/* * xfs_file_dio_aio_write - handle direct IO writes * * Lock the inode appropriately to prepare for and issue a direct IO write. * By separating it from the buffered write path we remove all the tricky to * follow locking changes and looping. * * If there are cached pages or we're extending the file, we need IOLOCK_EXCL * until we're sure the bytes at the new EOF have been zeroed and/or the cached * pages are flushed out. * * In most cases the direct IO writes will be done holding IOLOCK_SHARED * allowing them to be done in parallel with reads and other direct IO writes. * However, if the IO is not aligned to filesystem blocks, the direct IO layer * needs to do sub-block zeroing and that requires serialisation against other * direct IOs to the same block. In this case we need to serialise the * submission of the unaligned IOs so that we don't get racing block zeroing in * the dio layer. To avoid the problem with aio, we also need to wait for * outstanding IOs to complete so that unwritten extent conversion is completed * before we try to map the overlapping block. This is currently implemented by * hitting it with a big hammer (i.e. inode_dio_wait()). * * Returns with locks held indicated by @iolock and errors indicated by * negative return values. */ STATIC ssize_t xfs_file_dio_aio_write( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos, size_t ocount) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0; size_t count = ocount; int unaligned_io = 0; int iolock; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((pos & target->bt_smask) || (count & target->bt_smask)) return -XFS_ERROR(EINVAL); if ((pos & mp->m_blockmask) || ((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. */ if (unaligned_io || mapping->nrpages) iolock = XFS_IOLOCK_EXCL; 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); } ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); if (ret) goto out; if (mapping->nrpages) { ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) goto out; } /* * If we are doing unaligned IO, wait for all other IO to drain, * otherwise demote the lock if we had to flush cached pages */ if (unaligned_io) inode_dio_wait(inode); else if (iolock == XFS_IOLOCK_EXCL) { xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); ret = generic_file_direct_write(iocb, iovp, &nr_segs, pos, &iocb->ki_pos, count, ocount); out: xfs_rw_iunlock(ip, iolock); /* No fallback to buffered IO on errors for XFS. */ ASSERT(ret < 0 || ret == count); return ret; }
STATIC ssize_t xfs_file_aio_write( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0, error = 0; int ioflags = 0; xfs_fsize_t isize, new_size; int iolock; int eventsent = 0; size_t ocount = 0, count; int need_i_mutex; XFS_STATS_INC(xs_write_calls); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ); if (error) return error; count = ocount; if (count == 0) return 0; xfs_wait_for_freeze(mp, SB_FREEZE_WRITE); if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; relock: if (ioflags & IO_ISDIRECT) { iolock = XFS_IOLOCK_SHARED; need_i_mutex = 0; } else { iolock = XFS_IOLOCK_EXCL; need_i_mutex = 1; mutex_lock(&inode->i_mutex); } xfs_ilock(ip, XFS_ILOCK_EXCL|iolock); start: error = -generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (error) { xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock); goto out_unlock_mutex; } if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS) && !eventsent)) { int dmflags = FILP_DELAY_FLAG(file); if (need_i_mutex) dmflags |= DM_FLAGS_IMUX; xfs_iunlock(ip, XFS_ILOCK_EXCL); error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip, pos, count, dmflags, &iolock); if (error) { goto out_unlock_internal; } xfs_ilock(ip, XFS_ILOCK_EXCL); eventsent = 1; /* * The iolock was dropped and reacquired in XFS_SEND_DATA * so we have to recheck the size when appending. * We will only "goto start;" once, since having sent the * event prevents another call to XFS_SEND_DATA, which is * what allows the size to change in the first place. */ if ((file->f_flags & O_APPEND) && pos != ip->i_size) goto start; } if (ioflags & IO_ISDIRECT) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((pos & target->bt_smask) || (count & target->bt_smask)) { xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock); return XFS_ERROR(-EINVAL); } if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) { xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock); iolock = XFS_IOLOCK_EXCL; need_i_mutex = 1; mutex_lock(&inode->i_mutex); xfs_ilock(ip, XFS_ILOCK_EXCL|iolock); goto start; } } new_size = pos + count; if (new_size > ip->i_size) ip->i_new_size = new_size; if (likely(!(ioflags & IO_INVIS))) file_update_time(file); /* * If the offset is beyond the size of the file, we have a couple * of things to do. First, if there is already space allocated * we need to either create holes or zero the disk or ... * * If there is a page where the previous size lands, we need * to zero it out up to the new size. */ if (pos > ip->i_size) { error = xfs_zero_eof(ip, pos, ip->i_size); if (error) { xfs_iunlock(ip, XFS_ILOCK_EXCL); goto out_unlock_internal; } } xfs_iunlock(ip, XFS_ILOCK_EXCL); /* * If we're writing the file then make sure to clear the * setuid and setgid bits if the process is not being run * by root. This keeps people from modifying setuid and * setgid binaries. */ error = -file_remove_suid(file); if (unlikely(error)) goto out_unlock_internal; /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; if ((ioflags & IO_ISDIRECT)) { if (mapping->nrpages) { WARN_ON(need_i_mutex == 0); error = xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (error) goto out_unlock_internal; } if (need_i_mutex) { /* demote the lock now the cached pages are gone */ xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); mutex_unlock(&inode->i_mutex); iolock = XFS_IOLOCK_SHARED; need_i_mutex = 0; } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags); ret = generic_file_direct_write(iocb, iovp, &nr_segs, pos, &iocb->ki_pos, count, ocount); /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ if (ret >= 0 && ret != count) { XFS_STATS_ADD(xs_write_bytes, ret); pos += ret; count -= ret; ioflags &= ~IO_ISDIRECT; xfs_iunlock(ip, iolock); goto relock; } } else { int enospc = 0; ssize_t ret2 = 0; write_retry: trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags); ret2 = generic_file_buffered_write(iocb, iovp, nr_segs, pos, &iocb->ki_pos, count, ret); /* * if we just got an ENOSPC, flush the inode now we * aren't holding any page locks and retry *once* */ if (ret2 == -ENOSPC && !enospc) { error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE); if (error) goto out_unlock_internal; enospc = 1; goto write_retry; } ret = ret2; } current->backing_dev_info = NULL; isize = i_size_read(inode); if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize)) iocb->ki_pos = isize; if (iocb->ki_pos > ip->i_size) { xfs_ilock(ip, XFS_ILOCK_EXCL); if (iocb->ki_pos > ip->i_size) ip->i_size = iocb->ki_pos; xfs_iunlock(ip, XFS_ILOCK_EXCL); } if (ret == -ENOSPC && DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) { xfs_iunlock(ip, iolock); if (need_i_mutex) mutex_unlock(&inode->i_mutex); error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip, DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL, 0, 0, 0); /* Delay flag intentionally unused */ if (need_i_mutex) mutex_lock(&inode->i_mutex); xfs_ilock(ip, iolock); if (error) goto out_unlock_internal; goto start; } error = -ret; if (ret <= 0) goto out_unlock_internal; XFS_STATS_ADD(xs_write_bytes, ret); /* Handle various SYNC-type writes */ if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) { loff_t end = pos + ret - 1; int error2; xfs_iunlock(ip, iolock); if (need_i_mutex) mutex_unlock(&inode->i_mutex); error2 = filemap_write_and_wait_range(mapping, pos, end); if (!error) error = error2; if (need_i_mutex) mutex_lock(&inode->i_mutex); xfs_ilock(ip, iolock); error2 = -xfs_file_fsync(file, file->f_path.dentry, (file->f_flags & __O_SYNC) ? 0 : 1); if (!error) error = error2; } out_unlock_internal: if (ip->i_new_size) { xfs_ilock(ip, XFS_ILOCK_EXCL); ip->i_new_size = 0; /* * If this was a direct or synchronous I/O that failed (such * as ENOSPC) then part of the I/O may have been written to * disk before the error occured. In this case the on-disk * file size may have been adjusted beyond the in-memory file * size and now needs to be truncated back. */ if (ip->i_d.di_size > ip->i_size) ip->i_d.di_size = ip->i_size; xfs_iunlock(ip, XFS_ILOCK_EXCL); } xfs_iunlock(ip, iolock); out_unlock_mutex: if (need_i_mutex) mutex_unlock(&inode->i_mutex); return -error; }
STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; size_t size = 0; ssize_t ret = 0; int ioflags = 0; xfs_fsize_t n; XFS_STATS_INC(xs_read_calls); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE); if (ret < 0) return ret; if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((iocb->ki_pos & target->bt_smask) || (size & target->bt_smask)) { if (iocb->ki_pos == i_size_read(inode)) return 0; return -XFS_ERROR(EINVAL); } } n = mp->m_super->s_maxbytes - iocb->ki_pos; if (n <= 0 || size == 0) return 0; if (n < size) size = n; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; /* * 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 ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) { xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); if (inode->i_mapping->nrpages) { ret = -xfs_flushinval_pages(ip, (iocb->ki_pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) { xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags); ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos); if (ret > 0) XFS_STATS_ADD(xs_read_bytes, ret); xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; }
/* * xfs_file_dio_aio_write - handle direct IO writes * * Lock the inode appropriately to prepare for and issue a direct IO write. * By separating it from the buffered write path we remove all the tricky to * follow locking changes and looping. * * If there are cached pages or we're extending the file, we need IOLOCK_EXCL * until we're sure the bytes at the new EOF have been zeroed and/or the cached * pages are flushed out. * * In most cases the direct IO writes will be done holding IOLOCK_SHARED * allowing them to be done in parallel with reads and other direct IO writes. * However, if the IO is not aligned to filesystem blocks, the direct IO layer * needs to do sub-block zeroing and that requires serialisation against other * direct IOs to the same block. In this case we need to serialise the * submission of the unaligned IOs so that we don't get racing block zeroing in * the dio layer. To avoid the problem with aio, we also need to wait for * outstanding IOs to complete so that unwritten extent conversion is completed * before we try to map the overlapping block. This is currently implemented by * hitting it with a big hammer (i.e. xfs_ioend_wait()). * * Returns with locks held indicated by @iolock and errors indicated by * negative return values. */ STATIC ssize_t xfs_file_dio_aio_write( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos, size_t ocount, int *iolock) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0; size_t count = ocount; int unaligned_io = 0; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; *iolock = 0; if ((pos & target->bt_smask) || (count & target->bt_smask)) return -XFS_ERROR(EINVAL); if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask)) unaligned_io = 1; if (unaligned_io || mapping->nrpages || pos > ip->i_size) *iolock = XFS_IOLOCK_EXCL; else *iolock = XFS_IOLOCK_SHARED; xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock); ret = xfs_file_aio_write_checks(file, &pos, &count, iolock); if (ret) return ret; if (mapping->nrpages) { WARN_ON(*iolock != XFS_IOLOCK_EXCL); ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) return ret; } /* * If we are doing unaligned IO, wait for all other IO to drain, * otherwise demote the lock if we had to flush cached pages */ if (unaligned_io) xfs_ioend_wait(ip); else if (*iolock == XFS_IOLOCK_EXCL) { xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); *iolock = XFS_IOLOCK_SHARED; } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); ret = generic_file_direct_write(iocb, iovp, &nr_segs, pos, &iocb->ki_pos, count, ocount); /* No fallback to buffered IO on errors for XFS. */ ASSERT(ret < 0 || ret == count); return ret; }
STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; size_t size = 0; ssize_t ret = 0; int ioflags = 0; xfs_fsize_t n; unsigned long seg; XFS_STATS_INC(xs_read_calls); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; /* START copy & waste from filemap.c */ for (seg = 0; seg < nr_segs; seg++) { const struct iovec *iv = &iovp[seg]; /* * If any segment has a negative length, or the cumulative * length ever wraps negative then return -EINVAL. */ size += iv->iov_len; if (unlikely((ssize_t)(size|iv->iov_len) < 0)) return XFS_ERROR(-EINVAL); } /* END copy & waste from filemap.c */ if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((iocb->ki_pos & target->bt_smask) || (size & target->bt_smask)) { if (iocb->ki_pos == ip->i_size) return 0; return -XFS_ERROR(EINVAL); } } n = XFS_MAXIOFFSET(mp) - iocb->ki_pos; if (n <= 0 || size == 0) return 0; if (n < size) size = n; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; if (unlikely(ioflags & IO_ISDIRECT)) mutex_lock(&inode->i_mutex); xfs_ilock(ip, XFS_IOLOCK_SHARED); if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) { int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags); int iolock = XFS_IOLOCK_SHARED; ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size, dmflags, &iolock); if (ret) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); if (unlikely(ioflags & IO_ISDIRECT)) mutex_unlock(&inode->i_mutex); return ret; } } if (unlikely(ioflags & IO_ISDIRECT)) { if (inode->i_mapping->nrpages) { ret = -xfs_flushinval_pages(ip, (iocb->ki_pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); } mutex_unlock(&inode->i_mutex); if (ret) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } } trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags); ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos); if (ret > 0) XFS_STATS_ADD(xs_read_bytes, ret); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; }
static int xfs_swap_extents( xfs_inode_t *ip, /* target inode */ xfs_inode_t *tip, /* tmp inode */ xfs_swapext_t *sxp) { xfs_mount_t *mp = ip->i_mount; xfs_trans_t *tp; xfs_bstat_t *sbp = &sxp->sx_stat; xfs_ifork_t *tempifp, *ifp, *tifp; int ilf_fields, tilf_fields; int error = 0; int aforkblks = 0; int taforkblks = 0; __uint64_t tmp; tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL); if (!tempifp) { error = XFS_ERROR(ENOMEM); goto out; } /* * we have to do two separate lock calls here to keep lockdep * happy. If we try to get all the locks in one call, lock will * report false positives when we drop the ILOCK and regain them * below. */ xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL); xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL); /* Verify that both files have the same format */ if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) { error = XFS_ERROR(EINVAL); goto out_unlock; } /* Verify both files are either real-time or non-realtime */ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) { error = XFS_ERROR(EINVAL); goto out_unlock; } if (VN_CACHED(VFS_I(tip)) != 0) { error = xfs_flushinval_pages(tip, 0, -1, FI_REMAPF_LOCKED); if (error) goto out_unlock; } /* Verify O_DIRECT for ftmp */ if (VN_CACHED(VFS_I(tip)) != 0) { error = XFS_ERROR(EINVAL); goto out_unlock; } /* Verify all data are being swapped */ if (sxp->sx_offset != 0 || sxp->sx_length != ip->i_d.di_size || sxp->sx_length != tip->i_d.di_size) { error = XFS_ERROR(EFAULT); goto out_unlock; } trace_xfs_swap_extent_before(ip, 0); trace_xfs_swap_extent_before(tip, 1); /* check inode formats now that data is flushed */ error = xfs_swap_extents_check_format(ip, tip); if (error) { xfs_notice(mp, "%s: inode 0x%llx format is incompatible for exchanging.", __func__, ip->i_ino); goto out_unlock; } /* * Compare the current change & modify times with that * passed in. If they differ, we abort this swap. * This is the mechanism used to ensure the calling * process that the file was not changed out from * under it. */ if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) || (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) || (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) || (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) { error = XFS_ERROR(EBUSY); goto out_unlock; } /* We need to fail if the file is memory mapped. Once we have tossed * all existing pages, the page fault will have no option * but to go to the filesystem for pages. By making the page fault call * vop_read (or write in the case of autogrow) they block on the iolock * until we have switched the extents. */ if (VN_MAPPED(VFS_I(ip))) { error = XFS_ERROR(EBUSY); goto out_unlock; } xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iunlock(tip, XFS_ILOCK_EXCL); /* * There is a race condition here since we gave up the * ilock. However, the data fork will not change since * we have the iolock (locked for truncation too) so we * are safe. We don't really care if non-io related * fields change. */ xfs_tosspages(ip, 0, -1, FI_REMAPF); tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT); if ((error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0))) { xfs_iunlock(ip, XFS_IOLOCK_EXCL); xfs_iunlock(tip, XFS_IOLOCK_EXCL); xfs_trans_cancel(tp, 0); goto out; } xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL); /* * Count the number of extended attribute blocks */ if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) && (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) { error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks); if (error) goto out_trans_cancel; } if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) && (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) { error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &taforkblks); if (error) goto out_trans_cancel; } /* * Swap the data forks of the inodes */ ifp = &ip->i_df; tifp = &tip->i_df; *tempifp = *ifp; /* struct copy */ *ifp = *tifp; /* struct copy */ *tifp = *tempifp; /* struct copy */ /* * Fix the in-memory data fork values that are dependent on the fork * offset in the inode. We can't assume they remain the same as attr2 * has dynamic fork offsets. */ ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) / (uint)sizeof(xfs_bmbt_rec_t); tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) / (uint)sizeof(xfs_bmbt_rec_t); /* * Fix the on-disk inode values */ tmp = (__uint64_t)ip->i_d.di_nblocks; ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks; tip->i_d.di_nblocks = tmp + taforkblks - aforkblks; tmp = (__uint64_t) ip->i_d.di_nextents; ip->i_d.di_nextents = tip->i_d.di_nextents; tip->i_d.di_nextents = tmp; tmp = (__uint64_t) ip->i_d.di_format; ip->i_d.di_format = tip->i_d.di_format; tip->i_d.di_format = tmp; /* * The extents in the source inode could still contain speculative * preallocation beyond EOF (e.g. the file is open but not modified * while defrag is in progress). In that case, we need to copy over the * number of delalloc blocks the data fork in the source inode is * tracking beyond EOF so that when the fork is truncated away when the * temporary inode is unlinked we don't underrun the i_delayed_blks * counter on that inode. */ ASSERT(tip->i_delayed_blks == 0); tip->i_delayed_blks = ip->i_delayed_blks; ip->i_delayed_blks = 0; ilf_fields = XFS_ILOG_CORE; 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 (ip->i_d.di_nextents <= XFS_INLINE_EXTS) { ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext; } ilf_fields |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: ilf_fields |= XFS_ILOG_DBROOT; break; } tilf_fields = XFS_ILOG_CORE; 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 (tip->i_d.di_nextents <= XFS_INLINE_EXTS) { tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext; } tilf_fields |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: tilf_fields |= XFS_ILOG_DBROOT; break; } xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); xfs_trans_ijoin_ref(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); xfs_trans_log_inode(tp, ip, ilf_fields); xfs_trans_log_inode(tp, tip, tilf_fields); /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT); trace_xfs_swap_extent_after(ip, 0); trace_xfs_swap_extent_after(tip, 1); out: kmem_free(tempifp); return error; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); goto out; out_trans_cancel: xfs_trans_cancel(tp, 0); goto out_unlock; }
/* * xfs_file_dio_aio_write - handle direct IO writes * * Lock the inode appropriately to prepare for and issue a direct IO write. * By separating it from the buffered write path we remove all the tricky to * follow locking changes and looping. * * If there are cached pages or we're extending the file, we need IOLOCK_EXCL * until we're sure the bytes at the new EOF have been zeroed and/or the cached * pages are flushed out. * * In most cases the direct IO writes will be done holding IOLOCK_SHARED * allowing them to be done in parallel with reads and other direct IO writes. * However, if the IO is not aligned to filesystem blocks, the direct IO layer * needs to do sub-block zeroing and that requires serialisation against other * direct IOs to the same block. In this case we need to serialise the * submission of the unaligned IOs so that we don't get racing block zeroing in * the dio layer. To avoid the problem with aio, we also need to wait for * outstanding IOs to complete so that unwritten extent conversion is completed * before we try to map the overlapping block. This is currently implemented by * hitting it with a big hammer (i.e. inode_dio_wait()). * * Returns with locks held indicated by @iolock and errors indicated by * negative return values. */ STATIC ssize_t xfs_file_dio_aio_write( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos, size_t ocount) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0; size_t count = ocount; int unaligned_io = 0; int iolock; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((pos & target->bt_smask) || (count & target->bt_smask)) return -XFS_ERROR(EINVAL); if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask)) unaligned_io = 1; if (unaligned_io || mapping->nrpages) iolock = XFS_IOLOCK_EXCL; else iolock = XFS_IOLOCK_SHARED; xfs_rw_ilock(ip, iolock); if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) { xfs_rw_iunlock(ip, iolock); iolock = XFS_IOLOCK_EXCL; xfs_rw_ilock(ip, iolock); } ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); if (ret) goto out; if (mapping->nrpages) { ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) goto out; } if (unaligned_io) inode_dio_wait(inode); else if (iolock == XFS_IOLOCK_EXCL) { xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); ret = generic_file_direct_write(iocb, iovp, &nr_segs, pos, &iocb->ki_pos, count, ocount); out: xfs_rw_iunlock(ip, iolock); ASSERT(ret < 0 || ret == count); return ret; }
STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, const struct iovec *iovp, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; size_t size = 0; ssize_t ret = 0; int ioflags = 0; xfs_fsize_t n; unsigned long seg; XFS_STATS_INC(xs_read_calls); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; for (seg = 0; seg < nr_segs; seg++) { const struct iovec *iv = &iovp[seg]; size += iv->iov_len; if (unlikely((ssize_t)(size|iv->iov_len) < 0)) return XFS_ERROR(-EINVAL); } if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((iocb->ki_pos & target->bt_smask) || (size & target->bt_smask)) { if (iocb->ki_pos == i_size_read(inode)) return 0; return -XFS_ERROR(EINVAL); } } n = XFS_MAXIOFFSET(mp) - iocb->ki_pos; if (n <= 0 || size == 0) return 0; if (n < size) size = n; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) { xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); if (inode->i_mapping->nrpages) { ret = -xfs_flushinval_pages(ip, (iocb->ki_pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) { xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags); ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos); if (ret > 0) XFS_STATS_ADD(xs_read_bytes, ret); xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; }
ssize_t /* bytes written, or (-) error */ xfs_write( struct xfs_inode *xip, struct kiocb *iocb, const struct iovec *iovp, unsigned int nsegs, loff_t *offset, int ioflags) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned long segs = nsegs; xfs_mount_t *mp; ssize_t ret = 0, error = 0; xfs_fsize_t isize, new_size; int iolock; int eventsent = 0; size_t ocount = 0, count; loff_t pos; int need_i_mutex; XFS_STATS_INC(xs_write_calls); error = generic_segment_checks(iovp, &segs, &ocount, VERIFY_READ); if (error) return error; count = ocount; pos = *offset; if (count == 0) return 0; mp = xip->i_mount; xfs_wait_for_freeze(mp, SB_FREEZE_WRITE); if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; relock: if (ioflags & IO_ISDIRECT) { iolock = XFS_IOLOCK_SHARED; need_i_mutex = 0; } else { iolock = XFS_IOLOCK_EXCL; need_i_mutex = 1; mutex_lock(&inode->i_mutex); } xfs_ilock(xip, XFS_ILOCK_EXCL|iolock); start: error = -generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (error) { xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock); goto out_unlock_mutex; } if ((DM_EVENT_ENABLED(xip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS) && !eventsent)) { int dmflags = FILP_DELAY_FLAG(file); if (need_i_mutex) dmflags |= DM_FLAGS_IMUX; xfs_iunlock(xip, XFS_ILOCK_EXCL); error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, xip, pos, count, dmflags, &iolock); if (error) { goto out_unlock_internal; } xfs_ilock(xip, XFS_ILOCK_EXCL); eventsent = 1; /* * The iolock was dropped and reacquired in XFS_SEND_DATA * so we have to recheck the size when appending. * We will only "goto start;" once, since having sent the * event prevents another call to XFS_SEND_DATA, which is * what allows the size to change in the first place. */ if ((file->f_flags & O_APPEND) && pos != xip->i_size) goto start; } if (ioflags & IO_ISDIRECT) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(xip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((pos & target->bt_smask) || (count & target->bt_smask)) { xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock); return XFS_ERROR(-EINVAL); } if (!need_i_mutex && (mapping->nrpages || pos > xip->i_size)) { xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock); iolock = XFS_IOLOCK_EXCL; need_i_mutex = 1; mutex_lock(&inode->i_mutex); xfs_ilock(xip, XFS_ILOCK_EXCL|iolock); goto start; } } new_size = pos + count; if (new_size > xip->i_size) xip->i_new_size = new_size; if (likely(!(ioflags & IO_INVIS))) xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); /* * If the offset is beyond the size of the file, we have a couple * of things to do. First, if there is already space allocated * we need to either create holes or zero the disk or ... * * If there is a page where the previous size lands, we need * to zero it out up to the new size. */ if (pos > xip->i_size) { error = xfs_zero_eof(xip, pos, xip->i_size); if (error) { xfs_iunlock(xip, XFS_ILOCK_EXCL); goto out_unlock_internal; } } xfs_iunlock(xip, XFS_ILOCK_EXCL); /* * If we're writing the file then make sure to clear the * setuid and setgid bits if the process is not being run * by root. This keeps people from modifying setuid and * setgid binaries. */ if (((xip->i_d.di_mode & S_ISUID) || ((xip->i_d.di_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))) && !capable(CAP_FSETID)) { error = xfs_write_clear_setuid(xip); if (likely(!error)) error = -file_remove_suid(file); if (unlikely(error)) { goto out_unlock_internal; } } /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; if ((ioflags & IO_ISDIRECT)) { if (mapping->nrpages) { WARN_ON(need_i_mutex == 0); xfs_inval_cached_trace(xip, pos, -1, (pos & PAGE_CACHE_MASK), -1); error = xfs_flushinval_pages(xip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (error) goto out_unlock_internal; } if (need_i_mutex) { /* demote the lock now the cached pages are gone */ xfs_ilock_demote(xip, XFS_IOLOCK_EXCL); mutex_unlock(&inode->i_mutex); iolock = XFS_IOLOCK_SHARED; need_i_mutex = 0; } xfs_rw_enter_trace(XFS_DIOWR_ENTER, xip, (void *)iovp, segs, *offset, ioflags); ret = generic_file_direct_write(iocb, iovp, &segs, pos, offset, count, ocount); /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ if (ret >= 0 && ret != count) { XFS_STATS_ADD(xs_write_bytes, ret); pos += ret; count -= ret; ioflags &= ~IO_ISDIRECT; xfs_iunlock(xip, iolock); goto relock; } } else { xfs_rw_enter_trace(XFS_WRITE_ENTER, xip, (void *)iovp, segs, *offset, ioflags); ret = generic_file_buffered_write(iocb, iovp, segs, pos, offset, count, ret); } current->backing_dev_info = NULL; if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO)) ret = wait_on_sync_kiocb(iocb); isize = i_size_read(inode); if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize)) *offset = isize; if (*offset > xip->i_size) { xfs_ilock(xip, XFS_ILOCK_EXCL); if (*offset > xip->i_size) xip->i_size = *offset; xfs_iunlock(xip, XFS_ILOCK_EXCL); } if (ret == -ENOSPC && DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) { xfs_iunlock(xip, iolock); if (need_i_mutex) mutex_unlock(&inode->i_mutex); error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, xip, DM_RIGHT_NULL, xip, DM_RIGHT_NULL, NULL, NULL, 0, 0, 0); /* Delay flag intentionally unused */ if (need_i_mutex) mutex_lock(&inode->i_mutex); xfs_ilock(xip, iolock); if (error) goto out_unlock_internal; goto start; } error = -ret; if (ret <= 0) goto out_unlock_internal; XFS_STATS_ADD(xs_write_bytes, ret); /* Handle various SYNC-type writes */ if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) { int error2; xfs_iunlock(xip, iolock); if (need_i_mutex) mutex_unlock(&inode->i_mutex); error2 = sync_page_range(inode, mapping, pos, ret); if (!error) error = error2; if (need_i_mutex) mutex_lock(&inode->i_mutex); xfs_ilock(xip, iolock); error2 = xfs_write_sync_logforce(mp, xip); if (!error) error = error2; } out_unlock_internal: if (xip->i_new_size) { xfs_ilock(xip, XFS_ILOCK_EXCL); xip->i_new_size = 0; /* * If this was a direct or synchronous I/O that failed (such * as ENOSPC) then part of the I/O may have been written to * disk before the error occured. In this case the on-disk * file size may have been adjusted beyond the in-memory file * size and now needs to be truncated back. */ if (xip->i_d.di_size > xip->i_size) xip->i_d.di_size = xip->i_size; xfs_iunlock(xip, XFS_ILOCK_EXCL); } xfs_iunlock(xip, iolock); out_unlock_mutex: if (need_i_mutex) mutex_unlock(&inode->i_mutex); return -error; }
ssize_t /* bytes read, or (-) error */ xfs_read( xfs_inode_t *ip, struct kiocb *iocb, const struct iovec *iovp, unsigned int segs, loff_t *offset, int ioflags) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; xfs_mount_t *mp = ip->i_mount; size_t size = 0; ssize_t ret = 0; xfs_fsize_t n; unsigned long seg; XFS_STATS_INC(xs_read_calls); /* START copy & waste from filemap.c */ for (seg = 0; seg < segs; seg++) { const struct iovec *iv = &iovp[seg]; /* * If any segment has a negative length, or the cumulative * length ever wraps negative then return -EINVAL. */ size += iv->iov_len; if (unlikely((ssize_t)(size|iv->iov_len) < 0)) return XFS_ERROR(-EINVAL); } /* END copy & waste from filemap.c */ if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; if ((*offset & target->bt_smask) || (size & target->bt_smask)) { if (*offset == ip->i_size) { return (0); } return -XFS_ERROR(EINVAL); } } n = XFS_MAXIOFFSET(mp) - *offset; if ((n <= 0) || (size == 0)) return 0; if (n < size) size = n; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; if (unlikely(ioflags & IO_ISDIRECT)) mutex_lock(&inode->i_mutex); xfs_ilock(ip, XFS_IOLOCK_SHARED); if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) { int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags); int iolock = XFS_IOLOCK_SHARED; ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *offset, size, dmflags, &iolock); if (ret) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); if (unlikely(ioflags & IO_ISDIRECT)) mutex_unlock(&inode->i_mutex); return ret; } } if (unlikely(ioflags & IO_ISDIRECT)) { if (inode->i_mapping->nrpages) ret = -xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); mutex_unlock(&inode->i_mutex); if (ret) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } } xfs_rw_enter_trace(XFS_READ_ENTER, ip, (void *)iovp, segs, *offset, ioflags); iocb->ki_pos = *offset; ret = generic_file_aio_read(iocb, iovp, segs, *offset); if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO)) ret = wait_on_sync_kiocb(iocb); if (ret > 0) XFS_STATS_ADD(xs_read_bytes, ret); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; }