new iov_iter flavour - ITER_UBUF

Equivalent of single-segment iovec.  Initialized by iov_iter_ubuf(),
checked for by iter_is_ubuf(), otherwise behaves like ITER_IOVEC
ones.

We are going to expose the things like ->write_iter() et.al. to those
in subsequent commits.

New predicate (user_backed_iter()) that is true for ITER_IOVEC and
ITER_UBUF; places like direct-IO handling should use that for
checking that pages we modify after getting them from iov_iter_get_pages()
would need to be dirtied.

DO NOT assume that replacing iter_is_iovec() with user_backed_iter()
will solve all problems - there's code that uses iter_is_iovec() to
decide how to poke around in iov_iter guts and for that the predicate
replacement obviously won't suffice.

Signed-off-by: Al Viro <[email protected]>

block/fops.c

@@ -75,7 +75,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 
 	if (iov_iter_rw(iter) == READ) {
 		bio_init(&bio, bdev, vecs, nr_pages, REQ_OP_READ);
-		if (iter_is_iovec(iter))
+		if (user_backed_iter(iter))
 			should_dirty = true;
 	} else {
 		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
@@ -204,7 +204,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	dio->size = 0;
-	if (is_read && iter_is_iovec(iter))
+	if (is_read && user_backed_iter(iter))
 		dio->flags |= DIO_SHOULD_DIRTY;
 
 	blk_start_plug(&plug);
@@ -335,7 +335,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	dio->size = bio->bi_iter.bi_size;
 
 	if (is_read) {
-		if (iter_is_iovec(iter)) {
+		if (user_backed_iter(iter)) {
 			dio->flags |= DIO_SHOULD_DIRTY;
 			bio_set_pages_dirty(bio);
 		}

fs/ceph/file.c

@@ -1262,7 +1262,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	loff_t pos = iocb->ki_pos;
 	bool write = iov_iter_rw(iter) == WRITE;
-	bool should_dirty = !write && iter_is_iovec(iter);
+	bool should_dirty = !write && user_backed_iter(iter);
 
 	if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;

fs/cifs/file.c

@@ -4004,7 +4004,7 @@ static ssize_t __cifs_readv(
 	if (!is_sync_kiocb(iocb))
 		ctx->iocb = iocb;
 
-	if (iter_is_iovec(to))
+	if (user_backed_iter(to))
 		ctx->should_dirty = true;
 
 	if (direct) {

fs/direct-io.c

@@ -1251,7 +1251,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
-	dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ;
+	dio->should_dirty = user_backed_iter(iter) && iov_iter_rw(iter) == READ;
 	sdio.iter = iter;
 	sdio.final_block_in_request = end >> blkbits;
 

fs/fuse/dev.c

@@ -1356,7 +1356,7 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to)
 	if (!fud)
 		return -EPERM;
 
-	if (!iter_is_iovec(to))
+	if (!user_backed_iter(to))
 		return -EINVAL;
 
 	fuse_copy_init(&cs, 1, to);
@@ -1949,7 +1949,7 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from)
 	if (!fud)
 		return -EPERM;
 
-	if (!iter_is_iovec(from))
+	if (!user_backed_iter(from))
 		return -EINVAL;
 
 	fuse_copy_init(&cs, 0, from);

fs/fuse/file.c

@@ -1465,7 +1465,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			inode_unlock(inode);
 	}
 
-	io->should_dirty = !write && iter_is_iovec(iter);
+	io->should_dirty = !write && user_backed_iter(iter);
 	while (count) {
 		ssize_t nres;
 		fl_owner_t owner = current->files;

fs/gfs2/file.c

@@ -780,7 +780,7 @@ static inline bool should_fault_in_pages(struct iov_iter *i,
 
 	if (!count)
 		return false;
-	if (!iter_is_iovec(i))
+	if (!user_backed_iter(i))
 		return false;
 
 	size = PAGE_SIZE;

fs/iomap/direct-io.c

@@ -533,7 +533,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			iomi.flags |= IOMAP_NOWAIT;
 		}
 
-		if (iter_is_iovec(iter))
+		if (user_backed_iter(iter))
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
 		iomi.flags |= IOMAP_WRITE;

fs/nfs/direct.c

@@ -478,7 +478,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	if (iter_is_iovec(iter))
+	if (user_backed_iter(iter))
 		dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
 
 	if (!swap)

include/linux/uio.h

@@ -26,6 +26,7 @@ enum iter_type {
 	ITER_PIPE,
 	ITER_XARRAY,
 	ITER_DISCARD,
+	ITER_UBUF,
 };
 
 struct iov_iter_state {
@@ -38,6 +39,7 @@ struct iov_iter {
 	u8 iter_type;
 	bool nofault;
 	bool data_source;
+	bool user_backed;
 	size_t iov_offset;
 	size_t count;
 	union {
@@ -46,6 +48,7 @@ struct iov_iter {
 		const struct bio_vec *bvec;
 		struct xarray *xarray;
 		struct pipe_inode_info *pipe;
+		void __user *ubuf;
 	};
 	union {
 		unsigned long nr_segs;
@@ -70,6 +73,11 @@ static inline void iov_iter_save_state(struct iov_iter *iter,
 	state->nr_segs = iter->nr_segs;
 }
 
+static inline bool iter_is_ubuf(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_UBUF;
+}
+
 static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return iov_iter_type(i) == ITER_IOVEC;
@@ -105,6 +113,11 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i)
 	return i->data_source ? WRITE : READ;
 }
 
+static inline bool user_backed_iter(const struct iov_iter *i)
+{
+	return i->user_backed;
+}
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -322,4 +335,17 @@ ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 int import_single_range(int type, void __user *buf, size_t len,
 		 struct iovec *iov, struct iov_iter *i);
 
+static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
+			void __user *buf, size_t count)
+{
+	WARN_ON(direction & ~(READ | WRITE));
+	*i = (struct iov_iter) {
+		.iter_type = ITER_UBUF,
+		.user_backed = true,
+		.data_source = direction,
+		.ubuf = buf,
+		.count = count
+	};
+}
+
 #endif