[PATCH v5 07/21] netfs: Add a function to extract from an iter into a bvecq

[David Howells <dhowells@redhat.com>]

Add a function to extract a slice of data from an iterator of any type into
a bvec queue chain.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: Christoph Hellwig <hch@infradead.org>
cc: Steve French <sfrench@samba.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
 fs/netfs/iterator.c   | 143 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |   3 +
 2 files changed, 146 insertions(+)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index b375567e0520..0349634fe205 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -13,6 +13,149 @@
 #include <linux/netfs.h>
 #include "internal.h"
 
+/**
+ * netfs_extract_iter - Extract virtually contiguous pages from an iterator into a bvecq
+ * @orig: The original iterator
+ * @max_len: Maximum number of bytes to extract
+ * @max_pages: Maximum number of pages to extract
+ * @fpos: Starting file position to label the bvecq with
+ * @_bvecq_head: Where to cache the bvec queue
+ * @extraction_flags: Flags to qualify the request
+ *
+ * Extract virtually contiguous page fragments from the source iterator up to
+ * the given maxima and build bvec queue that refers to all of those bits.
+ * This allows the original iterator to disposed of.
+ *
+ * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be
+ * allowed on the pages extracted.
+ *
+ * On success or partial success, the amount of data in the bvec is returned,
+ * the original iterator will have been advanced by the amount extracted.
+ *
+ * If an error occurs and no pages are extracted, an error will be returned and
+ * any allocated bvecq will be freed.  If there is no data to be extracted (or
+ * @max_len or @max_pages are zero), a single empty bvecq will be returned.
+ *
+ * The bvecq segments are marked with indications on how to get clean up the
+ * extracted fragments.
+ */
+ssize_t netfs_extract_iter(struct iov_iter *orig, size_t max_len, size_t max_pages,
+			   unsigned long long fpos, struct bvecq **_bvecq_head,
+			   iov_iter_extraction_t extraction_flags)
+{
+	struct bvecq *bq_tail = NULL, *bq;
+	ssize_t ret = 0;
+	size_t extracted = 0;
+
+	_enter("{%u,%zx},%zx", orig->iter_type, orig->count, max_len);
+
+	*_bvecq_head = NULL;
+	if (max_len > orig->count)
+		max_len = orig->count;
+	if (WARN_ON_ONCE(!max_len || !max_pages))
+		goto alloc_empty;
+
+	max_pages = iov_iter_npages(orig, max_pages);
+	if (!max_pages)
+		goto alloc_empty;
+
+	do {
+		bq = bvecq_alloc_one(max_pages, GFP_NOFS);
+		if (!bq) {
+			ret = -ENOMEM;
+			break;
+		}
+		if (user_backed_iter(orig))
+			bq->mem_type = iov_iter_extract_will_pin(orig) ?
+				BVECQ_MEM_GUP : BVECQ_MEM_PAGECACHE;
+		bq->prev	= bq_tail;
+		bq->fpos	= fpos + extracted;
+
+		if (bq_tail)
+			bq_tail->next = bq;
+		else
+			*_bvecq_head = bq;
+		bq_tail = bq;
+
+		if (max_len == 0)
+			break;
+
+		struct bio_vec *bv = bq->bv;
+		unsigned int slot = 0;
+		do {
+			struct page **pages;
+			ssize_t got;
+			size_t offset;
+			size_t space = bq->max_slots - slot;
+			size_t bv_size = array_size(bq->max_slots, sizeof(*bv));
+			size_t pg_size = array_size(space, sizeof(*pages));
+
+			/* 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.
+			 */
+			pages = (void *)bv + bv_size - pg_size;
+
+			got = iov_iter_extract_pages(orig, &pages, max_len,
+						     min(space, max_pages),
+						     extraction_flags, &offset);
+			if (got < 0) {
+				ret = got;
+				goto out;
+			}
+
+			if (got == 0) {
+				pr_err("extract_pages gave nothing from %zu, %zu\n",
+				       extracted, max_len);
+				ret = -EIO;
+				goto out;
+			}
+
+			if (WARN(got > max_len,
+				 "%s: extract_pages overrun %zd > %zu bytes\n",
+				 __func__, got, max_len)) {
+				ret = -EIO;
+				goto out;
+			}
+
+			extracted += got;
+			max_len -= got;
+
+			do {
+				size_t len = umin(got, PAGE_SIZE - offset);
+
+				BUG_ON(slot >= bq->max_slots);
+
+				bvec_set_page(&bq->bv[slot], *pages++, len, offset);
+				slot++;
+				max_pages--;
+				got -= len;
+				offset = 0;
+			} while (got > 0);
+
+			bvecq_filled_to(bq, slot);
+		} while (max_len > 0 && !bvecq_is_full(bq));
+
+	} while (max_len > 0 && max_pages > 0);
+
+out:
+	if (extracted || ret == 0)
+		return extracted;
+	bvecq_put(*_bvecq_head);
+	*_bvecq_head = NULL;
+	return ret;
+
+alloc_empty:
+	bq = bvecq_alloc_one(1, GFP_NOFS);
+	if (!bq)
+		return -ENOMEM;
+	*_bvecq_head = bq;
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(netfs_extract_iter);
+
 /**
  * netfs_extract_user_iter - Extract the pages from a user iterator into a bvec
  * @orig: The original iterator
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 2999c4b7e6a9..787670c2e134 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -439,6 +439,9 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
+ssize_t netfs_extract_iter(struct iov_iter *orig, size_t max_len, size_t max_pages,
+			   unsigned long long fpos, struct bvecq **_bvecq_head,
+			   iov_iter_extraction_t extraction_flags);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);