diff options
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | fs/direct-io.c | 18 | ||||
| -rw-r--r-- | fs/open.c | 29 | ||||
| -rw-r--r-- | fs/xfs/xfs_acl.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_aops.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_bmap.c | 193 | ||||
| -rw-r--r-- | fs/xfs/xfs_bmap.h | 15 | ||||
| -rw-r--r-- | fs/xfs/xfs_bmap_util.c | 97 | ||||
| -rw-r--r-- | fs/xfs/xfs_bmap_util.h | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_buf_item.c | 19 | ||||
| -rw-r--r-- | fs/xfs/xfs_dquot.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_file.c | 26 | ||||
| -rw-r--r-- | fs/xfs/xfs_iomap.c | 10 | ||||
| -rw-r--r-- | fs/xfs/xfs_iops.c | 16 | ||||
| -rw-r--r-- | fs/xfs/xfs_log.h | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_cil.c | 22 | ||||
| -rw-r--r-- | fs/xfs/xfs_mount.c | 24 | ||||
| -rw-r--r-- | fs/xfs/xfs_rtalloc.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_sb.c | 11 | ||||
| -rw-r--r-- | fs/xfs/xfs_trace.h | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.c | 12 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans_resv.c | 6 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans_resv.h | 1 | ||||
| -rw-r--r-- | include/linux/fs.h | 3 | ||||
| -rw-r--r-- | include/uapi/linux/falloc.h | 35 |
25 files changed, 463 insertions, 89 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index b2cf5cf..e75188f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9715,7 +9715,6 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM P: Silicon Graphics Inc M: Dave Chinner <david@fromorbit.com> -M: Ben Myers <bpm@sgi.com> M: xfs@oss.sgi.com L: xfs@oss.sgi.com W: http://oss.sgi.com/projects/xfs diff --git a/fs/direct-io.c b/fs/direct-io.c index 160a548..a701752 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1194,13 +1194,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, } /* - * For file extending writes updating i_size before data - * writeouts complete can expose uninitialized blocks. So - * even for AIO, we need to wait for i/o to complete before - * returning in this case. + * For file extending writes updating i_size before data writeouts + * complete can expose uninitialized blocks in dumb filesystems. + * In that case we need to wait for I/O completion even if asked + * for an asynchronous write. */ - dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) && - (end > i_size_read(inode))); + if (is_sync_kiocb(iocb)) + dio->is_async = false; + else if (!(dio->flags & DIO_ASYNC_EXTEND) && + (rw & WRITE) && end > i_size_read(inode)) + dio->is_async = false; + else + dio->is_async = true; + dio->inode = inode; dio->rw = rw; @@ -231,7 +231,13 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EINVAL; /* Return error if mode is not supported */ - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) + return -EOPNOTSUPP; + + /* Punch hole and zero range are mutually exclusive */ + if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == + (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; /* Punch hole must have keep size set */ @@ -239,11 +245,20 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) !(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; + /* Collapse range should only be used exclusively. */ + if ((mode & FALLOC_FL_COLLAPSE_RANGE) && + (mode & ~FALLOC_FL_COLLAPSE_RANGE)) + return -EINVAL; + if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - /* It's not possible punch hole on append only file */ - if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode)) + /* + * It's not possible to punch hole or perform collapse range + * on append only file + */ + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE) + && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) @@ -271,6 +286,14 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) return -EFBIG; + /* + * There is no need to overlap collapse range with EOF, in which case + * it is effectively a truncate operation + */ + if ((mode & FALLOC_FL_COLLAPSE_RANGE) && + (offset + len >= i_size_read(inode))) + return -EINVAL; + if (!file->f_op->fallocate) return -EOPNOTSUPP; diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 0ecec18..6888ad8 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -281,7 +281,7 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (!acl) goto set_acl; - error = -EINVAL; + error = -E2BIG; if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb))) return error; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index db2cfb0..ef62c6b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1441,7 +1441,8 @@ xfs_vm_direct_IO( ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, nr_segs, xfs_get_blocks_direct, - xfs_end_io_direct_write, NULL, 0); + xfs_end_io_direct_write, NULL, + DIO_ASYNC_EXTEND); if (ret != -EIOCBQUEUED && iocb->private) goto out_destroy_ioend; } else { diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 152543c..5b6092e 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -5378,3 +5378,196 @@ error0: } return error; } + +/* + * Shift extent records to the left to cover a hole. + * + * The maximum number of extents to be shifted in a single operation + * is @num_exts, and @current_ext keeps track of the current extent + * index we have shifted. @offset_shift_fsb is the length by which each + * extent is shifted. If there is no hole to shift the extents + * into, this will be considered invalid operation and we abort immediately. + */ +int +xfs_bmap_shift_extents( + struct xfs_trans *tp, + struct xfs_inode *ip, + int *done, + xfs_fileoff_t start_fsb, + xfs_fileoff_t offset_shift_fsb, + xfs_extnum_t *current_ext, + xfs_fsblock_t *firstblock, + struct xfs_bmap_free *flist, + int num_exts) +{ + struct xfs_btree_cur *cur; + struct xfs_bmbt_rec_host *gotp; + struct xfs_bmbt_irec got; + struct xfs_bmbt_irec left; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp; + xfs_extnum_t nexts = 0; + xfs_fileoff_t startoff; + int error = 0; + int i; + int whichfork = XFS_DATA_FORK; + int logflags; + xfs_filblks_t blockcount = 0; + + if (unlikely(XFS_TEST_ERROR( + (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), + mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + XFS_ERROR_REPORT("xfs_bmap_shift_extents", + XFS_ERRLEVEL_LOW, mp); + return XFS_ERROR(EFSCORRUPTED); + } + + if (XFS_FORCED_SHUTDOWN(mp)) + return XFS_ERROR(EIO); + + ASSERT(current_ext != NULL); + + ifp = XFS_IFORK_PTR(ip, whichfork); + + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + /* Read in all the extents */ + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; + } + + /* + * If *current_ext is 0, we would need to lookup the extent + * from where we would start shifting and store it in gotp. + */ + if (!*current_ext) { + gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext); + /* + * gotp can be null in 2 cases: 1) if there are no extents + * or 2) start_fsb lies in a hole beyond which there are + * no extents. Either way, we are done. + */ + if (!gotp) { + *done = 1; + return 0; + } + } + + /* We are going to change core inode */ + logflags = XFS_ILOG_CORE; + + if (ifp->if_flags & XFS_IFBROOT) { + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); + cur->bc_private.b.firstblock = *firstblock; + cur->bc_private.b.flist = flist; + cur->bc_private.b.flags = 0; + } else { + cur = NULL; + logflags |= XFS_ILOG_DEXT; + } + + while (nexts++ < num_exts && + *current_ext < XFS_IFORK_NEXTENTS(ip, whichfork)) { + + gotp = xfs_iext_get_ext(ifp, *current_ext); + xfs_bmbt_get_all(gotp, &got); + startoff = got.br_startoff - offset_shift_fsb; + + /* + * Before shifting extent into hole, make sure that the hole + * is large enough to accomodate the shift. + */ + if (*current_ext) { + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, + *current_ext - 1), &left); + + if (startoff < left.br_startoff + left.br_blockcount) + error = XFS_ERROR(EINVAL); + } else if (offset_shift_fsb > got.br_startoff) { + /* + * When first extent is shifted, offset_shift_fsb + * should be less than the stating offset of + * the first extent. + */ + error = XFS_ERROR(EINVAL); + } + + if (error) + goto del_cursor; + + if (cur) { + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); + } + + /* Check if we can merge 2 adjacent extents */ + if (*current_ext && + left.br_startoff + left.br_blockcount == startoff && + left.br_startblock + left.br_blockcount == + got.br_startblock && + left.br_state == got.br_state && + left.br_blockcount + got.br_blockcount <= MAXEXTLEN) { + blockcount = left.br_blockcount + + got.br_blockcount; + xfs_iext_remove(ip, *current_ext, 1, 0); + if (cur) { + error = xfs_btree_delete(cur, &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); + } + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + gotp = xfs_iext_get_ext(ifp, --*current_ext); + xfs_bmbt_get_all(gotp, &got); + + /* Make cursor point to the extent we will update */ + if (cur) { + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); + } + + xfs_bmbt_set_blockcount(gotp, blockcount); + got.br_blockcount = blockcount; + } else { + /* We have to update the startoff */ + xfs_bmbt_set_startoff(gotp, startoff); + got.br_startoff = startoff; + } + + if (cur) { + error = xfs_bmbt_update(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + got.br_state); + if (error) + goto del_cursor; + } + + (*current_ext)++; + } + + /* Check if we are done */ + if (*current_ext == XFS_IFORK_NEXTENTS(ip, whichfork)) + *done = 1; + +del_cursor: + if (cur) + xfs_btree_del_cursor(cur, + error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + + xfs_trans_log_inode(tp, ip, logflags); + + return error; +} diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 33b41f3..f84bd7a 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -127,6 +127,16 @@ static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp) { BMAP_RIGHT_FILLING, "RF" }, \ { BMAP_ATTRFORK, "ATTR" } + +/* + * This macro is used to determine how many extents will be shifted + * in one write transaction. We could require two splits, + * an extent move on the first and an extent merge on the second, + * So it is proper that one extent is shifted inside write transaction + * at a time. + */ +#define XFS_BMAP_MAX_SHIFT_EXTENTS 1 + #ifdef DEBUG void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, int whichfork, unsigned long caller_ip); @@ -169,5 +179,10 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, 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); +int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip, + int *done, xfs_fileoff_t start_fsb, + xfs_fileoff_t offset_shift_fsb, xfs_extnum_t *current_ext, + xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist, + int num_exts); #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index f264616..01f6a64 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1349,7 +1349,6 @@ xfs_free_file_space( * the freeing of the space succeeds at ENOSPC. */ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); - tp->t_flags |= XFS_TRANS_RESERVE; error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0); /* @@ -1468,6 +1467,102 @@ out: } /* + * xfs_collapse_file_space() + * This routine frees disk space and shift extent for the given file. + * The first thing we do is to free data blocks in the specified range + * by calling xfs_free_file_space(). It would also sync dirty data + * and invalidate page cache over the region on which collapse range + * is working. And Shift extent records to the left to cover a hole. + * RETURNS: + * 0 on success + * errno on error + * + */ +int +xfs_collapse_file_space( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t len) +{ + int done = 0; + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + xfs_extnum_t current_ext = 0; + struct xfs_bmap_free free_list; + xfs_fsblock_t first_block; + int committed; + xfs_fileoff_t start_fsb; + xfs_fileoff_t shift_fsb; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + + trace_xfs_collapse_file_space(ip); + + start_fsb = XFS_B_TO_FSB(mp, offset + len); + shift_fsb = XFS_B_TO_FSB(mp, len); + + error = xfs_free_file_space(ip, offset, len); + if (error) + return error; + + while (!error && !done) { + tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); + tp->t_flags |= XFS_TRANS_RESERVE; + /* + * We would need to reserve permanent block for transaction. + * This will come into picture when after shifting extent into + * hole we found that adjacent extents can be merged which + * may lead to freeing of a block during record update. + */ + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, + XFS_DIOSTRAT_SPACE_RES(mp, 0), 0); + if (error) { + ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp)); + xfs_trans_cancel(tp, 0); + break; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, + XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, + XFS_QMOPT_RES_REGBLKS); + if (error) + goto out; + + xfs_trans_ijoin(tp, ip, 0); + + xfs_bmap_init(&free_list, &first_block); + + /* + * We are using the write transaction in which max 2 bmbt + * updates are allowed + */ + error = xfs_bmap_shift_extents(tp, ip, &done, start_fsb, + shift_fsb, ¤t_ext, + &first_block, &free_list, + XFS_BMAP_MAX_SHIFT_EXTENTS); + if (error) + goto out; + + error = xfs_bmap_finish(&tp, &free_list, &committed); + if (error) + goto out; + + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + } + + return error; + +out: + xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; +} + +/* * We need to check that the format of the data fork in the temporary inode is * valid for the target inode before doing the swap. This is not a problem with * attr1 because of the fixed fork offset, but attr2 has a dynamically sized diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 900747b..935ed2b2 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -99,6 +99,8 @@ int xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); int xfs_zero_file_space(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); +int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset, + xfs_off_t len); /* EOF block manipulation functions */ bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3314911..8752821 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -796,20 +796,6 @@ xfs_buf_item_init( bip->bli_formats[i].blf_map_size = map_size; } -#ifdef XFS_TRANS_DEBUG - /* - * Allocate the arrays for tracking what needs to be logged - * and what our callers request to be logged. bli_orig - * holds a copy of the original, clean buffer for comparison - * against, and bli_logged keeps a 1 bit flag per byte in - * the buffer to indicate which bytes the callers have asked - * to have logged. - */ - bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP); - memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length)); - bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP); -#endif - /* * Put the buf item into the list of items attached to the * buffer at the front. @@ -957,11 +943,6 @@ STATIC void xfs_buf_item_free( xfs_buf_log_item_t *bip) { -#ifdef XFS_TRANS_DEBUG - kmem_free(bip->bli_orig); - kmem_free(bip->bli_logged); -#endif /* XFS_TRANS_DEBUG */ - xfs_buf_item_free_format(bip); kmem_zone_free(xfs_buf_item_zone, bip); } diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 7aeb4c8..868b19f 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -615,7 +615,7 @@ xfs_qm_dqread( if (flags & XFS_QMOPT_DQALLOC) { tp = xfs_trans_alloc(mp, XFS_TRANS_QM_DQALLOC); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_attrsetm, + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_dqalloc, XFS_QM_DQALLOC_SPACE_RES(mp), 0); if (error) goto error1; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2e7989e..8fb97a6 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -823,7 +823,8 @@ xfs_file_fallocate( if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; xfs_ilock(ip, XFS_IOLOCK_EXCL); @@ -831,6 +832,20 @@ xfs_file_fallocate( error = xfs_free_file_space(ip, offset, len); if (error) goto out_unlock; + } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { + unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + + if (offset & blksize_mask || len & blksize_mask) { + error = -EINVAL; + goto out_unlock; + } + + ASSERT(offset + len < i_size_read(inode)); + new_size = i_size_read(inode) - len; + + error = xfs_collapse_file_space(ip, offset, len); + if (error) + goto out_unlock; } else { if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { @@ -840,8 +855,11 @@ xfs_file_fallocate( goto out_unlock; } - error = xfs_alloc_file_space(ip, offset, len, - XFS_BMAPI_PREALLOC); + if (mode & FALLOC_FL_ZERO_RANGE) + error = xfs_zero_file_space(ip, offset, len); + else + error = xfs_alloc_file_space(ip, offset, len, + XFS_BMAPI_PREALLOC); if (error) goto out_unlock; } @@ -859,7 +877,7 @@ xfs_file_fallocate( if (ip->i_d.di_mode & S_IXGRP) ip->i_d.di_mode &= ~S_ISGID; - if (!(mode & FALLOC_FL_PUNCH_HOLE)) + if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE))) ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 22d1cbe..3b80eba 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -128,7 +128,6 @@ xfs_iomap_write_direct( xfs_fsblock_t firstfsb; xfs_extlen_t extsz, temp; int nimaps; - int bmapi_flag; int quota_flag; int rt; xfs_trans_t *tp; @@ -200,18 +199,15 @@ xfs_iomap_write_direct( xfs_trans_ijoin(tp, ip, 0); - bmapi_flag = 0; - if (offset < XFS_ISIZE(ip) || extsz) - bmapi_flag |= XFS_BMAPI_PREALLOC; - /* * From this point onwards we overwrite the imap pointer that the * caller gave to us. */ xfs_bmap_init(&free_list, &firstfsb); nimaps = 1; - error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flag, - &firstfsb, 0, imap, &nimaps, &free_list); + error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, + XFS_BMAPI_PREALLOC, &firstfsb, 0, + imap, &nimaps, &free_list); if (error) goto out_bmap_cancel; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 234e843..bb3bb65 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -717,7 +717,6 @@ xfs_setattr_size( { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); - int mask = iattr->ia_valid; xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; @@ -738,8 +737,8 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); - ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| + ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; @@ -748,7 +747,7 @@ xfs_setattr_size( * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { - if (!(mask & (ATTR_CTIME|ATTR_MTIME))) + if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* @@ -836,10 +835,11 @@ xfs_setattr_size( * these flags set. For all other operations the VFS set these flags * explicitly if it wants a timestamp update. */ - if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { + if (newsize != oldsize && + !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = current_fs_time(inode->i_sb); - mask |= ATTR_CTIME | ATTR_MTIME; + iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } /* @@ -875,9 +875,9 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); } - if (mask & ATTR_MODE) + if (iattr->ia_valid & ATTR_MODE) xfs_setattr_mode(ip, iattr); - if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) + if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index b0f4ef7..2c40044 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -175,7 +175,7 @@ void xlog_iodone(struct xfs_buf *); struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket); void xfs_log_ticket_put(struct xlog_ticket *ticket); -int xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp, +void xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp, xfs_lsn_t *commit_lsn, int flags); bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 1270ded..7e54553 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -205,16 +205,25 @@ xlog_cil_insert_format_items( /* * We 64-bit align the length of each iovec so that the start * of the next one is naturally aligned. We'll need to - * account for that slack space here. + * account for that slack space here. Then round nbytes up + * to 64-bit alignment so that the initial buffer alignment is + * easy to calculate and verify. */ nbytes += niovecs * sizeof(uint64_t); + nbytes = round_up(nbytes, sizeof(uint64_t)); /* grab the old item if it exists for reservation accounting */ old_lv = lip->li_lv; - /* calc buffer size */ - buf_size = sizeof(struct xfs_log_vec) + nbytes + - niovecs * sizeof(struct xfs_log_iovec); + /* + * The data buffer needs to start 64-bit aligned, so round up + * that space to ensure we can align it appropriately and not + * overrun the buffer. + */ + buf_size = nbytes + + round_up((sizeof(struct xfs_log_vec) + + niovecs * sizeof(struct xfs_log_iovec)), + sizeof(uint64_t)); /* compare to existing item size */ if (lip->li_lv && buf_size <= lip->li_lv->lv_size) { @@ -251,6 +260,8 @@ xlog_cil_insert_format_items( /* The allocated data region lies beyond the iovec region */ lv->lv_buf_len = 0; lv->lv_buf = (char *)lv + buf_size - nbytes; + ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); + lip->li_ops->iop_format(lip, lv); insert: ASSERT(lv->lv_buf_len <= nbytes); @@ -714,7 +725,7 @@ xlog_cil_empty( * background commit, returns without it held once background commits are * allowed again. */ -int +void xfs_log_commit_cil( struct xfs_mount *mp, struct xfs_trans *tp, @@ -760,7 +771,6 @@ xfs_log_commit_cil( xlog_cil_push_background(log); up_read(&cil->xc_ctx_lock); - return 0; } /* diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 02df7b4..f96c056 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -282,22 +282,29 @@ xfs_readsb( struct xfs_sb *sbp = &mp->m_sb; int error; int loud = !(flags & XFS_MFSI_QUIET); + const struct xfs_buf_ops *buf_ops; ASSERT(mp->m_sb_bp == NULL); ASSERT(mp->m_ddev_targp != NULL); /* + * For the initial read, we must guess at the sector + * size based on the block device. It's enough to + * get the sb_sectsize out of the superblock and + * then reread with the proper length. + * We don't verify it yet, because it may not be complete. + */ + sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); + buf_ops = NULL; + + /* * Allocate a (locked) buffer to hold the superblock. * This will be kept around at all times to optimize * access to the superblock. */ - sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); - reread: bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), 0, - loud ? &xfs_sb_buf_ops - : &xfs_sb_quiet_buf_ops); + BTOBB(sector_size), 0, buf_ops); if (!bp) { if (loud) xfs_warn(mp, "SB buffer read failed"); @@ -328,12 +335,13 @@ reread: } /* - * If device sector size is smaller than the superblock size, - * re-read the superblock so the buffer is correctly sized. + * Re-read the superblock so the buffer is correctly sized, + * and properly verified. */ - if (sector_size < sbp->sb_sectsize) { + if (buf_ops == NULL) { xfs_buf_relse(bp); sector_size = sbp->sb_sectsize; + buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops; goto reread; } diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index a6a76b2..ec5ca65 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -842,7 +842,7 @@ xfs_growfs_rt_alloc( /* * Reserve space & log for one extent added to the file. */ - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growdata, + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtalloc, resblks, 0); if (error) goto error_cancel; diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index b7c9aea..75161a2 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -288,6 +288,7 @@ xfs_mount_validate_sb( sbp->sb_inodelog < XFS_DINODE_MIN_LOG || sbp->sb_inodelog > XFS_DINODE_MAX_LOG || sbp->sb_inodesize != (1 << sbp->sb_inodelog) || + sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) || (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) || (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) || (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) || @@ -295,8 +296,7 @@ xfs_mount_validate_sb( sbp->sb_dblocks == 0 || sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) { - XFS_CORRUPTION_ERROR("SB sanity check failed", - XFS_ERRLEVEL_LOW, mp, sbp); + xfs_notice(mp, "SB sanity check failed"); return XFS_ERROR(EFSCORRUPTED); } @@ -611,10 +611,10 @@ xfs_sb_read_verify( XFS_SB_VERSION_5) || dsb->sb_crc != 0)) { - if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize), + if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), offsetof(struct xfs_sb, sb_crc))) { /* Only fail bad secondaries on a known V5 filesystem */ - if (bp->b_bn != XFS_SB_DADDR && + if (bp->b_bn == XFS_SB_DADDR || xfs_sb_version_hascrc(&mp->m_sb)) { error = EFSCORRUPTED; goto out_error; @@ -625,7 +625,7 @@ xfs_sb_read_verify( out_error: if (error) { - if (error != EWRONGFS) + if (error == EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); xfs_buf_ioerror(bp, error); @@ -644,7 +644,6 @@ xfs_sb_quiet_read_verify( { struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp); - if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) { /* XFS filesystem, verify noisily! */ xfs_sb_read_verify(bp); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 425dfa4..a4ae41c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -603,6 +603,7 @@ DEFINE_INODE_EVENT(xfs_readlink); DEFINE_INODE_EVENT(xfs_inactive_symlink); DEFINE_INODE_EVENT(xfs_alloc_file_space); DEFINE_INODE_EVENT(xfs_free_file_space); +DEFINE_INODE_EVENT(xfs_collapse_file_space); DEFINE_INODE_EVENT(xfs_readdir); #ifdef CONFIG_XFS_POSIX_ACL DEFINE_INODE_EVENT(xfs_get_acl); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c812c5c0..54a5732 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -887,12 +887,7 @@ xfs_trans_commit( xfs_trans_apply_sb_deltas(tp); xfs_trans_apply_dquot_deltas(tp); - error = xfs_log_commit_cil(mp, tp, &commit_lsn, flags); - if (error == ENOMEM) { - xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR); - error = XFS_ERROR(EIO); - goto out_unreserve; - } + xfs_log_commit_cil(mp, tp, &commit_lsn, flags); current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); xfs_trans_free(tp); @@ -902,10 +897,7 @@ xfs_trans_commit( * log out now and wait for it. */ if (sync) { - if (!error) { - error = _xfs_log_force_lsn(mp, commit_lsn, - XFS_LOG_SYNC, NULL); - } + error = _xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL); XFS_STATS_INC(xs_trans_sync); } else { XFS_STATS_INC(xs_trans_async); diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c index 2ffd3e33..8515b04 100644 --- a/fs/xfs/xfs_trans_resv.c +++ b/fs/xfs/xfs_trans_resv.c @@ -644,15 +644,14 @@ xfs_calc_qm_setqlim_reservation( /* * Allocating quota on disk if needed. - * the write transaction log space: M_RES(mp)->tr_write.tr_logres + * the write transaction log space for quota file extent allocation * the unit of quota allocation: one system block size */ STATIC uint xfs_calc_qm_dqalloc_reservation( struct xfs_mount *mp) { - ASSERT(M_RES(mp)->tr_write.tr_logres); - return M_RES(mp)->tr_write.tr_logres + + return xfs_calc_write_reservation(mp) + xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1); } @@ -784,7 +783,6 @@ xfs_trans_resv_calc( /* The following transaction are logged in logical format */ resp->tr_ichange.tr_logres = xfs_calc_ichange_reservation(mp); resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp); - resp->tr_swrite.tr_logres = xfs_calc_swrite_reservation(mp); resp->tr_fsyncts.tr_logres = xfs_calc_swrite_reservation(mp); resp->tr_writeid.tr_logres = xfs_calc_writeid_reservation(mp); resp->tr_attrsetrt.tr_logres = xfs_calc_attrsetrt_reservation(mp); diff --git a/fs/xfs/xfs_trans_resv.h b/fs/xfs/xfs_trans_resv.h index de7de9a..f76c129 100644 --- a/fs/xfs/xfs_trans_resv.h +++ b/fs/xfs/xfs_trans_resv.h @@ -42,7 +42,6 @@ struct xfs_trans_resv { struct xfs_trans_res tr_ifree; /* inode free trans */ struct xfs_trans_res tr_ichange; /* inode update trans */ struct xfs_trans_res tr_growdata; /* fs data section grow trans */ - struct xfs_trans_res tr_swrite; /* sync write inode trans */ struct xfs_trans_res tr_addafork; /* add inode attr fork trans */ struct xfs_trans_res tr_writeid; /* write setuid/setgid file */ struct xfs_trans_res tr_attrinval; /* attr fork buffer diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c..f7faefc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2527,6 +2527,9 @@ enum { /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, + + /* filesystem can handle aio writes beyond i_size */ + DIO_ASYNC_EXTEND = 0x04, }; void dio_end_io(struct bio *bio, int error); diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index 990c4cc..d1197ae 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -5,5 +5,40 @@ #define FALLOC_FL_PUNCH_HOLE 0x02 /* de-allocates range */ #define FALLOC_FL_NO_HIDE_STALE 0x04 /* reserved codepoint */ +/* + * FALLOC_FL_COLLAPSE_RANGE is used to remove a range of a file + * without leaving a hole in the file. The contents of the file beyond + * the range being removed is appended to the start offset of the range + * being removed (i.e. the hole that was punched is "collapsed"), + * resulting in a file layout that looks like the range that was + * removed never existed. As such collapsing a range of a file changes + * the size of the file, reducing it by the same length of the range + * that has been removed by the operation. + * + * Different filesystems may implement different limitations on the + * granularity of the operation. Most will limit operations to + * filesystem block size boundaries, but this boundary may be larger or + * smaller depending on the filesystem and/or the configuration of the + * filesystem or file. + * + * Attempting to collapse a range that crosses the end of the file is + * considered an illegal operation - just use ftruncate(2) if you need + * to collapse a range that crosses EOF. + */ +#define FALLOC_FL_COLLAPSE_RANGE 0x08 + +/* + * FALLOC_FL_ZERO_RANGE is used to convert a range of file to zeros preferably + * without issuing data IO. Blocks should be preallocated for the regions that + * span holes in the file, and the entire range is preferable converted to + * unwritten extents - even though file system may choose to zero out the + * extent or do whatever which will result in reading zeros from the range + * while the range remains allocated for the file. + * + * This can be also used to preallocate blocks past EOF in the same way as + * with fallocate. Flag FALLOC_FL_KEEP_SIZE should cause the inode + * size to remain the same. + */ +#define FALLOC_FL_ZERO_RANGE 0x10 #endif /* _UAPI_FALLOC_H_ */ |
