fs: don't allow splice read/write without explicit ops

default_file_splice_write is the last piece of generic code that uses
set_fs to make the uaccess routines operate on kernel pointers.  It
implements a "fallback loop" for splicing from files that do not actually
provide a proper splice_read method.  The usual file systems and other
high bandwidth instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files.  If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/read_write.c b/fs/read_write.c
index 702c4301d9eb6b32a82ecc4cfa189482018915a1..8c61f67453e3d3a518b47bc4933b82c01309d490 100644 (file)
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1077,7 +1077,7 @@ 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];

diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07fff8cfc54a83adefba53207691a0..412df7b48f9eb79e5d6aaf82acbeb0f6e5e85191 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,89 +342,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-                           unsigned long vlen, loff_t offset)
-{
-       mm_segment_t old_fs;
-       loff_t pos = offset;
-       ssize_t res;
-
-       old_fs = get_fs();
-       set_fs(KERNEL_DS);
-       /* The cast to a user pointer is valid due to the set_fs() */
-       res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-       set_fs(old_fs);
-
-       return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-                                struct pipe_inode_info *pipe, size_t len,
-                                unsigned int flags)
-{
-       struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-       struct iov_iter to;
-       struct page **pages;
-       unsigned int nr_pages;
-       unsigned int mask;
-       size_t offset, base, copied = 0;
-       ssize_t res;
-       int i;
-
-       if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-               return -EAGAIN;
-
-       /*
-        * Try to keep page boundaries matching to source pagecache ones -
-        * it probably won't be much help, but...
-        */
-       offset = *ppos & ~PAGE_MASK;
-
-       iov_iter_pipe(&to, READ, pipe, len + offset);
-
-       res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-       if (res <= 0)
-               return -ENOMEM;
-
-       nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-       vec = __vec;
-       if (nr_pages > PIPE_DEF_BUFFERS) {
-               vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-               if (unlikely(!vec)) {
-                       res = -ENOMEM;
-                       goto out;
-               }
-       }
-
-       mask = pipe->ring_size - 1;
-       pipe->bufs[to.head & mask].offset = offset;
-       pipe->bufs[to.head & mask].len -= offset;
-
-       for (i = 0; i < nr_pages; i++) {
-               size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-               vec[i].iov_base = page_address(pages[i]) + offset;
-               vec[i].iov_len = this_len;
-               len -= this_len;
-               offset = 0;
-       }
-
-       res = kernel_readv(in, vec, nr_pages, *ppos);
-       if (res > 0) {
-               copied = res;
-               *ppos += res;
-       }
-
-       if (vec != __vec)
-               kfree(vec);
-out:
-       for (i = 0; i < nr_pages; i++)
-               put_page(pages[i]);
-       kvfree(pages);
-       iov_iter_advance(&to, copied);  /* truncates and discards */
-       return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -788,33 +705,6 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-                         struct splice_desc *sd)
-{
-       int ret;
-       void *data;
-       loff_t tmp = sd->pos;
-
-       data = kmap(buf->page);
-       ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-       kunmap(buf->page);
-
-       return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-                                        struct file *out, loff_t *ppos,
-                                        size_t len, unsigned int flags)
-{
-       ssize_t ret;
-
-       ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-       if (ret > 0)
-               *ppos += ret;
-
-       return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:      pipe to splice from
@@ -836,15 +726,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+       pr_debug_ratelimited(
+               "splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+               op, file, current->pid, current->comm);
+       return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
                           loff_t *ppos, size_t len, unsigned int flags)
 {
-       if (out->f_op->splice_write)
-               return out->f_op->splice_write(pipe, out, ppos, len, flags);
-       return default_file_splice_write(pipe, out, ppos, len, flags);
+       if (unlikely(!out->f_op->splice_write))
+               return warn_unsupported(out, "write");
+       return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -866,9 +764,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
        if (unlikely(len > MAX_RW_COUNT))
                len = MAX_RW_COUNT;
 
-       if (in->f_op->splice_read)
-               return in->f_op->splice_read(in, ppos, pipe, len, flags);
-       return default_file_splice_read(in, ppos, pipe, len, flags);
+       if (unlikely(!in->f_op->splice_read))
+               return warn_unsupported(in, "read");
+       return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**

diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347e6ebddea6cfeab01047c6af00660..d33cc3e8ed410b13852702eed8f1c0776f46c206 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-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,