All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: Paulo Alcantara <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>,
	Christian Brauner <christian@brauner.io>,
	Matthew Wilcox <willy@infradead.org>,
	Christoph Hellwig <hch@infradead.org>,
	Jens Axboe <axboe@kernel.dk>, Leon Romanovsky <leon@kernel.org>,
	Namjae Jeon <linkinjeon@kernel.org>,
	ChenXiaoSong <chenxiaosong@chenxiaosong.com>,
	Marc Dionne <marc.dionne@auristor.com>,
	Stefan Metzmacher <metze@samba.org>,
	Eric Van Hensbergen <ericvh@kernel.org>,
	Dominique Martinet <asmadeus@codewreck.org>,
	Ilya Dryomov <idryomov@gmail.com>,
	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, linux-block@vger.kernel.org
Subject: [PATCH v11 06/36] iov_iter: Make iov_iter_get_pages*() wrap iov_iter_extract_pages()
Date: Wed,  2 Sep 2026 18:33:18 +0100	[thread overview]
Message-ID: <20260902173350.3468672-7-dhowells@redhat.com> (raw)
In-Reply-To: <20260902173350.3468672-1-dhowells@redhat.com>

Make iov_iter_get_pages*() wrap iov_iter_extract_pages() for kernel
iterator types (e.g. ITER_BVEC, ITER_FOLIOQ, ITER_XARRAY).  The pages
obtained have their refcounts incremented afterwards if they're not slab
pages.  ITER_KVEC is left returning -EFAULT.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: Christoph Hellwig <hch@infradead.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: linux-block@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
 lib/iov_iter.c | 164 ++++++-------------------------------------------
 1 file changed, 19 insertions(+), 145 deletions(-)

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index c489569a5815..a16b86fd0278 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -910,118 +910,34 @@ static int want_pages_array(struct page ***res, size_t size,
 	return count;
 }
 
-static ssize_t iter_folioq_get_pages(struct iov_iter *iter,
+/*
+ * Wrap iov_iter_extract_pages() and then pin the non-slab pages we got back.
+ * This only works for non-user iterator types as get_pages uses get_user_pages
+ * not pin_user_pages.
+ */
+static ssize_t iter_get_kernel_pages(struct iov_iter *iter,
 				     struct page ***ppages, size_t maxsize,
 				     unsigned maxpages, size_t *_start_offset)
 {
-	const struct folio_queue *folioq = iter->folioq;
 	struct page **pages;
-	unsigned int slot = iter->folioq_slot;
-	size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset;
+	ssize_t ret, done;
 
-	if (slot >= folioq_nr_slots(folioq)) {
-		folioq = folioq->next;
-		slot = 0;
-		if (WARN_ON(iov_offset != 0))
-			return -EIO;
-	}
+	ret = iov_iter_extract_pages(iter, ppages, maxsize, maxpages,
+				     0, _start_offset);
+	if (ret <= 0)
+		return ret;
 
-	maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages);
-	if (!maxpages)
-		return -ENOMEM;
-	*_start_offset = iov_offset & ~PAGE_MASK;
 	pages = *ppages;
+	for (done = ret + *_start_offset; done > 0; done -= PAGE_SIZE) {
+		struct folio *folio = page_folio(*pages);
 
-	for (;;) {
-		struct folio *folio = folioq_folio(folioq, slot);
-		size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot);
-		size_t part = PAGE_SIZE - offset % PAGE_SIZE;
-
-		if (offset < fsize) {
-			part = umin(part, umin(maxsize - extracted, fsize - offset));
-			count -= part;
-			iov_offset += part;
-			extracted += part;
-
-			*pages = folio_page(folio, offset / PAGE_SIZE);
-			get_page(*pages);
-			pages++;
-			maxpages--;
-		}
-
-		if (maxpages == 0 || extracted >= maxsize)
-			break;
-
-		if (iov_offset >= fsize) {
-			iov_offset = 0;
-			slot++;
-			if (slot == folioq_nr_slots(folioq) && folioq->next) {
-				folioq = folioq->next;
-				slot = 0;
-			}
-		}
-	}
-
-	iter->count = count;
-	iter->iov_offset = iov_offset;
-	iter->folioq = folioq;
-	iter->folioq_slot = slot;
-	return extracted;
-}
-
-static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
-					  pgoff_t index, unsigned int nr_pages)
-{
-	XA_STATE(xas, xa, index);
-	struct folio *folio;
-	unsigned int ret = 0;
-
-	rcu_read_lock();
-	for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) {
-		if (xas_retry(&xas, folio))
-			continue;
-
-		/* Has the folio moved or been split? */
-		if (unlikely(folio != xas_reload(&xas))) {
-			xas_reset(&xas);
-			continue;
-		}
-
-		pages[ret] = folio_file_page(folio, xas.xa_index);
-		folio_get(folio);
-		if (++ret == nr_pages)
-			break;
+		if (!folio_test_slab(folio) && !folio_test_large_kmalloc(folio))
+			folio_get(folio);
+		pages++;
 	}
-	rcu_read_unlock();
 	return ret;
 }
 
-static ssize_t iter_xarray_get_pages(struct iov_iter *i,
-				     struct page ***pages, size_t maxsize,
-				     unsigned maxpages, size_t *_start_offset)
-{
-	unsigned nr, offset, count;
-	pgoff_t index;
-	loff_t pos;
-
-	pos = i->xarray_start + i->iov_offset;
-	index = pos >> PAGE_SHIFT;
-	offset = pos & ~PAGE_MASK;
-	*_start_offset = offset;
-
-	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;
-
-	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_UBUF or ITER_IOVEC one */
 static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size)
 {
@@ -1044,22 +960,6 @@ static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size)
 	BUG(); // if it had been empty, we wouldn't get called
 }
 
-/* must be done on non-empty ITER_BVEC one */
-static struct page *first_bvec_segment(const struct iov_iter *i,
-				       size_t *size, size_t *start)
-{
-	struct page *page;
-	size_t skip = i->iov_offset, len;
-
-	len = i->bvec->bv_len - skip;
-	if (*size > len)
-		*size = len;
-	skip += i->bvec->bv_offset;
-	page = i->bvec->bv_page + skip / PAGE_SIZE;
-	*start = skip % PAGE_SIZE;
-	return page;
-}
-
 static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 		   struct page ***pages, size_t maxsize,
 		   unsigned int maxpages, size_t *start)
@@ -1095,36 +995,10 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 		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 = want_pages_array(pages, maxsize, *start, maxpages);
-		if (!n)
-			return -ENOMEM;
-		p = *pages;
-		for (int k = 0; k < n; k++) {
-			struct folio *folio = page_folio(page + k);
-			p[k] = page + k;
-			if (!folio_test_slab(folio))
-				folio_get(folio);
-		}
-		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_folioq(i))
-		return iter_folioq_get_pages(i, pages, maxsize, maxpages, start);
-	if (iov_iter_is_xarray(i))
-		return iter_xarray_get_pages(i, pages, maxsize, maxpages, start);
-	return -EFAULT;
+	if (iov_iter_is_kvec(i))
+		return -EFAULT;
+	return iter_get_kernel_pages(i, pages, maxsize, maxpages, start);
 }
 
 ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,


  parent reply	other threads:[~2026-09-02 17:35 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-02 17:33 [PATCH v11 00/36] netfs: Keep track of folios in a segmented bio_vec[] chain David Howells
2026-09-02 17:33 ` [PATCH v11 01/36] block: Fix start and length check added to iov_iter_extract_bvecs() David Howells
2026-09-02 17:33 ` [PATCH v11 02/36] mm: Make readahead store folio count in readahead_control David Howells
2026-09-02 17:33 ` [PATCH v11 03/36] mm: Add a bulk end-writeback tool David Howells
2026-09-02 17:33 ` [PATCH v11 04/36] netfs: Use uoff_t instead of unsigned long long and loff_t David Howells
2026-09-02 17:33 ` [PATCH v11 05/36] Add a function to kmap one page of a multipage bio_vec David Howells
2026-09-02 17:33 ` David Howells [this message]
2026-09-02 17:33 ` [PATCH v11 07/36] iov_iter: Add a segmented queue of bio_vec[] David Howells
2026-09-02 17:33 ` [PATCH v11 08/36] netfs: Add some tools for managing bvecq chains David Howells
2026-09-02 17:33 ` [PATCH v11 09/36] netfs: Make mempool available for bvecq David Howells
2026-09-02 17:33 ` [PATCH v11 10/36] netfs: Add a function to extract from an iter into a bvecq David Howells
2026-09-02 17:33 ` [PATCH v11 11/36] afs: Use a bvecq to hold dir content rather than folioq David Howells
2026-09-02 17:33 ` [PATCH v11 12/36] cifs: Use a bvecq for buffering instead of a folioq David Howells
2026-09-02 17:33 ` [PATCH v11 13/36] smbdirect: Support ITER_BVECQ in smbdirect_map_sges_from_iter() David Howells
2026-09-02 17:33 ` [PATCH v11 14/36] netfs: Remove the writethrough code David Howells
2026-09-02 17:33 ` [PATCH v11 15/36] netfs: trace: Change the "clear" folio traces to "endwb" David Howells
2026-09-02 17:33 ` [PATCH v11 16/36] netfs: trace: Rejig a couple of the tracepoints David Howells
2026-09-02 17:33 ` [PATCH v11 17/36] netfs: Add some functions to wrap the all-queued handling David Howells
2026-09-02 17:33 ` [PATCH v11 18/36] netfs: Make deprecated PG_private_2 support optional David Howells
2026-09-02 17:33 ` [PATCH v11 19/36] cachefiles: Don't rely on backing fs storage map for most use cases David Howells
2026-09-02 17:33 ` [PATCH v11 20/36] netfs: Add the cache object ID to netfs_read/write tracepoints David Howells
2026-09-02 17:33 ` [PATCH v11 21/36] netfs: Switch to using bvecq rather than folio_queue and rolling_buffer David Howells
2026-09-02 17:33 ` [PATCH v11 22/36] smbdirect: Remove support for ITER_FOLIOQ from smbdirect_map_sges_from_iter() David Howells
2026-09-02 17:33 ` [PATCH v11 23/36] netfs: Remove netfs_alloc/free_folioq_buffer() David Howells
2026-09-02 17:33 ` [PATCH v11 24/36] netfs: Remove netfs_extract_user_iter() David Howells
2026-09-02 17:33 ` [PATCH v11 25/36] iov_iter: Remove ITER_FOLIOQ David Howells
2026-09-02 17:33 ` [PATCH v11 26/36] netfs: Remove folio_queue and rolling_buffer David Howells
2026-09-02 17:33 ` [PATCH v11 27/36] netfs: Build a list of regions undergoing writeback David Howells
2026-09-02 17:33 ` [PATCH v11 28/36] netfs: Simplify writeback cleanup David Howells
2026-09-02 17:33 ` [PATCH v11 29/36] netfs: Simplify read abandonment David Howells
2026-09-02 17:33 ` [PATCH v11 30/36] netfs: Check for too much data being read David Howells
2026-09-02 17:33 ` [PATCH v11 31/36] netfs: Add a method to get an estimate of the amount that can be written David Howells
2026-09-02 17:33 ` [PATCH v11 32/36] netfs: Rework writeback to estimate David Howells
2026-09-02 17:33 ` [PATCH v11 33/36] netfs: Set subrequest->source at alloc before trace emission David Howells
2026-09-02 17:33 ` [PATCH v11 34/36] netfs: Combine prepare and issue ops David Howells
2026-09-02 17:33 ` [PATCH v11 35/36] netfs: Clean up now-unused code David Howells
2026-09-02 17:33 ` [PATCH v11 36/36] cachefiles: Preset the state xattr when creating a new file David Howells
2026-09-03  6:06 ` [PATCH v11 00/36] netfs: Keep track of folios in a segmented bio_vec[] chain Christoph Hellwig

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=20260902173350.3468672-7-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=linkinjeon@kernel.org \
    --cc=linux-afs@lists.infradead.org \
    --cc=linux-block@vger.kernel.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=metze@samba.org \
    --cc=netfs@lists.linux.dev \
    --cc=pc@manguebit.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.