vfs: pass a flags argument to vfs_readv/vfs_writev

This way we can set kiocb flags also from the sync read/write path for
the read_iter/write_iter operations.  For now there is no way to pass
flags to plain read/write operations as there is no real need for that,
and all flags passed are explicitly rejected for these files.
Signed-off-by: Milosz Tanski <milosz@adfin.com>
[hch: rebased on top of my kiocb changes]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stephen Bates <stephen.bates@pmcs.com>
Tested-by: Stephen Bates <stephen.bates@pmcs.com>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/nfsd/vfs.c

@@ -870,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
 
 	oldfs = get_fs();
 	set_fs(KERNEL_DS);
-	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0);
 	set_fs(oldfs);
 	return nfsd_finish_read(file, count, host_err);
 }
@@ -957,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 
 	/* Write the data. */
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
+	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(oldfs);
 	if (host_err < 0)
 		goto out_nfserr;

fs/read_write.c

@@ -692,11 +692,14 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn)
+		loff_t *ppos, iter_fn_t fn, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
 
+	if (flags)
+		return -EOPNOTSUPP;
+
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
 
@@ -708,10 +711,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn)
+		loff_t *ppos, io_fn_t fn, int flags)
 {
 	ssize_t ret = 0;
 
+	if (flags)
+		return -EOPNOTSUPP;
+
 	while (iov_iter_count(iter)) {
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
@@ -812,7 +818,8 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 
 static ssize_t do_readv_writev(int type, struct file *file,
 			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -844,9 +851,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -863,27 +870,27 @@ static ssize_t do_readv_writev(int type, struct file *file,
 }
 
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
-		  unsigned long vlen, loff_t *pos)
+		  unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 
-	return do_readv_writev(READ, file, vec, vlen, pos);
+	return do_readv_writev(READ, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_readv);
 
 ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
-		   unsigned long vlen, loff_t *pos)
+		   unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
-	return do_readv_writev(WRITE, file, vec, vlen, pos);
+	return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_writev);
@@ -896,7 +903,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_readv(f.file, vec, vlen, &pos);
+		ret = vfs_readv(f.file, vec, vlen, &pos, 0);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -916,7 +923,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_writev(f.file, vec, vlen, &pos);
+		ret = vfs_writev(f.file, vec, vlen, &pos, 0);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -948,7 +955,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PREAD)
-			ret = vfs_readv(f.file, vec, vlen, &pos);
+			ret = vfs_readv(f.file, vec, vlen, &pos, 0);
 		fdput(f);
 	}
 
@@ -972,7 +979,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PWRITE)
-			ret = vfs_writev(f.file, vec, vlen, &pos);
+			ret = vfs_writev(f.file, vec, vlen, &pos, 0);
 		fdput(f);
 	}
 
@@ -986,7 +993,8 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 
 static ssize_t compat_do_readv_writev(int type, struct file *file,
 			       const struct compat_iovec __user *uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -1018,9 +1026,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -1049,7 +1057,7 @@ static size_t compat_readv(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_READ))
 		goto out;
 
-	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(READ, file, vec, vlen, pos, 0);
 
 out:
 	if (ret > 0)
@@ -1126,7 +1134,7 @@ static size_t compat_writev(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		goto out;
 
-	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0);
 
 out:
 	if (ret > 0)

fs/splice.c

@@ -577,7 +577,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
 	old_fs = get_fs();
 	set_fs(get_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);
+	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(old_fs);
 
 	return res;

include/linux/fs.h

@@ -1712,9 +1712,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *)
 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 *);
+		unsigned long, loff_t *, int);
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
-		unsigned long, loff_t *);
+		unsigned long, loff_t *, int);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,