static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret <= 0) goto out_unlock; ret = file_remove_privs(file); if (ret) goto out_unlock; ret = file_update_time(file); if (ret) goto out_unlock; ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); mark_inode_dirty(inode); } out_unlock: inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; }
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct fd real; const struct cred *old_cred; ssize_t ret; if (!iov_iter_count(iter)) return 0; inode_lock(inode); /* Update mode */ ovl_copyattr(ovl_inode_real(inode), inode); ret = file_remove_privs(file); if (ret) goto out_unlock; ret = ovl_real_fdget(file, &real); if (ret) goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); file_start_write(real.file); ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, ovl_iocb_to_rwf(iocb)); file_end_write(real.file); revert_creds(old_cred); /* Update size */ ovl_copyattr(ovl_inode_real(inode), inode); fdput(real); out_unlock: inode_unlock(inode); return ret; }
/* * Common pre-write limit and setup checks. * * Called with the iolocked held either shared and exclusive according to * @iolock, and returns with it held. Might upgrade the iolock to exclusive * if called for a direct write beyond i_size. */ STATIC ssize_t xfs_file_aio_write_checks( struct kiocb *iocb, struct iov_iter *from, int *iolock) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t error = 0; size_t count = iov_iter_count(from); bool drained_dio = false; restart: error = generic_write_checks(iocb, from); if (error <= 0) return error; error = xfs_break_layouts(inode, iolock); if (error) return error; /* * For changing security info in file_remove_privs() we need i_rwsem * exclusively. */ if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) { xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, *iolock); goto restart; } /* * If the offset is beyond the size of the file, we need to zero any * blocks that fall between the existing EOF and the start of this * write. If zeroing is needed and we are currently holding the * iolock shared, we need to update it to exclusive which implies * having to redo all checks before. * * We need to serialise against EOF updates that occur in IO * completions here. We want to make sure that nobody is changing the * size while we do this check until we have placed an IO barrier (i.e. * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched. * The spinlock effectively forms a memory barrier once we have the * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value * and hence be able to correctly determine if we need to run zeroing. */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, *iolock); iov_iter_reexpand(from, count); } /* * We now have an IO submission barrier in place, but * AIO can do EOF updates during IO completion and hence * we now need to wait for all of them to drain. Non-AIO * DIO will have drained before we are given the * XFS_IOLOCK_EXCL, and so for most cases this wait is a * no-op. */ inode_dio_wait(inode); drained_dio = true; goto restart; } error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else spin_unlock(&ip->i_flags_lock); /* * Updating the timestamps will grab the ilock again from * xfs_fs_dirty_inode, so we have to call it after dropping the * lock above. Eventually we should look into a way to avoid * the pointless lock roundtrip. */ if (likely(!(file->f_mode & FMODE_NOCMTIME))) { error = file_update_time(file); if (error) return error; } /* * 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 (!IS_NOSEC(inode)) return file_remove_privs(file); return 0; }
/* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { loff_t isize = i_size_read(inode_in); if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; if (*len == 0) return 0; } /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret) return ret; /* 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) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; ret = vfs_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same); if (ret) return ret; if (!is_same) return -EBADE; } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, remap_flags); if (ret) return ret; /* If can't alter the file contents, we're done. */ if (!(remap_flags & REMAP_FILE_DEDUP)) { /* Update the timestamps, since we can alter file contents. */ if (!(file_out->f_mode & FMODE_NOCMTIME)) { ret = file_update_time(file_out); if (ret) return ret; } /* * Clear the security bits if the process is not being run by * root. This keeps people from modifying setuid and setgid * binaries. */ ret = file_remove_privs(file_out); if (ret) return ret; } return 0; }