[RFC PATCH 1/9] netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator

[David Howells]

Add a function to extract the pages from a user-space supplied iterator
(UBUF- or IOVEC-type) into a BVEC-type iterator, pinning the pages as we
go.

This is useful in three situations:

 (1) A userspace thread may have a sibling that unmaps or remaps the
     process's VM during the operation, changing the assignment of the
     pages and potentially causing an error.  Pinning the pages keeps
     some pages around, even if this occurs; futher, we find out at the
     point of extraction if EFAULT is going to be incurred.

 (2) Pages might get swapped out/discarded if not pinned, so we want to pin
     them to avoid the reload causing a deadlock due to a DIO from/to an
     mmapped region on the same file.

 (3) The iterator may get passed to sendmsg() by the filesystem.  If a
     fault occurs, we may get a short write to a TCP stream that's then
     tricky to recover from.

We assume that other types of iterator (eg. BVEC-, KVEC- and XARRAY-type)
are constructed only by kernel internals and that the pages are pinned in
those cases.

DISCARD- and PIPE-type iterators aren't DIO'able.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
---

 fs/netfs/Makefile     |    1 +
 fs/netfs/iterator.c   |   96 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |    2 +
 3 files changed, 99 insertions(+)
 create mode 100644 fs/netfs/iterator.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index f684c0cd1ec5..386d6fb92793 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -3,6 +3,7 @@
 netfs-y := \
 	buffered_read.o \
 	io.o \
+	iterator.o \
 	main.o \
 	objects.o
 
diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
new file mode 100644
index 000000000000..6875c6c94466
--- /dev/null
+++ b/fs/netfs/iterator.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Iterator helpers.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@xxxxxxxxxx)
+ */
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/**
+ * netfs_extract_user_iter - Extract the pages from a user iterator into a bvec
+ * @orig: The original iterator
+ * @orig_len: The amount of iterator to copy
+ * @new: The iterator to be set up
+ *
+ * Extract the page fragments from the given amount of the source iterator and
+ * build up a second iterator that refers to all of those bits.  This allows
+ * the original iterator to disposed of.
+ *
+ * On success, the number of elements in the bvec is returned and the original
+ * iterator will have been advanced by the amount extracted.
+ */
+ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
+				struct iov_iter *new)
+{
+	struct bio_vec *bv = NULL;
+	struct page **pages;
+	unsigned int cur_npages;
+	unsigned int max_pages;
+	unsigned int npages = 0;
+	unsigned int i;
+	size_t count = orig_len;
+	ssize_t ret;
+	size_t bv_size, pg_size;
+	size_t start;
+	size_t len;
+
+	if (WARN_ON_ONCE(!iter_is_ubuf(orig) && !iter_is_iovec(orig)))
+		return -EIO;
+
+	max_pages = iov_iter_npages(orig, INT_MAX);
+	bv_size = array_size(max_pages, sizeof(*bv));
+	bv = kvmalloc(bv_size, GFP_KERNEL);
+	if (!bv)
+		return -ENOMEM;
+
+	/* Put the page list at the end of the bvec list storage.  bvec
+	 * elements are larger than page pointers, so as long as we work
+	 * 0->last, we should be fine.
+	 */
+	pg_size = array_size(max_pages, sizeof(*pages));
+	pages = (void *)bv + bv_size - pg_size;
+
+	while (count && npages < max_pages) {
+		ret = iov_iter_get_pages2(orig, pages, count, max_pages - npages,
+					  &start);
+		if (ret < 0) {
+			pr_err("Couldn't get user pages (rc=%zd)\n", ret);
+			break;
+		}
+
+		if (ret > count) {
+			pr_err("get_pages rc=%zd more than %zu\n", ret, count);
+			break;
+		}
+
+		count -= ret;
+		ret += start;
+		cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE);
+
+		if (npages + cur_npages > max_pages) {
+			pr_err("Out of bvec array capacity (%u vs %u)\n",
+			       npages + cur_npages, max_pages);
+			break;
+		}
+
+		for (i = 0; i < cur_npages; i++) {
+			len = ret > PAGE_SIZE ? PAGE_SIZE : ret;
+			bv[npages + i].bv_page	 = *pages++;
+			bv[npages + i].bv_offset = start;
+			bv[npages + i].bv_len	 = len - start;
+			ret -= len;
+			start = 0;
+		}
+
+		npages += cur_npages;
+	}
+
+	iov_iter_bvec(new, iov_iter_rw(orig), bv, npages, orig_len - count);
+	return npages;
+}
+EXPORT_SYMBOL(netfs_extract_user_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f2402ddeafbf..5f6ad0246946 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -288,6 +288,8 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  bool was_async, enum netfs_sreq_ref_trace what);
 void netfs_stats_show(struct seq_file *);
+ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
+				struct iov_iter *new);
 
 /**
  * netfs_inode - Get the netfs inode context from the inode