// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" #include #include #ifdef CONFIG_STUDENT extern const struct file_operations student_fops; #endif const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } return offset; } EXPORT_SYMBOL(vfs_setpos); /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { switch (whence) { case SEEK_END: offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (offset == 0) return file->f_pos; /* * f_lock protects against read/modify/write race with other * SEEK_CURs. Note that parallel writes and reads behave * like SEEK_SET. */ spin_lock(&file->f_lock); offset = vfs_setpos(file, file->f_pos + offset, maxsize); spin_unlock(&file->f_lock); return offset; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; inode_lock(inode); switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(f.file, offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } fdput_pos(f); return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) return -EBADF; retval = -EINVAL; if (whence > SEEK_MAX) goto out_putf; offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } out_putf: fdput_pos(f); return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } return security_file_permission(file, read_write == READ ? MAY_READ : MAY_WRITE); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op == &student_fops) { file->f_op->llseek(file, 42, 42); printk("The cookies aren't a lie!\n"); } if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_read(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_write(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = call_read_iter(filp, &kiocb, iter); else ret = call_write_iter(filp, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iovec.iov_base, iovec.iov_len, ppos); } else { nr = filp->f_op->write(filp, iovec.iov_base, iovec.iov_len, ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iovec.iov_len) break; iov_iter_advance(iter, nr); } return ret; } static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, iter, pos, READ, flags); else ret = do_loop_readv_writev(file, iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_read_iter(file, iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->read_iter) return -EINVAL; return do_iter_read(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_read); static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->write_iter) ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); return ret; } ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_write_iter(file, iocb, iter); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->write_iter) return -EINVAL; return do_iter_write(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { ret = do_iter_read(file, &iter, pos, flags); kfree(iov); } return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { file_start_write(file); ret = do_iter_write(file, &iter, pos, flags); file_end_write(file); kfree(iov); } return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ retval = -EBADF; in = fdget(in_fd); if (!in.file) goto out; if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; if (!ppos) { pos = in.file->f_pos; } else { pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; } retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ retval = -EBADF; out = fdget(out_fd); if (!out.file) goto fput_in; if (!(out.file->f_mode & FMODE_WRITE)) goto fput_out; in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) goto fput_out; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(out.file, true); if (!opipe) { retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; file_start_write(out.file); retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); file_end_write(out.file); } else { if (out.file->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); out.file->f_pos = out_pos; if (ppos) *ppos = pos; else in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; fput_out: fdput(out); fput_in: fdput(in); out: return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /** * generic_copy_file_range - copy data between two files * @file_in: file structure to read from * @pos_in: file offset to read from * @file_out: file structure to write data to * @pos_out: file offset to write data to * @len: amount of data to copy * @flags: copy flags * * This is a generic filesystem helper to copy data from one file to another. * It has no constraints on the source or destination file owners - the files * can belong to different superblocks and different filesystem types. Short * copies are allowed. * * This should be called from the @file_out filesystem, as per the * ->copy_file_range() method. * * Returns the number of bytes copied or a negative error indicating the * failure. */ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } EXPORT_SYMBOL(generic_copy_file_range); /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* 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; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; } if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, min_t(loff_t, MAX_RW_COUNT, len), REMAP_FILE_CAN_SHORTEN); if (ret > 0) goto done; } /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); file_end_write(file_out); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; struct fd f_in; struct fd f_out; ssize_t ret = -EBADF; f_in = fdget(fd_in); if (!f_in.file) goto out2; f_out = fdget(fd_out); if (!f_out.file) goto out1; ret = -EFAULT; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { pos_in = f_in.file->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { pos_out = f_out.file->f_pos; } ret = -EINVAL; if (flags != 0) goto out; ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { f_in.file->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { f_out.file->f_pos = pos_out; } } out: fdput(f_out); out1: fdput(f_in); out2: return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_mode & FMODE_BUF_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy 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; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; }