From f16acc9d9b3761ae5e45219c9302f99e20919829 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 5 Jun 2019 08:04:47 -0700 Subject: vfs: introduce generic_copy_file_range() Right now if vfs_copy_file_range() does not use any offload mechanism, it falls back to calling do_splice_direct(). This fails to do basic sanity checks on the files being copied. Before we start adding this necessarily functionality to the fallback path, separate it out into generic_copy_file_range(). generic_copy_file_range() has the same prototype as ->copy_file_range() so that filesystems can use it in their custom ->copy_file_range() method if they so choose. Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f7fdfe93e25d..ea17858310ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1889,6 +1889,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +extern 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); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, -- cgit v1.2.3 From a31713517dac0862a3f0ec9006df9160ce022b0c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 5 Jun 2019 08:04:48 -0700 Subject: vfs: introduce generic_file_rw_checks() Factor out helper with some checks on in/out file that are common to clone_file_range and copy_file_range. Suggested-by: Darrick J. Wong Signed-off-by: Amir Goldstein Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/read_write.c | 38 +++++++++++--------------------------- include/linux/fs.h | 1 + mm/filemap.c | 24 ++++++++++++++++++++++++ 3 files changed, 36 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index b63dcb4e4fe9..f1900bdb3127 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1617,17 +1617,18 @@ 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) { - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); ssize_t ret; if (flags != 0) return -EINVAL; - 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; + /* this could be relaxed once a method supports cross-fs copies */ + 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 (unlikely(ret)) + return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) @@ -1637,15 +1638,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (unlikely(ret)) return ret; - if (!(file_in->f_mode & FMODE_READ) || - !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND)) - return -EBADF; - - /* this could be relaxed once a method supports cross-fs copies */ - if (inode_in->i_sb != inode_out->i_sb) - return -EXDEV; - if (len == 0) return 0; @@ -2013,29 +2005,21 @@ 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) { - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); - 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; - /* * 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 (inode_in->i_sb != inode_out->i_sb) + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; - if (!(file_in->f_mode & FMODE_READ) || - !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND)) - return -EBADF; + ret = generic_file_rw_checks(file_in, file_out); + if (ret < 0) + return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; diff --git a/include/linux/fs.h b/include/linux/fs.h index ea17858310ff..89b9b73eb581 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3049,6 +3049,7 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); +extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index df2006ba0cfa..a38619a4a6af 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3041,6 +3041,30 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, return 0; } + +/* + * 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; +} + int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) -- cgit v1.2.3 From 96e6e8f4a68df2d94800311163faa67124df24e5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 5 Jun 2019 08:04:49 -0700 Subject: vfs: add missing checks to copy_file_range Like the clone and dedupe interfaces we've recently fixed, the copy_file_range() implementation is missing basic sanity, limits and boundary condition tests on the parameters that are passed to it from userspace. Create a new "generic_copy_file_checks()" function modelled on the generic_remap_checks() function to provide this missing functionality. [Amir] Shorten copy length instead of checking pos_in limits because input file size already abides by the limits. Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/read_write.c | 3 ++- include/linux/fs.h | 3 +++ mm/filemap.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index f1900bdb3127..b0fb1176b628 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1626,7 +1626,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; - ret = generic_file_rw_checks(file_in, file_out); + ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, + flags); if (unlikely(ret)) return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index 89b9b73eb581..e4d382c4342a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3050,6 +3050,9 @@ extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); +extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t *count, unsigned int flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 44361928bbb0..aac71aef4c61 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3056,6 +3056,59 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out) return 0; } +/* + * 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. + */ +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; + + /* 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; +} + int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) -- cgit v1.2.3 From e38f7f53c35213b1cbce70eee5de7ced17f40d4a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 5 Jun 2019 08:04:49 -0700 Subject: vfs: introduce file_modified() helper The combination of file_remove_privs() and file_update_mtime() is quite common in filesystem ->write_iter() methods. Modelled after the helper file_accessed(), introduce file_modified() and use it from generic_remap_file_range_prep(). Note that the order of calling file_remove_privs() before file_update_mtime() in the helper was matched to the more common order by filesystems and not the current order in generic_remap_file_range_prep(). Signed-off-by: Amir Goldstein Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/inode.c | 20 ++++++++++++++++++++ fs/read_write.c | 21 +++------------------ include/linux/fs.h | 2 ++ 3 files changed, 25 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index df6542ec3b88..4348cfb14562 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1899,6 +1899,26 @@ int file_update_time(struct file *file) } EXPORT_SYMBOL(file_update_time); +/* Caller must hold the file's inode lock */ +int file_modified(struct file *file) +{ + int err; + + /* + * Clear the security bits if the process is not being run by root. + * This keeps people from modifying setuid and setgid binaries. + */ + err = file_remove_privs(file); + if (err) + return err; + + if (unlikely(file->f_mode & FMODE_NOCMTIME)) + return 0; + + return file_update_time(file); +} +EXPORT_SYMBOL(file_modified); + int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) diff --git a/fs/read_write.c b/fs/read_write.c index b0fb1176b628..cec7e7b1f693 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1980,25 +1980,10 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, 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; - } + if (!(remap_flags & REMAP_FILE_DEDUP)) + ret = file_modified(file_out); - /* - * 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; + return ret; } EXPORT_SYMBOL(generic_remap_file_range_prep); diff --git a/include/linux/fs.h b/include/linux/fs.h index e4d382c4342a..79ffa2958bd8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2177,6 +2177,8 @@ static inline void file_accessed(struct file *file) touch_atime(&file->f_path); } +extern int file_modified(struct file *file); + int sync_inode(struct inode *inode, struct writeback_control *wbc); int sync_inode_metadata(struct inode *inode, int wait); -- cgit v1.2.3