Merge tag 'pull-work.iov_iter-rebased' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more iov_iter updates from Al Viro:

- more new_sync_{read,write}() speedups - ITER_UBUF introduction

- ITER_PIPE cleanups

- unification of iov_iter_get_pages/iov_iter_get_pages_alloc and
switching them to advancing semantics

- making ITER_PIPE take high-order pages without splitting them

- handling copy_page_from_iter() for high-order pages properly

* tag 'pull-work.iov_iter-rebased' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (32 commits)
fix copy_page_from_iter() for compound destinations
hugetlbfs: copy_page_to_iter() can deal with compound pages
copy_page_to_iter(): don't split high-order page in case of ITER_PIPE
expand those iov_iter_advance()...
pipe_get_pages(): switch to append_pipe()
get rid of non-advancing variants
ceph: switch the last caller of iov_iter_get_pages_alloc()
9p: convert to advancing variant of iov_iter_get_pages_alloc()
af_alg_make_sg(): switch to advancing variant of iov_iter_get_pages()
iter_to_pipe(): switch to advancing variant of iov_iter_get_pages()
block: convert to advancing variants of iov_iter_get_pages{,_alloc}()
iov_iter: advancing variants of iov_iter_get_pages{,_alloc}()
iov_iter: saner helper for page array allocation
fold __pipe_get_pages() into pipe_get_pages()
ITER_XARRAY: don't open-code DIV_ROUND_UP()
unify the rest of iov_iter_get_pages()/iov_iter_get_pages_alloc() guts
unify xarray_get_pages() and xarray_get_pages_alloc()
unify pipe_get_pages() and pipe_get_pages_alloc()
iov_iter_get_pages(): sanity-check arguments
iov_iter_get_pages_alloc(): lift freeing pages array on failure exits into wrapper
...

block/bio.c

···
 	struct page **pages = (struct page **)bv;
 	ssize_t size, left;
 	unsigned len, i = 0;
-	size_t offset;
+	size_t offset, trim;
 	int ret = 0;
 
 	/*
···
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size,
+	size = iov_iter_get_pages2(iter, pages, UINT_MAX - bio->bi_iter.bi_size,
 				  nr_pages, &offset);
-	if (size > 0) {
-		nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
-		size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev));
-	} else
-		nr_pages = 0;
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
 
-	if (unlikely(size <= 0)) {
-		ret = size ? size : -EFAULT;
+	nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
+
+	trim = size & (bdev_logical_block_size(bio->bi_bdev) - 1);
+	iov_iter_revert(iter, trim);
+
+	size -= trim;
+	if (unlikely(!size)) {
+		ret = -EFAULT;
 		goto out;
 	}
 
···
 		offset = 0;
 	}
 
-	iov_iter_advance(iter, size - left);
+	iov_iter_revert(iter, left);
 out:
 	while (i < nr_pages)
 		put_page(pages[i++]);

block/blk-map.c

···
 		size_t offs, added = 0;
 		int npages;
 
-		bytes = iov_iter_get_pages_alloc(iter, &pages, LONG_MAX, &offs);
+		bytes = iov_iter_get_pages_alloc2(iter, &pages, LONG_MAX, &offs);
 		if (unlikely(bytes <= 0)) {
 			ret = bytes ? bytes : -EFAULT;
 			goto out_unmap;
···
 				bytes -= n;
 				offs = 0;
 			}
-			iov_iter_advance(iter, added);
 		}
 		/*
 		 * release the pages we didn't map into the bio, if any
···
 			put_page(pages[j++]);
 		kvfree(pages);
 		/* couldn't stuff something into bio? */
-		if (bytes)
+		if (bytes) {
+			iov_iter_revert(iter, bytes);
 			break;
+		}
 	}
 
 	ret = blk_rq_append_bio(rq, bio);

block/fops.c

···
 
 	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));
···
 	}
 
 	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);
···
 	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);
 		}

crypto/af_alg.c

···
 	ssize_t n;
 	int npages, i;
 
-	n = iov_iter_get_pages(iter, sgl->pages, len, ALG_MAX_PAGES, &off);
+	n = iov_iter_get_pages2(iter, sgl->pages, len, ALG_MAX_PAGES, &off);
 	if (n < 0)
 		return n;
 
···
 		len += err;
 		atomic_add(err, &ctx->rcvused);
 		rsgl->sg_num_bytes = err;
-		iov_iter_advance(&msg->msg_iter, err);
 	}
 
 	*outlen = len;

crypto/algif_hash.c

···
 		err = crypto_wait_req(crypto_ahash_update(&ctx->req),
 				      &ctx->wait);
 		af_alg_free_sg(&ctx->sgl);
-		if (err)
+		if (err) {
+			iov_iter_revert(&msg->msg_iter, len);
 			goto unlock;
+		}
 
 		copied += len;
-		iov_iter_advance(&msg->msg_iter, len);
 	}
 
 	err = 0;

drivers/vhost/scsi.c

···
 	size_t offset;
 	unsigned int npages = 0;
 
-	bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
+	bytes = iov_iter_get_pages2(iter, pages, LONG_MAX,
 				VHOST_SCSI_PREALLOC_UPAGES, &offset);
 	/* No pages were pinned */
 	if (bytes <= 0)
 		return bytes < 0 ? bytes : -EFAULT;
-
-	iov_iter_advance(iter, bytes);
 
 	while (bytes) {
 		unsigned n = min_t(unsigned, PAGE_SIZE - offset, bytes);

fs/ceph/addr.c

···
 
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
 	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
-	err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
+	err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
 	if (err < 0) {
 		dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
 		goto out;

fs/ceph/file.c

···
 		size_t start;
 		int idx = 0;
 
-		bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+		bytes = iov_iter_get_pages2(iter, pages, maxsize - size,
 					   ITER_GET_BVECS_PAGES, &start);
 		if (bytes < 0)
 			return size ?: bytes;
 
-		iov_iter_advance(iter, bytes);
 		size += bytes;
 
 		for ( ; bytes; idx++, bvec_idx++) {
···
 	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

···
 		if (ctx->direct_io) {
 			ssize_t result;
 
-			result = iov_iter_get_pages_alloc(
+			result = iov_iter_get_pages_alloc2(
 				from, &pagevec, cur_len, &start);
 			if (result < 0) {
 				cifs_dbg(VFS,
···
 				break;
 			}
 			cur_len = (size_t)result;
-			iov_iter_advance(from, cur_len);
 
 			nr_pages =
 				(cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE;
···
 		if (ctx->direct_io) {
 			ssize_t result;
 
-			result = iov_iter_get_pages_alloc(
+			result = iov_iter_get_pages_alloc2(
 					&direct_iov, &pagevec,
 					cur_len, &start);
 			if (result < 0) {
···
 				break;
 			}
 			cur_len = (size_t)result;
-			iov_iter_advance(&direct_iov, cur_len);
 
 			rdata = cifs_readdata_direct_alloc(
 					pagevec, cifs_uncached_readv_complete);
···
 	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/cifs/misc.c

···
 	saved_len = count;
 
 	while (count && npages < max_pages) {
-		rc = iov_iter_get_pages(iter, pages, count, max_pages, &start);
+		rc = iov_iter_get_pages2(iter, pages, count, max_pages, &start);
 		if (rc < 0) {
 			cifs_dbg(VFS, "Couldn't get user pages (rc=%zd)\n", rc);
 			break;
···
 			break;
 		}
 
-		iov_iter_advance(iter, rc);
 		count -= rc;
 		rc += start;
 		cur_npages = DIV_ROUND_UP(rc, PAGE_SIZE);

fs/direct-io.c

···
 	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	ssize_t ret;
 
-	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
+	ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
 				&sdio->from);
 
 	if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
···
 	}
 
 	if (ret >= 0) {
-		iov_iter_advance(sdio->iter, ret);
 		ret += sdio->from;
 		sdio->head = 0;
 		sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
···
 	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

···
 		}
 	} else {
 		size_t off;
-		err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
+		err = iov_iter_get_pages2(cs->iter, &page, PAGE_SIZE, 1, &off);
 		if (err < 0)
 			return err;
 		BUG_ON(!err);
 		cs->len = err;
 		cs->offset = off;
 		cs->pg = page;
-		iov_iter_advance(cs->iter, err);
 	}
 
 	return lock_request(cs->req);
···
 	if (!fud)
 		return -EPERM;
 
-	if (!iter_is_iovec(to))
+	if (!user_backed_iter(to))
 		return -EINVAL;
 
 	fuse_copy_init(&cs, 1, to);
···
 	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

···
 	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
 		unsigned npages;
 		size_t start;
-		ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages],
+		ret = iov_iter_get_pages2(ii, &ap->pages[ap->num_pages],
 					*nbytesp - nbytes,
 					max_pages - ap->num_pages,
 					&start);
 		if (ret < 0)
 			break;
 
-		iov_iter_advance(ii, ret);
 		nbytes += ret;
 
 		ret += start;
···
 			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

···
 
 	if (!count)
 		return false;
-	if (!iter_is_iovec(i))
+	if (!user_backed_iter(i))
 		return false;
 
 	size = PAGE_SIZE;

fs/hugetlbfs/inode.c

···
 }
 #endif
 
-static size_t
-hugetlbfs_read_actor(struct page *page, unsigned long offset,
-			struct iov_iter *to, unsigned long size)
-{
-	size_t copied = 0;
-	int i, chunksize;
-
-	/* Find which 4k chunk and offset with in that chunk */
-	i = offset >> PAGE_SHIFT;
-	offset = offset & ~PAGE_MASK;
-
-	while (size) {
-		size_t n;
-		chunksize = PAGE_SIZE;
-		if (offset)
-			chunksize -= offset;
-		if (chunksize > size)
-			chunksize = size;
-		n = copy_page_to_iter(&page[i], offset, chunksize, to);
-		copied += n;
-		if (n != chunksize)
-			return copied;
-		offset = 0;
-		size -= chunksize;
-		i++;
-	}
-	return copied;
-}
-
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
  * data. This provides functionality similar to filemap_read().
···
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
-			copied = hugetlbfs_read_actor(page, offset, to, nr);
+			copied = copy_page_to_iter(page, offset, nr, to);
 			put_page(page);
 		}
 		offset += copied;

fs/iomap/direct-io.c

···
 			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

···
 		size_t pgbase;
 		unsigned npages, i;
 
-		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+		result = iov_iter_get_pages_alloc2(iter, &pagevec,
 						  rsize, &pgbase);
 		if (result < 0)
 			break;
 	
 		bytes = result;
-		iov_iter_advance(iter, bytes);
 		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
 		for (i = 0; i < npages; i++) {
 			struct nfs_page *req;
···
 	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)
···
 		size_t pgbase;
 		unsigned npages, i;
 
-		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+		result = iov_iter_get_pages_alloc2(iter, &pagevec,
 						  wsize, &pgbase);
 		if (result < 0)
 			break;
 
 		bytes = result;
-		iov_iter_advance(iter, bytes);
 		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
 		for (i = 0; i < npages; i++) {
 			struct nfs_page *req;

fs/read_write.c

···
 
 static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
-	struct iovec iov = { .iov_base = buf, .iov_len = len };
 	struct kiocb kiocb;
 	struct iov_iter iter;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = (ppos ? *ppos : 0);
-	iov_iter_init(&iter, READ, &iov, 1, len);
+	iov_iter_ubuf(&iter, READ, buf, len);
 
 	ret = call_read_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
···
 
 static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 {
-	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
 	struct kiocb kiocb;
 	struct iov_iter iter;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = (ppos ? *ppos : 0);
-	iov_iter_init(&iter, WRITE, &iov, 1, len);
+	iov_iter_ubuf(&iter, WRITE, (void __user *)buf, len);
 
 	ret = call_write_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);

fs/splice.c

···
 {
 	struct iov_iter to;
 	struct kiocb kiocb;
-	unsigned int i_head;
 	int ret;
 
 	iov_iter_pipe(&to, READ, pipe, len);
-	i_head = to.head;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
 	ret = call_read_iter(in, &kiocb, &to);
···
 		*ppos = kiocb.ki_pos;
 		file_accessed(in);
 	} else if (ret < 0) {
-		to.head = i_head;
-		to.iov_offset = 0;
-		iov_iter_advance(&to, 0); /* to free what was emitted */
+		/* free what was emitted */
+		pipe_discard_from(pipe, to.start_head);
 		/*
 		 * callers of ->splice_read() expect -EAGAIN on
 		 * "can't put anything in there", rather than -EFAULT.
···
 	};
 	size_t total = 0;
 	int ret = 0;
-	bool failed = false;
 
-	while (iov_iter_count(from) && !failed) {
+	while (iov_iter_count(from)) {
 		struct page *pages[16];
-		ssize_t copied;
+		ssize_t left;
 		size_t start;
-		int n;
+		int i, n;
 
-		copied = iov_iter_get_pages(from, pages, ~0UL, 16, &start);
-		if (copied <= 0) {
-			ret = copied;
+		left = iov_iter_get_pages2(from, pages, ~0UL, 16, &start);
+		if (left <= 0) {
+			ret = left;
 			break;
 		}
 
-		for (n = 0; copied; n++, start = 0) {
-			int size = min_t(int, copied, PAGE_SIZE - start);
-			if (!failed) {
-				buf.page = pages[n];
-				buf.offset = start;
-				buf.len = size;
-				ret = add_to_pipe(pipe, &buf);
-				if (unlikely(ret < 0)) {
-					failed = true;
-				} else {
-					iov_iter_advance(from, ret);
-					total += ret;
-				}
-			} else {
-				put_page(pages[n]);
+		n = DIV_ROUND_UP(left + start, PAGE_SIZE);
+		for (i = 0; i < n; i++) {
+			int size = min_t(int, left, PAGE_SIZE - start);
+
+			buf.page = pages[i];
+			buf.offset = start;
+			buf.len = size;
+			ret = add_to_pipe(pipe, &buf);
+			if (unlikely(ret < 0)) {
+				iov_iter_revert(from, left);
+				// this one got dropped by add_to_pipe()
+				while (++i < n)
+					put_page(pages[i]);
+				goto out;
 			}
-			copied -= size;
+			total += ret;
+			left -= size;
+			start = 0;
 		}
 	}
+out:
 	return total ? total : ret;
 }
 

include/linux/pipe_fs_i.h

···
 }
 
 /**
- * pipe_space_for_user - Return number of slots available to userspace
- * @head: The pipe ring head pointer
- * @tail: The pipe ring tail pointer
- * @pipe: The pipe info structure
- */
-static inline unsigned int pipe_space_for_user(unsigned int head, unsigned int tail,
-					       struct pipe_inode_info *pipe)
-{
-	unsigned int p_occupancy, p_space;
-
-	p_occupancy = pipe_occupancy(head, tail);
-	if (p_occupancy >= pipe->max_usage)
-		return 0;
-	p_space = pipe->ring_size - p_occupancy;
-	if (p_space > pipe->max_usage)
-		p_space = pipe->max_usage;
-	return p_space;
-}
-
-/**
  * pipe_buf_get - get a reference to a pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
  * @buf:	the buffer to get a reference to

include/linux/uio.h

···
 	ITER_PIPE,
 	ITER_XARRAY,
 	ITER_DISCARD,
+	ITER_UBUF,
 };
 
 struct iov_iter_state {
···
 	u8 iter_type;
 	bool nofault;
 	bool data_source;
-	size_t iov_offset;
+	bool user_backed;
+	union {
+		size_t iov_offset;
+		int last_offset;
+	};
 	size_t count;
 	union {
 		const struct iovec *iov;
···
 		const struct bio_vec *bvec;
 		struct xarray *xarray;
 		struct pipe_inode_info *pipe;
+		void __user *ubuf;
 	};
 	union {
 		unsigned long nr_segs;
···
 	state->iov_offset = iter->iov_offset;
 	state->count = iter->count;
 	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)
···
 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;
 }
 
 /*
···
 void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
 void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
 		     loff_t start, size_t count);
-ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
+ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
-ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
+ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
 void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
···
 		 struct iov_iter *i, bool compat);
 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

···
 
 #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;						\
···
 	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;				\
···
 	return n;
 }
 
+static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe,
+					   unsigned int slot)
+{
+	return &pipe->bufs[slot & (pipe->ring_size - 1)];
+}
+
 #ifdef PIPE_PARANOIA
 static bool sanity(const struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
 	unsigned int p_head = pipe->head;
 	unsigned int p_tail = pipe->tail;
-	unsigned int p_mask = pipe->ring_size - 1;
 	unsigned int p_occupancy = pipe_occupancy(p_head, p_tail);
 	unsigned int i_head = i->head;
 	unsigned int idx;
 
-	if (i->iov_offset) {
+	if (i->last_offset) {
 		struct pipe_buffer *p;
 		if (unlikely(p_occupancy == 0))
 			goto Bad;	// pipe must be non-empty
 		if (unlikely(i_head != p_head - 1))
 			goto Bad;	// must be at the last buffer...
 
-		p = &pipe->bufs[i_head & p_mask];
-		if (unlikely(p->offset + p->len != i->iov_offset))
+		p = pipe_buf(pipe, i_head);
+		if (unlikely(p->offset + p->len != abs(i->last_offset)))
 			goto Bad;	// ... at the end of segment
 	} else {
 		if (i_head != p_head)
···
 	}
 	return true;
 Bad:
-	printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset);
+	printk(KERN_ERR "idx = %d, offset = %d\n", i_head, i->last_offset);
 	printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n",
 			p_head, p_tail, pipe->ring_size);
 	for (idx = 0; idx < pipe->ring_size; idx++)
···
 #define sanity(i) true
 #endif
 
+static struct page *push_anon(struct pipe_inode_info *pipe, unsigned size)
+{
+	struct page *page = alloc_page(GFP_USER);
+	if (page) {
+		struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++);
+		*buf = (struct pipe_buffer) {
+			.ops = &default_pipe_buf_ops,
+			.page = page,
+			.offset = 0,
+			.len = size
+		};
+	}
+	return page;
+}
+
+static void push_page(struct pipe_inode_info *pipe, struct page *page,
+			unsigned int offset, unsigned int size)
+{
+	struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++);
+	*buf = (struct pipe_buffer) {
+		.ops = &page_cache_pipe_buf_ops,
+		.page = page,
+		.offset = offset,
+		.len = size
+	};
+	get_page(page);
+}
+
+static inline int last_offset(const struct pipe_buffer *buf)
+{
+	if (buf->ops == &default_pipe_buf_ops)
+		return buf->len;	// buf->offset is 0 for those
+	else
+		return -(buf->offset + buf->len);
+}
+
+static struct page *append_pipe(struct iov_iter *i, size_t size,
+				unsigned int *off)
+{
+	struct pipe_inode_info *pipe = i->pipe;
+	int offset = i->last_offset;
+	struct pipe_buffer *buf;
+	struct page *page;
+
+	if (offset > 0 && offset < PAGE_SIZE) {
+		// some space in the last buffer; add to it
+		buf = pipe_buf(pipe, pipe->head - 1);
+		size = min_t(size_t, size, PAGE_SIZE - offset);
+		buf->len += size;
+		i->last_offset += size;
+		i->count -= size;
+		*off = offset;
+		return buf->page;
+	}
+	// OK, we need a new buffer
+	*off = 0;
+	size = min_t(size_t, size, PAGE_SIZE);
+	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+		return NULL;
+	page = push_anon(pipe, size);
+	if (!page)
+		return NULL;
+	i->head = pipe->head - 1;
+	i->last_offset = size;
+	i->count -= size;
+	return page;
+}
+
 static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
-	struct pipe_buffer *buf;
-	unsigned int p_tail = pipe->tail;
-	unsigned int p_mask = pipe->ring_size - 1;
-	unsigned int i_head = i->head;
-	size_t off;
+	unsigned int head = pipe->head;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
···
 	if (!sanity(i))
 		return 0;
 
-	off = i->iov_offset;
-	buf = &pipe->bufs[i_head & p_mask];
-	if (off) {
-		if (offset == off && buf->page == page) {
-			/* merge with the last one */
+	if (offset && i->last_offset == -offset) { // could we merge it?
+		struct pipe_buffer *buf = pipe_buf(pipe, head - 1);
+		if (buf->page == page) {
 			buf->len += bytes;
-			i->iov_offset += bytes;
-			goto out;
+			i->last_offset -= bytes;
+			i->count -= bytes;
+			return bytes;
 		}
-		i_head++;
-		buf = &pipe->bufs[i_head & p_mask];
 	}
-	if (pipe_full(i_head, p_tail, pipe->max_usage))
+	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
 		return 0;
 
-	buf->ops = &page_cache_pipe_buf_ops;
-	buf->flags = 0;
-	get_page(page);
-	buf->page = page;
-	buf->offset = offset;
-	buf->len = bytes;
-
-	pipe->head = i_head + 1;
-	i->iov_offset = offset + bytes;
-	i->head = i_head;
-out:
+	push_page(pipe, page, offset, bytes);
+	i->last_offset = -(offset + bytes);
+	i->head = head;
 	i->count -= bytes;
 	return bytes;
 }
···
  */
 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;
···
  */
 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;
···
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
 		.nofault = false,
+		.user_backed = true,
 		.data_source = direction,
 		.iov = iov,
 		.nr_segs = nr_segs,
···
 }
 EXPORT_SYMBOL(iov_iter_init);
 
-static inline bool allocated(struct pipe_buffer *buf)
-{
-	return buf->ops == &default_pipe_buf_ops;
-}
-
-static inline void data_start(const struct iov_iter *i,
-			      unsigned int *iter_headp, size_t *offp)
-{
-	unsigned int p_mask = i->pipe->ring_size - 1;
-	unsigned int iter_head = i->head;
-	size_t off = i->iov_offset;
-
-	if (off && (!allocated(&i->pipe->bufs[iter_head & p_mask]) ||
-		    off == PAGE_SIZE)) {
-		iter_head++;
-		off = 0;
-	}
-	*iter_headp = iter_head;
-	*offp = off;
-}
-
-static size_t push_pipe(struct iov_iter *i, size_t size,
-			int *iter_headp, size_t *offp)
+// returns the offset in partial buffer (if any)
+static inline unsigned int pipe_npages(const struct iov_iter *i, int *npages)
 {
 	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_tail = pipe->tail;
-	unsigned int p_mask = pipe->ring_size - 1;
-	unsigned int iter_head;
-	size_t off;
-	ssize_t left;
+	int used = pipe->head - pipe->tail;
+	int off = i->last_offset;
 
-	if (unlikely(size > i->count))
-		size = i->count;
-	if (unlikely(!size))
-		return 0;
+	*npages = max((int)pipe->max_usage - used, 0);
 
-	left = size;
-	data_start(i, &iter_head, &off);
-	*iter_headp = iter_head;
-	*offp = off;
-	if (off) {
-		left -= PAGE_SIZE - off;
-		if (left <= 0) {
-			pipe->bufs[iter_head & p_mask].len += size;
-			return size;
-		}
-		pipe->bufs[iter_head & p_mask].len = PAGE_SIZE;
-		iter_head++;
+	if (off > 0 && off < PAGE_SIZE) { // anon and not full
+		(*npages)++;
+		return off;
 	}
-	while (!pipe_full(iter_head, p_tail, pipe->max_usage)) {
-		struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask];
-		struct page *page = alloc_page(GFP_USER);
-		if (!page)
-			break;
-
-		buf->ops = &default_pipe_buf_ops;
-		buf->flags = 0;
-		buf->page = page;
-		buf->offset = 0;
-		buf->len = min_t(ssize_t, left, PAGE_SIZE);
-		left -= buf->len;
-		iter_head++;
-		pipe->head = iter_head;
-
-		if (left == 0)
-			return size;
-	}
-	return size - left;
+	return 0;
 }
 
 static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
 				struct iov_iter *i)
 {
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_mask = pipe->ring_size - 1;
-	unsigned int i_head;
-	size_t n, off;
+	unsigned int off, chunk;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+	if (unlikely(!bytes))
+		return 0;
 
 	if (!sanity(i))
 		return 0;
 
-	bytes = n = push_pipe(i, bytes, &i_head, &off);
-	if (unlikely(!n))
-		return 0;
-	do {
-		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
-		memcpy_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk);
-		i->head = i_head;
-		i->iov_offset = off + chunk;
-		n -= chunk;
+	for (size_t n = bytes; n; n -= chunk) {
+		struct page *page = append_pipe(i, n, &off);
+		chunk = min_t(size_t, n, PAGE_SIZE - off);
+		if (!page)
+			return bytes - n;
+		memcpy_to_page(page, off, addr, chunk);
 		addr += chunk;
-		off = 0;
-		i_head++;
-	} while (n);
-	i->count -= bytes;
+	}
 	return bytes;
 }
 
···
 static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
 					 struct iov_iter *i, __wsum *sump)
 {
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_mask = pipe->ring_size - 1;
 	__wsum sum = *sump;
 	size_t off = 0;
-	unsigned int i_head;
-	size_t r;
+	unsigned int chunk, r;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+	if (unlikely(!bytes))
+		return 0;
 
 	if (!sanity(i))
 		return 0;
 
-	bytes = push_pipe(i, bytes, &i_head, &r);
 	while (bytes) {
-		size_t chunk = min_t(size_t, bytes, PAGE_SIZE - r);
-		char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page);
+		struct page *page = append_pipe(i, bytes, &r);
+		char *p;
+
+		if (!page)
+			break;
+		chunk = min_t(size_t, bytes, PAGE_SIZE - r);
+		p = kmap_local_page(page);
 		sum = csum_and_memcpy(p + r, addr + off, chunk, sum, off);
 		kunmap_local(p);
-		i->head = i_head;
-		i->iov_offset = r + chunk;
-		bytes -= chunk;
 		off += chunk;
-		r = 0;
-		i_head++;
+		bytes -= chunk;
 	}
 	*sump = sum;
-	i->count -= off;
 	return off;
 }
 
···
 {
 	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),
···
 static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 				struct iov_iter *i)
 {
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_mask = pipe->ring_size - 1;
-	unsigned int i_head;
-	unsigned int valid = pipe->head;
-	size_t n, off, xfer = 0;
+	size_t xfer = 0;
+	unsigned int off, chunk;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+	if (unlikely(!bytes))
+		return 0;
 
 	if (!sanity(i))
 		return 0;
 
-	n = push_pipe(i, bytes, &i_head, &off);
-	while (n) {
-		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
-		char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page);
+	while (bytes) {
+		struct page *page = append_pipe(i, bytes, &off);
 		unsigned long rem;
+		char *p;
+
+		if (!page)
+			break;
+		chunk = min_t(size_t, bytes, PAGE_SIZE - off);
+		p = kmap_local_page(page);
 		rem = copy_mc_to_kernel(p + off, addr + xfer, chunk);
 		chunk -= rem;
 		kunmap_local(p);
-		if (chunk) {
-			i->head = i_head;
-			i->iov_offset = off + chunk;
-			xfer += chunk;
-			valid = i_head + 1;
-		}
+		xfer += chunk;
+		bytes -= chunk;
 		if (rem) {
-			pipe->bufs[i_head & p_mask].len -= rem;
-			pipe_discard_from(pipe, valid);
+			iov_iter_revert(i, rem);
 			break;
 		}
-		n -= chunk;
-		off = 0;
-		i_head++;
 	}
-	i->count -= xfer;
 	return xfer;
 }
 
···
 {
 	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),
···
 		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),
···
 	return false;
 }
 
-static size_t __copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
-{
-	if (unlikely(iov_iter_is_pipe(i))) {
-		return copy_page_to_iter_pipe(page, offset, bytes, i);
-	} else {
-		void *kaddr = kmap_local_page(page);
-		size_t wanted = _copy_to_iter(kaddr + offset, bytes, i);
-		kunmap_local(kaddr);
-		return wanted;
-	}
-}
-
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
 	size_t res = 0;
 	if (unlikely(!page_copy_sane(page, offset, bytes)))
 		return 0;
+	if (unlikely(iov_iter_is_pipe(i)))
+		return copy_page_to_iter_pipe(page, offset, bytes, i);
 	page += offset / PAGE_SIZE; // first subpage
 	offset %= PAGE_SIZE;
 	while (1) {
-		size_t n = __copy_page_to_iter(page, offset,
-				min(bytes, (size_t)PAGE_SIZE - offset), i);
+		void *kaddr = kmap_local_page(page);
+		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
+		n = _copy_to_iter(kaddr + offset, n, i);
+		kunmap_local(kaddr);
 		res += n;
 		bytes -= n;
 		if (!bytes || !n)
···
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
-	if (page_copy_sane(page, offset, bytes)) {
+	size_t res = 0;
+	if (!page_copy_sane(page, offset, bytes))
+		return 0;
+	page += offset / PAGE_SIZE; // first subpage
+	offset %= PAGE_SIZE;
+	while (1) {
 		void *kaddr = kmap_local_page(page);
-		size_t wanted = _copy_from_iter(kaddr + offset, bytes, i);
+		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
+		n = _copy_from_iter(kaddr + offset, n, i);
 		kunmap_local(kaddr);
-		return wanted;
+		res += n;
+		bytes -= n;
+		if (!bytes || !n)
+			break;
+		offset += n;
+		if (offset == PAGE_SIZE) {
+			page++;
+			offset = 0;
+		}
 	}
-	return 0;
+	return res;
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
 static size_t pipe_zero(size_t bytes, struct iov_iter *i)
 {
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_mask = pipe->ring_size - 1;
-	unsigned int i_head;
-	size_t n, off;
+	unsigned int chunk, off;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+	if (unlikely(!bytes))
+		return 0;
 
 	if (!sanity(i))
 		return 0;
 
-	bytes = n = push_pipe(i, bytes, &i_head, &off);
-	if (unlikely(!n))
-		return 0;
+	for (size_t n = bytes; n; n -= chunk) {
+		struct page *page = append_pipe(i, n, &off);
+		char *p;
 
-	do {
-		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
-		char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page);
+		if (!page)
+			return bytes - n;
+		chunk = min_t(size_t, n, PAGE_SIZE - off);
+		p = kmap_local_page(page);
 		memset(p + off, 0, chunk);
 		kunmap_local(p);
-		i->head = i_head;
-		i->iov_offset = off + chunk;
-		n -= chunk;
-		off = 0;
-		i_head++;
-	} while (n);
-	i->count -= bytes;
+	}
 	return bytes;
 }
 
···
 }
 EXPORT_SYMBOL(copy_page_from_iter_atomic);
 
-static inline void pipe_truncate(struct iov_iter *i)
-{
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_tail = pipe->tail;
-	unsigned int p_head = pipe->head;
-	unsigned int p_mask = pipe->ring_size - 1;
-
-	if (!pipe_empty(p_head, p_tail)) {
-		struct pipe_buffer *buf;
-		unsigned int i_head = i->head;
-		size_t off = i->iov_offset;
-
-		if (off) {
-			buf = &pipe->bufs[i_head & p_mask];
-			buf->len = off - buf->offset;
-			i_head++;
-		}
-		while (p_head != i_head) {
-			p_head--;
-			pipe_buf_release(pipe, &pipe->bufs[p_head & p_mask]);
-		}
-
-		pipe->head = p_head;
-	}
-}
-
 static void pipe_advance(struct iov_iter *i, size_t size)
 {
 	struct pipe_inode_info *pipe = i->pipe;
-	if (size) {
-		struct pipe_buffer *buf;
-		unsigned int p_mask = pipe->ring_size - 1;
-		unsigned int i_head = i->head;
-		size_t off = i->iov_offset, left = size;
+	int off = i->last_offset;
 
-		if (off) /* make it relative to the beginning of buffer */
-			left += off - pipe->bufs[i_head & p_mask].offset;
-		while (1) {
-			buf = &pipe->bufs[i_head & p_mask];
-			if (left <= buf->len)
-				break;
-			left -= buf->len;
-			i_head++;
-		}
-		i->head = i_head;
-		i->iov_offset = buf->offset + left;
+	if (!off && !size) {
+		pipe_discard_from(pipe, i->start_head); // discard everything
+		return;
 	}
 	i->count -= size;
-	/* ... and discard everything past that point */
-	pipe_truncate(i);
+	while (1) {
+		struct pipe_buffer *buf = pipe_buf(pipe, i->head);
+		if (off) /* make it relative to the beginning of buffer */
+			size += abs(off) - buf->offset;
+		if (size <= buf->len) {
+			buf->len = size;
+			i->last_offset = last_offset(buf);
+			break;
+		}
+		size -= buf->len;
+		i->head++;
+		off = 0;
+	}
+	pipe_discard_from(pipe, i->head + 1); // discard everything past this one
 }
 
 static void iov_iter_bvec_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;
 	}
···
 	i->count += unroll;
 	if (unlikely(iov_iter_is_pipe(i))) {
 		struct pipe_inode_info *pipe = i->pipe;
-		unsigned int p_mask = pipe->ring_size - 1;
-		unsigned int i_head = i->head;
-		size_t off = i->iov_offset;
-		while (1) {
-			struct pipe_buffer *b = &pipe->bufs[i_head & p_mask];
-			size_t n = off - b->offset;
-			if (unroll < n) {
-				off -= unroll;
-				break;
+		unsigned int head = pipe->head;
+
+		while (head > i->start_head) {
+			struct pipe_buffer *b = pipe_buf(pipe, --head);
+			if (unroll < b->len) {
+				b->len -= unroll;
+				i->last_offset = last_offset(b);
+				i->head = head;
+				return;
 			}
-			unroll -= n;
-			if (!unroll && i_head == i->start_head) {
-				off = 0;
-				break;
-			}
-			i_head--;
-			b = &pipe->bufs[i_head & p_mask];
-			off = b->offset + b->len;
+			unroll -= b->len;
+			pipe_buf_release(pipe, b);
+			pipe->head--;
 		}
-		i->iov_offset = off;
-		i->head = i_head;
-		pipe_truncate(i);
+		i->last_offset = 0;
+		i->head = head;
 		return;
 	}
 	if (unlikely(iov_iter_is_discard(i)))
···
 		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.
···
 		.pipe = pipe,
 		.head = pipe->head,
 		.start_head = pipe->head,
-		.iov_offset = 0,
+		.last_offset = 0,
 		.count = count
 	};
 }
···
 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);
 
···
 		return iov_iter_aligned_bvec(i, addr_mask, len_mask);
 
 	if (iov_iter_is_pipe(i)) {
-		unsigned int p_mask = i->pipe->ring_size - 1;
 		size_t size = i->count;
 
 		if (size & len_mask)
 			return false;
-		if (size && allocated(&i->pipe->bufs[i->head & p_mask])) {
-			if (i->iov_offset & addr_mask)
+		if (size && i->last_offset > 0) {
+			if (i->last_offset & addr_mask)
 				return false;
 		}
 
···
 
 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);
···
 		return iov_iter_alignment_bvec(i);
 
 	if (iov_iter_is_pipe(i)) {
-		unsigned int p_mask = i->pipe->ring_size - 1;
 		size_t size = i->count;
 
-		if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask]))
-			return size | i->iov_offset;
+		if (size && i->last_offset > 0)
+			return size | i->last_offset;
 		return size;
 	}
 
···
 	unsigned long v = 0;
 	size_t size = i->count;
 	unsigned k;
+
+	if (iter_is_ubuf(i))
+		return 0;
 
 	if (WARN_ON(!iter_is_iovec(i)))
 		return ~0U;
···
 }
 EXPORT_SYMBOL(iov_iter_gap_alignment);
 
-static inline ssize_t __pipe_get_pages(struct iov_iter *i,
-				size_t maxsize,
-				struct page **pages,
-				int iter_head,
-				size_t *start)
+static int want_pages_array(struct page ***res, size_t size,
+			    size_t start, unsigned int maxpages)
 {
-	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int p_mask = pipe->ring_size - 1;
-	ssize_t n = push_pipe(i, maxsize, &iter_head, start);
-	if (!n)
-		return -EFAULT;
+	unsigned int count = DIV_ROUND_UP(size + start, PAGE_SIZE);
 
-	maxsize = n;
-	n += *start;
-	while (n > 0) {
-		get_page(*pages++ = pipe->bufs[iter_head & p_mask].page);
-		iter_head++;
-		n -= PAGE_SIZE;
+	if (count > maxpages)
+		count = maxpages;
+	WARN_ON(!count);	// caller should've prevented that
+	if (!*res) {
+		*res = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL);
+		if (!*res)
+			return 0;
 	}
-
-	return maxsize;
+	return count;
 }
 
 static ssize_t pipe_get_pages(struct iov_iter *i,
-		   struct page **pages, size_t maxsize, unsigned maxpages,
+		   struct page ***pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
-	unsigned int iter_head, npages;
-	size_t capacity;
+	unsigned int npages, count, off, chunk;
+	struct page **p;
+	size_t left;
 
 	if (!sanity(i))
 		return -EFAULT;
 
-	data_start(i, &iter_head, start);
-	/* Amount of free space: some of this one + all after this one */
-	npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
-	capacity = min(npages, maxpages) * PAGE_SIZE - *start;
-
-	return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start);
+	*start = off = pipe_npages(i, &npages);
+	if (!npages)
+		return -EFAULT;
+	count = want_pages_array(pages, maxsize, off, min(npages, maxpages));
+	if (!count)
+		return -ENOMEM;
+	p = *pages;
+	for (npages = 0, left = maxsize ; npages < count; npages++, left -= chunk) {
+		struct page *page = append_pipe(i, left, &off);
+		if (!page)
+			break;
+		chunk = min_t(size_t, left, PAGE_SIZE - off);
+		get_page(*p++ = page);
+	}
+	if (!npages)
+		return -EFAULT;
+	return maxsize - left;
 }
 
 static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
···
 }
 
 static ssize_t iter_xarray_get_pages(struct iov_iter *i,
-				     struct page **pages, size_t maxsize,
+				     struct page ***pages, size_t maxsize,
 				     unsigned maxpages, size_t *_start_offset)
 {
-	unsigned nr, offset;
-	pgoff_t index, count;
-	size_t size = maxsize;
+	unsigned nr, offset, count;
+	pgoff_t index;
 	loff_t pos;
-
-	if (!size || !maxpages)
-		return 0;
 
 	pos = i->xarray_start + i->iov_offset;
 	index = pos >> PAGE_SHIFT;
 	offset = pos & ~PAGE_MASK;
 	*_start_offset = offset;
 
-	count = 1;
-	if (size > PAGE_SIZE - offset) {
-		size -= PAGE_SIZE - offset;
-		count += size >> PAGE_SHIFT;
-		size &= ~PAGE_MASK;
-		if (size)
-			count++;
-	}
-
-	if (count > maxpages)
-		count = maxpages;
-
-	nr = iter_xarray_populate_pages(pages, i->xarray, index, count);
+	count = want_pages_array(pages, maxsize, offset, maxpages);
+	if (!count)
+		return -ENOMEM;
+	nr = iter_xarray_populate_pages(*pages, i->xarray, index, count);
 	if (nr == 0)
 		return 0;
 
-	return min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+	maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+	i->iov_offset += maxsize;
+	i->count -= maxsize;
+	return 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;
···
 	return page;
 }
 
-ssize_t iov_iter_get_pages(struct iov_iter *i,
-		   struct page **pages, size_t maxsize, unsigned maxpages,
-		   size_t *start)
+static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   unsigned int maxpages, size_t *start)
 {
-	int n, res;
+	unsigned int n;
 
 	if (maxsize > i->count)
 		maxsize = i->count;
···
 	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;
+		int res;
 
 		if (iov_iter_rw(i) != WRITE)
 			gup_flags |= FOLL_WRITE;
···
 		addr = first_iovec_segment(i, &maxsize);
 		*start = addr % PAGE_SIZE;
 		addr &= PAGE_MASK;
-		n = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
-		if (n > maxpages)
-			n = maxpages;
-		res = get_user_pages_fast(addr, n, gup_flags, pages);
+		n = want_pages_array(pages, maxsize, *start, maxpages);
+		if (!n)
+			return -ENOMEM;
+		res = get_user_pages_fast(addr, n, gup_flags, *pages);
 		if (unlikely(res <= 0))
 			return res;
-		return min_t(size_t, maxsize, res * PAGE_SIZE - *start);
+		maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start);
+		iov_iter_advance(i, maxsize);
+		return maxsize;
 	}
 	if (iov_iter_is_bvec(i)) {
+		struct page **p;
 		struct page *page;
 
 		page = first_bvec_segment(i, &maxsize, start);
-		n = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
-		if (n > maxpages)
-			n = maxpages;
+		n = want_pages_array(pages, maxsize, *start, maxpages);
+		if (!n)
+			return -ENOMEM;
+		p = *pages;
 		for (int k = 0; k < n; k++)
-			get_page(*pages++ = page++);
-		return min_t(size_t, maxsize, n * PAGE_SIZE - *start);
+			get_page(p[k] = page + k);
+		maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start);
+		i->count -= maxsize;
+		i->iov_offset += maxsize;
+		if (i->iov_offset == i->bvec->bv_len) {
+			i->iov_offset = 0;
+			i->bvec++;
+			i->nr_segs--;
+		}
+		return maxsize;
 	}
 	if (iov_iter_is_pipe(i))
 		return pipe_get_pages(i, pages, maxsize, maxpages, start);
···
 		return iter_xarray_get_pages(i, pages, maxsize, maxpages, start);
 	return -EFAULT;
 }
-EXPORT_SYMBOL(iov_iter_get_pages);
 
-static struct page **get_pages_array(size_t n)
+ssize_t iov_iter_get_pages2(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
+		   size_t *start)
 {
-	return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL);
-}
+	if (!maxpages)
+		return 0;
+	BUG_ON(!pages);
 
-static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
+	return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start);
+}
+EXPORT_SYMBOL(iov_iter_get_pages2);
+
+ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i,
 		   struct page ***pages, size_t maxsize,
 		   size_t *start)
 {
-	struct page **p;
-	unsigned int iter_head, npages;
-	ssize_t n;
+	ssize_t len;
 
-	if (!sanity(i))
-		return -EFAULT;
+	*pages = NULL;
 
-	data_start(i, &iter_head, start);
-	/* Amount of free space: some of this one + all after this one */
-	npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
-	n = npages * PAGE_SIZE - *start;
-	if (maxsize > n)
-		maxsize = n;
-	else
-		npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
-	p = get_pages_array(npages);
-	if (!p)
-		return -ENOMEM;
-	n = __pipe_get_pages(i, maxsize, p, iter_head, start);
-	if (n > 0)
-		*pages = p;
-	else
-		kvfree(p);
-	return n;
-}
-
-static ssize_t iter_xarray_get_pages_alloc(struct iov_iter *i,
-					   struct page ***pages, size_t maxsize,
-					   size_t *_start_offset)
-{
-	struct page **p;
-	unsigned nr, offset;
-	pgoff_t index, count;
-	size_t size = maxsize;
-	loff_t pos;
-
-	if (!size)
-		return 0;
-
-	pos = i->xarray_start + i->iov_offset;
-	index = pos >> PAGE_SHIFT;
-	offset = pos & ~PAGE_MASK;
-	*_start_offset = offset;
-
-	count = 1;
-	if (size > PAGE_SIZE - offset) {
-		size -= PAGE_SIZE - offset;
-		count += size >> PAGE_SHIFT;
-		size &= ~PAGE_MASK;
-		if (size)
-			count++;
+	len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start);
+	if (len <= 0) {
+		kvfree(*pages);
+		*pages = NULL;
 	}
-
-	p = get_pages_array(count);
-	if (!p)
-		return -ENOMEM;
-	*pages = p;
-
-	nr = iter_xarray_populate_pages(p, i->xarray, index, count);
-	if (nr == 0)
-		return 0;
-
-	return min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+	return len;
 }
-
-ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
-		   struct page ***pages, size_t maxsize,
-		   size_t *start)
-{
-	struct page **p;
-	int n, res;
-
-	if (maxsize > i->count)
-		maxsize = i->count;
-	if (!maxsize)
-		return 0;
-	if (maxsize > MAX_RW_COUNT)
-		maxsize = MAX_RW_COUNT;
-
-	if (likely(iter_is_iovec(i))) {
-		unsigned int gup_flags = 0;
-		unsigned long addr;
-
-		if (iov_iter_rw(i) != WRITE)
-			gup_flags |= FOLL_WRITE;
-		if (i->nofault)
-			gup_flags |= FOLL_NOFAULT;
-
-		addr = first_iovec_segment(i, &maxsize);
-		*start = addr % PAGE_SIZE;
-		addr &= PAGE_MASK;
-		n = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
-		p = get_pages_array(n);
-		if (!p)
-			return -ENOMEM;
-		res = get_user_pages_fast(addr, n, gup_flags, p);
-		if (unlikely(res <= 0)) {
-			kvfree(p);
-			*pages = NULL;
-			return res;
-		}
-		*pages = p;
-		return min_t(size_t, maxsize, res * PAGE_SIZE - *start);
-	}
-	if (iov_iter_is_bvec(i)) {
-		struct page *page;
-
-		page = first_bvec_segment(i, &maxsize, start);
-		n = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
-		*pages = p = get_pages_array(n);
-		if (!p)
-			return -ENOMEM;
-		for (int k = 0; k < n; k++)
-			get_page(*p++ = page++);
-		return min_t(size_t, maxsize, n * PAGE_SIZE - *start);
-	}
-	if (iov_iter_is_pipe(i))
-		return pipe_get_pages_alloc(i, pages, maxsize, start);
-	if (iov_iter_is_xarray(i))
-		return iter_xarray_get_pages_alloc(i, pages, maxsize, start);
-	return -EFAULT;
-}
-EXPORT_SYMBOL(iov_iter_get_pages_alloc);
+EXPORT_SYMBOL(iov_iter_get_pages_alloc2);
 
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 			       struct iov_iter *i)
···
 {
 	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);
 	if (iov_iter_is_bvec(i))
 		return bvec_npages(i, maxpages);
 	if (iov_iter_is_pipe(i)) {
-		unsigned int iter_head;
 		int npages;
-		size_t off;
 
 		if (!sanity(i))
 			return 0;
 
-		data_start(i, &iter_head, &off);
-		/* some of this one + all after this one */
-		npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
+		pipe_npages(i, &npages);
 		return min(npages, maxpages);
 	}
 	if (iov_iter_is_xarray(i)) {
···
 		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);
 
···
 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

···
 			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

net/9p/client.c

···
 	struct p9_client *clnt = fid->clnt;
 	struct p9_req_t *req;
 	int count = iov_iter_count(to);
-	int rsize, non_zc = 0;
+	int rsize, received, non_zc = 0;
 	char *dataptr;
 
 	*err = 0;
···
 	}
 	if (IS_ERR(req)) {
 		*err = PTR_ERR(req);
+		if (!non_zc)
+			iov_iter_revert(to, count - iov_iter_count(to));
 		return 0;
 	}
 
 	*err = p9pdu_readf(&req->rc, clnt->proto_version,
-			   "D", &count, &dataptr);
+			   "D", &received, &dataptr);
 	if (*err) {
+		if (!non_zc)
+			iov_iter_revert(to, count - iov_iter_count(to));
 		trace_9p_protocol_dump(clnt, &req->rc);
 		p9_req_put(clnt, req);
 		return 0;
 	}
-	if (rsize < count) {
-		pr_err("bogus RREAD count (%d > %d)\n", count, rsize);
-		count = rsize;
+	if (rsize < received) {
+		pr_err("bogus RREAD count (%d > %d)\n", received, rsize);
+		received = rsize;
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 
 	if (non_zc) {
-		int n = copy_to_iter(dataptr, count, to);
+		int n = copy_to_iter(dataptr, received, to);
 
-		if (n != count) {
+		if (n != received) {
 			*err = -EFAULT;
 			p9_req_put(clnt, req);
 			return n;
 		}
 	} else {
-		iov_iter_advance(to, count);
+		iov_iter_revert(to, count - received - iov_iter_count(to));
 	}
 	p9_req_put(clnt, req);
-	return count;
+	return received;
 }
 EXPORT_SYMBOL(p9_client_read_once);
 
···
 	while (iov_iter_count(from)) {
 		int count = iov_iter_count(from);
 		int rsize = fid->iounit;
+		int written;
 
 		if (!rsize || rsize > clnt->msize - P9_IOHDRSZ)
 			rsize = clnt->msize - P9_IOHDRSZ;
···
 					    offset, rsize, from);
 		}
 		if (IS_ERR(req)) {
+			iov_iter_revert(from, count - iov_iter_count(from));
 			*err = PTR_ERR(req);
 			break;
 		}
 
-		*err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &count);
+		*err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written);
 		if (*err) {
+			iov_iter_revert(from, count - iov_iter_count(from));
 			trace_9p_protocol_dump(clnt, &req->rc);
 			p9_req_put(clnt, req);
 			break;
 		}
-		if (rsize < count) {
-			pr_err("bogus RWRITE count (%d > %d)\n", count, rsize);
-			count = rsize;
+		if (rsize < written) {
+			pr_err("bogus RWRITE count (%d > %d)\n", written, rsize);
+			written = rsize;
 		}
 
 		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
 		p9_req_put(clnt, req);
-		iov_iter_advance(from, count);
-		total += count;
-		offset += count;
+		iov_iter_revert(from, count - written - iov_iter_count(from));
+		total += written;
+		offset += written;
 	}
 	return total;
 }

net/9p/protocol.c

···
 pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
 {
 	size_t len = min(pdu->capacity - pdu->size, size);
-	struct iov_iter i = *from;
 
-	if (!copy_from_iter_full(&pdu->sdata[pdu->size], len, &i))
+	if (!copy_from_iter_full(&pdu->sdata[pdu->size], len, from))
 		len = 0;
 
 	pdu->size += len;

net/9p/trans_virtio.c

···
 			if (err == -ERESTARTSYS)
 				return err;
 		}
-		n = iov_iter_get_pages_alloc(data, pages, count, offs);
+		n = iov_iter_get_pages_alloc2(data, pages, count, offs);
 		if (n < 0)
 			return n;
 		*need_drop = 1;
···
 				(*pages)[index] = kmap_to_page(p);
 			p += PAGE_SIZE;
 		}
+		iov_iter_advance(data, len);
 		return len;
 	}
 }

net/core/datagram.c

···
 		if (frag == MAX_SKB_FRAGS)
 			return -EMSGSIZE;
 
-		copied = iov_iter_get_pages(from, pages, length,
+		copied = iov_iter_get_pages2(from, pages, length,
 					    MAX_SKB_FRAGS - frag, &start);
 		if (copied < 0)
 			return -EFAULT;
 
-		iov_iter_advance(from, copied);
 		length -= copied;
 
 		truesize = PAGE_ALIGN(copied + start);

net/core/skmsg.c

···
 			goto out;
 		}
 
-		copied = iov_iter_get_pages(from, pages, bytes, maxpages,
+		copied = iov_iter_get_pages2(from, pages, bytes, maxpages,
 					    &offset);
 		if (copied <= 0) {
 			ret = -EFAULT;
 			goto out;
 		}
 
-		iov_iter_advance(from, copied);
 		bytes -= copied;
 		msg->sg.size += copied;
 

net/rds/message.c

···
 		size_t start;
 		ssize_t copied;
 
-		copied = iov_iter_get_pages(from, &pages, PAGE_SIZE,
+		copied = iov_iter_get_pages2(from, &pages, PAGE_SIZE,
 					    1, &start);
 		if (copied < 0) {
 			struct mmpin *mmp;
···
 			goto err;
 		}
 		total_copied += copied;
-		iov_iter_advance(from, copied);
 		length -= copied;
 		sg_set_page(sg, pages, copied, start);
 		rm->data.op_nents++;

net/tls/tls_sw.c

···
 			rc = -EFAULT;
 			goto out;
 		}
-		copied = iov_iter_get_pages(from, pages,
+		copied = iov_iter_get_pages2(from, pages,
 					    length,
 					    maxpages, &offset);
 		if (copied <= 0) {
 			rc = -EFAULT;
 			goto out;
 		}
-
-		iov_iter_advance(from, copied);
 
 		length -= copied;
 		size += copied;