diff options
Diffstat (limited to 'fs/read_write.c')
| -rw-r--r-- | fs/read_write.c | 1245 |
1 files changed, 338 insertions, 907 deletions
diff --git a/fs/read_write.c b/fs/read_write.c index 59d819c5b92e..328ce8cf9a85 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -227,12 +227,6 @@ loff_t noop_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(noop_llseek); -loff_t no_llseek(struct file *file, loff_t offset, int whence) -{ - return -ESPIPE; -} -EXPORT_SYMBOL(no_llseek); - loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); @@ -290,18 +284,13 @@ EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { - loff_t (*fn)(struct file *, loff_t, int); - - fn = no_llseek; - if (file->f_mode & FMODE_LSEEK) { - if (file->f_op->llseek) - fn = file->f_op->llseek; - } - return fn(file, offset, whence); + if (!(file->f_mode & FMODE_LSEEK)) + return -ESPIPE; + return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); -off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) +static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); @@ -331,7 +320,8 @@ COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned i } #endif -#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) +#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) @@ -364,52 +354,37 @@ out_putf: int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { - struct inode *inode; - int retval = -EINVAL; - - inode = file_inode(file); if (unlikely((ssize_t) count < 0)) - return retval; + return -EINVAL; - /* - * ranged mandatory locking does not apply to streams - it makes sense - * only for files where position has a meaning. - */ if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) - return retval; + 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 retval; - } - - if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - retval = locks_mandatory_area(inode, file, pos, pos + count - 1, - read_write == READ ? F_RDLCK : F_WRLCK); - if (retval < 0) - return retval; + 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 iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); - iov_iter_init(&iter, READ, &iov, 1, len); + iov_iter_ubuf(&iter, READ, buf, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); @@ -418,28 +393,57 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo return ret; } -ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, - loff_t *pos) +static int warn_unsupported(struct file *file, const char *op) { - if (file->f_op->read) - return file->f_op->read(file, buf, count, pos); - else if (file->f_op->read_iter) - return new_sync_read(file, buf, count, pos); - else + 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, READ, &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) { - mm_segment_t old_fs; - ssize_t result; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - result = vfs_read(file, (void __user *)buf, count, pos); - set_fs(old_fs); - return result; + ret = rw_verify_area(READ, file, pos, count); + if (ret) + return ret; + return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); @@ -455,30 +459,34 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - ret = __vfs_read(file, buf, count, pos); - if (ret > 0) { - fsnotify_access(file); - add_rchar(current, ret); - } - inc_syscr(current); - } + if (ret) + return ret; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + 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 iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); - iov_iter_init(&iter, WRITE, &iov, 1, len); + iov_iter_ubuf(&iter, WRITE, (void __user *)buf, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); @@ -487,55 +495,69 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t return ret; } -static ssize_t __vfs_write(struct file *file, const char __user *p, - size_t count, loff_t *pos) +/* 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) { - if (file->f_op->write) - return file->f_op->write(file, p, count, pos); - else if (file->f_op->write_iter) - return new_sync_write(file, p, count, pos); - else - return -EINVAL; -} - -ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) -{ - mm_segment_t old_fs; - const char __user *p; + 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"); - old_fs = get_fs(); - set_fs(KERNEL_DS); - p = (__force const char __user *)buf; - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - ret = __vfs_write(file, p, count, pos); - set_fs(old_fs); + 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; } -EXPORT_SYMBOL(__kernel_write); + +/* 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, WRITE, &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) { - mm_segment_t old_fs; - ssize_t res; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_write(file, (__force const char __user *)buf, count, pos); - set_fs(old_fs); + ret = rw_verify_area(WRITE, file, pos, count); + if (ret) + return ret; - return res; + file_start_write(file); + ret = __kernel_write(file, buf, count, pos); + file_end_write(file); + return ret; } EXPORT_SYMBOL(kernel_write); @@ -551,19 +573,23 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - file_start_write(file); - ret = __vfs_write(file, buf, count, pos); - if (ret > 0) { - fsnotify_modify(file); - add_wchar(current, ret); - } - inc_syscw(current); - file_end_write(file); + 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; } @@ -649,6 +675,14 @@ SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, 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) { @@ -675,6 +709,14 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, 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) { @@ -732,185 +774,6 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, return ret; } -/** - * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace - * into the kernel and check that it is valid. - * - * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE. - * @uvector: Pointer to the userspace array. - * @nr_segs: Number of elements in userspace array. - * @fast_segs: Number of elements in @fast_pointer. - * @fast_pointer: Pointer to (usually small on-stack) kernel array. - * @ret_pointer: (output parameter) Pointer to a variable that will point to - * either @fast_pointer, a newly allocated kernel array, or NULL, - * depending on which array was used. - * - * This function copies an array of &struct iovec of @nr_segs from - * userspace into the kernel and checks that each element is valid (e.g. - * it does not point to a kernel address or cause overflow by being too - * large, etc.). - * - * As an optimization, the caller may provide a pointer to a small - * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long - * (the size of this array, or 0 if unused, should be given in @fast_segs). - * - * @ret_pointer will always point to the array that was used, so the - * caller must take care not to call kfree() on it e.g. in case the - * @fast_pointer array was used and it was allocated on the stack. - * - * Return: The total number of bytes covered by the iovec array on success - * or a negative error code on error. - */ -ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer) -{ - unsigned long seg; - ssize_t ret; - struct iovec *iov = fast_pointer; - - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - if (nr_segs == 0) { - ret = 0; - goto out; - } - - /* - * First get the "struct iovec" from user memory and - * verify all the pointers - */ - if (nr_segs > UIO_MAXIOV) { - ret = -EINVAL; - goto out; - } - if (nr_segs > fast_segs) { - iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); - if (iov == NULL) { - ret = -ENOMEM; - goto out; - } - } - if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) { - ret = -EFAULT; - goto out; - } - - /* - * According to the Single Unix Specification we should return EINVAL - * if an element length is < 0 when cast to ssize_t or if the - * total length would overflow the ssize_t return value of the - * system call. - * - * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the - * overflow case. - */ - ret = 0; - for (seg = 0; seg < nr_segs; seg++) { - void __user *buf = iov[seg].iov_base; - ssize_t len = (ssize_t)iov[seg].iov_len; - - /* see if we we're about to use an invalid len or if - * it's about to overflow ssize_t */ - if (len < 0) { - ret = -EINVAL; - goto out; - } - if (type >= 0 - && unlikely(!access_ok(buf, len))) { - ret = -EFAULT; - goto out; - } - if (len > MAX_RW_COUNT - ret) { - len = MAX_RW_COUNT - ret; - iov[seg].iov_len = len; - } - ret += len; - } -out: - *ret_pointer = iov; - return ret; -} - -#ifdef CONFIG_COMPAT -ssize_t compat_rw_copy_check_uvector(int type, - const struct compat_iovec __user *uvector, unsigned long nr_segs, - unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer) -{ - compat_ssize_t tot_len; - struct iovec *iov = *ret_pointer = fast_pointer; - ssize_t ret = 0; - int seg; - - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - if (nr_segs == 0) - goto out; - - ret = -EINVAL; - if (nr_segs > UIO_MAXIOV) - goto out; - if (nr_segs > fast_segs) { - ret = -ENOMEM; - iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); - if (iov == NULL) - goto out; - } - *ret_pointer = iov; - - ret = -EFAULT; - if (!access_ok(uvector, nr_segs*sizeof(*uvector))) - goto out; - - /* - * Single unix specification: - * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. - * - * In Linux, the total length is limited to MAX_RW_COUNT, there is - * no overflow possibility. - */ - tot_len = 0; - ret = -EINVAL; - for (seg = 0; seg < nr_segs; seg++) { - compat_uptr_t buf; - compat_ssize_t len; - - if (__get_user(len, &uvector->iov_len) || - __get_user(buf, &uvector->iov_base)) { - ret = -EFAULT; - goto out; - } - if (len < 0) /* size_t not fitting in compat_ssize_t .. */ - goto out; - if (type >= 0 && - !access_ok(compat_ptr(buf), len)) { - ret = -EFAULT; - goto out; - } - if (len > MAX_RW_COUNT - tot_len) - len = MAX_RW_COUNT - tot_len; - tot_len += len; - iov->iov_base = compat_ptr(buf); - iov->iov_len = (compat_size_t) len; - uvector++; - iov++; - } - ret = tot_len; - -out: - return ret; -} -#endif - static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { @@ -1040,7 +903,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, } EXPORT_SYMBOL(vfs_iter_write); -ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, +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]; @@ -1227,230 +1090,100 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, 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 -static size_t compat_readv(struct file *file, - const struct compat_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 = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter); - if (ret >= 0) { - ret = do_iter_read(file, &iter, pos, flags); - kfree(iov); - } - if (ret > 0) - add_rchar(current, ret); - inc_syscr(current); - return ret; -} - -static size_t do_compat_readv(compat_ulong_t fd, - const struct compat_iovec __user *vec, - compat_ulong_t vlen, rwf_t flags) -{ - struct fd f = fdget_pos(fd); - ssize_t ret; - loff_t pos; - - if (!f.file) - return -EBADF; - pos = f.file->f_pos; - ret = compat_readv(f.file, vec, vlen, &pos, flags); - if (ret >= 0) - f.file->f_pos = pos; - fdput_pos(f); - return ret; - -} - -COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, - const struct compat_iovec __user *,vec, - compat_ulong_t, vlen) -{ - return do_compat_readv(fd, vec, vlen, 0); -} - -static long do_compat_preadv64(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, rwf_t flags) -{ - struct fd f; - ssize_t ret; - - if (pos < 0) - return -EINVAL; - f = fdget(fd); - if (!f.file) - return -EBADF; - ret = -ESPIPE; - if (f.file->f_mode & FMODE_PREAD) - ret = compat_readv(f.file, vec, vlen, &pos, flags); - fdput(f); - return ret; -} - #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, - const struct compat_iovec __user *,vec, + const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { - return do_compat_preadv64(fd, vec, vlen, pos, 0); + return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, - const struct compat_iovec __user *,vec, + 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_compat_preadv64(fd, vec, vlen, pos, 0); + return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, - const struct compat_iovec __user *,vec, + const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) - return do_compat_readv(fd, vec, vlen, flags); - - return do_compat_preadv64(fd, vec, vlen, pos, flags); + 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 compat_iovec __user *,vec, + 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_compat_readv(fd, vec, vlen, flags); - - return do_compat_preadv64(fd, vec, vlen, pos, flags); -} - -static size_t compat_writev(struct file *file, - const struct compat_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 = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter); - if (ret >= 0) { - file_start_write(file); - ret = do_iter_write(file, &iter, pos, flags); - file_end_write(file); - kfree(iov); - } - if (ret > 0) - add_wchar(current, ret); - inc_syscw(current); - return ret; -} - -static size_t do_compat_writev(compat_ulong_t fd, - const struct compat_iovec __user* vec, - compat_ulong_t vlen, rwf_t flags) -{ - struct fd f = fdget_pos(fd); - ssize_t ret; - loff_t pos; - - if (!f.file) - return -EBADF; - pos = f.file->f_pos; - ret = compat_writev(f.file, vec, vlen, &pos, flags); - if (ret >= 0) - f.file->f_pos = pos; - fdput_pos(f); - return ret; -} - -COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, - const struct compat_iovec __user *, vec, - compat_ulong_t, vlen) -{ - return do_compat_writev(fd, vec, vlen, 0); -} - -static long do_compat_pwritev64(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, rwf_t flags) -{ - struct fd f; - ssize_t ret; - - if (pos < 0) - return -EINVAL; - f = fdget(fd); - if (!f.file) - return -EBADF; - ret = -ESPIPE; - if (f.file->f_mode & FMODE_PWRITE) - ret = compat_writev(f.file, vec, vlen, &pos, flags); - fdput(f); - return ret; + 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 compat_iovec __user *,vec, + const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { - return do_compat_pwritev64(fd, vec, vlen, pos, 0); + return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, - const struct compat_iovec __user *,vec, + 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_compat_pwritev64(fd, vec, vlen, pos, 0); + return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, - const struct compat_iovec __user *,vec, + const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) - return do_compat_writev(fd, vec, vlen, flags); - - return do_compat_pwritev64(fd, vec, vlen, pos, flags); + 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 compat_iovec __user *,vec, + 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_compat_writev(fd, vec, vlen, flags); - - return do_compat_pwritev64(fd, vec, vlen, pos, flags); + return do_writev(fd, vec, vlen, flags); + return do_pwritev(fd, vec, vlen, pos, flags); } - -#endif +#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; @@ -1491,9 +1224,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; - retval = rw_verify_area(WRITE, out.file, &out_pos, count); - if (retval < 0) - goto fput_out; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1516,9 +1246,21 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - file_start_write(out.file); - retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); - file_end_write(out.file); + 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); @@ -1651,26 +1393,75 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(generic_copy_file_range); -static ssize_t do_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) +/* + * 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; + /* - * Although we now allow filesystems to handle cross sb copy, passing + * 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 defines - * several different file_system_type structures, but they all end up + * 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 (file_out->f_op->copy_file_range && - file_out->f_op->copy_file_range == file_in->f_op->copy_file_range) - return file_out->f_op->copy_file_range(file_in, pos_in, - file_out, pos_out, - len, flags); + 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; + } - return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, - flags); + /* 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; } /* @@ -1706,26 +1497,41 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, file_start_write(file_out); /* - * Try cloning first, this is supported by more file systems, and - * more efficient if both clone and copy are supported (e.g. NFS). + * 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 (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 (file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { - loff_t cloned; - - cloned = file_in->f_op->remap_file_range(file_in, pos_in, + 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 (cloned > 0) { - ret = cloned; + if (ret > 0) goto done; - } } - ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len, - flags); - WARN_ON_ONCE(ret == -EOPNOTSUPP); + /* + * 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(). + */ + ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, + flags); + done: if (ret > 0) { fsnotify_access(file_in); @@ -1805,475 +1611,100 @@ out2: return ret; } -static int remap_verify_area(struct file *file, loff_t pos, loff_t len, - bool write) -{ - struct inode *inode = file_inode(file); - - if (unlikely(pos < 0 || len < 0)) - return -EINVAL; - - if (unlikely((loff_t) (pos + len) < 0)) - return -EINVAL; - - if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - loff_t end = len ? pos + len - 1 : OFFSET_MAX; - int retval; - - retval = locks_mandatory_area(inode, file, pos, end, - write ? F_WRLCK : F_RDLCK); - if (retval < 0) - return retval; - } - - return security_file_permission(file, write ? MAY_WRITE : MAY_READ); -} /* - * Ensure that we don't remap a partial EOF block in the middle of something - * else. Assume that the offsets have already been checked for block - * alignment. - * - * For clone we only link a partial EOF block above or at the destination file's - * EOF. For deduplication we accept a partial EOF block only if it ends at the - * destination file's EOF (can not link it into the middle of a file). - * - * Shorten the request if possible. + * 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. */ -static int generic_remap_check_len(struct inode *inode_in, - struct inode *inode_out, - loff_t pos_out, - loff_t *len, - unsigned int remap_flags) +int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { - u64 blkmask = i_blocksize(inode_in) - 1; - loff_t new_len = *len; - - if ((*len & blkmask) == 0) - return 0; - - if (pos_out + *len < i_size_read(inode_out)) - new_len &= ~blkmask; - - if (new_len == *len) - return 0; + struct inode *inode = file->f_mapping->host; + loff_t max_size = inode->i_sb->s_maxbytes; + loff_t limit = rlimit(RLIMIT_FSIZE); - if (remap_flags & REMAP_FILE_CAN_SHORTEN) { - *len = new_len; - return 0; + if (limit != RLIM_INFINITY) { + if (pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + *count = min(*count, limit - pos); } - return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; -} - -/* Read a page's worth of file data into the page cache. */ -static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) -{ - struct page *page; + if (!(file->f_flags & O_LARGEFILE)) + max_size = MAX_NON_LFS; - page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL); - if (IS_ERR(page)) - return page; - if (!PageUptodate(page)) { - put_page(page); - return ERR_PTR(-EIO); - } - return page; -} + if (unlikely(pos >= max_size)) + return -EFBIG; -/* - * Lock two pages, ensuring that we lock in offset order if the pages are from - * the same file. - */ -static void vfs_lock_two_pages(struct page *page1, struct page *page2) -{ - /* Always lock in order of increasing index. */ - if (page1->index > page2->index) - swap(page1, page2); + *count = min(*count, max_size - pos); - lock_page(page1); - if (page1 != page2) - lock_page(page2); + return 0; } -/* Unlock two pages, being careful not to unlock the same page twice. */ -static void vfs_unlock_two_pages(struct page *page1, struct page *page2) +/* Like generic_write_checks(), but takes size of write instead of iter. */ +int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { - unlock_page(page1); - if (page1 != page2) - unlock_page(page2); -} - -/* - * Compare extents of two files to see if they are the same. - * Caller must have locked both inodes to prevent write races. - */ -static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same) -{ - loff_t src_poff; - loff_t dest_poff; - void *src_addr; - void *dest_addr; - struct page *src_page; - struct page *dest_page; - loff_t cmp_len; - bool same; - int error; - - error = -EINVAL; - same = true; - while (len) { - src_poff = srcoff & (PAGE_SIZE - 1); - dest_poff = destoff & (PAGE_SIZE - 1); - cmp_len = min(PAGE_SIZE - src_poff, - PAGE_SIZE - dest_poff); - cmp_len = min(cmp_len, len); - if (cmp_len <= 0) - goto out_error; - - src_page = vfs_dedupe_get_page(src, srcoff); - if (IS_ERR(src_page)) { - error = PTR_ERR(src_page); - goto out_error; - } - dest_page = vfs_dedupe_get_page(dest, destoff); - if (IS_ERR(dest_page)) { - error = PTR_ERR(dest_page); - put_page(src_page); - goto out_error; - } - - vfs_lock_two_pages(src_page, dest_page); - - /* - * Now that we've locked both pages, make sure they're still - * mapped to the file data we're interested in. If not, - * someone is invalidating pages on us and we lose. - */ - if (!PageUptodate(src_page) || !PageUptodate(dest_page) || - src_page->mapping != src->i_mapping || - dest_page->mapping != dest->i_mapping) { - same = false; - goto unlock; - } - - src_addr = kmap_atomic(src_page); - dest_addr = kmap_atomic(dest_page); - - flush_dcache_page(src_page); - flush_dcache_page(dest_page); - - if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) - same = false; + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; - kunmap_atomic(dest_addr); - kunmap_atomic(src_addr); -unlock: - vfs_unlock_two_pages(src_page, dest_page); - put_page(dest_page); - put_page(src_page); + if (IS_SWAPFILE(inode)) + return -ETXTBSY; - if (!same) - break; + if (!*count) + return 0; - srcoff += cmp_len; - destoff += cmp_len; - len -= cmp_len; - } + if (iocb->ki_flags & IOCB_APPEND) + iocb->ki_pos = i_size_read(inode); - *is_same = same; - return 0; + if ((iocb->ki_flags & IOCB_NOWAIT) && + !((iocb->ki_flags & IOCB_DIRECT) || + (file->f_mode & FMODE_BUF_WASYNC))) + return -EINVAL; -out_error: - return error; + return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } +EXPORT_SYMBOL(generic_write_checks_count); /* - * 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. + * Performs necessary checks before doing a write * - * If there's an error, then the usual negative error code is returned. - * Otherwise returns 0 with *len set to the request length. + * 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. */ -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) +ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); - bool same_inode = (inode_in == inode_out); + loff_t count = iov_iter_count(from); 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)) - ret = file_modified(file_out); - - return ret; -} -EXPORT_SYMBOL(generic_remap_file_range_prep); - -loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags) -{ - loff_t ret; - - WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); - - /* - * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on - * the same mount. Practically, they only need to be on the same file - * system. - */ - if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) - return -EXDEV; - - ret = generic_file_rw_checks(file_in, file_out); - if (ret < 0) - return ret; - - if (!file_in->f_op->remap_file_range) - return -EOPNOTSUPP; - - ret = remap_verify_area(file_in, pos_in, len, false); - if (ret) - return ret; - - ret = remap_verify_area(file_out, pos_out, len, true); - if (ret) - return ret; - - ret = file_in->f_op->remap_file_range(file_in, pos_in, - file_out, pos_out, len, remap_flags); - if (ret < 0) - return ret; - - fsnotify_access(file_in); - fsnotify_modify(file_out); - return ret; -} -EXPORT_SYMBOL(do_clone_file_range); - -loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags) -{ - loff_t ret; - - file_start_write(file_out); - ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len, - remap_flags); - file_end_write(file_out); - - return ret; -} -EXPORT_SYMBOL(vfs_clone_file_range); - -/* Check whether we are allowed to dedupe the destination file */ -static bool allow_file_dedupe(struct file *file) -{ - if (capable(CAP_SYS_ADMIN)) - return true; - if (file->f_mode & FMODE_WRITE) - return true; - if (uid_eq(current_fsuid(), file_inode(file)->i_uid)) - return true; - if (!inode_permission(file_inode(file), MAY_WRITE)) - return true; - return false; -} - -loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - loff_t len, unsigned int remap_flags) -{ - loff_t ret; - - WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | - REMAP_FILE_CAN_SHORTEN)); - - ret = mnt_want_write_file(dst_file); + ret = generic_write_checks_count(iocb, &count); if (ret) return ret; - ret = remap_verify_area(dst_file, dst_pos, len, true); - if (ret < 0) - goto out_drop_write; - - ret = -EPERM; - if (!allow_file_dedupe(dst_file)) - goto out_drop_write; - - ret = -EXDEV; - if (src_file->f_path.mnt != dst_file->f_path.mnt) - goto out_drop_write; - - ret = -EISDIR; - if (S_ISDIR(file_inode(dst_file)->i_mode)) - goto out_drop_write; - - ret = -EINVAL; - if (!dst_file->f_op->remap_file_range) - goto out_drop_write; - - if (len == 0) { - ret = 0; - goto out_drop_write; - } - - ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, - dst_pos, len, remap_flags | REMAP_FILE_DEDUP); -out_drop_write: - mnt_drop_write_file(dst_file); - - return ret; + iov_iter_truncate(from, count); + return iov_iter_count(from); } -EXPORT_SYMBOL(vfs_dedupe_file_range_one); +EXPORT_SYMBOL(generic_write_checks); -int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) +/* + * 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 file_dedupe_range_info *info; - struct inode *src = file_inode(file); - u64 off; - u64 len; - int i; - int ret; - u16 count = same->dest_count; - loff_t deduped; - - if (!(file->f_mode & FMODE_READ)) - return -EINVAL; - - if (same->reserved1 || same->reserved2) - return -EINVAL; - - off = same->src_offset; - len = same->src_length; + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); - if (S_ISDIR(src->i_mode)) + /* Don't copy dirs, pipes, sockets... */ + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; - - if (!S_ISREG(src->i_mode)) - return -EINVAL; - - if (!file->f_op->remap_file_range) - return -EOPNOTSUPP; - - ret = remap_verify_area(file, off, len, false); - if (ret < 0) - return ret; - ret = 0; - - if (off + len > i_size_read(src)) + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; - /* Arbitrary 1G limit on a single dedupe request, can be raised. */ - len = min_t(u64, len, 1 << 30); - - /* pre-format output fields to sane values */ - for (i = 0; i < count; i++) { - same->info[i].bytes_deduped = 0ULL; - same->info[i].status = FILE_DEDUPE_RANGE_SAME; - } - - for (i = 0, info = same->info; i < count; i++, info++) { - struct fd dst_fd = fdget(info->dest_fd); - struct file *dst_file = dst_fd.file; - - if (!dst_file) { - info->status = -EBADF; - goto next_loop; - } - - if (info->reserved) { - info->status = -EINVAL; - goto next_fdput; - } - - deduped = vfs_dedupe_file_range_one(file, off, dst_file, - info->dest_offset, len, - REMAP_FILE_CAN_SHORTEN); - if (deduped == -EBADE) - info->status = FILE_DEDUPE_RANGE_DIFFERS; - else if (deduped < 0) - info->status = deduped; - else - info->bytes_deduped = len; + if (!(file_in->f_mode & FMODE_READ) || + !(file_out->f_mode & FMODE_WRITE) || + (file_out->f_flags & O_APPEND)) + return -EBADF; -next_fdput: - fdput(dst_fd); -next_loop: - if (fatal_signal_pending(current)) - break; - } - return ret; + return 0; } -EXPORT_SYMBOL(vfs_dedupe_file_range); |