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 <viro@zeniv.linux.org.uk>

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

lib/iov_iter.c

@@ -16,6 +16,16 @@
 
 #define PIPE_PARANOIA /* for now */
 
+/* covers ubuf and kbuf alike */
+#define iterate_buf(i, n, base, len, off, __p, STEP) {		\
+	size_t __maybe_unused off = 0;				\
+	len = n;						\
+	base = __p + i->iov_offset;				\
+	len -= (STEP);						\
+	i->iov_offset += len;					\
+	n = len;						\
+}
+
 /* covers iovec and kvec alike */
 #define iterate_iovec(i, n, base, len, off, __p, STEP) {	\
 	size_t off = 0;						\
@@ -110,7 +120,12 @@ __out:								\
 	if (unlikely(i->count < n))				\
 		n = i->count;					\
 	if (likely(n)) {					\
-		if (likely(iter_is_iovec(i))) {			\
+		if (likely(iter_is_ubuf(i))) {			\
+			void __user *base;			\
+			size_t len;				\
+			iterate_buf(i, n, base, len, off,	\
+						i->ubuf, (I)) 	\
+		} else if (likely(iter_is_iovec(i))) {		\
 			const struct iovec *iov = i->iov;	\
 			void __user *base;			\
 			size_t len;				\
@@ -275,7 +290,11 @@ out:
  */
 size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size)
 {
-	if (iter_is_iovec(i)) {
+	if (iter_is_ubuf(i)) {
+		size_t n = min(size, iov_iter_count(i));
+		n -= fault_in_readable(i->ubuf + i->iov_offset, n);
+		return size - n;
+	} else if (iter_is_iovec(i)) {
 		size_t count = min(size, iov_iter_count(i));
 		const struct iovec *p;
 		size_t skip;
@@ -314,7 +333,11 @@ EXPORT_SYMBOL(fault_in_iov_iter_readable);
  */
 size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
 {
-	if (iter_is_iovec(i)) {
+	if (iter_is_ubuf(i)) {
+		size_t n = min(size, iov_iter_count(i));
+		n -= fault_in_safe_writeable(i->ubuf + i->iov_offset, n);
+		return size - n;
+	} else if (iter_is_iovec(i)) {
 		size_t count = min(size, iov_iter_count(i));
 		const struct iovec *p;
 		size_t skip;
@@ -345,6 +368,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
 		.nofault = false,
+		.user_backed = true,
 		.data_source = direction,
 		.iov = iov,
 		.nr_segs = nr_segs,
@@ -494,7 +518,7 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(iov_iter_is_pipe(i)))
 		return copy_pipe_to_iter(addr, bytes, i);
-	if (iter_is_iovec(i))
+	if (user_backed_iter(i))
 		might_fault();
 	iterate_and_advance(i, bytes, base, len, off,
 		copyout(base, addr + off, len),
@@ -583,7 +607,7 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(iov_iter_is_pipe(i)))
 		return copy_mc_pipe_to_iter(addr, bytes, i);
-	if (iter_is_iovec(i))
+	if (user_backed_iter(i))
 		might_fault();
 	__iterate_and_advance(i, bytes, base, len, off,
 		copyout_mc(base, addr + off, len),
@@ -601,7 +625,7 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 		WARN_ON(1);
 		return 0;
 	}
-	if (iter_is_iovec(i))
+	if (user_backed_iter(i))
 		might_fault();
 	iterate_and_advance(i, bytes, base, len, off,
 		copyin(addr + off, base, len),
@@ -894,16 +918,16 @@ void iov_iter_advance(struct iov_iter *i, size_t size)
 {
 	if (unlikely(i->count < size))
 		size = i->count;
-	if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) {
+	if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) {
+		i->iov_offset += size;
+		i->count -= size;
+	} else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) {
 		/* iovec and kvec have identical layouts */
 		iov_iter_iovec_advance(i, size);
 	} else if (iov_iter_is_bvec(i)) {
 		iov_iter_bvec_advance(i, size);
 	} else if (iov_iter_is_pipe(i)) {
 		pipe_advance(i, size);
-	} else if (unlikely(iov_iter_is_xarray(i))) {
-		i->iov_offset += size;
-		i->count -= size;
 	} else if (iov_iter_is_discard(i)) {
 		i->count -= size;
 	}
@@ -950,7 +974,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 		return;
 	}
 	unroll -= i->iov_offset;
-	if (iov_iter_is_xarray(i)) {
+	if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) {
 		BUG(); /* We should never go beyond the start of the specified
 			* range since we might then be straying into pages that
 			* aren't pinned.
@@ -1158,6 +1182,14 @@ static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
 bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
 			 unsigned len_mask)
 {
+	if (likely(iter_is_ubuf(i))) {
+		if (i->count & len_mask)
+			return false;
+		if ((unsigned long)(i->ubuf + i->iov_offset) & addr_mask)
+			return false;
+		return true;
+	}
+
 	if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
 		return iov_iter_aligned_iovec(i, addr_mask, len_mask);
 
@@ -1233,6 +1265,13 @@ static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
 
 unsigned long iov_iter_alignment(const struct iov_iter *i)
 {
+	if (likely(iter_is_ubuf(i))) {
+		size_t size = i->count;
+		if (size)
+			return ((unsigned long)i->ubuf + i->iov_offset) | size;
+		return 0;
+	}
+
 	/* iovec and kvec have identical layouts */
 	if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
 		return iov_iter_alignment_iovec(i);
@@ -1263,6 +1302,9 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
 	size_t size = i->count;
 	unsigned k;
 
+	if (iter_is_ubuf(i))
+		return 0;
+
 	if (WARN_ON(!iter_is_iovec(i)))
 		return ~0U;
 
@@ -1385,12 +1427,15 @@ static ssize_t iter_xarray_get_pages(struct iov_iter *i,
 	return min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
 }
 
-/* must be done on non-empty ITER_IOVEC one */
+/* must be done on non-empty ITER_UBUF or ITER_IOVEC one */
 static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size)
 {
 	size_t skip;
 	long k;
 
+	if (iter_is_ubuf(i))
+		return (unsigned long)i->ubuf + i->iov_offset;
+
 	for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) {
 		size_t len = i->iov[k].iov_len - skip;
 
@@ -1432,7 +1477,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 	if (maxsize > MAX_RW_COUNT)
 		maxsize = MAX_RW_COUNT;
 
-	if (likely(iter_is_iovec(i))) {
+	if (likely(user_backed_iter(i))) {
 		unsigned int gup_flags = 0;
 		unsigned long addr;
 
@@ -1559,7 +1604,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 	if (maxsize > MAX_RW_COUNT)
 		maxsize = MAX_RW_COUNT;
 
-	if (likely(iter_is_iovec(i))) {
+	if (likely(user_backed_iter(i))) {
 		unsigned int gup_flags = 0;
 		unsigned long addr;
 
@@ -1715,6 +1760,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages)
 {
 	if (unlikely(!i->count))
 		return 0;
+	if (likely(iter_is_ubuf(i))) {
+		unsigned offs = offset_in_page(i->ubuf + i->iov_offset);
+		int npages = DIV_ROUND_UP(offs + i->count, PAGE_SIZE);
+		return min(npages, maxpages);
+	}
 	/* iovec and kvec have identical layouts */
 	if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
 		return iov_npages(i, maxpages);
@@ -1749,17 +1799,16 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 		WARN_ON(1);
 		return NULL;
 	}
-	if (unlikely(iov_iter_is_discard(new) || iov_iter_is_xarray(new)))
-		return NULL;
 	if (iov_iter_is_bvec(new))
 		return new->bvec = kmemdup(new->bvec,
 				    new->nr_segs * sizeof(struct bio_vec),
 				    flags);
-	else
+	else if (iov_iter_is_kvec(new) || iter_is_iovec(new))
 		/* iovec and kvec have identical layout */
 		return new->iov = kmemdup(new->iov,
 				   new->nr_segs * sizeof(struct iovec),
 				   flags);
+	return NULL;
 }
 EXPORT_SYMBOL(dup_iter);
 
@@ -1953,10 +2002,12 @@ EXPORT_SYMBOL(import_single_range);
 void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
 {
 	if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) &&
-			 !iov_iter_is_kvec(i))
+			 !iov_iter_is_kvec(i) && !iter_is_ubuf(i))
 		return;
 	i->iov_offset = state->iov_offset;
 	i->count = state->count;
+	if (iter_is_ubuf(i))
+		return;
 	/*
 	 * For the *vec iters, nr_segs + iov is constant - if we increment
 	 * the vec, then we also decrement the nr_segs count. Hence we don't

mm/shmem.c

@@ -2602,7 +2602,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			ret = copy_page_to_iter(page, offset, nr, to);
 			put_page(page);
 
-		} else if (iter_is_iovec(to)) {
+		} else if (user_backed_iter(to)) {
 			/*
 			 * Copy to user tends to be so well optimized, but
 			 * clear_user() not so much, that it is noticeably