diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-21 11:53:05 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-21 11:53:05 -0700 |
commit | 53d2e6976bd4042672ed7b90dfbf4b31635b7dcf (patch) | |
tree | 1d137e044c52433df6b4785fed1c7aafbb9333bc /fs | |
parent | d407574e7948210223a7adca5ff26e3b0ec8143e (diff) | |
parent | 2cdb958aba6afbced5bc563167813b972b6acbfe (diff) |
Merge tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs
Pull xfs updates from Dave Chinner:
"There's quite a lot in this request, and there's some cross-over with
ext4, dax and quota code due to the nature of the changes being made.
As for the rest of the XFS changes, there are lots of little things
all over the place, which add up to a lot of changes in the end.
The major changes are that we've reduced the size of the struct
xfs_inode by ~100 bytes (gives an inode cache footprint reduction of
>10%), the writepage code now only does a single set of mapping tree
lockups so uses less CPU, delayed allocation reservations won't
overrun under random write loads anymore, and we added compile time
verification for on-disk structure sizes so we find out when a commit
or platform/compiler change breaks the on disk structure as early as
possible.
Change summary:
- error propagation for direct IO failures fixes for both XFS and
ext4
- new quota interfaces and XFS implementation for iterating all the
quota IDs in the filesystem
- locking fixes for real-time device extent allocation
- reduction of duplicate information in the xfs and vfs inode, saving
roughly 100 bytes of memory per cached inode.
- buffer flag cleanup
- rework of the writepage code to use the generic write clustering
mechanisms
- several fixes for inode flag based DAX enablement
- rework of remount option parsing
- compile time verification of on-disk format structure sizes
- delayed allocation reservation overrun fixes
- lots of little error handling fixes
- small memory leak fixes
- enable xfsaild freezing again"
* tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (66 commits)
xfs: always set rvalp in xfs_dir2_node_trim_free
xfs: ensure committed is initialized in xfs_trans_roll
xfs: borrow indirect blocks from freed extent when available
xfs: refactor delalloc indlen reservation split into helper
xfs: update freeblocks counter after extent deletion
xfs: debug mode forced buffered write failure
xfs: remove impossible condition
xfs: check sizes of XFS on-disk structures at compile time
xfs: ioends require logically contiguous file offsets
xfs: use named array initializers for log item dumping
xfs: fix computation of inode btree maxlevels
xfs: reinitialise per-AG structures if geometry changes during recovery
xfs: remove xfs_trans_get_block_res
xfs: fix up inode32/64 (re)mount handling
xfs: fix format specifier , should be %llx and not %llu
xfs: sanitize remount options
xfs: convert mount option parsing to tokens
xfs: fix two memory leaks in xfs_attr_list.c error paths
xfs: XFS_DIFLAG2_DAX limited by PAGE_SIZE
xfs: dynamically switch modes when XFS_DIFLAG2_DAX is set/cleared
...
Diffstat (limited to 'fs')
66 files changed, 2178 insertions, 1590 deletions
@@ -286,8 +286,13 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode, if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) inode_unlock(inode); - if ((retval > 0) && end_io) - end_io(iocb, pos, retval, bh.b_private); + if (end_io) { + int err; + + err = end_io(iocb, pos, retval, bh.b_private); + if (err) + retval = err; + } if (!(flags & DIO_SKIP_DIO_COUNT)) inode_dio_end(inode); diff --git a/fs/direct-io.c b/fs/direct-io.c index 0a8d937c6775..476f1ecbd1f0 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -253,8 +253,13 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, if (ret == 0) ret = transferred; - if (dio->end_io && dio->result) - dio->end_io(dio->iocb, offset, transferred, dio->private); + if (dio->end_io) { + int err; + + err = dio->end_io(dio->iocb, offset, ret, dio->private); + if (err) + ret = err; + } if (!(dio->flags & DIO_SKIP_DIO_COUNT)) inode_dio_end(dio->inode); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 393689dfa1af..c04743519865 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1511,15 +1511,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } -static inline void ext4_set_io_unwritten_flag(struct inode *inode, - struct ext4_io_end *io_end) -{ - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_unwritten); - } -} - /* * Inode dynamic state flags */ @@ -3293,6 +3284,27 @@ extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern int ext4_resize_begin(struct super_block *sb); extern void ext4_resize_end(struct super_block *sb); +static inline void ext4_set_io_unwritten_flag(struct inode *inode, + struct ext4_io_end *io_end) +{ + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_unwritten); + } +} + +static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) +{ + struct inode *inode = io_end->inode; + + if (io_end->flag & EXT4_IO_END_UNWRITTEN) { + io_end->flag &= ~EXT4_IO_END_UNWRITTEN; + /* Wake up anyone waiting on unwritten extent conversion */ + if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) + wake_up_all(ext4_ioend_wq(inode)); + } +} + #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b2e9576450eb..dab84a2530ff 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3289,22 +3289,32 @@ out: } #endif -static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, +static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private) { ext4_io_end_t *io_end = private; /* if not async direct IO just return */ if (!io_end) - return; + return 0; ext_debug("ext4_end_io_dio(): io_end 0x%p " "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", io_end, io_end->inode->i_ino, iocb, offset, size); + /* + * Error during AIO DIO. We cannot convert unwritten extents as the + * data was not written. Just clear the unwritten flag and drop io_end. + */ + if (size <= 0) { + ext4_clear_io_unwritten_flag(io_end); + size = 0; + } io_end->offset = offset; io_end->size = size; ext4_put_io_end(io_end); + + return 0; } /* diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 349d7aa04fe7..d77d15f4b674 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -136,16 +136,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end) kmem_cache_free(io_end_cachep, io_end); } -static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) -{ - struct inode *inode = io_end->inode; - - io_end->flag &= ~EXT4_IO_END_UNWRITTEN; - /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) - wake_up_all(ext4_ioend_wq(inode)); -} - /* * Check a range of space and convert unwritten extents to written. Note that * we are protected from truncate touching same part of extent tree by the diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index cda0361e95a4..043110e5212d 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -620,7 +620,7 @@ bail: * particularly interested in the aio/dio case. We use the rw_lock DLM lock * to protect io on one node from truncation on another. */ -static void ocfs2_dio_end_io(struct kiocb *iocb, +static int ocfs2_dio_end_io(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private) @@ -628,6 +628,9 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, struct inode *inode = file_inode(iocb->ki_filp); int level; + if (bytes <= 0) + return 0; + /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); @@ -644,6 +647,8 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); } + + return 0; } static int ocfs2_releasepage(struct page *page, gfp_t wait) diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 3746367098fd..0ebc90496525 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -79,7 +79,7 @@ unsigned int qtype_enforce_flag(int type) return 0; } -static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, +static int quota_quotaon(struct super_block *sb, int type, qid_t id, struct path *path) { if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) @@ -222,6 +222,34 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, return 0; } +/* + * Return quota for next active quota >= this id, if any exists, + * otherwise return -ESRCH via ->get_nextdqblk + */ +static int quota_getnextquota(struct super_block *sb, int type, qid_t id, + void __user *addr) +{ + struct kqid qid; + struct qc_dqblk fdq; + struct if_nextdqblk idq; + int ret; + + if (!sb->s_qcop->get_nextdqblk) + return -ENOSYS; + qid = make_kqid(current_user_ns(), type, id); + if (!qid_valid(qid)) + return -EINVAL; + ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq); + if (ret) + return ret; + /* struct if_nextdqblk is a superset of struct if_dqblk */ + copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq); + idq.dqb_id = from_kqid(current_user_ns(), qid); + if (copy_to_user(addr, &idq, sizeof(idq))) + return -EFAULT; + return 0; +} + static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); @@ -625,6 +653,34 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id, return ret; } +/* + * Return quota for next active quota >= this id, if any exists, + * otherwise return -ESRCH via ->get_nextdqblk. + */ +static int quota_getnextxquota(struct super_block *sb, int type, qid_t id, + void __user *addr) +{ + struct fs_disk_quota fdq; + struct qc_dqblk qdq; + struct kqid qid; + qid_t id_out; + int ret; + + if (!sb->s_qcop->get_nextdqblk) + return -ENOSYS; + qid = make_kqid(current_user_ns(), type, id); + if (!qid_valid(qid)) + return -EINVAL; + ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq); + if (ret) + return ret; + id_out = from_kqid(current_user_ns(), qid); + copy_to_xfs_dqblk(&fdq, &qdq, type, id_out); + if (copy_to_user(addr, &fdq, sizeof(fdq))) + return -EFAULT; + return ret; +} + static int quota_rmxquota(struct super_block *sb, void __user *addr) { __u32 flags; @@ -659,7 +715,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, switch (cmd) { case Q_QUOTAON: - return quota_quotaon(sb, type, cmd, id, path); + return quota_quotaon(sb, type, id, path); case Q_QUOTAOFF: return quota_quotaoff(sb, type); case Q_GETFMT: @@ -670,6 +726,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return quota_setinfo(sb, type, addr); case Q_GETQUOTA: return quota_getquota(sb, type, id, addr); + case Q_GETNEXTQUOTA: + return quota_getnextquota(sb, type, id, addr); case Q_SETQUOTA: return quota_setquota(sb, type, id, addr); case Q_SYNC: @@ -690,6 +748,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return quota_setxquota(sb, type, id, addr); case Q_XGETQUOTA: return quota_getxquota(sb, type, id, addr); + case Q_XGETNEXTQUOTA: + return quota_getnextxquota(sb, type, id, addr); case Q_XQUOTASYNC: if (sb->s_flags & MS_RDONLY) return -EROFS; @@ -708,10 +768,12 @@ static int quotactl_cmd_write(int cmd) switch (cmd) { case Q_GETFMT: case Q_GETINFO: + case Q_GETNEXTQUOTA: case Q_SYNC: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETQUOTA: + case Q_XGETNEXTQUOTA: case Q_XQUOTASYNC: return 0; } diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 444626ddbd1b..d9b42425291e 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -118,8 +118,6 @@ xfs_allocbt_free_block( xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); - - xfs_trans_binval(cur->bc_tp, bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h index 919756e3ba53..90928bbe693c 100644 --- a/fs/xfs/libxfs/xfs_attr_sf.h +++ b/fs/xfs/libxfs/xfs_attr_sf.h @@ -24,22 +24,6 @@ * Small attribute lists are packed as tightly as possible so as * to fit into the literal area of the inode. */ - -/* - * Entries are packed toward the top as tight as possible. - */ -typedef struct xfs_attr_shortform { - struct xfs_attr_sf_hdr { /* constant-structure header block */ - __be16 totsize; /* total bytes in shortform list */ - __u8 count; /* count of active entries */ - } hdr; - struct xfs_attr_sf_entry { - __uint8_t namelen; /* actual length of name (no NULL) */ - __uint8_t valuelen; /* actual length of value (no NULL) */ - __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ - __uint8_t nameval[1]; /* name & value bytes concatenated */ - } list[1]; /* variable sized array */ -} xfs_attr_shortform_t; typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t; typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index ef00156f4f96..041b6948aecc 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -477,10 +477,7 @@ xfs_bmap_check_leaf_extents( } block = XFS_BUF_TO_BLOCK(bp); } - if (bp_release) { - bp_release = 0; - xfs_trans_brelse(NULL, bp); - } + return; error0: @@ -912,7 +909,7 @@ xfs_bmap_local_to_extents( * We don't want to deal with the case of keeping inode data inline yet. * So sending the data fork of a regular inode is invalid. */ - ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK)); + ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK)); ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); @@ -1079,7 +1076,7 @@ xfs_bmap_add_attrfork_local( if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip)) return 0; - if (S_ISDIR(ip->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip)->i_mode)) { memset(&dargs, 0, sizeof(dargs)); dargs.geo = ip->i_mount->m_dir_geo; dargs.dp = ip; @@ -1091,7 +1088,7 @@ xfs_bmap_add_attrfork_local( return xfs_dir2_sf_to_block(&dargs); } - if (S_ISLNK(ip->i_d.di_mode)) + if (S_ISLNK(VFS_I(ip)->i_mode)) return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags, XFS_DATA_FORK, xfs_symlink_local_to_remote); @@ -4721,6 +4718,66 @@ error0: } /* + * When a delalloc extent is split (e.g., due to a hole punch), the original + * indlen reservation must be shared across the two new extents that are left + * behind. + * + * Given the original reservation and the worst case indlen for the two new + * extents (as calculated by xfs_bmap_worst_indlen()), split the original + * reservation fairly across the two new extents. If necessary, steal available + * blocks from a deleted extent to make up a reservation deficiency (e.g., if + * ores == 1). The number of stolen blocks is returned. The availability and + * subsequent accounting of stolen blocks is the responsibility of the caller. + */ +static xfs_filblks_t +xfs_bmap_split_indlen( + xfs_filblks_t ores, /* original res. */ + xfs_filblks_t *indlen1, /* ext1 worst indlen */ + xfs_filblks_t *indlen2, /* ext2 worst indlen */ + xfs_filblks_t avail) /* stealable blocks */ +{ + xfs_filblks_t len1 = *indlen1; + xfs_filblks_t len2 = *indlen2; + xfs_filblks_t nres = len1 + len2; /* new total res. */ + xfs_filblks_t stolen = 0; + + /* + * Steal as many blocks as we can to try and satisfy the worst case + * indlen for both new extents. + */ + while (nres > ores && avail) { + nres--; + avail--; + stolen++; + } + + /* + * The only blocks available are those reserved for the original + * extent and what we can steal from the extent being removed. + * If this still isn't enough to satisfy the combined + * requirements for the two new extents, skim blocks off of each + * of the new reservations until they match what is available. + */ + while (nres > ores) { + if (len1) { + len1--; + nres--; + } + if (nres == ores) + break; + if (len2) { + len2--; + nres--; + } + } + + *indlen1 = len1; + *indlen2 = len2; + + return stolen; +} + +/* * Called by xfs_bmapi to update file extent records and the btree * after removing space (or undoing a delayed allocation). */ @@ -4984,28 +5041,29 @@ xfs_bmap_del_extent( XFS_IFORK_NEXT_SET(ip, whichfork, XFS_IFORK_NEXTENTS(ip, whichfork) + 1); } else { + xfs_filblks_t stolen; ASSERT(whichfork == XFS_DATA_FORK); - temp = xfs_bmap_worst_indlen(ip, temp); + + /* + * 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 in xfs_bunmapi(). + */ + temp = xfs_bmap_worst_indlen(ip, got.br_blockcount); + temp2 = xfs_bmap_worst_indlen(ip, new.br_blockcount); + stolen = xfs_bmap_split_indlen(da_old, &temp, &temp2, + del->br_blockcount); + da_new = temp + temp2 - stolen; + del->br_blockcount -= stolen; + + /* + * Set the reservation for each extent. Warn if either + * is zero as this can lead to delalloc problems. + */ + WARN_ON_ONCE(!temp || !temp2); 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, *idx, state, _THIS_IP_); xfs_iext_insert(ip, *i |