSERT((ip->i_d.di_size == 0 && ip->i_size == 0) || - (!S_ISREG(ip->i_d.di_mode))); + ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode)); ASSERT(ip->i_d.di_nblocks == 0); /* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4acbe740be46..cd99e43fa8f0 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -246,16 +246,12 @@ typedef struct xfs_inode { xfs_icdinode_t i_d; /* most of ondisk inode */ - xfs_fsize_t i_size; /* in-memory size */ xfs_fsize_t i_new_size; /* size when write completes */ /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ } xfs_inode_t; -#define XFS_ISIZE(ip) S_ISREG((ip)->i_d.di_mode) ? \ - (ip)->i_size : (ip)->i_d.di_size; - /* Convert from vfs inode to xfs inode */ static inline struct xfs_inode *XFS_I(struct inode *inode) { @@ -268,6 +264,18 @@ static inline struct inode *VFS_I(struct xfs_inode *ip) return &ip->i_vnode; } +/* + * For regular files we only update the on-disk filesize when actually + * writing data back to disk. Until then only the copy in the VFS inode + * is uptodate. + */ +static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip) +{ + if (S_ISREG(ip->i_d.di_mode)) + return i_size_read(VFS_I(ip)); + return ip->i_d.di_size; +} + /* * i_flags helper functions */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a27a44659da6..246c7d57c6f9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -74,7 +74,7 @@ xfs_iomap_eof_align_last_fsb( else if (mp->m_dalign) align = mp->m_dalign; - if (align && ip->i_size >= XFS_FSB_TO_B(mp, align)) + if (align && XFS_ISIZE(ip) >= XFS_FSB_TO_B(mp, align)) new_last_fsb = roundup_64(*last_fsb, align); } @@ -154,7 +154,7 @@ xfs_iomap_write_direct( offset_fsb = XFS_B_TO_FSBT(mp, offset); last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count))); - if ((offset + count) > ip->i_size) { + if ((offset + count) > XFS_ISIZE(ip)) { error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb); if (error) goto error_out; @@ -211,7 +211,7 @@ xfs_iomap_write_direct( xfs_trans_ijoin(tp, ip, 0); bmapi_flag = 0; - if (offset < ip->i_size || extsz) + if (offset < XFS_ISIZE(ip) || extsz) bmapi_flag |= XFS_BMAPI_PREALLOC; /* @@ -286,7 +286,7 @@ xfs_iomap_eof_want_preallocate( int found_delalloc = 0; *prealloc = 0; - if ((offset + count) <= ip->i_size) + if (offset + count <= XFS_ISIZE(ip)) return 0; /* @@ -340,7 +340,7 @@ xfs_iomap_prealloc_size( * if we pass in alloc_blocks = 0. Hence the "+ 1" to * ensure we always pass in a non-zero value. */ - alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size) + 1; + alloc_blocks = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)) + 1; alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN, rounddown_pow_of_two(alloc_blocks)); @@ -564,7 +564,7 @@ xfs_iomap_write_allocate( * back.... */ nimaps = 1; - end_fsb = XFS_B_TO_FSB(mp, ip->i_size); + end_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); error = xfs_bmap_last_offset(NULL, ip, &last_block, XFS_DATA_FORK); if (error) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f02eaa298d3c..ab302539e5b9 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -778,7 +778,7 @@ xfs_setattr_size( lock_flags |= XFS_IOLOCK_EXCL; xfs_ilock(ip, lock_flags); - oldsize = ip->i_size; + oldsize = inode->i_size; newsize = iattr->ia_size; /* @@ -897,7 +897,6 @@ xfs_setattr_size( * they get written to. */ ip->i_d.di_size = newsize; - ip->i_size = newsize; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); if (newsize <= oldsize) { diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 27378650b5cb..eafbcff81f3a 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -265,7 +265,6 @@ xfs_qm_scall_trunc_qfile( xfs_trans_ijoin(tp, ip, 0); ip->i_d.di_size = 0; - ip->i_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 81efa0416173..2aabcc9c507e 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1038,7 +1038,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = ip->i_ino; - __entry->isize = ip->i_size; + __entry->isize = VFS_I(ip)->i_size; __entry->disize = ip->i_d.di_size; __entry->new_size = ip->i_new_size; __entry->offset = offset; diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 96ff03421753..0cf52da9d246 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -175,7 +175,7 @@ xfs_free_eofblocks( * Figure out if there are any blocks beyond the end * of the file. If not, then there is nothing to do. */ - end_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)ip->i_size)); + end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip)); last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp)); if (last_fsb <= end_fsb) return 0; @@ -233,7 +233,7 @@ xfs_free_eofblocks( * may be full of holes (ie NULL files bug). */ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, - ip->i_size); + XFS_ISIZE(ip)); if (error) { /* * If we get an error at this point we simply don't @@ -547,8 +547,8 @@ xfs_release( return 0; if ((S_ISREG(ip->i_d.di_mode) && - ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 || - ip->i_delayed_blks > 0)) && + (VFS_I(ip)->i_size > 0 || + (VN_CACHED(VFS_I(ip)) > 0 || ip->i_delayed_blks > 0)) && (ip->i_df.if_flags & XFS_IFEXTENTS)) && (!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) { @@ -625,7 +625,7 @@ xfs_inactive( * only one with a reference to the inode. */ truncate = ((ip->i_d.di_nlink == 0) && - ((ip->i_d.di_size != 0) || (ip->i_size != 0) || + ((ip->i_d.di_size != 0) || XFS_ISIZE(ip) != 0 || (ip->i_d.di_nextents > 0) || (ip->i_delayed_blks > 0)) && S_ISREG(ip->i_d.di_mode)); @@ -639,12 +639,12 @@ xfs_inactive( if (ip->i_d.di_nlink != 0) { if ((S_ISREG(ip->i_d.di_mode) && - ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 || - ip->i_delayed_blks > 0)) && - (ip->i_df.if_flags & XFS_IFEXTENTS) && - (!(ip->i_d.di_flags & + (VFS_I(ip)->i_size > 0 || + (VN_CACHED(VFS_I(ip)) > 0 || ip->i_delayed_blks > 0)) && + (ip->i_df.if_flags & XFS_IFEXTENTS) && + (!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) || - (ip->i_delayed_blks != 0)))) { + ip->i_delayed_blks != 0))) { error = xfs_free_eofblocks(mp, ip, 0); if (error) return VN_INACTIVE_CACHE; @@ -678,7 +678,6 @@ xfs_inactive( xfs_trans_ijoin(tp, ip, 0); ip->i_d.di_size = 0; - ip->i_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); @@ -1974,11 +1973,11 @@ xfs_zero_remaining_bytes( * since nothing can read beyond eof. The space will * be zeroed when the file is extended anyway. */ - if (startoff >= ip->i_size) + if (startoff >= XFS_ISIZE(ip)) return 0; - if (endoff > ip->i_size) - endoff = ip->i_size; + if (endoff > XFS_ISIZE(ip)) + endoff = XFS_ISIZE(ip); bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp, @@ -2273,7 +2272,7 @@ xfs_change_file_space( bf->l_start += offset; break; case 2: /*SEEK_END*/ - bf->l_start += ip->i_size; + bf->l_start += XFS_ISIZE(ip); break; default: return XFS_ERROR(EINVAL); @@ -2290,7 +2289,7 @@ xfs_change_file_space( bf->l_whence = 0; startoffset = bf->l_start; - fsize = ip->i_size; + fsize = XFS_ISIZE(ip); /* * XFS_IOC_RESVSP and XFS_IOC_UNRESVSP will reserve or unreserve -- cgit v1.2.3 From 2813d682e8e6a278f94817429afd46b30875bb6e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Dec 2011 20:00:12 +0000 Subject: xfs: remove the i_new_size field in struct xfs_inode Now that we use the VFS i_size field throughout XFS there is no need for the i_new_size field any more given that the VFS i_size field gets updated in ->write_end before unlocking the page, and thus is always uptodate when writeback could see a page. Removing i_new_size also has the advantage that we will never have to trim back di_size during a failed buffered write, given that it never gets updated past i_size. Note that currently the generic direct I/O code only updates i_size after calling our end_io handler, which requires a small workaround to make sure di_size actually makes it to disk. I hope to fix this properly in the generic code. A downside is that we lose the support for parallel non-overlapping O_DIRECT appending writes that recently was added. I don't think keeping the complex and fragile i_new_size infrastructure for this is a good tradeoff - if we really care about parallel appending writers we should investigate turning the iolock into a range lock, which would also allow for parallel non-overlapping buffered writers. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_aops.c | 29 ++++++++++++---------- fs/xfs/xfs_file.c | 72 ++++++++---------------------------------------------- fs/xfs/xfs_iget.c | 1 - fs/xfs/xfs_inode.h | 2 -- fs/xfs/xfs_trace.h | 18 +++----------- 5 files changed, 30 insertions(+), 92 deletions(-) (limited to 'fs/xfs/xfs_inode.h') diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4d27ea117e0e..74b9baf36ac3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -111,8 +111,7 @@ xfs_ioend_new_eof( xfs_fsize_t bsize; bsize = ioend->io_offset + ioend->io_size; - isize = MAX(i_size_read(VFS_I(ip)), ip->i_new_size); - isize = MIN(isize, bsize); + isize = MIN(i_size_read(VFS_I(ip)), bsize); return isize > ip->i_d.di_size ? isize : 0; } @@ -126,11 +125,7 @@ static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend) } /* - * Update on-disk file size now that data has been written to disk. The - * current in-memory file size is i_size. If a write is beyond eof i_new_size - * will be the intended file size until i_size is updated. If this write does - * not extend all the way to the valid file size then restrict this update to - * the end of the write. + * Update on-disk file size now that data has been written to disk. * * This function does not block as blocking on the inode lock in IO completion * can lead to IO completion order dependency deadlocks.. If it can't get the @@ -1278,6 +1273,15 @@ xfs_end_io_direct_write( { struct xfs_ioend *ioend = iocb->private; + /* + * While the generic direct I/O code updates the inode size, it does + * so only after the end_io handler is called, which means our + * end_io handler thinks the on-disk size is outside the in-core + * size. To prevent this just update it a little bit earlier here. + */ + if (offset + size > i_size_read(ioend->io_inode)) + i_size_write(ioend->io_inode, offset + size); + /* * blockdev_direct_IO can return an error even after the I/O * completion handler was called. Thus we need to protect @@ -1340,12 +1344,11 @@ xfs_vm_write_failed( if (to > inode->i_size) { /* - * punch out the delalloc blocks we have already allocated. We - * don't call xfs_setattr() to do this as we may be in the - * middle of a multi-iovec write and so the vfs inode->i_size - * will not match the xfs ip->i_size and so it will zero too - * much. Hence we jus truncate the page cache to zero what is - * necessary and punch the delalloc blocks directly. + * Punch out the delalloc blocks we have already allocated. + * + * Don't bother with xfs_setattr given that nothing can have + * made it to disk yet as the page is still locked at this + * point. */ struct xfs_inode *ip = XFS_I(inode); xfs_fileoff_t start_fsb; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 86d5dc260464..632313926788 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -412,27 +412,6 @@ xfs_file_splice_read( return ret; } -/* - * If this was a direct or synchronous I/O that failed (such as ENOSPC) then - * part of the I/O may have been written to disk before the error occurred. In - * this case the on-disk file size may have been adjusted beyond the in-memory - * file size and now needs to be truncated back. - */ -STATIC void -xfs_aio_write_newsize_update( - struct xfs_inode *ip, - xfs_fsize_t new_size) -{ - if (new_size == ip->i_new_size) { - xfs_rw_ilock(ip, XFS_ILOCK_EXCL); - if (new_size == ip->i_new_size) - ip->i_new_size = 0; - if (ip->i_d.di_size > i_size_read(VFS_I(ip))) - ip->i_d.di_size = i_size_read(VFS_I(ip)); - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); - } -} - /* * xfs_file_splice_write() does not use xfs_rw_ilock() because * generic_file_splice_write() takes the i_mutex itself. This, in theory, @@ -451,7 +430,6 @@ xfs_file_splice_write( { struct inode *inode = outfilp->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); - xfs_fsize_t new_size; int ioflags = 0; ssize_t ret; @@ -465,20 +443,12 @@ xfs_file_splice_write( xfs_ilock(ip, XFS_IOLOCK_EXCL); - new_size = *ppos + count; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - if (new_size > i_size_read(inode)) - ip->i_new_size = new_size; - xfs_iunlock(ip, XFS_ILOCK_EXCL); - trace_xfs_file_splice_write(ip, count, *ppos, ioflags); ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags); if (ret > 0) XFS_STATS_ADD(xs_write_bytes, ret); - xfs_aio_write_newsize_update(ip, new_size); xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } @@ -673,16 +643,13 @@ xfs_file_aio_write_checks( struct file *file, loff_t *pos, size_t *count, - xfs_fsize_t *new_sizep, int *iolock) { struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); - xfs_fsize_t new_size; int error = 0; xfs_rw_ilock(ip, XFS_ILOCK_EXCL); - *new_sizep = 0; restart: error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode)); if (error) { @@ -697,15 +664,13 @@ restart: /* * If the offset is beyond the size of the file, we need to zero any * blocks that fall between the existing EOF and the start of this - * write. There is no need to issue zeroing if another in-flght IO ends - * at or before this one If zeronig is needed and we are currently - * holding the iolock shared, we need to update it to exclusive which - * involves dropping all locks and relocking to maintain correct locking - * order. If we do this, restart the function to ensure all checks and - * values are still valid. + * write. If zeroing is needed and we are currently holding the + * iolock shared, we need to update it to exclusive which involves + * dropping all locks and relocking to maintain correct locking order. + * If we do this, restart the function to ensure all checks and values + * are still valid. */ - if ((ip->i_new_size && *pos > ip->i_new_size) || - (!ip->i_new_size && *pos > i_size_read(inode))) { + if (*pos > i_size_read(inode)) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock); *iolock = XFS_IOLOCK_EXCL; @@ -714,19 +679,6 @@ restart: } error = -xfs_zero_eof(ip, *pos, i_size_read(inode)); } - - /* - * If this IO extends beyond EOF, we may need to update ip->i_new_size. - * We have already zeroed space beyond EOF (if necessary). Only update - * ip->i_new_size if this IO ends beyond any other in-flight writes. - */ - new_size = *pos + *count; - if (new_size > i_size_read(inode)) { - if (new_size > ip->i_new_size) - ip->i_new_size = new_size; - *new_sizep = new_size; - } - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); if (error) return error; @@ -772,7 +724,6 @@ xfs_file_dio_aio_write( unsigned long nr_segs, loff_t pos, size_t ocount, - xfs_fsize_t *new_size, int *iolock) { struct file *file = iocb->ki_filp; @@ -817,7 +768,7 @@ xfs_file_dio_aio_write( xfs_rw_ilock(ip, *iolock); } - ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock); + ret = xfs_file_aio_write_checks(file, &pos, &count, iolock); if (ret) return ret; @@ -855,7 +806,6 @@ xfs_file_buffered_aio_write( unsigned long nr_segs, loff_t pos, size_t ocount, - xfs_fsize_t *new_size, int *iolock) { struct file *file = iocb->ki_filp; @@ -869,7 +819,7 @@ xfs_file_buffered_aio_write( *iolock = XFS_IOLOCK_EXCL; xfs_rw_ilock(ip, *iolock); - ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock); + ret = xfs_file_aio_write_checks(file, &pos, &count, iolock); if (ret) return ret; @@ -909,7 +859,6 @@ xfs_file_aio_write( ssize_t ret; int iolock; size_t ocount = 0; - xfs_fsize_t new_size = 0; XFS_STATS_INC(xs_write_calls); @@ -929,10 +878,10 @@ xfs_file_aio_write( if (unlikely(file->f_flags & O_DIRECT)) ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, - ocount, &new_size, &iolock); + ocount, &iolock); else ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos, - ocount, &new_size, &iolock); + ocount, &iolock); if (ret <= 0) goto out_unlock; @@ -953,7 +902,6 @@ xfs_file_aio_write( } out_unlock: - xfs_aio_write_newsize_update(ip, new_size); xfs_rw_iunlock(ip, iolock); return ret; } diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 3b5b78aa3b87..8c3e46394d48 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -94,7 +94,6 @@ xfs_inode_alloc( ip->i_update_core = 0; ip->i_delayed_blks = 0; memset(&ip->i_d, 0, sizeof(xfs_icdinode_t)); - ip->i_new_size = 0; return ip; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index cd99e43fa8f0..2f27b7454085 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -246,8 +246,6 @@ typedef struct xfs_inode { xfs_icdinode_t i_d; /* most of ondisk inode */ - xfs_fsize_t i_new_size; /* size when write completes */ - /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ } xfs_inode_t; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 2aabcc9c507e..6b6df5802e95 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -891,7 +891,6 @@ DECLARE_EVENT_CLASS(xfs_file_class, __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsize_t, size) - __field(xfs_fsize_t, new_size) __field(loff_t, offset) __field(size_t, count) __field(int, flags) @@ -900,17 +899,15 @@ DECLARE_EVENT_CLASS(xfs_file_class, __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = ip->i_ino; __entry->size = ip->i_d.di_size; - __entry->new_size = ip->i_new_size; __entry->offset = offset; __entry->count = count; __entry->flags = flags; ), - TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " + TP_printk("dev %d:%d ino 0x%llx size 0x%llx " "offset 0x%llx count 0x%zx ioflags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, - __entry->new_size, __entry->offset, __entry->count, __print_flags(__entry->flags, "|", XFS_IO_FLAGS)) @@ -978,7 +975,6 @@ DECLARE_EVENT_CLASS(xfs_imap_class, __field(dev_t, dev) __field(xfs_ino_t, ino) __field(loff_t, size) - __field(loff_t, new_size) __field(loff_t, offset) __field(size_t, count) __field(int, type) @@ -990,7 +986,6 @@ DECLARE_EVENT_CLASS(xfs_imap_class, __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = ip->i_ino; __entry->size = ip->i_d.di_size; - __entry->new_size = ip->i_new_size; __entry->offset = offset; __entry->count = count; __entry->type = type; @@ -998,13 +993,11 @@ DECLARE_EVENT_CLASS(xfs_imap_class, __entry->startblock = irec ? irec->br_startblock : 0; __entry->blockcount = irec ? irec->br_blockcount : 0; ), - TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " - "offset 0x%llx count %zd type %s " - "startoff 0x%llx startblock %lld blockcount 0x%llx", + TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx count %zd " + "type %s startoff 0x%llx startblock %lld blockcount 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, - __entry->new_size, __entry->offset, __entry->count, __print_symbolic(__entry->type, XFS_IO_TYPES), @@ -1031,7 +1024,6 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class, __field(xfs_ino_t, ino) __field(loff_t, isize) __field(loff_t, disize) - __field(loff_t, new_size) __field(loff_t, offset) __field(size_t, count) ), @@ -1040,17 +1032,15 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class, __entry->ino = ip->i_ino; __entry->isize = VFS_I(ip)->i_size; __entry->disize = ip->i_d.di_size; - __entry->new_size = ip->i_new_size; __entry->offset = offset; __entry->count = count; ), - TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx new_size 0x%llx " + TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx " "offset 0x%llx count %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->disize, - __entry->new_size, __entry->offset, __entry->count) ); -- cgit v1.2.3