From 1d55a4bfd080ff4c6c96acfccfb7cdd2615ed6c2 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 20 Oct 2016 15:40:55 +1100 Subject: xfs: remove redundant assignment of ifp Remove redundant ifp = ifp statement, it does nothing. Found with static analysis by CoverityScan. Signed-off-by: Colin Ian King Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c27344cf38e1..0283b7eaf973 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5204,7 +5204,7 @@ xfs_bunmapi_cow( ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof, &eidx, &got, &new); - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp; + ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ASSERT((eidx >= 0) && (eidx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))); ASSERT(del->br_blockcount > 0); -- cgit v1.2.3 From 1be7f9be0efa4e90547f50b8188f4e70710a1173 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 20 Oct 2016 15:41:48 +1100 Subject: xfs: Fix uninitialized variable in xfs_reflink_reserve_cow_range() with gcc 4.1.2: fs/xfs/xfs_reflink.c: In function xfs_reflink_reserve_cow_range: fs/xfs/xfs_reflink.c:327: warning: error may be used uninitialized in this function Indeed, if "count" is zero, the function will return an uninitialized error value. While "count" is unlikely to be zero, this function is called through the public iomap API. Hence fix this by preinitializing error to zero. Fixes: 2a06705cd5954030 ("xfs: create delalloc extents in CoW fork") Signed-off-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 5965e9455d91..d48a7cc2fe00 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -324,7 +324,7 @@ xfs_reflink_reserve_cow_range( struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb, end_fsb; bool skipped = false; - int error; + int error = 0; trace_xfs_reflink_reserve_cow_range(ip, offset, count); -- cgit v1.2.3 From f1b8243c55ca6fd2a3898e2f586b8cfcfff684bb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 20 Oct 2016 15:42:30 +1100 Subject: xfs: add some 'static' annotations sparse reported that several variables and a function were not forward-declared anywhere and therefore should be 'static'. Found with sparse by running 'make C=2 CF=-D__CHECK_ENDIAN__ fs/xfs/' Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 2 +- fs/xfs/xfs_sysfs.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5c8e6f2ce44f..0e80993c8a59 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4826,7 +4826,7 @@ xfs_btree_calc_size( return rval; } -int +static int xfs_btree_count_blocks_helper( struct xfs_btree_cur *cur, int level, diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 5f8d55d29a11..276d3023d60f 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = { }; -struct kobj_type xfs_error_cfg_ktype = { +static struct kobj_type xfs_error_cfg_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, .default_attrs = xfs_error_attrs, }; -struct kobj_type xfs_error_ktype = { +static struct kobj_type xfs_error_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, }; -- cgit v1.2.3 From 0ee7a3f6b5b2f22bb69bfc6c60d0ea0777003098 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:44:14 +1100 Subject: xfs: don't take the IOLOCK exclusive for direct I/O page invalidation XFS historically took the iolock exclusive when invalidating pages before direct I/O operations to protect against writeback starvations. But this writeback starvation issues has been fixed a long time ago in the core writeback code, and all other file systems manage to do without the exclusive lock. Convert XFS over to avoid the exclusive lock in this case, and also move to range invalidations like done by the other file systems. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Carlos Maiolino Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 98 +++++++++++++++++-------------------------------------- 1 file changed, 30 insertions(+), 68 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a314fc7b56fa..0dc9971d3c84 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -249,6 +249,7 @@ xfs_file_dio_aio_read( struct xfs_inode *ip = XFS_I(inode); loff_t isize = i_size_read(inode); size_t count = iov_iter_count(to); + loff_t end = iocb->ki_pos + count - 1; struct iov_iter data; struct xfs_buftarg *target; ssize_t ret = 0; @@ -272,49 +273,21 @@ xfs_file_dio_aio_read( file_accessed(iocb->ki_filp); - /* - * Locking is a bit tricky here. If we take an exclusive lock for direct - * IO, we effectively serialise all new concurrent read IO to this file - * and block it behind IO that is currently in progress because IO in - * progress holds the IO lock shared. We only need to hold the lock - * exclusive to blow away the page cache, so only take lock exclusively - * if the page cache needs invalidation. This allows the normal direct - * IO case of no page cache pages to proceeed concurrently without - * serialisation. - */ xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); if (mapping->nrpages) { - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); - xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + if (ret) + goto out_unlock; /* - * The generic dio code only flushes the range of the particular - * I/O. Because we take an exclusive lock here, this whole - * sequence is considerably more expensive for us. This has a - * noticeable performance impact for any file with cached pages, - * even when outside of the range of the particular I/O. - * - * Hence, amortize the cost of the lock against a full file - * flush and reduce the chances of repeated iolock cycles going - * forward. + * Invalidate whole pages. This can return an error if we fail + * to invalidate a page, but this should never happen on XFS. + * Warn if it does fail. */ - if (mapping->nrpages) { - ret = filemap_write_and_wait(mapping); - if (ret) { - xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; - } - - /* - * Invalidate whole pages. This can return an error if - * we fail to invalidate a page, but this should never - * happen on XFS. Warn if it does fail. - */ - ret = invalidate_inode_pages2(mapping); - WARN_ON_ONCE(ret); - ret = 0; - } - xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; } data = *to; @@ -324,8 +297,9 @@ xfs_file_dio_aio_read( iocb->ki_pos += ret; iov_iter_advance(to, ret); } - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); +out_unlock: + xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } @@ -570,61 +544,49 @@ xfs_file_dio_aio_write( if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL; - /* "unaligned" here means not aligned to a filesystem block */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) - unaligned_io = 1; - /* - * We don't need to take an exclusive lock unless there page cache needs - * to be invalidated or unaligned IO is being executed. 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. + * 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. */ - if (unaligned_io || mapping->nrpages) + if ((iocb->ki_pos & mp->m_blockmask) || + ((iocb->ki_pos + count) & mp->m_blockmask)) { + unaligned_io = 1; iolock = XFS_IOLOCK_EXCL; - else + } else { iolock = XFS_IOLOCK_SHARED; - xfs_rw_ilock(ip, iolock); - - /* - * Recheck if there are cached pages that need invalidate after we got - * the iolock to protect against other threads adding new pages while - * we were waiting for the iolock. - */ - if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, iolock); - iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, iolock); } + xfs_rw_ilock(ip, iolock); + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; count = iov_iter_count(from); end = iocb->ki_pos + count - 1; - /* - * See xfs_file_dio_aio_read() for why we do a full-file flush here. - */ if (mapping->nrpages) { - ret = filemap_write_and_wait(VFS_I(ip)->i_mapping); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); if (ret) goto out; + /* * Invalidate whole pages. This can return an error if we fail * to invalidate a page, but this should never happen on XFS. * Warn if it does fail. */ - ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } /* * If we are doing unaligned IO, wait for all other IO to drain, - * otherwise demote the lock if we had to flush cached pages + * otherwise demote the lock if we had to take the exclusive lock + * for other reasons in xfs_file_aio_write_checks. */ if (unaligned_io) inode_dio_wait(inode); -- cgit v1.2.3 From fe23759eaf2f6540de20c1623f066aad967ff9c9 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 20 Oct 2016 15:44:53 +1100 Subject: xfs: remove pointless error goto in xfs_bmap_remap_alloc The commit: f65306ea xfs: map an inode's offset to an exact physical block added a pointless error0: target; remove it. Addresses-Coverity-Id: 1373865 Signed-off-by: Eric Sandeen Reviewed-by: Bill O'Donnell Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 0283b7eaf973..80bdb11ca6bf 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc( * allocating, so skip that check by pretending to be freeing. */ error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING); - if (error) - goto error0; -error0: xfs_perag_put(args.pag); if (error) trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_); -- cgit v1.2.3 From d099245297e28fc9f8493edd9d5a1f0967a72511 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 20 Oct 2016 15:45:40 +1100 Subject: xfs: unset MS_ACTIVE if mount fails As part of the inode block map intent log item recovery process, we had to set the IRECOVERY flag to prevent an unlinked inode from being truncated during the first iput call. This required us to set MS_ACTIVE so that iput puts the inode on the lru instead of immediately evicting the inode. Unfortunately, if the mount fails later on, the inodes that have been loaded (root dir and realtime) actually need to be evicted since we're aborting the mount. If we don't clear MS_ACTIVE in the failure step, those inodes are not evicted and therefore leak. The leak was found by running xfs/130 and rmmoding xfs immediately after the test. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_mount.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fc7873942bea..b341f10cf481 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1009,6 +1009,7 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: + mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); -- cgit v1.2.3 From 58d789678546d46d7bbd809dd7dab417c0f23655 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 20 Oct 2016 15:46:18 +1100 Subject: libxfs: clean up _calc_dquots_per_chunk The function xfs_calc_dquots_per_chunk takes a parameter in units of basic blocks. The kernel seems to get the units wrong, but userspace got 'fixed' by commenting out the unnecessary conversion. Fix both. cc: Signed-off-by: Darrick J. Wong Reviewed-by: Eric Sandeen Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_dquot_buf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 3cc3cf767474..ac9a003dd29a 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc( if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else - ndquots = xfs_calc_dquots_per_chunk( - XFS_BB_TO_FSB(mp, bp->b_length)); + ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), -- cgit v1.2.3 From 8cdcc8102c0cfad20513ed1bfb96e0e9963928a8 Mon Sep 17 00:00:00 2001 From: Roger Willcocks Date: Thu, 20 Oct 2016 15:48:38 +1100 Subject: libxfs: v3 inodes are only valid on crc-enabled filesystems xfs_repair was not detecting that version 3 inodes are invalid for for non-CRC filesystems. The result is specific inode corruptions go undetected and hence aren't repaired if only the version number is out of range. The core of the problem is that the XFS_DINODE_GOOD_VERSION() macro doesn't know that valid inode versions are dependent on a superblock version number. Fix this in libxfs, and propagate the new function out into the rest of xfsprogs to fix the issue. [Darrick: port to kernel from xfsprogs] Reported-by: Leslie Rhorer Signed-off-by: Roger Willcocks Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_format.h | 1 - fs/xfs/libxfs/xfs_inode_buf.c | 13 ++++++++++++- fs/xfs/libxfs/xfs_inode_buf.h | 2 ++ 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f6547fc5e016..6b7579e7b60a 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -865,7 +865,6 @@ typedef struct xfs_timestamp { * padding field for v3 inodes. */ #define XFS_DINODE_MAGIC 0x494e /* 'IN' */ -#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3) typedef struct xfs_dinode { __be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */ __be16 di_mode; /* mode and type of file */ diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 8de9a3a29589..134424fac434 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -57,6 +57,17 @@ xfs_inobp_check( } #endif +bool +xfs_dinode_good_version( + struct xfs_mount *mp, + __u8 version) +{ + if (xfs_sb_version_hascrc(&mp->m_sb)) + return version == 3; + + return version == 1 || version == 2; +} + /* * If we are doing readahead on an inode buffer, we might be in log recovery * reading an inode allocation buffer that hasn't yet been replayed, and hence @@ -91,7 +102,7 @@ xfs_inode_buf_verify( dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog)); di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) && - XFS_DINODE_GOOD_VERSION(dip->di_version); + xfs_dinode_good_version(mp, dip->di_version); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, XFS_RANDOM_ITOBP_INOTOBP))) { diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 62d9d4681c8c..3cfe12a4f58a 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -74,6 +74,8 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, struct xfs_dinode *to); +bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version); + #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #else -- cgit v1.2.3 From 4fbc2c65255f77b315a4ee3ccac397d677a35737 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:48:54 +1100 Subject: xfs: remove the same fs check from xfs_file_share_range The VFS already does the check, and the placement of this duplicate is in the way of the following locking rework. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0dc9971d3c84..194f8f396e4d 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -965,9 +965,6 @@ xfs_file_share_range( IS_SWAPFILE(inode_out)) return -ETXTBSY; - /* Reflink only works within this filesystem. */ - if (inode_in->i_sb != inode_out->i_sb) - return -EXDEV; same_inode = (inode_in->i_ino == inode_out->i_ino); /* Don't reflink dirs, pipes, sockets... */ -- cgit v1.2.3 From a62e82b35b97e60e9e22a4e303900f342139822f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:49:03 +1100 Subject: xfs: fix the same_inode check in xfs_file_share_range The VFS i_ino is an unsigned long, while XFS inode numbers are 64-bit wide, so checking i_ino for equality could lead to rate false positives on 32-bit architectures. Just compare the inode pointers themselves to be safe. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 194f8f396e4d..d5b835e82b2d 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -965,7 +965,7 @@ xfs_file_share_range( IS_SWAPFILE(inode_out)) return -ETXTBSY; - same_inode = (inode_in->i_ino == inode_out->i_ino); + same_inode = (inode_in == inode_out); /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) -- cgit v1.2.3 From 576177818e6f1e65f6109ed4a8fae8b60131c861 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:49:19 +1100 Subject: xfs: move inode locking from xfs_reflink_remap_range to xfs_file_share_range We need the iolock protection to stabilizie the IS_SWAPFILE and IS_IMMUTABLE values, as well as preventing new buffered writers re-dirtying the file data that we just wrote out. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 62 ++++++++++++++++++++++++++++++++++------------------ fs/xfs/xfs_reflink.c | 15 ------------- 2 files changed, 41 insertions(+), 36 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index d5b835e82b2d..663761edd778 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -958,38 +958,54 @@ xfs_file_share_range( inode_out = file_inode(file_out); bs = inode_out->i_sb->s_blocksize; + /* Lock both files against IO */ + same_inode = (inode_in == inode_out); + if (same_inode) { + xfs_ilock(XFS_I(inode_in), XFS_IOLOCK_EXCL); + xfs_ilock(XFS_I(inode_in), XFS_MMAPLOCK_EXCL); + } else { + xfs_lock_two_inodes(XFS_I(inode_in), XFS_I(inode_out), + XFS_IOLOCK_EXCL); + xfs_lock_two_inodes(XFS_I(inode_in), XFS_I(inode_out), + XFS_MMAPLOCK_EXCL); + } + /* Don't touch certain kinds of inodes */ + ret = -EPERM; if (IS_IMMUTABLE(inode_out)) - return -EPERM; - if (IS_SWAPFILE(inode_in) || - IS_SWAPFILE(inode_out)) - return -ETXTBSY; - - same_inode = (inode_in == inode_out); + goto out_unlock; + ret = -ETXTBSY; + if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) + goto out_unlock; /* Don't reflink dirs, pipes, sockets... */ + ret = -EISDIR; if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; + goto out_unlock; + ret = -EINVAL; if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) - return -EINVAL; + goto out_unlock; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; + goto out_unlock; /* Don't share DAX file data for now. */ if (IS_DAX(inode_in) || IS_DAX(inode_out)) - return -EINVAL; + goto out_unlock; /* Are we going all the way to the end? */ isize = i_size_read(inode_in); - if (isize == 0) - return 0; + if (isize == 0) { + ret = 0; + goto out_unlock; + } + if (len == 0) len = isize - pos_in; /* Ensure offsets don't wrap and the input is inside i_size */ if (pos_in + len < pos_in || pos_out + len < pos_out || pos_in + len > isize) - return -EINVAL; + goto out_unlock; /* Don't allow dedupe past EOF in the dest file */ if (is_dedupe) { @@ -997,7 +1013,7 @@ xfs_file_share_range( disize = i_size_read(inode_out); if (pos_out >= disize || pos_out + len > disize) - return -EINVAL; + goto out_unlock; } /* If we're linking to EOF, continue to the block boundary. */ @@ -1009,28 +1025,32 @@ xfs_file_share_range( /* Only reflink if we're aligned to block boundaries */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; + goto out_unlock; /* Don't allow overlapped reflink within the same file */ if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; + goto out_unlock; /* Wait for the completion of any pending IOs on srcfile */ ret = xfs_file_wait_for_io(inode_in, pos_in, len); if (ret) - goto out; + goto out_unlock; ret = xfs_file_wait_for_io(inode_out, pos_out, len); if (ret) - goto out; + goto out_unlock; if (is_dedupe) flags |= XFS_REFLINK_DEDUPE; ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out), pos_out, len, flags); - if (ret < 0) - goto out; -out: +out_unlock: + xfs_iunlock(XFS_I(inode_in), XFS_MMAPLOCK_EXCL); + xfs_iunlock(XFS_I(inode_in), XFS_IOLOCK_EXCL); + if (!same_inode) { + xfs_iunlock(XFS_I(inode_out), XFS_MMAPLOCK_EXCL); + xfs_iunlock(XFS_I(inode_out), XFS_IOLOCK_EXCL); + } return ret; } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index d48a7cc2fe00..3b1c1a6bb5da 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1341,15 +1341,6 @@ xfs_reflink_remap_range( trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff); - /* Lock both files against IO */ - if (src->i_ino == dest->i_ino) { - xfs_ilock(src, XFS_IOLOCK_EXCL); - xfs_ilock(src, XFS_MMAPLOCK_EXCL); - } else { - xfs_lock_two_inodes(src, dest, XFS_IOLOCK_EXCL); - xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); - } - /* * Check that the extents are the same. */ @@ -1401,12 +1392,6 @@ xfs_reflink_remap_range( goto out_error; out_error: - xfs_iunlock(src, XFS_MMAPLOCK_EXCL); - xfs_iunlock(src, XFS_IOLOCK_EXCL); - if (src->i_ino != dest->i_ino) { - xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); - xfs_iunlock(dest, XFS_IOLOCK_EXCL); - } if (error) trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_); return error; -- cgit v1.2.3 From ec40759902556f21f37641ad9f19d02c4dd4b555 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:49:55 +1100 Subject: xfs: remove xfs_file_wait_for_io filemap_write_and_wait_range operates on full pages, so there is no need for the rounding operations. Additionally this allows us to micro-optimize by skipping the second inode_dio_wait for a intra-file clone. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 39 ++++++++++----------------------------- 1 file changed, 10 insertions(+), 29 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 663761edd778..93729752bccb 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -909,32 +909,6 @@ out_unlock: return error; } -/* - * Flush all file writes out to disk. - */ -static int -xfs_file_wait_for_io( - struct inode *inode, - loff_t offset, - size_t len) -{ - loff_t rounding; - loff_t ioffset; - loff_t iendoffset; - loff_t bs; - int ret; - - bs = inode->i_sb->s_blocksize; - inode_dio_wait(inode); - - rounding = max_t(xfs_off_t, bs, PAGE_SIZE); - ioffset = round_down(offset, rounding); - iendoffset = round_up(offset + len, rounding) - 1; - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - iendoffset); - return ret; -} - /* Hook up to the VFS reflink function */ STATIC int xfs_file_share_range( @@ -1031,11 +1005,18 @@ xfs_file_share_range( if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen) goto out_unlock; - /* Wait for the completion of any pending IOs on srcfile */ - ret = xfs_file_wait_for_io(inode_in, pos_in, len); + /* Wait for the completion of any pending IOs on both files */ + inode_dio_wait(inode_in); + if (!same_inode) + inode_dio_wait(inode_out); + + ret = filemap_write_and_wait_range(inode_in->i_mapping, + pos_in, pos_in + len - 1); if (ret) goto out_unlock; - ret = xfs_file_wait_for_io(inode_out, pos_out, len); + + ret = filemap_write_and_wait_range(inode_out->i_mapping, + pos_out, pos_out + len - 1); if (ret) goto out_unlock; -- cgit v1.2.3 From 5faaf4fa0a20d38edc4df57baf24ea35b7e91178 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:50:07 +1100 Subject: xfs: merge xfs_reflink_remap_range and xfs_file_share_range There is no clear division of responsibility between those functions, so just merge them into one to keep the code simple. Also move xfs_file_wait_for_io to xfs_reflink.c together with its only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 132 +------------------------------------- fs/xfs/xfs_reflink.c | 178 +++++++++++++++++++++++++++++++++++++++------------ fs/xfs/xfs_reflink.h | 7 +- 3 files changed, 143 insertions(+), 174 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 93729752bccb..6e4f7f900fea 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -909,132 +909,6 @@ out_unlock: return error; } -/* Hook up to the VFS reflink function */ -STATIC int -xfs_file_share_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe) -{ - struct inode *inode_in; - struct inode *inode_out; - ssize_t ret; - loff_t bs; - loff_t isize; - int same_inode; - loff_t blen; - unsigned int flags = 0; - - inode_in = file_inode(file_in); - inode_out = file_inode(file_out); - bs = inode_out->i_sb->s_blocksize; - - /* Lock both files against IO */ - same_inode = (inode_in == inode_out); - if (same_inode) { - xfs_ilock(XFS_I(inode_in), XFS_IOLOCK_EXCL); - xfs_ilock(XFS_I(inode_in), XFS_MMAPLOCK_EXCL); - } else { - xfs_lock_two_inodes(XFS_I(inode_in), XFS_I(inode_out), - XFS_IOLOCK_EXCL); - xfs_lock_two_inodes(XFS_I(inode_in), XFS_I(inode_out), - XFS_MMAPLOCK_EXCL); - } - - /* Don't touch certain kinds of inodes */ - ret = -EPERM; - if (IS_IMMUTABLE(inode_out)) - goto out_unlock; - ret = -ETXTBSY; - if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) - goto out_unlock; - - /* Don't reflink dirs, pipes, sockets... */ - ret = -EISDIR; - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - goto out_unlock; - ret = -EINVAL; - if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) - goto out_unlock; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - goto out_unlock; - - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) - goto out_unlock; - - /* Are we going all the way to the end? */ - isize = i_size_read(inode_in); - if (isize == 0) { - ret = 0; - goto out_unlock; - } - - if (len == 0) - len = isize - pos_in; - - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + len < pos_in || pos_out + len < pos_out || - pos_in + len > isize) - goto out_unlock; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + len > disize) - goto out_unlock; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - goto out_unlock; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen) - goto out_unlock; - - /* Wait for the completion of any pending IOs on both files */ - inode_dio_wait(inode_in); - if (!same_inode) - inode_dio_wait(inode_out); - - ret = filemap_write_and_wait_range(inode_in->i_mapping, - pos_in, pos_in + len - 1); - if (ret) - goto out_unlock; - - ret = filemap_write_and_wait_range(inode_out->i_mapping, - pos_out, pos_out + len - 1); - if (ret) - goto out_unlock; - - if (is_dedupe) - flags |= XFS_REFLINK_DEDUPE; - ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out), - pos_out, len, flags); - -out_unlock: - xfs_iunlock(XFS_I(inode_in), XFS_MMAPLOCK_EXCL); - xfs_iunlock(XFS_I(inode_in), XFS_IOLOCK_EXCL); - if (!same_inode) { - xfs_iunlock(XFS_I(inode_out), XFS_MMAPLOCK_EXCL); - xfs_iunlock(XFS_I(inode_out), XFS_IOLOCK_EXCL); - } - return ret; -} - STATIC ssize_t xfs_file_copy_range( struct file *file_in, @@ -1046,7 +920,7 @@ xfs_file_copy_range( { int error; - error = xfs_file_share_range(file_in, pos_in, file_out, pos_out, + error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); if (error) return error; @@ -1061,7 +935,7 @@ xfs_file_clone_range( loff_t pos_out, u64 len) { - return xfs_file_share_range(file_in, pos_in, file_out, pos_out, + return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); } @@ -1084,7 +958,7 @@ xfs_file_dedupe_range( if (len > XFS_MAX_DEDUPE_LEN) len = XFS_MAX_DEDUPE_LEN; - error = xfs_file_share_range(src_file, loff, dst_file, dst_loff, + error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff, len, true); if (error) return error; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 3b1c1a6bb5da..6592daa833a4 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1312,19 +1312,26 @@ out_error: */ int xfs_reflink_remap_range( - struct xfs_inode *src, - xfs_off_t srcoff, - struct xfs_inode *dest, - xfs_off_t destoff, - xfs_off_t len, - unsigned int flags) + struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe) { + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); struct xfs_mount *mp = src->i_mount; + loff_t bs = inode_out->i_sb->s_blocksize; + bool same_inode = (inode_in == inode_out); xfs_fileoff_t sfsbno, dfsbno; xfs_filblks_t fsblen; - int error; xfs_extlen_t cowextsize; - bool is_same; + loff_t isize; + ssize_t ret; + loff_t blen; if (!xfs_sb_version_hasreflink(&mp->m_sb)) return -EOPNOTSUPP; @@ -1332,48 +1339,135 @@ xfs_reflink_remap_range( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; + /* Lock both files against IO */ + if (same_inode) { + xfs_ilock(src, XFS_IOLOCK_EXCL); + xfs_ilock(src, XFS_MMAPLOCK_EXCL); + } else { + xfs_lock_two_inodes(src, dest, XFS_IOLOCK_EXCL); + xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); + } + + /* Don't touch certain kinds of inodes */ + ret = -EPERM; + if (IS_IMMUTABLE(inode_out)) + goto out_unlock; + + ret = -ETXTBSY; + if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) + goto out_unlock; + + + /* Don't reflink dirs, pipes, sockets... */ + ret = -EISDIR; + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + goto out_unlock; + ret = -EINVAL; + if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) + goto out_unlock; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + goto out_unlock; + /* Don't reflink realtime inodes */ if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) - return -EINVAL; + goto out_unlock; + + /* Don't share DAX file data for now. */ + if (IS_DAX(inode_in) || IS_DAX(inode_out)) + goto out_unlock; + + /* Are we going all the way to the end? */ + isize = i_size_read(inode_in); + if (isize == 0) { + ret = 0; + goto out_unlock; + } + + if (len == 0) + len = isize - pos_in; + + /* Ensure offsets don't wrap and the input is inside i_size */ + if (pos_in + len < pos_in || pos_out + len < pos_out || + pos_in + len > isize) + goto out_unlock; - if (flags & ~XFS_REFLINK_ALL) - return -EINVAL; + /* Don't allow dedupe past EOF in the dest file */ + if (is_dedupe) { + loff_t disize; - trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff); + disize = i_size_read(inode_out); + if (pos_out >= disize || pos_out + len > disize) + goto out_unlock; + } + + /* If we're linking to EOF, continue to the block boundary. */ + if (pos_in + len == isize) + blen = ALIGN(isize, bs) - pos_in; + else + blen = len; + + /* Only reflink if we're aligned to block boundaries */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || + !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) + goto out_unlock; + + /* Don't allow overlapped reflink within the same file */ + if (same_inode) { + if (pos_out + blen > pos_in && pos_out < pos_in + blen) + goto out_unlock; + } + + /* Wait for the completion of any pending IOs on both files */ + inode_dio_wait(inode_in); + if (!same_inode) + inode_dio_wait(inode_out); + + ret = filemap_write_and_wait_range(inode_in->i_mapping, + pos_in, pos_in + len - 1); + if (ret) + goto out_unlock; + + ret = filemap_write_and_wait_range(inode_out->i_mapping, + pos_out, pos_out + len - 1); + if (ret) + goto out_unlock; + + trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); /* * Check that the extents are the same. */ - if (flags & XFS_REFLINK_DEDUPE) { - is_same = false; - error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest), - destoff, len, &is_same); - if (error) - goto out_error; + if (is_dedupe) { + bool is_same = false; + + ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out, + len, &is_same); + if (ret) + goto out_unlock; if (!is_same) { - error = -EBADE; - goto out_error; + ret = -EBADE; + goto out_unlock; } } - error = xfs_reflink_set_inode_flag(src, dest); - if (error) - goto out_error; + ret = xfs_reflink_set_inode_flag(src, dest); + if (ret) + goto out_unlock; /* * Invalidate the page cache so that we can clear any CoW mappings * in the destination file. */ - truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff, - PAGE_ALIGN(destoff + len) - 1); + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + len) - 1); - dfsbno = XFS_B_TO_FSBT(mp, destoff); - sfsbno = XFS_B_TO_FSBT(mp, srcoff); + dfsbno = XFS_B_TO_FSBT(mp, pos_out); + sfsbno = XFS_B_TO_FSBT(mp, pos_in); fsblen = XFS_B_TO_FSB(mp, len); - error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, - destoff + len); - if (error) - goto out_error; + ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, + pos_out + len); + if (ret) + goto out_unlock; /* * Carry the cowextsize hint from src to dest if we're sharing the @@ -1381,20 +1475,24 @@ xfs_reflink_remap_range( * has a cowextsize hint, and the destination file does not. */ cowextsize = 0; - if (srcoff == 0 && len == i_size_read(VFS_I(src)) && + if (pos_in == 0 && len == i_size_read(inode_in) && (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && - destoff == 0 && len >= i_size_read(VFS_I(dest)) && + pos_out == 0 && len >= i_size_read(inode_out) && !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) cowextsize = src->i_d.di_cowextsize; - error = xfs_reflink_update_dest(dest, destoff + len, cowextsize); - if (error) - goto out_error; + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize); -out_error: - if (error) - trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_); - return error; +out_unlock: + xfs_iunlock(src, XFS_MMAPLOCK_EXCL); + xfs_iunlock(src, XFS_IOLOCK_EXCL); + if (src->i_ino != dest->i_ino) { + xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); + xfs_iunlock(dest, XFS_IOLOCK_EXCL); + } + if (ret) + trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + return ret; } /* diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 5dc3c8ac12aa..7ddd9f69560d 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); -#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */ -#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE) -extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff, - struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len, - unsigned int flags); +extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, struct xfs_trans **tpp); extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, -- cgit v1.2.3 From d33fd776f992332be110f6ceca6dad60cb5d513f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:51:28 +1100 Subject: iomap: add IOMAP_REPORT This allows the file system to tell a FIEMAP from a read operation, and thus avoids the need to report flags that aren't actually used in the read path. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/iomap.c | 2 +- include/linux/iomap.h | 17 +++++++++++------ 2 files changed, 12 insertions(+), 7 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 013d1d36fbbf..a92204012e2d 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -561,7 +561,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, } while (len > 0) { - ret = iomap_apply(inode, start, len, 0, ops, &ctx, + ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx, iomap_fiemap_actor); /* inode with no (attribute) mapping will give ENOENT */ if (ret == -ENOENT) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index e63e288dee83..7892f55a1866 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -19,11 +19,15 @@ struct vm_fault; #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ /* - * Flags for iomap mappings: + * Flags for all iomap mappings: */ -#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */ -#define IOMAP_F_SHARED 0x02 /* block shared with another file */ -#define IOMAP_F_NEW 0x04 /* blocks have been newly allocated */ +#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ + +/* + * Flags that only need to be reported for IOMAP_REPORT requests: + */ +#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ +#define IOMAP_F_SHARED 0x20 /* block shared with another file */ /* * Magic value for blkno: @@ -42,8 +46,9 @@ struct iomap { /* * Flags for iomap_begin / iomap_end. No flag implies a read. */ -#define IOMAP_WRITE (1 << 0) -#define IOMAP_ZERO (1 << 1) +#define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */ +#define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */ +#define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ struct iomap_ops { /* -- cgit v1.2.3 From 0a0af28cad9a43d90f13c2047bd8ee3d4cffb7f3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 20 Oct 2016 15:51:50 +1100 Subject: xfs: add xfs_trim_extent This helpers allows to trim an extent to a subset of it's original range while making sure the block numbers in it remain valid, In the future xfs_trim_extent and xfs_bmapi_trim_map should probably be merged in some form. Signed-off-by: Darrick J. Wong [hch: split from a previous patch from Darrick, moved around and added support for "raw" delayed extents"] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 33 +++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_bmap.h | 2 ++ 2 files changed, 35 insertions(+) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 80bdb11ca6bf..381e7659598c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3996,6 +3996,39 @@ xfs_bmap_alloc( return xfs_bmap_btalloc(ap); } +/* Trim extent to fit a logical block range. */ +void +xfs_trim_extent( + struct xfs_bmbt_irec *irec, + xfs_fileoff_t bno, + xfs_filblks_t len) +{ + xfs_fileoff_t distance; + xfs_fileoff_t end = bno + len; + + if (irec->br_startoff + irec->br_blockcount <= bno || + irec->br_startoff >= end) { + irec->br_blockcount = 0; + return; + } + + if (irec->br_startoff < bno) { + distance = bno - irec->br_startoff; + if (isnullstartblock(irec->br_startblock)) + irec->br_startblock = DELAYSTARTBLOCK; + if (irec->br_startblock != DELAYSTARTBLOCK && + irec->br_startblock != HOLESTARTBLOCK) + irec->br_startblock += distance; + irec->br_startoff += distance; + irec->br_blockcount -= distance; + } + + if (end < irec->br_startoff + irec->br_blockcount) { + distance = irec->br_startoff + irec->br_blockcount - end; + irec->br_blockcount -= distance; + } +} + /* * Trim the returned map to the required bounds */ diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index f97db7132564..eb86af0c988b 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -190,6 +190,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, #define XFS_BMAP_TRACE_EXLIST(ip,c,w) #endif +void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, + xfs_filblks_t len); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, -- cgit v1.2.3 From 62c5ac89de7d5eecdbaa94ca3d554b0bd41578b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:52:00 +1100 Subject: xfs: handle "raw" delayed extents xfs_reflink_trim_around_shared Delalloc extents in the extent list contain the number of reserved indirect blocks in their startblock value and don't use the magic DELAYSTARTBLOCK constant. Ensure that xfs_reflink_trim_around_shared handles them properly by checking for isnullstartblock(). Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6592daa833a4..6c4c215634ec 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared( if (!xfs_is_reflink_inode(ip) || ISUNWRITTEN(irec) || irec->br_startblock == HOLESTARTBLOCK || - irec->br_startblock == DELAYSTARTBLOCK) { + irec->br_startblock == DELAYSTARTBLOCK || + isnullstartblock(irec->br_startblock)) { *shared = false; return 0; } -- cgit v1.2.3 From 5f9268ca53aca992106d74edde3e7cf6c1be60a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:53:32 +1100 Subject: xfs: don't bother looking at the refcount tree for reads There is no need to trim an extent into a shared or non-shared one, or report any flags for plain old reads. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d907eb9f8ef3..1dabf2eb136a 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -996,11 +996,14 @@ xfs_file_iomap_begin( return error; } - /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); - if (error) { - xfs_iunlock(ip, lockmode); - return error; + if (flags & (IOMAP_WRITE | IOMAP_ZERO | IOMAP_REPORT)) { + /* Trim the mapping to the nearest shared extent boundary. */ + error = xfs_reflink_trim_around_shared(ip, &imap, &shared, + &trimmed); + if (error) { + xfs_iunlock(ip, lockmode); + return error; + } } if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { -- cgit v1.2.3 From 3ba020befef030aaabbd5eb82a09f6ddf02a9542 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:53:50 +1100 Subject: xfs: optimize writes to reflink files Instead of reserving space as the first thing in write_begin move it past reading the extent in the data fork. That way we only have to read from the data fork once and can reuse that information for trimming the extent to the shared/unshared boundary. Additionally this allows to easily limit the actual write size to said boundary, and avoid a roundtrip on the ilock. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 56 ++++++++++++++------ fs/xfs/xfs_reflink.c | 142 +++++++++++++++++++++------------------------------ fs/xfs/xfs_reflink.h | 4 +- fs/xfs/xfs_trace.h | 3 +- 4 files changed, 100 insertions(+), 105 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1dabf2eb136a..436e109bb01e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay( xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx, &got, &prev); if (!eof && got.br_startoff <= offset_fsb) { + if (xfs_is_reflink_inode(ip)) { + bool shared; + + end_fsb = min(XFS_B_TO_FSB(mp, offset + count), + maxbytes_fsb); + xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb); + error = xfs_reflink_reserve_cow(ip, &got, &shared); + if (error) + goto out_unlock; + } + trace_xfs_iomap_found(ip, offset, count, 0, &got); goto done; } @@ -961,19 +972,13 @@ xfs_file_iomap_begin( struct xfs_mount *mp = ip->i_mount; struct xfs_bmbt_irec imap; xfs_fileoff_t offset_fsb, end_fsb; - bool shared, trimmed; int nimaps = 1, error = 0; + bool shared = false, trimmed = false; unsigned lockmode; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { - error = xfs_reflink_reserve_cow_range(ip, offset, length); - if (error < 0) - return error; - } - if ((flags & IOMAP_WRITE) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ @@ -981,7 +986,16 @@ xfs_file_iomap_begin( iomap); } - lockmode = xfs_ilock_data_map_shared(ip); + /* + * COW writes will allocate delalloc space, so we need to make sure + * to take the lock exclusively here. + */ + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, XFS_ILOCK_EXCL); + } else { + lockmode = xfs_ilock_data_map_shared(ip); + } ASSERT(offset <= mp->m_super->s_maxbytes); if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) @@ -991,19 +1005,24 @@ xfs_file_iomap_begin( error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); - if (error) { - xfs_iunlock(ip, lockmode); - return error; - } + if (error) + goto out_unlock; - if (flags & (IOMAP_WRITE | IOMAP_ZERO | IOMAP_REPORT)) { + if (flags & IOMAP_REPORT) { /* Trim the mapping to the nearest shared extent boundary. */ error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); - if (error) { - xfs_iunlock(ip, lockmode); - return error; - } + if (error) + goto out_unlock; + } + + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + error = xfs_reflink_reserve_cow(ip, &imap, &shared); + if (error) + goto out_unlock; + + end_fsb = imap.br_startoff + imap.br_blockcount; + length = XFS_FSB_TO_B(mp, end_fsb) - offset; } if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { @@ -1042,6 +1061,9 @@ xfs_file_iomap_begin( if (shared) iomap->flags |= IOMAP_F_SHARED; return 0; +out_unlock: + xfs_iunlock(ip, lockmode); + return error; } static int diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6c4c215634ec..9c477de3c1ac 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -228,50 +228,54 @@ xfs_reflink_trim_around_shared( } } -/* Create a CoW reservation for a range of blocks within a file. */ -static int -__xfs_reflink_reserve_cow( +/* + * Trim the passed in imap to the next shared/unshared extent boundary, and + * if imap->br_startoff points to a shared extent reserve space for it in the + * COW fork. In this case *shared is set to true, else to false. + * + * Note that imap will always contain the block numbers for the existing blocks + * in the data fork, as the upper layers need them for read-modify-write + * operations. + */ +int +xfs_reflink_reserve_cow( struct xfs_inode *ip, - xfs_fileoff_t *offset_fsb, - xfs_fileoff_t end_fsb, - bool *skipped) + struct xfs_bmbt_irec *imap, + bool *shared) { - struct xfs_bmbt_irec got, prev, imap; - xfs_fileoff_t orig_end_fsb; - int nimaps, eof = 0, error = 0; - bool shared = false, trimmed = false; + struct xfs_bmbt_irec got, prev; + xfs_fileoff_t end_fsb, orig_end_fsb; + int eof = 0, error = 0; + bool trimmed; xfs_extnum_t idx; xfs_extlen_t align; - /* Already reserved? Skip the refcount btree access. */ - xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx, + /* + * Search the COW fork extent list first. This serves two purposes: + * first this implement the speculative preallocation using cowextisze, + * so that we also unshared block adjacent to shared blocks instead + * of just the shared blocks themselves. Second the lookup in the + * extent list is generally faster than going out to the shared extent + * tree. + */ + xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx, &got, &prev); - if (!eof && got.br_startoff <= *offset_fsb) { - end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount; - trace_xfs_reflink_cow_found(ip, &got); - goto done; - } + if (!eof && got.br_startoff <= imap->br_startoff) { + trace_xfs_reflink_cow_found(ip, imap); + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); - /* Read extent from the source file. */ - nimaps = 1; - error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, - &imap, &nimaps, 0); - if (error) - goto out_unlock; - ASSERT(nimaps == 1); + *shared = true; + return 0; + } /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); + error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); if (error) - goto out_unlock; - - end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount; + return error; /* Not shared? Just report the (potentially capped) extent. */ - if (!shared) { - *skipped = true; - goto done; - } + if (!*shared) + return 0; /* * Fork all the shared blocks from our write offset until the end of @@ -279,72 +283,38 @@ __xfs_reflink_reserve_cow( */ error = xfs_qm_dqattach_locked(ip, 0); if (error) - goto out_unlock; + return error; + + end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount; align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip)); if (align) end_fsb = roundup_64(end_fsb, align); retry: - error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb, - end_fsb - *offset_fsb, &got, - &prev, &idx, eof); + error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, + end_fsb - imap->br_startoff, &got, &prev, &idx, eof); switch (error) { case 0: break; case -ENOSPC: case -EDQUOT: /* retry without any preallocation */ - trace_xfs_reflink_cow_enospc(ip, &imap); + trace_xfs_reflink_cow_enospc(ip, imap); if (end_fsb != orig_end_fsb) { end_fsb = orig_end_fsb; goto retry; } /*FALLTHRU*/ default: - goto out_unlock; + return error; } if (end_fsb != orig_end_fsb) xfs_inode_set_cowblocks_tag(ip); trace_xfs_reflink_cow_alloc(ip, &got); -done: - *offset_fsb = end_fsb; -out_unlock: - return error; -} - -/* Create a CoW reservation for part of a file. */ -int -xfs_reflink_reserve_cow_range( - struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t count) -{ - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb, end_fsb; - bool skipped = false; - int error = 0; - - trace_xfs_reflink_reserve_cow_range(ip, offset, count); - - offset_fsb = XFS_B_TO_FSBT(mp, offset); - end_fsb = XFS_B_TO_FSB(mp, offset + count); - - xfs_ilock(ip, XFS_ILOCK_EXCL); - while (offset_fsb < end_fsb) { - error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb, - &skipped); - if (error) { - trace_xfs_reflink_reserve_cow_range_error(ip, error, - _RET_IP_); - break; - } - } - xfs_iunlock(ip, XFS_ILOCK_EXCL); - - return error; + return 0; } /* Allocate all CoW reservations covering a range of blocks in a file. */ @@ -359,9 +329,8 @@ __xfs_reflink_allocate_cow( struct xfs_defer_ops dfops; struct xfs_trans *tp; xfs_fsblock_t first_block; - xfs_fileoff_t next_fsb; int nimaps = 1, error; - bool skipped = false; + bool shared; xfs_defer_init(&dfops, &first_block); @@ -372,33 +341,38 @@ __xfs_reflink_allocate_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); - next_fsb = *offset_fsb; - error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped); + /* Read extent from the source file. */ + nimaps = 1; + error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, + &imap, &nimaps, 0); + if (error) + goto out_unlock; + ASSERT(nimaps == 1); + + error = xfs_reflink_reserve_cow(ip, &imap, &shared); if (error) goto out_trans_cancel; - if (skipped) { - *offset_fsb = next_fsb; + if (!shared) { + *offset_fsb = imap.br_startoff + imap.br_blockcount; goto out_trans_cancel; } xfs_trans_ijoin(tp, ip, 0); - error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb, + error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount, XFS_BMAPI_COWFORK, &first_block, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), &imap, &nimaps, &dfops); if (error) goto out_trans_cancel; - /* We might not have been able to map the whole delalloc extent */ - *offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb); - error = xfs_defer_finish(&tp, &dfops, NULL); if (error) goto out_trans_cancel; error = xfs_trans_commit(tp); + *offset_fsb = imap.br_startoff + imap.br_blockcount; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 7ddd9f69560d..fad11607c9ad 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno, extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed); -extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip, - xfs_off_t offset, xfs_off_t count); +extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, bool *shared); extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ad188d3a83f3..72f9f6b7a76a 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); -DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range); +DEFINE_RW_EVENT(xfs_reflink_reserve_cow); DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range); DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write); @@ -3358,7 +3358,6 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece); -DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); -- cgit v1.2.3 From fa5c836ca8eb5bad6316ddfc066acbc4e2485356 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:54:14 +1100 Subject: xfs: refactor xfs_bunmapi_cow Split out two helpers for deleting delayed or real extents from the COW fork. This allows to call them directly from xfs_reflink_cow_end_io once that function is refactored to iterate the extent tree. It will also allow to reuse the delalloc deletion from xfs_bunmapi in the future. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 374 ++++++++++++++++++++++++++++------------------- fs/xfs/libxfs/xfs_bmap.h | 5 + fs/xfs/xfs_reflink.c | 5 - 3 files changed, 225 insertions(+), 159 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 381e7659598c..d7ad51132f4f 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4859,6 +4859,219 @@ xfs_bmap_split_indlen( return stolen; } +int +xfs_bmap_del_extent_delay( + struct xfs_inode *ip, + int whichfork, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec new; + int64_t da_old, da_new, da_diff = 0; + xfs_fileoff_t del_endoff, got_endoff; + xfs_filblks_t got_indlen, new_indlen, stolen; + int error = 0, state = 0; + bool isrt; + + XFS_STATS_INC(mp, xs_del_exlist); + + isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + da_old = startblockval(got->br_startblock); + da_new = 0; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + + if (isrt) { + int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount); + + do_div(rtexts, mp->m_sb.sb_rextsize); + xfs_mod_frextents(mp, rtexts); + } + + /* + * Update the inode delalloc counter now and wait to update the + * sb counters as we might have to borrow some blocks for the + * indirect block accounting. + */ + xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0, + isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + ip->i_delayed_blks -= del->br_blockcount; + + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = got->br_blockcount - del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + * + * Distribute the original indlen reservation across the two new + * extents. Steal blocks from the deleted extent if necessary. + * Stealing blocks simply fudges the fdblocks accounting below. + * Warn if either of the new indlen reservations is zero as this + * can lead to delalloc problems. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + + got->br_blockcount = del->br_startoff - got->br_startoff; + got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount); + + new.br_blockcount = got_endoff - del_endoff; + new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount); + + WARN_ON_ONCE(!got_indlen || !new_indlen); + stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen, + del->br_blockcount); + + got->br_startblock = nullstartblock((int)got_indlen); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_state = got->br_state; + new.br_startblock = nullstartblock((int)new_indlen); + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + + da_new = got_indlen + new_indlen - stolen; + del->br_blockcount -= stolen; + break; + } + + ASSERT(da_old >= da_new); + da_diff = da_old - da_new; + if (!isrt) + da_diff += del->br_blockcount; + if (da_diff) + xfs_mod_fdblocks(mp, da_diff, false); + return error; +} + +void +xfs_bmap_del_extent_cow( + struct xfs_inode *ip, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec new; + xfs_fileoff_t del_endoff, got_endoff; + int state = BMAP_COWFORK; + + XFS_STATS_INC(mp, xs_del_exlist); + + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + ASSERT(!isnullstartblock(got->br_startblock)); + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + got->br_startblock = del->br_startblock + del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount -= del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = del->br_startoff - got->br_startoff; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_blockcount = got_endoff - del_endoff; + new.br_state = got->br_state; + new.br_startblock = del->br_startblock + del->br_blockcount; + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + break; + } +} + /* * Called by xfs_bmapi to update file extent records and the btree * after removing space (or undoing a delayed allocation). @@ -5207,167 +5420,20 @@ xfs_bunmapi_cow( struct xfs_inode *ip, struct xfs_bmbt_irec *del) { - xfs_filblks_t da_new; - xfs_filblks_t da_old; - xfs_fsblock_t del_endblock = 0; - xfs_fileoff_t del_endoff; - int delay; struct xfs_bmbt_rec_host *ep; - int error; struct xfs_bmbt_irec got; - xfs_fileoff_t got_endoff; - struct xfs_ifork *ifp; - struct xfs_mount *mp; - xfs_filblks_t nblks; struct xfs_bmbt_irec new; - /* REFERENCED */ - uint qfield; - xfs_filblks_t temp; - xfs_filblks_t temp2; - int state = BMAP_COWFORK; int eof; xfs_extnum_t eidx; - mp = ip->i_mount; - XFS_STATS_INC(mp, xs_del_exlist); - ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof, - &eidx, &got, &new); - - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - ASSERT((eidx >= 0) && (eidx < ifp->if_bytes / - (uint)sizeof(xfs_bmbt_rec_t))); - ASSERT(del->br_blockcount > 0); - ASSERT(got.br_startoff <= del->br_startoff); - del_endoff = del->br_startoff + del->br_blockcount; - got_endoff = got.br_startoff + got.br_blockcount; - ASSERT(got_endoff >= del_endoff); - delay = isnullstartblock(got.br_startblock); - ASSERT(isnullstartblock(del->br_startblock) == delay); - qfield = 0; - error = 0; - /* - * If deleting a real allocation, must free up the disk space. - */ - if (!delay) { - nblks = del->br_blockcount; - qfield = XFS_TRANS_DQ_BCOUNT; - /* - * Set up del_endblock and cur for later. - */ - del_endblock = del->br_startblock + del->br_blockcount; - da_old = da_new = 0; - } else { - da_old = startblockval(got.br_startblock); - da_new = 0; - nblks = 0; - } - qfield = qfield; - nblks = nblks; - - /* - * Set flag value to use in switch statement. - * Left-contig is 2, right-contig is 1. - */ - switch (((got.br_startoff == del->br_startoff) << 1) | - (got_endoff == del_endoff)) { - case 3: - /* - * Matches the whole extent. Delete the entry. - */ - xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK); - --eidx; - break; - - case 2: - /* - * Deleting the first part of the extent. - */ - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_startoff(ep, del_endoff); - temp = got.br_blockcount - del->br_blockcount; - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - xfs_bmbt_set_startblock(ep, del_endblock); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 1: - /* - * Deleting the last part of the extent. - */ - temp = got.br_blockcount - del->br_blockcount; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 0: - /* - * Deleting the middle of the extent. - */ - temp = del->br_startoff - got.br_startoff; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - new.br_startoff = del_endoff; - temp2 = got_endoff - del_endoff; - new.br_blockcount = temp2; - new.br_state = got.br_state; - if (!delay) { - new.br_startblock = del_endblock; - } else { - temp = xfs_bmap_worst_indlen(ip, temp); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - temp2 = xfs_bmap_worst_indlen(ip, temp2); - new.br_startblock = nullstartblock((int)temp2); - da_new = temp + temp2; - while (da_new > da_old) { - if (temp) { - temp--; - da_new--; - xfs_bmbt_set_startblock(ep, - nullstartblock((int)temp)); - } - if (da_new == da_old) - break; - if (temp2) { - temp2--; - da_new--; - new.br_startblock = - nullstartblock((int)temp2); - } - } - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - xfs_iext_insert(ip, eidx + 1, 1, &new, state); - ++eidx; - break; - } - - /* - * Account for change in delayed indirect blocks. - * Nothing to do for disk quota accounting here. - */ - ASSERT(da_old >= da_new); - if (da_old > da_new) - xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false); - - return error; + &eidx, &got, &new); + ASSERT(ep); + if (isnullstartblock(got.br_startblock)) + xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &eidx, &got, del); + else + xfs_bmap_del_extent_cow(ip, &eidx, &got, del); + return 0; } /* diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index eb86af0c988b..5f18248cbac2 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -224,6 +224,11 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extnum_t nexts, xfs_fsblock_t *firstblock, struct xfs_defer_ops *dfops, int *done); int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del); +int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, + xfs_extnum_t *idx, struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del); +void xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx, xfs_extnum_t num); uint xfs_default_attroffset(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 9c477de3c1ac..09bd5dcd90cd 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -534,11 +534,6 @@ xfs_reflink_cancel_cow_blocks( trace_xfs_reflink_cancel_cow(ip, &irec); if (irec.br_startblock == DELAYSTARTBLOCK) { - /* Free a delayed allocation. */ - xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount, - false); - ip->i_delayed_blks -= irec.br_blockcount; - /* Remove the mapping from the CoW fork. */ error = xfs_bunmapi_cow(ip, &irec); if (error) -- cgit v1.2.3 From 3e0ee78f7a5a8ed43b129e9e4c5c0ff10c71df74 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:54:31 +1100 Subject: xfs: optimize xfs_reflink_cancel_cow_blocks Rewrite xfs_reflink_cancel_cow_blocks so that we only do a search for the first extent in the extent list and then iterate over the remaining extents using the extent index, passing the extent we operate on directly to xfs_bmap_del_extent_delay or xfs_bmap_del_extent_cow instead of going through xfs_bunmapi and doing yet another extent list lookup. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 51 +++++++++++++++++++++++---------------------------- 1 file changed, 23 insertions(+), 28 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 09bd5dcd90cd..1e9c589d22cc 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -511,53 +511,49 @@ xfs_reflink_cancel_cow_blocks( xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb) { - struct xfs_bmbt_irec irec; - xfs_filblks_t count_fsb; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; + xfs_extnum_t idx; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error = 0; - int nimaps; + int error = 0, eof = 0; if (!xfs_is_reflink_inode(ip)) return 0; - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - break; - ASSERT(nimaps == 1); + xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx, + &got, &prev); + if (eof) + return 0; - trace_xfs_reflink_cancel_cow(ip, &irec); + while (got.br_startoff < end_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + trace_xfs_reflink_cancel_cow(ip, &del); - if (irec.br_startblock == DELAYSTARTBLOCK) { - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); + if (isnullstartblock(del.br_startblock)) { + error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, + &idx, &got, &del); if (error) break; - } else if (irec.br_startblock == HOLESTARTBLOCK) { - /* empty */ } else { xfs_trans_ijoin(*tpp, ip, 0); xfs_defer_init(&dfops, &firstfsb); /* Free the CoW orphan record. */ error = xfs_refcount_free_cow_extent(ip->i_mount, - &dfops, irec.br_startblock, - irec.br_blockcount); + &dfops, del.br_startblock, + del.br_blockcount); if (error) break; xfs_bmap_add_free(ip->i_mount, &dfops, - irec.br_startblock, irec.br_blockcount, + del.br_startblock, del.br_blockcount, NULL); /* Update quota accounting */ xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT, - -(long)irec.br_blockcount); + -(long)del.br_blockcount); /* Roll the transaction */ error = xfs_defer_finish(tpp, &dfops, ip); @@ -567,13 +563,12 @@ xfs_reflink_cancel_cow_blocks( } /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); - if (error) - break; + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); } - /* Roll on... */ - offset_fsb = irec.br_startoff + irec.br_blockcount; + if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)) + return 0; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } return error; -- cgit v1.2.3 From c1112b6e626637ec09319883b63e705a931c398b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:54:45 +1100 Subject: xfs: optimize xfs_reflink_end_cow Instead of doing a full extent list search for each extent that is to be deleted using xfs_bmapi_read and then doing another one inside of xfs_bunmapi_cow use the same scheme that xfs_bumapi uses: look up the last extent to be deleted and then use the extent index to walk downward until we are outside the range to be deleted. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 119 ++++++++++++++++++++++++--------------------------- fs/xfs/xfs_trace.h | 1 - 2 files changed, 56 insertions(+), 64 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 1e9c589d22cc..cd308f119e20 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -633,25 +633,26 @@ xfs_reflink_end_cow( xfs_off_t offset, xfs_off_t count) { - struct xfs_bmbt_irec irec; - struct xfs_bmbt_irec uirec; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; struct xfs_trans *tp; xfs_fileoff_t offset_fsb; xfs_fileoff_t end_fsb; - xfs_filblks_t count_fsb; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error; + int error, eof = 0; unsigned int resblks; - xfs_filblks_t ilen; xfs_filblks_t rlen; - int nimaps; + xfs_extnum_t idx; trace_xfs_reflink_end_cow(ip, offset, count); + /* No COW extents? That's easy! */ + if (ifp->if_bytes == 0) + return 0; + offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count); - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); /* Start a rolling transaction to switch the mappings */ resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK); @@ -663,72 +664,65 @@ xfs_reflink_end_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - /* Read extent from the source file */ - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - goto out_cancel; - ASSERT(nimaps == 1); + xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx, + &got, &prev); - ASSERT(irec.br_startblock != DELAYSTARTBLOCK); - trace_xfs_reflink_cow_remap(ip, &irec); + /* If there is a hole at end_fsb - 1 go to the previous extent */ + if (eof || got.br_startoff > end_fsb) { + ASSERT(idx > 0); + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); + } - /* - * We can have a hole in the CoW fork if part of a directio - * write is CoW but part of it isn't. - */ - rlen = ilen = irec.br_blockcount; - if (irec.br_startblock == HOLESTARTBLOCK) + /* Walk backwards until we're out of the I/O range... */ + while (got.br_startoff + got.br_blockcount > offset_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + + /* Extent delete may have bumped idx forward */ + if (!del.br_blockcount) { + idx--; goto next_extent; + } + + ASSERT(!isnullstartblock(got.br_startblock)); /* Unmap the old blocks in the data fork. */ - while (rlen) { - xfs_defer_init(&dfops, &firstfsb); - error = __xfs_bunmapi(tp, ip, irec.br_startoff, - &rlen, 0, 1, &firstfsb, &dfops); - if (error) - goto out_defer; - - /* - * Trim the extent to whatever got unmapped. - * Remember, bunmapi works backwards. - */ - uirec.br_startblock = irec.br_startblock + rlen; - uirec.br_startoff = irec.br_startoff + rlen; - uirec.br_blockcount = irec.br_blockcount - rlen; - irec.br_blockcount = rlen; - trace_xfs_reflink_cow_remap_piece(ip, &uirec); + xfs_defer_init(&dfops, &firstfsb); + rlen = del.br_blockcount; + error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1, + &firstfsb, &dfops); + if (error) + goto out_defer; - /* Free the CoW orphan record. */ - error = xfs_refcount_free_cow_extent(tp->t_mountp, - &dfops, uirec.br_startblock, - uirec.br_blockcount); - if (error) - goto out_defer; + /* Trim the extent to whatever got unmapped. */ + if (rlen) { + xfs_trim_extent(&del, del.br_startoff + rlen, + del.br_blockcount - rlen); + } + trace_xfs_reflink_cow_remap(ip, &del); - /* Map the new blocks into the data fork. */ - error = xfs_bmap_map_extent(tp->t_mountp, &dfops, - ip, &uirec); - if (error) - goto out_defer; + /* Free the CoW orphan record. */ + error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops, + del.br_startblock, del.br_blockcount); + if (error) + goto out_defer; - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &uirec); - if (error) - goto out_defer; + /* Map the new blocks into the data fork. */ + error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del); + if (error) + goto out_defer; - error = xfs_defer_finish(&tp, &dfops, ip); - if (error) - goto out_defer; - } + /* Remove the mapping from the CoW fork. */ + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); + + error = xfs_defer_finish(&tp, &dfops, ip); + if (error) + goto out_defer; next_extent: - /* Roll on... */ - offset_fsb = irec.br_startoff + ilen; + if (idx < 0) + break; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } error = xfs_trans_commit(tp); @@ -739,7 +733,6 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); -out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 72f9f6b7a76a..0907752be62d 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3356,7 +3356,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec); 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); -DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece); DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); -- cgit v1.2.3 From 64e6428ddd00f864e3ca105f914a2b6920c2bc41 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:54:59 +1100 Subject: xfs: remove xfs_bunmapi_cow Since no one uses it anymore. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 22 ---------------------- fs/xfs/libxfs/xfs_bmap.h | 1 - 2 files changed, 23 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index d7ad51132f4f..c6eb21940783 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5414,28 +5414,6 @@ done: return error; } -/* Remove an extent from the CoW fork. Similar to xfs_bmap_del_extent. */ -int -xfs_bunmapi_cow( - struct xfs_inode *ip, - struct xfs_bmbt_irec *del) -{ - struct xfs_bmbt_rec_host *ep; - struct xfs_bmbt_irec got; - struct xfs_bmbt_irec new; - int eof; - xfs_extnum_t eidx; - - ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof, - &eidx, &got, &new); - ASSERT(ep); - if (isnullstartblock(got.br_startblock)) - xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &eidx, &got, del); - else - xfs_bmap_del_extent_cow(ip, &eidx, &got, del); - return 0; -} - /* * Unmap (remove) blocks from a file. * If nexts is nonzero then the number of extents to remove is limited to diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 5f18248cbac2..7cae6ec27fa6 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -223,7 +223,6 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, int flags, xfs_extnum_t nexts, xfs_fsblock_t *firstblock, struct xfs_defer_ops *dfops, int *done); -int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del); int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, xfs_extnum_t *idx, struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); -- cgit v1.2.3 From c663e29f8885269c1608b5aa6057729fa9267b35 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 Oct 2016 14:20:25 +1100 Subject: fs: Do to trim high file position bits in iomap_page_mkwrite_actor iomap_page_mkwrite_actor() calls __block_write_begin_int() with position masked as pos & ~PAGE_MASK which is equivalent to pos & (PAGE_SIZE-1). Thus it masks off high bits of file position. However __block_write_begin_int() expects full file position on input. This does not cause any visible issues because all __block_write_begin_int() really cares about are low file position bits but still it is a bug waiting to happen. Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/iomap.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index a92204012e2d..a8ee8c33ca78 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, struct page *page = data; int ret; - ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length, - NULL, iomap); + ret = __block_write_begin_int(page, pos, length, NULL, iomap); if (ret) return ret; -- cgit v1.2.3 From 7b7381f043568224af798b1decb607dca97b4114 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 24 Oct 2016 14:21:00 +1100 Subject: xfs: fix up inode cowblocks tracking tracepoints These calls are still using the eofblocks tracepoints. The cowblocks equivalents are already defined, we just aren't actually calling them. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 14796b744e0a..f295049db681 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1656,9 +1656,9 @@ void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_set_eofblocks_tag(ip); + trace_xfs_inode_set_cowblocks_tag(ip); return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, - trace_xfs_perag_set_eofblocks, + trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1666,7 +1666,7 @@ void xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_clear_eofblocks_tag(ip); + trace_xfs_inode_clear_cowblocks_tag(ip); return __xfs_inode_clear_eofblocks_tag(ip, - trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG); + trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } -- cgit v1.2.3 From c17a8ef43d6b80ed3519b828c37d18645445949f Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 24 Oct 2016 14:21:08 +1100 Subject: xfs: clear cowblocks tag when cow fork is emptied The background cowblocks scan job takes care of scanning for inodes with potentially lingering blocks in the cow fork and clearing them out. If the background scanner reclaims the cow fork blocks, however, it doesn't immediately clear the cowblocks tag from the inode. Instead, the inode remains tagged until the background scanner comes around again, discovers the inode cow fork has no blocks, clears the tag and fires the trace_xfs_inode_free_cowblocks_invalid() tracepoint to indicate that the inode may have been incorrectly tagged. This is not a major functional problem as the tag is ultimately cleared. Nonetheless, clear the tag when an inode cow fork is explicitly emptied to avoid the extra round trip through the background scanner and spurious "invalid" tracepoint. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cd308f119e20..a279b4e7f5fe 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -567,10 +567,14 @@ xfs_reflink_cancel_cow_blocks( } if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)) - return 0; + break; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } + /* clear tag if cow fork is emptied */ + if (!ifp->if_bytes) + xfs_inode_clear_cowblocks_tag(ip); + return error; } -- cgit v1.2.3 From b77428b12b55437b28deae738d9ce8b2e0663b55 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 24 Oct 2016 14:21:18 +1100 Subject: xfs: defer should abort intent items if the trans roll fails If the deferred ops transaction roll fails, we need to abort the intent items if we haven't already logged a done item for it, regardless of whether or not the deferred ops has had a transaction committed. Dave found this while running generic/388. Move the tracepoint to make it easier to track object lifetimes. Reported-by: Dave Chinner Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_defer.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 613c5cf19436..5c2929f94bd3 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -199,9 +199,9 @@ xfs_defer_intake_work( struct xfs_defer_pending *dfp; list_for_each_entry(dfp, &dop->dop_intake, dfp_list) { - trace_xfs_defer_intake_work(tp->t_mountp, dfp); dfp->dfp_intent = dfp->dfp_type->create_intent(tp, dfp->dfp_count); + trace_xfs_defer_intake_work(tp->t_mountp, dfp); list_sort(tp->t_mountp, &dfp->dfp_work, dfp->dfp_type->diff_items); list_for_each(li, &dfp->dfp_work) @@ -221,21 +221,14 @@ xfs_defer_trans_abort( struct xfs_defer_pending *dfp; trace_xfs_defer_trans_abort(tp->t_mountp, dop); - /* - * If the transaction was committed, drop the intent reference - * since we're bailing out of here. The other reference is - * dropped when the intent hits the AIL. If the transaction - * was not committed, the intent is freed by the intent item - * unlock handler on abort. - */ - if (!dop->dop_committed) - return; - /* Abort intent items. */ + /* Abort intent items that don't have a done item. */ list_for_each_entry(dfp, &dop->dop_pending, dfp_list) { trace_xfs_defer_pending_abort(tp->t_mountp, dfp); - if (!dfp->dfp_done) + if (dfp->dfp_intent && !dfp->dfp_done) { dfp->dfp_type->abort_intent(dfp->dfp_intent); + dfp->dfp_intent = NULL; + } } /* Shut down FS. */ -- cgit v1.2.3 From 399372349a7f9b2d7e56e4fa4467c69822d07024 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Tue, 8 Nov 2016 12:53:33 +1100 Subject: xfs: don't skip cow forks w/ delalloc blocks in cowblocks scan The cowblocks background scanner currently clears the cowblocks tag for inodes without any real allocations in the cow fork. This excludes inodes with only delalloc blocks in the cow fork. While we might never expect to clear delalloc blocks from the cow fork in the background scanner, it is not necessarily correct to clear the cowblocks tag from such inodes. For example, if the background scanner happens to process an inode between a buffered write and writeback, the scanner catches the inode in a state after delalloc blocks have been allocated to the cow fork but before the delalloc blocks have been converted to real blocks by writeback. The background scanner then incorrectly clears the cowblocks tag, even if part of the aforementioned delalloc reservation will not be remapped to the data fork (i.e., extra blocks due to the cowextsize hint). This means that any such additional blocks in the cow fork might never be reclaimed by the background scanner and could persist until the inode itself is reclaimed. To address this problem, only skip and clear inodes without any cow fork allocations whatsoever from the background scanner. While we generally do not want to cancel delalloc reservations from the background scanner, the pagecache dirty check following the cowblocks check should prevent that situation. If we do end up with delalloc cow fork blocks without a dirty address space mapping, this is probably an indication that something has gone wrong and the blocks should be reclaimed, as they may never be converted to a real allocation. Signed-off-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 7 ++++++- fs/xfs/xfs_reflink.c | 34 ---------------------------------- fs/xfs/xfs_reflink.h | 2 -- 3 files changed, 6 insertions(+), 37 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index f295049db681..1b4861f5d3d8 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1580,10 +1580,15 @@ xfs_inode_free_cowblocks( struct xfs_eofblocks *eofb = args; bool need_iolock = true; int match; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); - if (!xfs_reflink_has_real_cow_blocks(ip)) { + /* + * Just clear the tag if we have an empty cow fork or none at all. It's + * possible the inode was fully unshared since it was originally tagged. + */ + if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) { trace_xfs_inode_free_cowblocks_invalid(ip); xfs_inode_clear_cowblocks_tag(ip); return 0; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index a279b4e7f5fe..c06904893202 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1697,37 +1697,3 @@ out: trace_xfs_reflink_unshare_error(ip, error, _RET_IP_); return error; } - -/* - * Does this inode have any real CoW reservations? - */ -bool -xfs_reflink_has_real_cow_blocks( - struct xfs_inode *ip) -{ - struct xfs_bmbt_irec irec; - struct xfs_ifork *ifp; - struct xfs_bmbt_rec_host *gotp; - xfs_extnum_t idx; - - if (!xfs_is_reflink_inode(ip)) - return false; - - /* Go find the old extent in the CoW fork. */ - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - gotp = xfs_iext_bno_to_ext(ifp, 0, &idx); - while (gotp) { - xfs_bmbt_get_all(gotp, &irec); - - if (!isnullstartblock(irec.br_startblock)) - return true; - - /* Roll on... */ - idx++; - if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t)) - break; - gotp = xfs_iext_get_ext(ifp, idx); - } - - return false; -} diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index fad11607c9ad..97ea9b487884 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -50,6 +50,4 @@ extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); -extern bool xfs_reflink_has_real_cow_blocks(struct xfs_inode *ip); - #endif /* __XFS_REFLINK_H */ -- cgit v1.2.3 From 04197b341f23b908193308b8d63d17ff23232598 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Tue, 8 Nov 2016 12:54:14 +1100 Subject: xfs: don't BUG() on mixed direct and mapped I/O We've had reports of generic/095 causing XFS to BUG() in __xfs_get_blocks() due to the existence of delalloc blocks on a direct I/O read. generic/095 issues a mix of various types of I/O, including direct and memory mapped I/O to a single file. This is clearly not supported behavior and is known to lead to such problems. E.g., the lack of exclusion between the direct I/O and write fault paths means that a write fault can allocate delalloc blocks in a region of a file that was previously a hole after the direct read has attempted to flush/inval the file range, but before it actually reads the block mapping. In turn, the direct read discovers a delalloc extent and cannot proceed. While the appropriate solution here is to not mix direct and memory mapped I/O to the same regions of the same file, the current BUG_ON() behavior is probably overkill as it can crash the entire system. Instead, localize the failure to the I/O in question by returning an error for a direct I/O that cannot be handled safely due to delalloc blocks. Be careful to allow the case of a direct write to post-eof delalloc blocks. This can occur due to speculative preallocation and is safe as post-eof blocks are not accompanied by dirty pages in pagecache (conversely, preallocation within eof must have been zeroed, and thus dirtied, before the inode size could have been increased beyond said blocks). Finally, provide an additional warning if a direct I/O write occurs while the file is memory mapped. This may not catch all problematic scenarios, but provides a hint that some known-to-be-problematic I/O methods are in use. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_aops.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3e57a56cf829..2693ba84ec25 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1361,6 +1361,26 @@ __xfs_get_blocks( if (error) goto out_unlock; + /* + * The only time we can ever safely find delalloc blocks on direct I/O + * is a dio write to post-eof speculative preallocation. All other + * scenarios are indicative of a problem or misuse (such as mixing + * direct and mapped I/O). + * + * The file may be unmapped by the time we get here so we cannot + * reliably fail the I/O based on mapping. Instead, fail the I/O if this + * is a read or a write within eof. Otherwise, carry on but warn as a + * precuation if the file happens to be mapped. + */ + if (direct && imap.br_startblock == DELAYSTARTBLOCK) { + if (!create || offset < i_size_read(VFS_I(ip))) { + WARN_ON_ONCE(1); + error = -EIO; + goto out_unlock; + } + WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping)); + } + /* for DAX, we convert unwritten extents directly */ if (create && (!nimaps || @@ -1450,8 +1470,6 @@ __xfs_get_blocks( (new || ISUNWRITTEN(&imap)))) set_buffer_new(bh_result); - BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK); - return 0; out_unlock: -- cgit v1.2.3 From 4dfce57db6354603641132fac3c887614e3ebe81 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 8 Nov 2016 12:55:18 +1100 Subject: xfs: fix up xfs_swap_extent_forks inline extent handling There have been several reports over the years of NULL pointer dereferences in xfs_trans_log_inode during xfs_fsr processes, when the process is doing an fput and tearing down extents on the temporary inode, something like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 PID: 29439 TASK: ffff880550584fa0 CPU: 6 COMMAND: "xfs_fsr" [exception RIP: xfs_trans_log_inode+0x10] #9 [ffff8800a57bbbe0] xfs_bunmapi at ffffffffa037398e [xfs] #10 [ffff8800a57bbce8] xfs_itruncate_extents at ffffffffa0391b29 [xfs] #11 [ffff8800a57bbd88] xfs_inactive_truncate at ffffffffa0391d0c [xfs] #12 [ffff8800a57bbdb8] xfs_inactive at ffffffffa0392508 [xfs] #13 [ffff8800a57bbdd8] xfs_fs_evict_inode at ffffffffa035907e [xfs] #14 [ffff8800a57bbe00] evict at ffffffff811e1b67 #15 [ffff8800a57bbe28] iput at ffffffff811e23a5 #16 [ffff8800a57bbe58] dentry_kill at ffffffff811dcfc8 #17 [ffff8800a57bbe88] dput at ffffffff811dd06c #18 [ffff8800a57bbea8] __fput at ffffffff811c823b #19 [ffff8800a57bbef0] ____fput at ffffffff811c846e #20 [ffff8800a57bbf00] task_work_run at ffffffff81093b27 #21 [ffff8800a57bbf30] do_notify_resume at ffffffff81013b0c #22 [ffff8800a57bbf50] int_signal at ffffffff8161405d As it turns out, this is because the i_itemp pointer, along with the d_ops pointer, has been overwritten with zeros when we tear down the extents during truncate. When the in-core inode fork on the temporary inode used by xfs_fsr was originally set up during the extent swap, we mistakenly looked at di_nextents to determine whether all extents fit inline, but this misses extents generated by speculative preallocation; we should be using if_bytes instead. This mistake corrupts the in-memory inode, and code in xfs_iext_remove_inline eventually gets bad inputs, causing it to memmove and memset incorrect ranges; this became apparent because the two values in ifp->if_u2.if_inline_ext[1] contained what should have been in d_ops and i_itemp; they were memmoved due to incorrect array indexing and then the original locations were zeroed with memset, again due to an array overrun. Fix this by properly using i_df.if_bytes to determine the number of extents, not di_nextents. Thanks to dchinner for looking at this with me and spotting the root cause. Cc: stable@vger.kernel.org Signed-off-by: Eric Sandeen Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_bmap_util.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 552465e011ec..47074e0c33f3 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1792,6 +1792,7 @@ xfs_swap_extent_forks( struct xfs_ifork tempifp, *ifp, *tifp; int aforkblks = 0; int taforkblks = 0; + xfs_extnum_t nextents; __uint64_t tmp; int error; @@ -1881,7 +1882,8 @@ xfs_swap_extent_forks( * pointer. Otherwise it's already NULL or * pointing to the extent. */ - if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) { + nextents = ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + if (nextents <= XFS_INLINE_EXTS) { ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext; } @@ -1900,7 +1902,8 @@ xfs_swap_extent_forks( * pointer. Otherwise it's already NULL or * pointing to the extent. */ - if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) { + nextents = tip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + if (nextents <= XFS_INLINE_EXTS) { tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext; } -- cgit v1.2.3 From 5d829300bee000980a09ac2ccb761cb25867b67c Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 8 Nov 2016 12:59:42 +1100 Subject: xfs: provide helper for counting extents from if_bytes The open-coded pattern: ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t) is all over the xfs code; provide a new helper xfs_iext_count(ifp) to count the number of inline extents in an inode fork. [dchinner: pick up several missed conversions] Signed-off-by: Eric Sandeen Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 49 ++++++++++++++++++++---------------------- fs/xfs/libxfs/xfs_inode_fork.c | 31 +++++++++++++++----------- fs/xfs/libxfs/xfs_inode_fork.h | 1 + fs/xfs/xfs_bmap_util.c | 34 ++++++++++++----------------- fs/xfs/xfs_inode_item.c | 4 ++-- fs/xfs/xfs_ioctl.c | 6 ++---- fs/xfs/xfs_qm.c | 2 +- fs/xfs/xfs_reflink.c | 4 ++-- 8 files changed, 64 insertions(+), 67 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c6eb21940783..42f4e7a84e2e 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -515,7 +515,7 @@ xfs_bmap_trace_exlist( state |= BMAP_ATTRFORK; ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(cnt == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))); + ASSERT(cnt == xfs_iext_count(ifp)); for (idx = 0; idx < cnt; idx++) trace_xfs_extlist(ip, idx, whichfork, caller_ip); } @@ -811,7 +811,7 @@ try_another_ag: XFS_BTREE_LONG_PTRS); arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); for (cnt = i = 0; i < nextents; i++) { ep = xfs_iext_get_ext(ifp, i); if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) { @@ -1296,7 +1296,7 @@ xfs_bmap_read_extents( /* * Here with bp and block set to the leftmost leaf node in the tree. */ - room = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + room = xfs_iext_count(ifp); i = 0; /* * Loop over all leaf nodes. Copy information to the extent records. @@ -1361,7 +1361,7 @@ xfs_bmap_read_extents( return error; block = XFS_BUF_TO_BLOCK(bp); } - ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))); + ASSERT(i == xfs_iext_count(ifp)); ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork)); XFS_BMAP_TRACE_EXLIST(ip, i, whichfork); return 0; @@ -1404,7 +1404,7 @@ xfs_bmap_search_multi_extents( if (lastx > 0) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp); } - if (lastx < (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) { + if (lastx < xfs_iext_count(ifp)) { xfs_bmbt_get_all(ep, gotp); *eofp = 0; } else { @@ -1497,7 +1497,7 @@ xfs_bmap_first_unused( (error = xfs_iread_extents(tp, ip, whichfork))) return error; lowest = *first_unused; - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) { xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx); off = xfs_bmbt_get_startoff(ep); @@ -1582,7 +1582,7 @@ xfs_bmap_last_extent( return error; } - nextents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); if (nextents == 0) { *is_empty = 1; return 0; @@ -1735,7 +1735,7 @@ xfs_bmap_add_extent_delay_real( &bma->ip->i_d.di_nextents); ASSERT(bma->idx >= 0); - ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(bma->idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); ASSERT(!bma->cur || (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); @@ -1794,7 +1794,7 @@ xfs_bmap_add_extent_delay_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) { + if (bma->idx < xfs_iext_count(ifp) - 1) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT); @@ -2300,7 +2300,7 @@ xfs_bmap_add_extent_unwritten_real( ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); ASSERT(*idx >= 0); - ASSERT(*idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); XFS_STATS_INC(mp, xs_add_exlist); @@ -2356,7 +2356,7 @@ xfs_bmap_add_extent_unwritten_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) { + if (*idx < xfs_iext_count(&ip->i_df) - 1) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT); if (isnullstartblock(RIGHT.br_startblock)) @@ -2836,7 +2836,7 @@ xfs_bmap_add_extent_hole_delay( * Check and set flags if the current (right) segment exists. * If it doesn't exist, we're converting the hole at end-of-file. */ - if (*idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) { + if (*idx < xfs_iext_count(ifp)) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right); @@ -2966,7 +2966,7 @@ xfs_bmap_add_extent_hole_real( ifp = XFS_IFORK_PTR(bma->ip, whichfork); ASSERT(bma->idx >= 0); - ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(bma->idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); ASSERT(!bma->cur || !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); @@ -2992,7 +2992,7 @@ xfs_bmap_add_extent_hole_real( * Check and set flags if this segment has a current value. * Not true if we're inserting into the "hole" at eof. */ - if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) { + if (bma->idx < xfs_iext_count(ifp)) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx), &right); if (isnullstartblock(right.br_startblock)) @@ -4221,7 +4221,7 @@ xfs_bmapi_read( break; /* Else go on to the next record. */ - if (++lastx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t)) + if (++lastx < xfs_iext_count(ifp)) xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx), &got); else eof = 1; @@ -4733,7 +4733,7 @@ xfs_bmapi_write( /* Else go on to the next record. */ bma.prev = bma.got; - if (++bma.idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t)) { + if (++bma.idx < xfs_iext_count(ifp)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma.idx), &bma.got); } else @@ -4885,7 +4885,7 @@ xfs_bmap_del_extent_delay( da_new = 0; ASSERT(*idx >= 0); - ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(del->br_blockcount > 0); ASSERT(got->br_startoff <= del->br_startoff); ASSERT(got_endoff >= del_endoff); @@ -5013,7 +5013,7 @@ xfs_bmap_del_extent_cow( got_endoff = got->br_startoff + got->br_blockcount; ASSERT(*idx >= 0); - ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(del->br_blockcount > 0); ASSERT(got->br_startoff <= del->br_startoff); ASSERT(got_endoff >= del_endoff); @@ -5119,8 +5119,7 @@ xfs_bmap_del_extent( state |= BMAP_COWFORK; ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT((*idx >= 0) && (*idx < ifp->if_bytes / - (uint)sizeof(xfs_bmbt_rec_t))); + ASSERT((*idx >= 0) && (*idx < xfs_iext_count(ifp))); ASSERT(del->br_blockcount > 0); ep = xfs_iext_get_ext(ifp, *idx); xfs_bmbt_get_all(ep, &got); @@ -5445,7 +5444,6 @@ __xfs_bunmapi( int logflags; /* transaction logging flags */ xfs_extlen_t mod; /* rt extent offset */ xfs_mount_t *mp; /* mount structure */ - xfs_extnum_t nextents; /* number of file extents */ xfs_bmbt_irec_t prev; /* previous extent record */ xfs_fileoff_t start; /* first file offset deleted */ int tmp_logflags; /* partial logging flags */ @@ -5477,8 +5475,7 @@ __xfs_bunmapi( if (!(ifp->if_flags & XFS_IFEXTENTS) && (error = xfs_iread_extents(tp, ip, whichfork))) return error; - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); - if (nextents == 0) { + if (xfs_iext_count(ifp) == 0) { *rlen = 0; return 0; } @@ -5963,7 +5960,7 @@ xfs_bmse_shift_one( mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); - total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + total_extents = xfs_iext_count(ifp); xfs_bmbt_get_all(gotp, &got); @@ -6140,7 +6137,7 @@ xfs_bmap_shift_extents( * are collapsing out, so we cannot use the count of real extents here. * Instead we have to calculate it from the incore fork. */ - total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + total_extents = xfs_iext_count(ifp); if (total_extents == 0) { *done = 1; goto del_cursor; @@ -6200,7 +6197,7 @@ xfs_bmap_shift_extents( * count can change. Update the total and grade the next record. */ if (direction == SHIFT_LEFT) { - total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + total_extents = xfs_iext_count(ifp); stop_extent = total_extents; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 5dd56d3dbb3a..5fbe24c31679 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -775,6 +775,13 @@ xfs_idestroy_fork( } } +/* Count number of incore extents based on if_bytes */ +xfs_extnum_t +xfs_iext_count(struct xfs_ifork *ifp) +{ + return ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); +} + /* * Convert in-core extents to on-disk form * @@ -803,7 +810,7 @@ xfs_iextents_copy( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(ifp->if_bytes > 0); - nrecs = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nrecs = xfs_iext_count(ifp); XFS_BMAP_TRACE_EXLIST(ip, nrecs, whichfork); ASSERT(nrecs > 0); @@ -941,7 +948,7 @@ xfs_iext_get_ext( xfs_extnum_t idx) /* index of target extent */ { ASSERT(idx >= 0); - ASSERT(idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t)); + ASSERT(idx < xfs_iext_count(ifp)); if ((ifp->if_flags & XFS_IFEXTIREC) && (idx == 0)) { return ifp->if_u1.if_ext_irec->er_extbuf; @@ -1017,7 +1024,7 @@ xfs_iext_add( int new_size; /* size of extents after adding */ xfs_extnum_t nextents; /* number of extents in file */ - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); ASSERT((idx >= 0) && (idx <= nextents)); byte_diff = ext_diff * sizeof(xfs_bmbt_rec_t); new_size = ifp->if_bytes + byte_diff; @@ -1241,7 +1248,7 @@ xfs_iext_remove( trace_xfs_iext_remove(ip, idx, state, _RET_IP_); ASSERT(ext_diff > 0); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); new_size = (nextents - ext_diff) * sizeof(xfs_bmbt_rec_t); if (new_size == 0) { @@ -1270,7 +1277,7 @@ xfs_iext_remove_inline( ASSERT(!(ifp->if_flags & XFS_IFEXTIREC)); ASSERT(idx < XFS_INLINE_EXTS); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); ASSERT(((nextents - ext_diff) > 0) && (nextents - ext_diff) < XFS_INLINE_EXTS); @@ -1309,7 +1316,7 @@ xfs_iext_remove_direct( ASSERT(!(ifp->if_flags & XFS_IFEXTIREC)); new_size = ifp->if_bytes - (ext_diff * sizeof(xfs_bmbt_rec_t)); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); if (new_size == 0) { xfs_iext_destroy(ifp); @@ -1546,7 +1553,7 @@ xfs_iext_indirect_to_direct( int size; /* size of file extents */ ASSERT(ifp->if_flags & XFS_IFEXTIREC); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); ASSERT(nextents <= XFS_LINEAR_EXTS); size = nextents * sizeof(xfs_bmbt_rec_t); @@ -1620,7 +1627,7 @@ xfs_iext_bno_to_ext( xfs_extnum_t nextents; /* number of file extents */ xfs_fileoff_t startoff = 0; /* start offset of extent */ - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); if (nextents == 0) { *idxp = 0; return NULL; @@ -1733,8 +1740,8 @@ xfs_iext_idx_to_irec( ASSERT(ifp->if_flags & XFS_IFEXTIREC); ASSERT(page_idx >= 0); - ASSERT(page_idx <= ifp->if_bytes / sizeof(xfs_bmbt_rec_t)); - ASSERT(page_idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t) || realloc); + ASSERT(page_idx <= xfs_iext_count(ifp)); + ASSERT(page_idx < xfs_iext_count(ifp) || realloc); nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; erp_idx = 0; @@ -1782,7 +1789,7 @@ xfs_iext_irec_init( xfs_extnum_t nextents; /* number of extents in file */ ASSERT(!(ifp->if_flags & XFS_IFEXTIREC)); - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); ASSERT(nextents <= XFS_LINEAR_EXTS); erp = kmem_alloc(sizeof(xfs_ext_irec_t), KM_NOFS); @@ -1906,7 +1913,7 @@ xfs_iext_irec_compact( ASSERT(ifp->if_flags & XFS_IFEXTIREC); nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); if (nextents == 0) { xfs_iext_destroy(ifp); diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index c9476f50e32d..8bf112e29aa1 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -152,6 +152,7 @@ void xfs_init_local_fork(struct xfs_inode *, int, const void *, int); struct xfs_bmbt_rec_host * xfs_iext_get_ext(struct xfs_ifork *, xfs_extnum_t); +xfs_extnum_t xfs_iext_count(struct xfs_ifork *); void xfs_iext_insert(struct xfs_inode *, xfs_extnum_t, xfs_extnum_t, struct xfs_bmbt_irec *, int); void xfs_iext_add(struct xfs_ifork *, xfs_extnum_t, int); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 47074e0c33f3..0670a8bd5818 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -359,9 +359,7 @@ xfs_bmap_count_blocks( mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) { - xfs_bmap_count_leaves(ifp, 0, - ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t), - count); + xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count); return 0; } @@ -426,7 +424,7 @@ xfs_getbmapx_fix_eof_hole( ifp = XFS_IFORK_PTR(ip, whichfork); if (!moretocome && xfs_iext_bno_to_ext(ifp, fileblock, &lastx) && - (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1)) + (lastx == xfs_iext_count(ifp) - 1)) out->bmv_oflags |= BMV_OF_LAST; } @@ -1878,15 +1876,13 @@ xfs_swap_extent_forks( switch (ip->i_d.di_format) { case XFS_DINODE_FMT_EXTENTS: - /* If the extents fit in the inode, fix the - * pointer. Otherwise it's already NULL or - * pointing to the extent. + /* + * If the extents fit in the inode, fix the pointer. Otherwise + * it's already NULL or pointing to the extent. */ - nextents = ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); - if (nextents <= XFS_INLINE_EXTS) { - ifp->if_u1.if_extents = - ifp->if_u2.if_inline_ext; - } + nextents = xfs_iext_count(&ip->i_df); + if (nextents <= XFS_INLINE_EXTS) + ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext; (*src_log_flags) |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: @@ -1898,15 +1894,13 @@ xfs_swap_extent_forks( switch (tip->i_d.di_format) { case XFS_DINODE_FMT_EXTENTS: - /* If the extents fit in the inode, fix the - * pointer. Otherwise it's already NULL or - * pointing to the extent. + /* + * If the extents fit in the inode, fix the pointer. Otherwise + * it's already NULL or pointing to the extent. */ - nextents = tip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); - if (nextents <= XFS_INLINE_EXTS) { - tifp->if_u1.if_extents = - tifp->if_u2.if_inline_ext; - } + nextents = xfs_iext_count(&tip->i_df); + if (nextents <= XFS_INLINE_EXTS) + tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext; (*target_log_flags) |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 9610e9c00952..d90e7811ccdd 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -164,7 +164,7 @@ xfs_inode_item_format_data_fork( struct xfs_bmbt_rec *p; ASSERT(ip->i_df.if_u1.if_extents != NULL); - ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0); + ASSERT(xfs_iext_count(&ip->i_df) > 0); p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT); data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK); @@ -261,7 +261,7 @@ xfs_inode_item_format_attr_fork( ip->i_afp->if_bytes > 0) { struct xfs_bmbt_rec *p; - ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) == + ASSERT(xfs_iext_count(ip->i_afp) == ip->i_d.di_anextents); ASSERT(ip->i_afp->if_u1.if_extents != NULL); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c245bed3249b..a39197501a7c 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -910,16 +910,14 @@ xfs_ioc_fsgetxattr( if (attr) { if (ip->i_afp) { if (ip->i_afp->if_flags & XFS_IFEXTENTS) - fa.fsx_nextents = ip->i_afp->if_bytes / - sizeof(xfs_bmbt_rec_t); + fa.fsx_nextents = xfs_iext_count(ip->i_afp); else fa.fsx_nextents = ip->i_d.di_anextents; } else fa.fsx_nextents = 0; } else { if (ip->i_df.if_flags & XFS_IFEXTENTS) - fa.fsx_nextents = ip->i_df.if_bytes / - sizeof(xfs_bmbt_rec_t); + fa.fsx_nextents = xfs_iext_count(&ip->i_df); else fa.fsx_nextents = ip->i_d.di_nextents; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index a60d9e2739d1..45e50ea90769 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1135,7 +1135,7 @@ xfs_qm_get_rtblks( return error; } rtblks = 0; - nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + nextents = xfs_iext_count(ifp); for (idx = 0; idx < nextents; idx++) rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx)); *O_rtblks = (xfs_qcnt_t)rtblks; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index c06904893202..0edf835af32d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -486,7 +486,7 @@ xfs_reflink_trim_irec_to_next_cow( /* This is the extent before; try sliding up one. */ if (irec.br_startoff < offset_fsb) { idx++; - if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t)) + if (idx >= xfs_iext_count(ifp)) return 0; gotp = xfs_iext_get_ext(ifp, idx); xfs_bmbt_get_all(gotp, &irec); @@ -566,7 +566,7 @@ xfs_reflink_cancel_cow_blocks( xfs_bmap_del_extent_cow(ip, &idx, &got, &del); } - if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)) + if (++idx >= xfs_iext_count(ifp)) break; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } -- cgit v1.2.3 From 98efe8af1c9ffac47e842b7a75ded903e2f028da Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Thu, 10 Nov 2016 08:23:22 +1100 Subject: xfs: fix unbalanced inode reclaim flush locking Filesystem shutdown testing on an older distro kernel has uncovered an imbalanced locking pattern for the inode flush lock in xfs_reclaim_inode(). Specifically, there is a double unlock sequence between the call to xfs_iflush_abort() and xfs_reclaim_inode() at the "reclaim:" label. This actually does not cause obvious problems on current kernels due to the current flush lock implementation. Older kernels use a counting based flush lock mechanism, however, which effectively breaks the lock indefinitely when an already unlocked flush lock is repeatedly unlocked. Though this only currently occurs on filesystem shutdown, it has reproduced the effect of elevating an fs shutdown to a system-wide crash or hang. As it turns out, the flush lock is not actually required for the reclaim logic in xfs_reclaim_inode() because by that time we have already cycled the flush lock once while holding ILOCK_EXCL. Therefore, remove the additional flush lock/unlock cycle around the 'reclaim:' label and update branches into this label to release the flush lock where appropriate. Add an assert to xfs_ifunlock() to help prevent future occurences of the same problem. Reported-by: Zorro Lang Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 27 ++++++++++++++------------- fs/xfs/xfs_inode.h | 11 ++++++----- 2 files changed, 20 insertions(+), 18 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 1b4861f5d3d8..9c3e5c6ddf20 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -123,7 +123,6 @@ __xfs_inode_free( { /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!xfs_isiflocked(ip)); XFS_STATS_DEC(ip->i_mount, vn_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); @@ -133,6 +132,8 @@ void xfs_inode_free( struct xfs_inode *ip) { + ASSERT(!xfs_isiflocked(ip)); + /* * Because we use RCU freeing we need to ensure the inode always * appears to be reclaimed with an invalid inode number when in the @@ -981,6 +982,7 @@ restart: if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { xfs_iunpin_wait(ip); + /* xfs_iflush_abort() drops the flush lock */ xfs_iflush_abort(ip, false); goto reclaim; } @@ -989,10 +991,10 @@ restart: goto out_ifunlock; xfs_iunpin_wait(ip); } - if (xfs_iflags_test(ip, XFS_ISTALE)) - goto reclaim; - if (xfs_inode_clean(ip)) + if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) { + xfs_ifunlock(ip); goto reclaim; + } /* * Never flush out dirty data during non-blocking reclaim, as it would @@ -1030,25 +1032,24 @@ restart: xfs_buf_relse(bp); } - xfs_iflock(ip); reclaim: + ASSERT(!xfs_isiflocked(ip)); + /* * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. - * We do this as early as possible under the ILOCK and flush lock so - * that xfs_iflush_cluster() can be guaranteed to detect races with us - * here. By doing this, we guarantee that once xfs_iflush_cluster has - * locked both the XFS_ILOCK and the flush lock that it will see either - * a valid, flushable inode that will serialise correctly against the - * locks below, or it will see a clean (and invalid) inode that it can - * skip. + * We do this as early as possible under the ILOCK so that + * xfs_iflush_cluster() can be guaranteed to detect races with us here. + * By doing this, we guarantee that once xfs_iflush_cluster has locked + * XFS_ILOCK that it will see either a valid, flushable inode that will + * serialise correctly, or it will see a clean (and invalid) inode that + * it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; ip->i_ino = 0; spin_unlock(&ip->i_flags_lock); - xfs_ifunlock(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index f14c1de2549d..71e8a81c91a3 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -246,6 +246,11 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) * Synchronize processes attempting to flush the in-core inode back to disk. */ +static inline int xfs_isiflocked(struct xfs_inode *ip) +{ + return xfs_iflags_test(ip, XFS_IFLOCK); +} + extern void __xfs_iflock(struct xfs_inode *ip); static inline int xfs_iflock_nowait(struct xfs_inode *ip) @@ -261,16 +266,12 @@ static inline void xfs_iflock(struct xfs_inode *ip) static inline void xfs_ifunlock(struct xfs_inode *ip) { + ASSERT(xfs_isiflocked(ip)); xfs_iflags_clear(ip, XFS_IFLOCK); smp_mb(); 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) -- cgit v1.2.3 From 93533c7855c3c78c8a900cac65c8d669bb14935d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:32 +1100 Subject: xfs: new inode extent list lookup helpers xfs_iext_lookup_extent looks up a single extent at the passed in offset, and returns the extent covering the area, or the one behind it in case of a hole, as well as the index of the returned extent in arguments, as well as a simple bool as return value that is set to false if no extent could be found because the offset is behind EOF. It is a simpler replacement for xfs_bmap_search_extent that leaves looking up the rarely needed previous extent to the caller and has a nicer calling convention. xfs_iext_get_extent is a helper for iterating over the extent list, it takes an extent index as input, and returns the extent at that index in it's expanded form in an argument if it exists. The actual return value is a bool whether the index is valid or not. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_inode_fork.c | 46 ++++++++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_inode_fork.h | 6 ++++++ 2 files changed, 52 insertions(+) diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 5fbe24c31679..222e103356c6 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -2003,3 +2003,49 @@ xfs_ifork_init_cow( ip->i_cformat = XFS_DINODE_FMT_EXTENTS; ip->i_cnextents = 0; } + +/* + * Lookup the extent covering bno. + * + * If there is an extent covering bno return the extent index, and store the + * expanded extent structure in *gotp, and the extent index in *idx. + * If there is no extent covering bno, but there is an extent after it (e.g. + * it lies in a hole) return that extent in *gotp and its index in *idx + * instead. + * If bno is beyond the last extent return false, and return the index after + * the last valid index in *idxp. + */ +bool +xfs_iext_lookup_extent( + struct xfs_inode *ip, + struct xfs_ifork *ifp, + xfs_fileoff_t bno, + xfs_extnum_t *idxp, + struct xfs_bmbt_irec *gotp) +{ + struct xfs_bmbt_rec_host *ep; + + XFS_STATS_INC(ip->i_mount, xs_look_exlist); + + ep = xfs_iext_bno_to_ext(ifp, bno, idxp); + if (!ep) + return false; + xfs_bmbt_get_all(ep, gotp); + return true; +} + +/* + * Return true if there is an extent at index idx, and return the expanded + * extent structure at idx in that case. Else return false. + */ +bool +xfs_iext_get_extent( + struct xfs_ifork *ifp, + xfs_extnum_t idx, + struct xfs_bmbt_irec *gotp) +{ + if (idx < 0 || idx >= xfs_iext_count(ifp)) + return false; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), gotp); + return true; +} diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 8bf112e29aa1..7fb8365326d1 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -182,6 +182,12 @@ void xfs_iext_irec_compact_pages(struct xfs_ifork *); void xfs_iext_irec_compact_full(struct xfs_ifork *); void xfs_iext_irec_update_extoffs(struct xfs_ifork *, int, int); +bool xfs_iext_lookup_extent(struct xfs_inode *ip, + struct xfs_ifork *ifp, xfs_fileoff_t bno, + xfs_extnum_t *idxp, struct xfs_bmbt_irec *gotp); +bool xfs_iext_get_extent(struct xfs_ifork *ifp, xfs_extnum_t idx, + struct xfs_bmbt_irec *gotp); + extern struct kmem_zone *xfs_ifork_zone; extern void xfs_ifork_init_cow(struct xfs_inode *ip); -- cgit v1.2.3 From 86685f7ba5c0fdbcc159ecdbcc530b9b3509a675 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:38 +1100 Subject: xfs: cleanup xfs_bmap_last_before Rewrite the function using xfs_iext_lookup_extent and xfs_iext_get_extent, and massage the flow into something easily understandable. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 64 ++++++++++++++++++++++++------------------------ 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 42f4e7a84e2e..13f62da67bbc 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1523,44 +1523,44 @@ xfs_bmap_first_unused( */ int /* error */ xfs_bmap_last_before( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode */ - xfs_fileoff_t *last_block, /* last block */ - int whichfork) /* data or attr fork */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode */ + xfs_fileoff_t *last_block, /* last block */ + int whichfork) /* data or attr fork */ { - xfs_fileoff_t bno; /* input file offset */ - int eof; /* hit end of file */ - xfs_bmbt_rec_host_t *ep; /* pointer to last extent */ - int error; /* error return value */ - xfs_bmbt_irec_t got; /* current extent value */ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_extnum_t lastx; /* last extent used */ - xfs_bmbt_irec_t prev; /* previous extent value */ + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec got; + xfs_extnum_t idx; + int error; - if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL) - return -EIO; - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) { + switch (XFS_IFORK_FORMAT(ip, whichfork)) { + case XFS_DINODE_FMT_LOCAL: *last_block = 0; return 0; + case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_EXTENTS: + break; + default: + return -EIO; } - ifp = XFS_IFORK_PTR(ip, whichfork); - if (!(ifp->if_flags & XFS_IFEXTENTS) && - (error = xfs_iread_extents(tp, ip, whichfork))) - return error; - bno = *last_block - 1; - ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got, - &prev); - if (eof || xfs_bmbt_get_startoff(ep) > bno) { - if (prev.br_startoff == NULLFILEOFF) - *last_block = 0; - else - *last_block = prev.br_startoff + prev.br_blockcount; + + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; } - /* - * Otherwise *last_block is already the right answer. - */ + + if (xfs_iext_lookup_extent(ip, ifp, *last_block - 1, &idx, &got)) { + if (got.br_startoff <= *last_block - 1) + return 0; + } + + if (xfs_iext_get_extent(ifp, idx - 1, &got)) { + *last_block = got.br_startoff + got.br_blockcount; + return 0; + } + + *last_block = 0; return 0; } -- cgit v1.2.3 From 334f3423d6a6c39483aa0744ea044e105ca0e5ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:43 +1100 Subject: xfs: use new extent lookup helpers in xfs_bmapi_read Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 13f62da67bbc..aac5cc3cd9ef 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4145,12 +4145,11 @@ xfs_bmapi_read( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; struct xfs_bmbt_irec got; - struct xfs_bmbt_irec prev; xfs_fileoff_t obno; xfs_fileoff_t end; - xfs_extnum_t lastx; + xfs_extnum_t idx; int error; - int eof; + bool eof = false; int n = 0; int whichfork = xfs_bmapi_whichfork(flags); @@ -4190,7 +4189,8 @@ xfs_bmapi_read( return error; } - xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got, &prev); + if (!xfs_iext_lookup_extent(ip, ifp, bno, &idx, &got)) + eof = true; end = bno + len; obno = bno; @@ -4221,10 +4221,8 @@ xfs_bmapi_read( break; /* Else go on to the next record. */ - if (++lastx < xfs_iext_count(ifp)) - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx), &got); - else - eof = 1; + if (!xfs_iext_get_extent(ifp, ++idx, &got)) + eof = true; } *nmap = n; return 0; -- cgit v1.2.3 From 2d58f6ef79db10257d77ae8cd8e9e8432816c9ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:43 +1100 Subject: xfs: use new extent lookup helpers in xfs_bmapi_write Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index aac5cc3cd9ef..1c2e0eaf5aaf 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4561,7 +4561,7 @@ xfs_bmapi_write( struct xfs_ifork *ifp; struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */ xfs_fileoff_t end; /* end of mapped file region */ - int eof; /* after the end of extents */ + bool eof = false; /* after the end of extents */ int error; /* error return */ int n; /* current extent index */ xfs_fileoff_t obno; /* old block number (offset) */ @@ -4639,12 +4639,14 @@ xfs_bmapi_write( goto error0; } - xfs_bmap_search_extents(ip, bno, whichfork, &eof, &bma.idx, &bma.got, - &bma.prev); n = 0; end = bno + len; obno = bno; + if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.idx, &bma.got)) + eof = true; + if (!xfs_iext_get_extent(ifp, bma.idx - 1, &bma.prev)) + bma.prev.br_startoff = NULLFILEOFF; bma.tp = tp; bma.ip = ip; bma.total = total; @@ -4731,11 +4733,8 @@ xfs_bmapi_write( /* Else go on to the next record. */ bma.prev = bma.got; - if (++bma.idx < xfs_iext_count(ifp)) { - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma.idx), - &bma.got); - } else - eof = 1; + if (!xfs_iext_get_extent(ifp, ++bma.idx, &bma.got)) + eof = true; } *nmap = n; -- cgit v1.2.3 From 7efc794561f6bfe34d26c3724289108f6cda3a4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:44 +1100 Subject: xfs: use new extent lookup helpers in __xfs_bunmapi Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 40 +++++++++++++--------------------------- 1 file changed, 13 insertions(+), 27 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1c2e0eaf5aaf..05608faa28ce 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5430,8 +5430,6 @@ __xfs_bunmapi( { xfs_btree_cur_t *cur; /* bmap btree cursor */ xfs_bmbt_irec_t del; /* extent being deleted */ - int eof; /* is deleting at eof */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ int error; /* error return value */ xfs_extnum_t extno; /* extent number in list */ xfs_bmbt_irec_t got; /* current extent record */ @@ -5441,7 +5439,6 @@ __xfs_bunmapi( int logflags; /* transaction logging flags */ xfs_extlen_t mod; /* rt extent offset */ xfs_mount_t *mp; /* mount structure */ - xfs_bmbt_irec_t prev; /* previous extent record */ xfs_fileoff_t start; /* first file offset deleted */ int tmp_logflags; /* partial logging flags */ int wasdel; /* was a delayed alloc extent */ @@ -5480,18 +5477,17 @@ __xfs_bunmapi( isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); start = bno; bno = start + len - 1; - ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got, - &prev); /* * Check to see if the given block number is past the end of the * file, back up to the last block if so... */ - if (eof) { - ep = xfs_iext_get_ext(ifp, --lastx); - xfs_bmbt_get_all(ep, &got); + if (!xfs_iext_lookup_extent(ip, ifp, bno, &lastx, &got)) { + ASSERT(lastx > 0); + xfs_iext_get_extent(ifp, --lastx, &got); bno = got.br_startoff + got.br_blockcount - 1; } + logflags = 0; if (ifp->if_flags & XFS_IFBROOT) { ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE); @@ -5522,8 +5518,7 @@ __xfs_bunmapi( if (got.br_startoff > bno) { if (--lastx < 0) break; - ep = xfs_iext_get_ext(ifp, lastx); - xfs_bmbt_get_all(ep, &got); + xfs_iext_get_extent(ifp, lastx, &got); } /* * Is the last block of this extent before the range @@ -5537,7 +5532,6 @@ __xfs_bunmapi( * Then deal with the (possibly delayed) allocated space * we found. */ - ASSERT(ep != NULL); del = got; wasdel = isnullstartblock(del.br_startblock); if (got.br_startoff < start) { @@ -5618,15 +5612,12 @@ __xfs_bunmapi( */ ASSERT(bno >= del.br_blockcount); bno -= del.br_blockcount; - if (got.br_startoff > bno) { - if (--lastx >= 0) { - ep = xfs_iext_get_ext(ifp, - lastx); - xfs_bmbt_get_all(ep, &got); - } - } + if (got.br_startoff > bno && --lastx >= 0) + xfs_iext_get_extent(ifp, lastx, &got); continue; } else if (del.br_state == XFS_EXT_UNWRITTEN) { + struct xfs_bmbt_irec prev; + /* * This one is already unwritten. * It must have a written left neighbor. @@ -5634,8 +5625,7 @@ __xfs_bunmapi( * try again. */ ASSERT(lastx > 0); - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, - lastx - 1), &prev); + xfs_iext_get_extent(ifp, lastx - 1, &prev); ASSERT(prev.br_state == XFS_EXT_NORM); ASSERT(!isnullstartblock(prev.br_startblock)); ASSERT(del.br_startblock == @@ -5733,13 +5723,9 @@ nodelete: */ if (bno != (xfs_fileoff_t)-1 && bno >= start) { if (lastx >= 0) { - ep = xfs_iext_get_ext(ifp, lastx); - if (xfs_bmbt_get_startoff(ep) > bno) { - if (--lastx >= 0) - ep = xfs_iext_get_ext(ifp, - lastx); - } - xfs_bmbt_get_all(ep, &got); + xfs_iext_get_extent(ifp, lastx, &got); + if (got.br_startoff > bno && --lastx >= 0) + xfs_iext_get_extent(ifp, lastx, &got); } extno++; } -- cgit v1.2.3 From 65c5f419788d623a0410eca1866134f5e4628594 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:44 +1100 Subject: xfs: remove prev argument to xfs_bmapi_reserve_delalloc We can easily lookup the previous extent for the cases where we need it, which saves the callers from looking it up for us later in the series. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 8 ++++++-- fs/xfs/libxfs/xfs_bmap.h | 3 +-- fs/xfs/xfs_iomap.c | 3 +-- fs/xfs/xfs_reflink.c | 2 +- 4 files changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 05608faa28ce..6af34b734ce8 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4235,7 +4235,6 @@ xfs_bmapi_reserve_delalloc( xfs_fileoff_t aoff, xfs_filblks_t len, struct xfs_bmbt_irec *got, - struct xfs_bmbt_irec *prev, xfs_extnum_t *lastx, int eof) { @@ -4257,7 +4256,12 @@ xfs_bmapi_reserve_delalloc( else extsz = xfs_get_extsz_hint(ip); if (extsz) { - error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof, + struct xfs_bmbt_irec prev; + + if (!xfs_iext_get_extent(ifp, *lastx - 1, &prev)) + prev.br_startoff = NULLFILEOFF; + + error = xfs_bmap_extsize_align(mp, got, &prev, extsz, rt, eof, 1, 0, &aoff, &alen); ASSERT(!error); } diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 7cae6ec27fa6..e3c2b5adf505 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -243,8 +243,7 @@ struct xfs_bmbt_rec_host * struct xfs_bmbt_irec *gotp, struct xfs_bmbt_irec *prevp); int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork, xfs_fileoff_t aoff, xfs_filblks_t len, - struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *prev, - xfs_extnum_t *lastx, int eof); + struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof); enum xfs_bmap_intent_type { XFS_BMAP_MAP = 1, diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 436e109bb01e..59ffcac8a47d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -622,8 +622,7 @@ xfs_file_iomap_begin_delay( retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb, - end_fsb - offset_fsb, &got, - &prev, &idx, eof); + end_fsb - offset_fsb, &got, &idx, eof); switch (error) { case 0: break; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 0edf835af32d..52cdfbaca30d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -293,7 +293,7 @@ xfs_reflink_reserve_cow( retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, - end_fsb - imap->br_startoff, &got, &prev, &idx, eof); + end_fsb - imap->br_startoff, &got, &idx, eof); switch (error) { case 0: break; -- cgit v1.2.3 From 656152e552e5cbe0c11ad261b524376217c2fb13 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:44 +1100 Subject: xfs: use new extent lookup helpers xfs_file_iomap_begin_delay And only lookup the previous extent inside xfs_iomap_prealloc_size if we actually need it. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 59ffcac8a47d..2272190b70ae 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -395,11 +395,12 @@ xfs_iomap_prealloc_size( struct xfs_inode *ip, loff_t offset, loff_t count, - xfs_extnum_t idx, - struct xfs_bmbt_irec *prev) + xfs_extnum_t idx) { struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + struct xfs_bmbt_irec prev; int shift = 0; int64_t freesp; xfs_fsblock_t qblocks; @@ -419,8 +420,8 @@ xfs_iomap_prealloc_size( */ if ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) || XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) || - idx == 0 || - prev->br_startoff + prev->br_blockcount < offset_fsb) + !xfs_iext_get_extent(ifp, idx - 1, &prev) || + prev.br_startoff + prev.br_blockcount < offset_fsb) return mp->m_writeio_blocks; /* @@ -439,8 +440,8 @@ xfs_iomap_prealloc_size( * always extends to MAXEXTLEN rather than falling short due to things * like stripe unit/width alignment of real extents. */ - if (prev->br_blockcount <= (MAXEXTLEN >> 1)) - alloc_blocks = prev->br_blockcount << 1; + if (prev.br_blockcount <= (MAXEXTLEN >> 1)) + alloc_blocks = prev.br_blockcount << 1; else alloc_blocks = XFS_B_TO_FSB(mp, offset); if (!alloc_blocks) @@ -538,7 +539,6 @@ xfs_file_iomap_begin_delay( xfs_fileoff_t end_fsb, orig_end_fsb; int error = 0, eof = 0; struct xfs_bmbt_irec got; - struct xfs_bmbt_irec prev; xfs_extnum_t idx; ASSERT(!XFS_IS_REALTIME_INODE(ip)); @@ -563,8 +563,7 @@ xfs_file_iomap_begin_delay( goto out_unlock; } - xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx, - &got, &prev); + eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got); if (!eof && got.br_startoff <= offset_fsb) { if (xfs_is_reflink_inode(ip)) { bool shared; @@ -601,8 +600,7 @@ xfs_file_iomap_begin_delay( if (eof) { xfs_fsblock_t prealloc_blocks; - prealloc_blocks = - xfs_iomap_prealloc_size(ip, offset, count, idx, &prev); + prealloc_blocks = xfs_iomap_prealloc_size(ip, offset, count, idx); if (prealloc_blocks) { xfs_extlen_t align; xfs_off_t end_offset; -- cgit v1.2.3 From 2755fc4438501c8c28e7783df890e889f6772bee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:49 +1100 Subject: xfs: use new extent lookup helpers in __xfs_reflink_reserve_cow Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 52cdfbaca30d..35e02cecc444 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -243,10 +243,11 @@ xfs_reflink_reserve_cow( struct xfs_bmbt_irec *imap, bool *shared) { - struct xfs_bmbt_irec got, prev; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got; xfs_fileoff_t end_fsb, orig_end_fsb; - int eof = 0, error = 0; - bool trimmed; + int error = 0; + bool eof = false, trimmed; xfs_extnum_t idx; xfs_extlen_t align; @@ -258,8 +259,9 @@ xfs_reflink_reserve_cow( * extent list is generally faster than going out to the shared extent * tree. */ - xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx, - &got, &prev); + + if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &idx, &got)) + eof = true; if (!eof && got.br_startoff <= imap->br_startoff) { trace_xfs_reflink_cow_found(ip, imap); xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); -- cgit v1.2.3 From 092d5d9d5812a80e4496cdbb24fe58e6f77da56b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:49 +1100 Subject: xfs: cleanup xfs_reflink_find_cow_mapping Use xfs_iext_lookup_extent to look up the extent, drop a useless check, drop a unneeded return value and clean up the general style a little bit. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_aops.c | 16 ++++++++-------- fs/xfs/xfs_reflink.c | 33 ++++++++++----------------------- fs/xfs/xfs_reflink.h | 2 +- 3 files changed, 19 insertions(+), 32 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2693ba84ec25..4923b54da556 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -777,7 +777,7 @@ xfs_map_cow( { struct xfs_inode *ip = XFS_I(inode); struct xfs_bmbt_irec imap; - bool is_cow = false, need_alloc = false; + bool is_cow = false; int error; /* @@ -795,7 +795,7 @@ xfs_map_cow( * Else we need to check if there is a COW mapping at this offset. */ xfs_ilock(ip, XFS_ILOCK_SHARED); - is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap, &need_alloc); + is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap); xfs_iunlock(ip, XFS_ILOCK_SHARED); if (!is_cow) @@ -805,7 +805,7 @@ xfs_map_cow( * And if the COW mapping has a delayed extent here we need to * allocate real space for it now. */ - if (need_alloc) { + if (isnullstartblock(imap.br_startblock)) { error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset, &imap); if (error) @@ -1312,7 +1312,6 @@ __xfs_get_blocks( ssize_t size; int new = 0; bool is_cow = false; - bool need_alloc = false; BUG_ON(create && !direct); @@ -1338,9 +1337,11 @@ __xfs_get_blocks( end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size); offset_fsb = XFS_B_TO_FSBT(mp, offset); - if (create && direct && xfs_is_reflink_inode(ip)) - is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap, - &need_alloc); + if (create && direct && xfs_is_reflink_inode(ip)) { + is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap); + ASSERT(!is_cow || !isnullstartblock(imap.br_startblock)); + } + if (!is_cow) { error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, XFS_BMAPI_ENTIRE); @@ -1357,7 +1358,6 @@ __xfs_get_blocks( xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, &imap); } - ASSERT(!need_alloc); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 35e02cecc444..e92355a39304 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -420,44 +420,31 @@ xfs_reflink_allocate_cow_range( } /* - * Find the CoW reservation (and whether or not it needs block allocation) - * for a given byte offset of a file. + * Find the CoW reservation for a given byte offset of a file. */ bool xfs_reflink_find_cow_mapping( struct xfs_inode *ip, xfs_off_t offset, - struct xfs_bmbt_irec *imap, - bool *need_alloc) + struct xfs_bmbt_irec *imap) { - struct xfs_bmbt_irec irec; - struct xfs_ifork *ifp; - struct xfs_bmbt_rec_host *gotp; - xfs_fileoff_t bno; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + xfs_fileoff_t offset_fsb; + struct xfs_bmbt_irec got; xfs_extnum_t idx; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); ASSERT(xfs_is_reflink_inode(ip)); - /* Find the extent in the CoW fork. */ - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - bno = XFS_B_TO_FSBT(ip->i_mount, offset); - gotp = xfs_iext_bno_to_ext(ifp, bno, &idx); - if (!gotp) + offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); + if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got)) return false; - - xfs_bmbt_get_all(gotp, &irec); - if (bno >= irec.br_startoff + irec.br_blockcount || - bno < irec.br_startoff) + if (got.br_startoff > offset_fsb) return false; trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE, - &irec); - - /* If it's still delalloc, we must allocate later. */ - *imap = irec; - *need_alloc = !!(isnullstartblock(irec.br_startblock)); - + &got); + *imap = got; return true; } diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 97ea9b487884..cff5fc329359 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -31,7 +31,7 @@ extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, - struct xfs_bmbt_irec *imap, bool *need_alloc); + struct xfs_bmbt_irec *imap); extern int xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap); -- cgit v1.2.3 From 86f12ab05ffc45fa88a09110f582875fa9f07c8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:50 +1100 Subject: xfs: use new extent lookup helpers in xfs_reflink_trim_irec_to_next_cow And remove the unused return value. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 33 ++++++++++++--------------------- fs/xfs/xfs_reflink.h | 2 +- 2 files changed, 13 insertions(+), 22 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e92355a39304..d3cfae842237 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -451,43 +451,34 @@ xfs_reflink_find_cow_mapping( /* * Trim an extent to end at the next CoW reservation past offset_fsb. */ -int +void xfs_reflink_trim_irec_to_next_cow( struct xfs_inode *ip, xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap) { - struct xfs_bmbt_irec irec; - struct xfs_ifork *ifp; - struct xfs_bmbt_rec_host *gotp; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got; xfs_extnum_t idx; if (!xfs_is_reflink_inode(ip)) - return 0; + return; /* Find the extent in the CoW fork. */ - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - gotp = xfs_iext_bno_to_ext(ifp, offset_fsb, &idx); - if (!gotp) - return 0; - xfs_bmbt_get_all(gotp, &irec); + if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got)) + return; /* This is the extent before; try sliding up one. */ - if (irec.br_startoff < offset_fsb) { - idx++; - if (idx >= xfs_iext_count(ifp)) - return 0; - gotp = xfs_iext_get_ext(ifp, idx); - xfs_bmbt_get_all(gotp, &irec); + if (got.br_startoff < offset_fsb) { + if (!xfs_iext_get_extent(ifp, idx + 1, &got)) + return; } - if (irec.br_startoff >= imap->br_startoff + imap->br_blockcount) - return 0; + if (got.br_startoff >= imap->br_startoff + imap->br_blockcount) + return; - imap->br_blockcount = irec.br_startoff - imap->br_startoff; + imap->br_blockcount = got.br_startoff - imap->br_startoff; trace_xfs_reflink_trim_irec(ip, imap); - - return 0; } /* diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index cff5fc329359..aa6a4d64bd35 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -32,7 +32,7 @@ extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, struct xfs_bmbt_irec *imap); -extern int xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, +extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap); extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip, -- cgit v1.2.3 From df5ab1b5a841aecd4854b75b4c2102a9d2d1996b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:50 +1100 Subject: xfs: use new extent lookup helpers in xfs_reflink_cancel_cow_blocks Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index d3cfae842237..4e07da3d5af5 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -492,18 +492,15 @@ xfs_reflink_cancel_cow_blocks( xfs_fileoff_t end_fsb) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - struct xfs_bmbt_irec got, prev, del; + struct xfs_bmbt_irec got, del; xfs_extnum_t idx; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error = 0, eof = 0; + int error = 0; if (!xfs_is_reflink_inode(ip)) return 0; - - xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx, - &got, &prev); - if (eof) + if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got)) return 0; while (got.br_startoff < end_fsb) { @@ -546,9 +543,8 @@ xfs_reflink_cancel_cow_blocks( xfs_bmap_del_extent_cow(ip, &idx, &got, &del); } - if (++idx >= xfs_iext_count(ifp)) + if (!xfs_iext_get_extent(ifp, ++idx, &got)) break; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } /* clear tag if cow fork is emptied */ -- cgit v1.2.3 From 4ab8671c19620f335d97673f941a631e15aa0d6e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:39:50 +1100 Subject: xfs: use new extent lookup helpers in xfs_reflink_end_cow Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 4e07da3d5af5..56372bee08c5 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -614,13 +614,13 @@ xfs_reflink_end_cow( xfs_off_t count) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - struct xfs_bmbt_irec got, prev, del; + struct xfs_bmbt_irec got, del; struct xfs_trans *tp; xfs_fileoff_t offset_fsb; xfs_fileoff_t end_fsb; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error, eof = 0; + int error; unsigned int resblks; xfs_filblks_t rlen; xfs_extnum_t idx; @@ -644,13 +644,11 @@ xfs_reflink_end_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx, - &got, &prev); - /* If there is a hole at end_fsb - 1 go to the previous extent */ - if (eof || got.br_startoff > end_fsb) { + if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) || + got.br_startoff > end_fsb) { ASSERT(idx > 0); - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); + xfs_iext_get_extent(ifp, --idx, &got); } /* Walk backwards until we're out of the I/O range... */ @@ -698,11 +696,9 @@ xfs_reflink_end_cow( error = xfs_defer_finish(&tp, &dfops, ip); if (error) goto out_defer; - next_extent: - if (idx < 0) + if (!xfs_iext_get_extent(ifp, idx, &got)) break; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } error = xfs_trans_commit(tp); -- cgit v1.2.3 From 6edc977f775e5ac10655b03607ef091d2b06f2f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:40:14 +1100 Subject: xfs: remove xfs_bmap_search_extents Now that all users are gone. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 91 ------------------------------------------------ fs/xfs/libxfs/xfs_bmap.h | 4 --- 2 files changed, 95 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 6af34b734ce8..dcc847ceaebe 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1370,97 +1370,6 @@ error0: return -EFSCORRUPTED; } - -/* - * Search the extent records for the entry containing block bno. - * If bno lies in a hole, point to the next entry. If bno lies - * past eof, *eofp will be set, and *prevp will contain the last - * entry (null if none). Else, *lastxp will be set to the index - * of the found entry; *gotp will contain the entry. - */ -STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */ -xfs_bmap_search_multi_extents( - xfs_ifork_t *ifp, /* inode fork pointer */ - xfs_fileoff_t bno, /* block number searched for */ - int *eofp, /* out: end of file found */ - xfs_extnum_t *lastxp, /* out: last extent index */ - xfs_bmbt_irec_t *gotp, /* out: extent entry found */ - xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */ -{ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ - xfs_extnum_t lastx; /* last extent index */ - - /* - * Initialize the extent entry structure to catch access to - * uninitialized br_startblock field. - */ - gotp->br_startoff = 0xffa5a5a5a5a5a5a5LL; - gotp->br_blockcount = 0xa55a5a5a5a5a5a5aLL; - gotp->br_state = XFS_EXT_INVALID; - gotp->br_startblock = 0xffffa5a5a5a5a5a5LL; - prevp->br_startoff = NULLFILEOFF; - - ep = xfs_iext_bno_to_ext(ifp, bno, &lastx); - if (lastx > 0) { - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp); - } - if (lastx < xfs_iext_count(ifp)) { - xfs_bmbt_get_all(ep, gotp); - *eofp = 0; - } else { - if (lastx > 0) { - *gotp = *prevp; - } - *eofp = 1; - ep = NULL; - } - *lastxp = lastx; - return ep; -} - -/* - * Search the extents list for the inode, for the extent containing bno. - * If bno lies in a hole, point to the next entry. If bno lies past eof, - * *eofp will be set, and *prevp will contain the last entry (null if none). - * Else, *lastxp will be set to the index of the found - * entry; *gotp will contain the entry. - */ -xfs_bmbt_rec_host_t * /* pointer to found extent entry */ -xfs_bmap_search_extents( - xfs_inode_t *ip, /* incore inode pointer */ - xfs_fileoff_t bno, /* block number searched for */ - int fork, /* data or attr fork */ - int *eofp, /* out: end of file found */ - xfs_extnum_t *lastxp, /* out: last extent index */ - xfs_bmbt_irec_t *gotp, /* out: extent entry found */ - xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */ -{ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ - - XFS_STATS_INC(ip->i_mount, xs_look_exlist); - ifp = XFS_IFORK_PTR(ip, fork); - - ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp); - - if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) && - !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) { - xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO, - "Access to block zero in inode %llu " - "start_block: %llx start_off: %llx " - "blkcnt: %llx extent-state: %x lastx: %x", - (unsigned long long)ip->i_ino, - (unsigned long long)gotp->br_startblock, - (unsigned long long)gotp->br_startoff, - (unsigned long long)gotp->br_blockcount, - gotp->br_state, *lastxp); - *lastxp = NULLEXTNUM; - *eofp = 1; - return NULL; - } - return ep; -} - /* * Returns the file-relative block number of the first unused block(s) * in the file with at least "len" logically contiguous blocks free. diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e3c2b5adf505..ffed1f9208ce 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -237,10 +237,6 @@ int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip, struct xfs_defer_ops *dfops, enum shift_direction direction, int num_exts); int xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset); -struct xfs_bmbt_rec_host * - xfs_bmap_search_extents(struct xfs_inode *ip, xfs_fileoff_t bno, - int fork, int *eofp, xfs_extnum_t *lastxp, - struct xfs_bmbt_irec *gotp, struct xfs_bmbt_irec *prevp); int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork, xfs_fileoff_t aoff, xfs_filblks_t len, struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof); -- cgit v1.2.3 From 0e8d630ba039d9976d250eedb82c3a423ad15447 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Nov 2016 11:40:32 +1100 Subject: xfs: remove NULLEXTNUM We only ever set a field to this constant for an impossible to reach error case in xfs_bmap_search_extents. That functions has been removed, so we can remove the constant as well. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 2 +- fs/xfs/libxfs/xfs_types.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index dcc847ceaebe..c2e13db14563 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4260,7 +4260,7 @@ xfs_bmapi_allocate( if (bma->wasdel) { bma->length = (xfs_extlen_t)bma->got.br_blockcount; bma->offset = bma->got.br_startoff; - if (bma->idx != NULLEXTNUM && bma->idx) { + if (bma->idx) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1), &bma->prev); } diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 8d74870468c2..f9a1076de911 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -57,7 +57,6 @@ typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ #define NULLAGBLOCK ((xfs_agblock_t)-1) #define NULLAGNUMBER ((xfs_agnumber_t)-1) -#define NULLEXTNUM ((xfs_extnum_t)-1) #define NULLCOMMITLSN ((xfs_lsn_t)-1) -- cgit v1.2.3 From 1247ec4c5f6e64b3cf01af58173820cdc61f11ed Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: add XBF_XBF_NO_IOACCT to buf trace output When XBF_NO_IOACCT got added, it missed the translation in XFS_BUF_FLAGS, so we see "0x8" in trace output rather than the flag name. Fix it. Signed-off-by: Eric Sandeen Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_buf.h | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 1c2e52b2d926..38c9a95bda7d 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -71,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_READ, "READ" }, \ { XBF_WRITE, "WRITE" }, \ { XBF_READ_AHEAD, "READ_AHEAD" }, \ + { XBF_NO_IOACCT, "NO_IOACCT" }, \ { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ -- cgit v1.2.3 From fd26a88093bab6529ea2de819114ca92dbd1d71d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: factor rmap btree size into the indlen calculations When we're estimating the amount of space it's going to take to satisfy a delalloc reservation, we need to include the space that we might need to grow the rmapbt. This helps us to avoid running out of space later when _iomap_write_allocate needs more space than we reserved. Eryu Guan observed this happening on generic/224 when sunit/swidth were set. Reported-by: Eryu Guan Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c2e13db14563..164790c1b419 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,6 +49,7 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" +#include "xfs_rmap_btree.h" kmem_zone_t *xfs_bmap_free_item_zone; @@ -190,8 +191,12 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ + xfs_filblks_t orig_len; mp = ip->i_mount; + + /* Calculate the worst-case size of the bmbt. */ + orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -199,12 +204,20 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) - return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) { + rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; + break; + } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } + + /* Calculate the worst-case size of the rmapbt. */ + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) + rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + + mp->m_rmap_maxlevels; + return rval; } -- cgit v1.2.3 From bb6e0ebed7f7474e0e44cf6b778ee2fda759ddd6 Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: fs: xfs: xfs_icreate_item: constify xfs_item_ops structure Declare the structure xfs_item_ops as const as it is only passed as an argument to the function xfs_log_item_init. As this argument is of type const struct xfs_item_ops *, so xfs_item_ops structures having this property can be declared as const. Done using Coccinelle: @r1 disable optional_qualifier @ identifier i; position p; @@ static struct xfs_item_ops i@p = {...}; @ok1@ identifier r1.i; position p; expression e1,e2,e3; @@ xfs_log_item_init(e1,e2,e3,&i@p) @bad@ position p!={r1.p,ok1.p}; identifier r1.i; @@ i@p @depends on !bad disable optional_qualifier@ identifier r1.i; @@ static +const struct xfs_item_ops i={...}; @depends on !bad disable optional_qualifier@ identifier r1.i; @@ +const struct xfs_item_ops i; File size before: text data bss dec hex filename 737 64 8 809 329 fs/xfs/xfs_icreate_item.o File size after: text data bss dec hex filename 801 0 8 809 329 fs/xfs/xfs_icreate_item.o Signed-off-by: Bhumika Goyal Reviewed-by: Eric Sandeen Signed-off-by: Dave Chinner --- fs/xfs/xfs_icreate_item.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index d45ca72af6fb..865ad1373e5e 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -133,7 +133,7 @@ xfs_icreate_item_committing( /* * This is the ops vector shared by all buf log items. */ -static struct xfs_item_ops xfs_icreate_item_ops = { +static const struct xfs_item_ops xfs_icreate_item_ops = { .iop_size = xfs_icreate_item_size, .iop_format = xfs_icreate_item_format, .iop_pin = xfs_icreate_item_pin, -- cgit v1.2.3 From cf7841c12d85d1fe0ad33fb8bc5746809a882010 Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: fs: xfs: libxfs: constify xfs_nameops structures Declare the structure xfs_nameops as const as it is only stored in the m_dirnameops field of a xfs_mount structure. This field is of type const struct xfs_nameops *, so xfs_nameops structures having this property can be declared as const. Done using Coccinelle: @r1 disable optional_qualifier @ identifier i; position p; @@ static struct xfs_nameops i@p = {...}; @ok1@ identifier r1.i; position p; struct xfs_mount mp; @@ mp.m_dirnameops=&i@p @bad@ position p!={r1.p,ok1.p}; identifier r1.i; @@ i@p @depends on !bad disable optional_qualifier@ identifier r1.i; @@ static +const struct xfs_nameops i={...}; @depends on !bad disable optional_qualifier@ identifier r1.i; @@ +const struct xfs_nameops i; File size before: text data bss dec hex filename 5302 85 0 5387 150b fs/xfs/libxfs/xfs_dir2.o File size after: text data bss dec hex filename 5318 69 0 5387 150b fs/xfs/libxfs/xfs_dir2.o Signed-off-by: Bhumika Goyal Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_dir2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 20a96dd5af7e..c58d72c220f5 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -93,7 +93,7 @@ xfs_ascii_ci_compname( return result; } -static struct xfs_nameops xfs_ascii_ci_nameops = { +static const struct xfs_nameops xfs_ascii_ci_nameops = { .hashname = xfs_ascii_ci_hashname, .compname = xfs_ascii_ci_compname, }; -- cgit v1.2.3 From fba3e594ef0ad911fa8f559732d588172f212d71 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: always succeed when deduping zero bytes It turns out that btrfs and xfs had differing interpretations of what to do when the dedupe length is zero. Change xfs to follow btrfs' semantics so that the userland interface is consistent. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 56372bee08c5..c58371fde08d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1317,8 +1317,14 @@ xfs_reflink_remap_range( goto out_unlock; } - if (len == 0) + /* Zero length dedupe exits immediately; reflink goes to EOF. */ + if (len == 0) { + if (is_dedupe) { + ret = 0; + goto out_unlock; + } len = isize - pos_in; + } /* Ensure offsets don't wrap and the input is inside i_size */ if (pos_in + len < pos_in || pos_out + len < pos_out || -- cgit v1.2.3 From 974ae922efd93b07b6cdf989ae959883f6f05fd8 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: track preallocation separately in xfs_bmapi_reserve_delalloc() Speculative preallocation is currently processed entirely by the callers of xfs_bmapi_reserve_delalloc(). The caller determines how much preallocation to include, adjusts the extent length and passes down the resulting request. While this works fine for post-eof speculative preallocation, it is not as reliable for COW fork preallocation. COW fork preallocation is implemented via the cowextszhint, which aligns the start offset as well as the length of the extent. Further, it is difficult for the caller to accurately identify when preallocation occurs because the returned extent could have been merged with neighboring extents in the fork. To simplify this situation and facilitate further COW fork preallocation enhancements, update xfs_bmapi_reserve_delalloc() to take a separate preallocation parameter to incorporate into the allocation request. The preallocation blocks value is tacked onto the end of the request and adjusted to accommodate neighboring extents and extent size limits. Since xfs_bmapi_reserve_delalloc() now knows precisely how much preallocation was included in the allocation, it can also tag the inodes appropriately to support preallocation reclaim. Note that xfs_bmapi_reserve_delalloc() callers are not yet updated to use the preallocation mechanism. This patch should not change behavior outside of correctly tagging reflink inodes when start offset preallocation occurs (which the caller does not handle correctly). Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 23 +++++++++++++++++++++-- fs/xfs/libxfs/xfs_bmap.h | 2 +- fs/xfs/xfs_iomap.c | 2 +- fs/xfs/xfs_reflink.c | 2 +- 4 files changed, 24 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 164790c1b419..6b7e6eb29414 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -50,6 +50,7 @@ #include "xfs_ag_resv.h" #include "xfs_refcount.h" #include "xfs_rmap_btree.h" +#include "xfs_icache.h" kmem_zone_t *xfs_bmap_free_item_zone; @@ -4154,8 +4155,9 @@ int xfs_bmapi_reserve_delalloc( struct xfs_inode *ip, int whichfork, - xfs_fileoff_t aoff, + xfs_fileoff_t off, xfs_filblks_t len, + xfs_filblks_t prealloc, struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof) @@ -4167,10 +4169,17 @@ xfs_bmapi_reserve_delalloc( char rt = XFS_IS_REALTIME_INODE(ip); xfs_extlen_t extsz; int error; + xfs_fileoff_t aoff = off; - alen = XFS_FILBLKS_MIN(len, MAXEXTLEN); + /* + * Cap the alloc length. Keep track of prealloc so we know whether to + * tag the inode before we return. + */ + alen = XFS_FILBLKS_MIN(len + prealloc, MAXEXTLEN); if (!eof) alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff); + if (prealloc && alen >= len) + prealloc = alen - len; /* Figure out the extent size, adjust alen */ if (whichfork == XFS_COW_FORK) @@ -4236,6 +4245,16 @@ xfs_bmapi_reserve_delalloc( */ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got); + /* + * Tag the inode if blocks were preallocated. Note that COW fork + * preallocation can occur at the start or end of the extent, even when + * prealloc == 0, so we must also check the aligned offset and length. + */ + if (whichfork == XFS_DATA_FORK && prealloc) + xfs_inode_set_eofblocks_tag(ip); + if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) + xfs_inode_set_cowblocks_tag(ip); + ASSERT(got->br_startoff <= aoff); ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen); ASSERT(isnullstartblock(got->br_startblock)); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index ffed1f9208ce..cecd094404cc 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -238,7 +238,7 @@ int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip, int num_exts); int xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset); int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork, - xfs_fileoff_t aoff, xfs_filblks_t len, + xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc, struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof); enum xfs_bmap_intent_type { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2272190b70ae..e4bfde212cc2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -620,7 +620,7 @@ xfs_file_iomap_begin_delay( retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb, - end_fsb - offset_fsb, &got, &idx, eof); + end_fsb - offset_fsb, 0, &got, &idx, eof); switch (error) { case 0: break; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index c58371fde08d..a5b027a43990 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -295,7 +295,7 @@ xfs_reflink_reserve_cow( retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, - end_fsb - imap->br_startoff, &got, &idx, eof); + end_fsb - imap->br_startoff, 0, &got, &idx, eof); switch (error) { case 0: break; -- cgit v1.2.3 From 0260d8ff5f76617e3a55a1c471383ecb4404c3ad Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: clean up cow fork reservation and tag inodes correctly COW fork reservation is implemented via delayed allocation. The code is modeled after the traditional delalloc allocation code, but is slightly different in terms of how preallocation occurs. Rather than post-eof speculative preallocation, COW fork preallocation is implemented via a COW extent size hint that is designed to minimize fragmentation as a reflinked file is split over time. xfs_reflink_reserve_cow() still uses logic that is oriented towards dealing with post-eof speculative preallocation, however, and is stale or not necessarily correct. First, the EOF alignment to the COW extent size hint is implemented in xfs_bmapi_reserve_delalloc() (which does so correctly by aligning the start and end offsets) and so is not necessary in xfs_reflink_reserve_cow(). The backoff and retry logic on ENOSPC is also ineffective for the same reason, as xfs_bmapi_reserve_delalloc() will simply perform the same allocation request on the retry. Finally, since the COW extent size hint aligns the start and end offset of the range to allocate, the end_fsb != orig_end_fsb logic is not sufficient. Indeed, if a write request happens to end on an aligned offset, it is possible that we do not tag the inode for COW preallocation even though xfs_bmapi_reserve_delalloc() may have preallocated at the start offset. Kill the unnecessary, duplicate code in xfs_reflink_reserve_cow(). Remove the inode tag logic as well since xfs_bmapi_reserve_delalloc() has been updated to tag the inode correctly. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 29 +++-------------------------- 1 file changed, 3 insertions(+), 26 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index a5b027a43990..becf2465dd23 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -245,11 +245,9 @@ xfs_reflink_reserve_cow( { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); struct xfs_bmbt_irec got; - xfs_fileoff_t end_fsb, orig_end_fsb; int error = 0; bool eof = false, trimmed; xfs_extnum_t idx; - xfs_extlen_t align; /* * Search the COW fork extent list first. This serves two purposes: @@ -287,33 +285,12 @@ xfs_reflink_reserve_cow( if (error) return error; - end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount; - - align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip)); - if (align) - end_fsb = roundup_64(end_fsb, align); - -retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, - end_fsb - imap->br_startoff, 0, &got, &idx, eof); - switch (error) { - case 0: - break; - case -ENOSPC: - case -EDQUOT: - /* retry without any preallocation */ + imap->br_blockcount, 0, &got, &idx, eof); + if (error == -ENOSPC || error == -EDQUOT) trace_xfs_reflink_cow_enospc(ip, imap); - if (end_fsb != orig_end_fsb) { - end_fsb = orig_end_fsb; - goto retry; - } - /*FALLTHRU*/ - default: + if (error) return error; - } - - if (end_fsb != orig_end_fsb) - xfs_inode_set_cowblocks_tag(ip); trace_xfs_reflink_cow_alloc(ip, &got); return 0; -- cgit v1.2.3 From f782088c9e5d08e9494c63e68b4e85716df3e5f8 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 28 Nov 2016 14:57:42 +1100 Subject: xfs: pass post-eof speculative prealloc blocks to bmapi xfs_file_iomap_begin_delay() implements post-eof speculative preallocation by extending the block count of the requested delayed allocation. Now that xfs_bmapi_reserve_delalloc() has been updated to handle prealloc blocks separately and tag the inode, update xfs_file_iomap_begin_delay() to use the new parameter and rely on the former to tag the inode. Note that this patch does not change behavior. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index e4bfde212cc2..15a83813b708 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -536,10 +536,11 @@ xfs_file_iomap_begin_delay( xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); xfs_fileoff_t maxbytes_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes); - xfs_fileoff_t end_fsb, orig_end_fsb; + xfs_fileoff_t end_fsb; int error = 0, eof = 0; struct xfs_bmbt_irec got; xfs_extnum_t idx; + xfs_fsblock_t prealloc_blocks = 0; ASSERT(!XFS_IS_REALTIME_INODE(ip)); ASSERT(!xfs_get_extsz_hint(ip)); @@ -594,33 +595,32 @@ xfs_file_iomap_begin_delay( * the lower level functions are updated. */ count = min_t(loff_t, count, 1024 * PAGE_SIZE); - end_fsb = orig_end_fsb = - min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb); + end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb); if (eof) { - xfs_fsblock_t prealloc_blocks; - prealloc_blocks = xfs_iomap_prealloc_size(ip, offset, count, idx); if (prealloc_blocks) { xfs_extlen_t align; xfs_off_t end_offset; + xfs_fileoff_t p_end_fsb; end_offset = XFS_WRITEIO_ALIGN(mp, offset + count - 1); - end_fsb = XFS_B_TO_FSBT(mp, end_offset) + - prealloc_blocks; + p_end_fsb = XFS_B_TO_FSBT(mp, end_offset) + + prealloc_blocks; align = xfs_eof_alignment(ip, 0); if (align) - end_fsb = roundup_64(end_fsb, align); + p_end_fsb = roundup_64(p_end_fsb, align); - end_fsb = min(end_fsb, maxbytes_fsb); - ASSERT(end_fsb > offset_fsb); + p_end_fsb = min(p_end_fsb, maxbytes_fsb); + ASSERT(p_end_fsb > offset_fsb); + prealloc_blocks = p_end_fsb - end_fsb; } } retry: error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb, - end_fsb - offset_fsb, 0, &got, &idx, eof); + end_fsb - offset_fsb, prealloc_blocks, &got, &idx, eof); switch (error) { case 0: break; @@ -628,8 +628,8 @@ retry: case -EDQUOT: /* retry without any preallocation */ trace_xfs_delalloc_enospc(ip, offset, count); - if (end_fsb != orig_end_fsb) { - end_fsb = orig_end_fsb; + if (prealloc_blocks) { + prealloc_blocks = 0; goto retry; } /*FALLTHRU*/ @@ -637,13 +637,6 @@ retry: goto out_unlock; } - /* - * Tag the inode as speculatively preallocated so we can reclaim this - * space on demand, if necessary. - */ - if (end_fsb != orig_end_fsb) - xfs_inode_set_eofblocks_tag(ip); - trace_xfs_iomap_alloc(ip, offset, count, 0, &got); done: if (isnullstartblock(got.br_startblock)) -- cgit v1.2.3