Linux CIFS filesystem development
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: Christian Brauner <christian@brauner.io>,
	Matthew Wilcox <willy@infradead.org>,
	Christoph Hellwig <hch@infradead.org>
Cc: David Howells <dhowells@redhat.com>,
	Paulo Alcantara <pc@manguebit.org>, Jens Axboe <axboe@kernel.dk>,
	Leon Romanovsky <leon@kernel.org>,
	Steve French <sfrench@samba.org>,
	ChenXiaoSong <chenxiaosong@chenxiaosong.com>,
	Marc Dionne <marc.dionne@auristor.com>,
	Eric Van Hensbergen <ericvh@kernel.org>,
	Dominique Martinet <asmadeus@codewreck.org>,
	Ilya Dryomov <idryomov@gmail.com>,
	Trond Myklebust <trondmy@kernel.org>,
	netfs@lists.linux.dev, linux-afs@lists.infradead.org,
	linux-cifs@vger.kernel.org, linux-nfs@vger.kernel.org,
	ceph-devel@vger.kernel.org, v9fs@lists.linux.dev,
	linux-erofs@lists.ozlabs.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v3 10/22] netfs: Add a function to extract from an iter into a bvecq
Date: Mon,  8 Jun 2026 15:54:18 +0100	[thread overview]
Message-ID: <20260608145432.681865-11-dhowells@redhat.com> (raw)
In-Reply-To: <20260608145432.681865-1-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   | 125 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |   3 +
 2 files changed, 128 insertions(+)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index b375567e0520..d2c3055a488c 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -13,6 +13,131 @@
 #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, the amount of data in the bvec is returned, the original
+ * iterator will have been advanced by the amount extracted.
+ *
+ * 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;
+	ssize_t ret = 0;
+	size_t extracted = 0;
+
+	_enter("{%u,%zx},%zx", orig->iter_type, orig->count, max_len);
+
+	if (max_len > orig->count)
+		max_len = orig->count;
+	if (WARN_ON_ONCE(!max_len || !max_pages))
+		return 0;
+
+	max_pages = iov_iter_npages(orig, max_pages);
+	if (!max_pages)
+		return 0;
+
+	do {
+		struct bvecq *bq;
+
+		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;
+		do {
+			struct page **pages;
+			ssize_t got;
+			size_t offset;
+			size_t space = bq->max_slots - bq->nr_slots;
+			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,
+						     space, 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;
+				break;
+			}
+
+			extracted += got;
+			max_len -= got;
+
+			do {
+				size_t len = umin(got, PAGE_SIZE - offset);
+
+				BUG_ON(bq->nr_slots >= bq->max_slots);
+
+				bvec_set_page(&bq->bv[bq->nr_slots],
+					      *pages++, len, offset);
+				bq->nr_slots++;
+				got -= len;
+				offset = 0;
+			} while (got > 0);
+		} while (max_len > 0 && !bvecq_is_full(bq));
+
+		max_pages -= bq->nr_slots;
+	} while (max_len > 0 && max_pages > 0);
+
+out:
+	return extracted ?: ret;
+}
+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 12e5c51c11c8..40f45ecf1db8 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -460,6 +460,9 @@ 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);


  parent reply	other threads:[~2026-06-08 14:56 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-08 14:54 [PATCH v3 00/22] netfs: Keep track of folios in a segmented bio_vec[] chain David Howells
2026-06-08 14:54 ` [PATCH v3 01/22] netfs: Fix decision whether to disallow write-streaming due to fscache use David Howells
2026-06-08 14:54 ` [PATCH v3 02/22] cachefiles: Don't rely on backing fs storage map for most use cases David Howells
2026-06-08 14:54 ` [PATCH v3 03/22] netfs: Add the cache object ID to netfs_read/write tracepoints David Howells
2026-06-08 14:54 ` [PATCH v3 04/22] mm: Make readahead store folio count in readahead_control David Howells
2026-06-08 14:54 ` [PATCH v3 05/22] netfs: Bulk load the readahead-provided folios up front David Howells
2026-06-08 14:54 ` [PATCH v3 06/22] Add a function to kmap one page of a multipage bio_vec David Howells
2026-06-08 14:54 ` [PATCH v3 07/22] iov_iter: Make iov_iter_get_pages*() wrap iov_iter_extract_pages() David Howells
2026-06-08 14:54 ` [PATCH v3 08/22] iov_iter: Add a segmented queue of bio_vec[] David Howells
2026-06-08 14:54 ` [PATCH v3 09/22] netfs: Add some tools for managing bvecq chains David Howells
2026-06-08 14:54 ` David Howells [this message]
2026-06-08 14:54 ` [PATCH v3 11/22] afs: Use a bvecq to hold dir content rather than folioq David Howells
2026-06-08 14:54 ` [PATCH v3 12/22] cifs: Use a bvecq for buffering instead of a folioq David Howells
2026-06-08 14:54 ` [PATCH v3 13/22] smbdirect: Support ITER_BVECQ in smbdirect_map_sges_from_iter() David Howells
2026-06-08 14:54 ` [PATCH v3 14/22] netfs: Switch to using bvecq rather than folio_queue and rolling_buffer David Howells
2026-06-08 14:54 ` [PATCH v3 15/22] smbdirect: Remove support for ITER_FOLIOQ from smbdirect_map_sges_from_iter() David Howells
2026-06-08 14:54 ` [PATCH v3 16/22] netfs: Remove netfs_alloc/free_folioq_buffer() David Howells
2026-06-08 14:54 ` [PATCH v3 17/22] netfs: Remove netfs_extract_user_iter() David Howells
2026-06-08 14:54 ` [PATCH v3 18/22] iov_iter: Remove ITER_FOLIOQ David Howells
2026-06-08 14:54 ` [PATCH v3 19/22] netfs: Remove folio_queue and rolling_buffer David Howells
2026-06-08 14:54 ` [PATCH v3 20/22] netfs: Check for too much data being read David Howells
2026-06-08 14:54 ` [PATCH v3 21/22] netfs: Limit the minimum trigger for progress reporting David Howells
2026-06-08 14:54 ` [PATCH v3 22/22] netfs: Combine prepare and issue ops and grab the buffers on request David Howells

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260608145432.681865-11-dhowells@redhat.com \
    --to=dhowells@redhat.com \
    --cc=asmadeus@codewreck.org \
    --cc=axboe@kernel.dk \
    --cc=ceph-devel@vger.kernel.org \
    --cc=chenxiaosong@chenxiaosong.com \
    --cc=christian@brauner.io \
    --cc=ericvh@kernel.org \
    --cc=hch@infradead.org \
    --cc=idryomov@gmail.com \
    --cc=leon@kernel.org \
    --cc=linux-afs@lists.infradead.org \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-erofs@lists.ozlabs.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=marc.dionne@auristor.com \
    --cc=netfs@lists.linux.dev \
    --cc=pc@manguebit.org \
    --cc=sfrench@samba.org \
    --cc=trondmy@kernel.org \
    --cc=v9fs@lists.linux.dev \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox