[PATCH v5 00/11] fuse: support large folios

[PATCH v5 00/11] fuse: support large folios

[Joanne Koong]

This patchset adds support for large folios in fuse.

This does not yet switch fuse to using large folios. Using large folios in
fuse is dependent on adding granular dirty-page tracking. This will be done
in a separate patchset that will have fuse use iomap [1]. There also needs
to be a followup (also part of future work) for having dirty page balancing
not tank performance for unprivileged servers where bdi limits lead to subpar
throttling [1], before enabling large folios for fuse.

This patchset (v5) is pretty much identical to v3 except for fixing up
readahead error handling.

[1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a38pv3OgFZRfdTiDMXuPWuBgN8KY47XfOsYHj=N2wxAg@mail.gmail.com/#t

Changelog:
v4: https://lore.kernel.org/linux-fsdevel/20250123012448.2479372-1-joannelkoong@gmail.com/
v4 -> v5:
* Now that temp pages are removed in FUSE, resubmit v3.
 
v3: https://lore.kernel.org/linux-fsdevel/20241213221818.322371-1-joannelkoong@gmail.com/
v3 -> v4:
* Add Jeff's reviewed-bys
* Drop writeback large folios changes, drop turning large folios on. These
  will be part of a separate future patchset

v2: https://lore.kernel.org/linux-fsdevel/20241125220537.3663725-1-joannelkoong@gmail.com/
v2 -> v3:
* Fix direct io parsing to check each extracted page instead of assuming all
  pages in a large folio will be used (Matthew)

v1: https://lore.kernel.org/linux-fsdevel/20241109001258.2216604-1-joannelkoong@gmail.com/
v1 -> v2:
* Change naming from "non-writeback write" to "writethrough write"
* Fix deadlock for writethrough writes by calling fault_in_iov_iter_readable()
* first
  before __filemap_get_folio() (Josef)
* For readahead, retain original folio_size() for descs.length (Josef)
* Use folio_zero_range() api in fuse_copy_folio() (Josef)
* Add Josef's reviewed-bys

Joanne Koong (11):
  fuse: support copying large folios
  fuse: support large folios for retrieves
  fuse: refactor fuse_fill_write_pages()
  fuse: support large folios for writethrough writes
  fuse: support large folios for folio reads
  fuse: support large folios for symlinks
  fuse: support large folios for stores
  fuse: support large folios for queued writes
  fuse: support large folios for readahead
  fuse: optimize direct io large folios processing
  fuse: support large folios for writeback

 fs/fuse/dev.c        | 126 ++++++++++++++++++------------------
 fs/fuse/dir.c        |   8 +--
 fs/fuse/file.c       | 148 +++++++++++++++++++++++++++++--------------
 fs/fuse/fuse_dev_i.h |   2 +-
 4 files changed, 169 insertions(+), 115 deletions(-)

-- 
2.47.1

[PATCH v5 01/11] fuse: support copying large folios

[Joanne Koong]

Currently, all folios associated with fuse are one page size. As part of
the work to enable large folios, this commit adds support for copying
to/from folios larger than one page size.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/dev.c        | 84 +++++++++++++++++++-------------------------
 fs/fuse/fuse_dev_i.h |  2 +-
 2 files changed, 37 insertions(+), 49 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 155bb6aeaef5..7b0e3a394480 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -955,10 +955,10 @@ static int fuse_check_folio(struct folio *folio)
  * folio that was originally in @pagep will lose a reference and the new
  * folio returned in @pagep will carry a reference.
  */
-static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
+static int fuse_try_move_folio(struct fuse_copy_state *cs, struct folio **foliop)
 {
 	int err;
-	struct folio *oldfolio = page_folio(*pagep);
+	struct folio *oldfolio = *foliop;
 	struct folio *newfolio;
 	struct pipe_buffer *buf = cs->pipebufs;
 
@@ -979,7 +979,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	cs->pipebufs++;
 	cs->nr_segs--;
 
-	if (cs->len != PAGE_SIZE)
+	if (cs->len != folio_size(oldfolio))
 		goto out_fallback;
 
 	if (!pipe_buf_try_steal(cs->pipe, buf))
@@ -1025,7 +1025,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	if (test_bit(FR_ABORTED, &cs->req->flags))
 		err = -ENOENT;
 	else
-		*pagep = &newfolio->page;
+		*foliop = newfolio;
 	spin_unlock(&cs->req->waitq.lock);
 
 	if (err) {
@@ -1058,8 +1058,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	goto out_put_old;
 }
 
-static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
-			 unsigned offset, unsigned count)
+static int fuse_ref_folio(struct fuse_copy_state *cs, struct folio *folio,
+			  unsigned offset, unsigned count)
 {
 	struct pipe_buffer *buf;
 	int err;
@@ -1067,17 +1067,17 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
 	if (cs->nr_segs >= cs->pipe->max_usage)
 		return -EIO;
 
-	get_page(page);
+	folio_get(folio);
 	err = unlock_request(cs->req);
 	if (err) {
-		put_page(page);
+		folio_put(folio);
 		return err;
 	}
 
 	fuse_copy_finish(cs);
 
 	buf = cs->pipebufs;
-	buf->page = page;
+	buf->page = &folio->page;
 	buf->offset = offset;
 	buf->len = count;
 
@@ -1089,20 +1089,21 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
 }
 
 /*
- * Copy a page in the request to/from the userspace buffer.  Must be
+ * Copy a folio in the request to/from the userspace buffer.  Must be
  * done atomically
  */
-static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
-			  unsigned offset, unsigned count, int zeroing)
+static int fuse_copy_folio(struct fuse_copy_state *cs, struct folio **foliop,
+			   unsigned offset, unsigned count, int zeroing)
 {
 	int err;
-	struct page *page = *pagep;
+	struct folio *folio = *foliop;
+	size_t size = folio_size(folio);
 
-	if (page && zeroing && count < PAGE_SIZE)
-		clear_highpage(page);
+	if (folio && zeroing && count < size)
+		folio_zero_range(folio, 0, size);
 
 	while (count) {
-		if (cs->write && cs->pipebufs && page) {
+		if (cs->write && cs->pipebufs && folio) {
 			/*
 			 * Can't control lifetime of pipe buffers, so always
 			 * copy user pages.
@@ -1112,12 +1113,12 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
 				if (err)
 					return err;
 			} else {
-				return fuse_ref_page(cs, page, offset, count);
+				return fuse_ref_folio(cs, folio, offset, count);
 			}
 		} else if (!cs->len) {
-			if (cs->move_pages && page &&
-			    offset == 0 && count == PAGE_SIZE) {
-				err = fuse_try_move_page(cs, pagep);
+			if (cs->move_folios && folio &&
+			    offset == 0 && count == folio_size(folio)) {
+				err = fuse_try_move_folio(cs, foliop);
 				if (err <= 0)
 					return err;
 			} else {
@@ -1126,22 +1127,22 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
 					return err;
 			}
 		}
-		if (page) {
-			void *mapaddr = kmap_local_page(page);
-			void *buf = mapaddr + offset;
+		if (folio) {
+			void *mapaddr = kmap_local_folio(folio, offset);
+			void *buf = mapaddr;
 			offset += fuse_copy_do(cs, &buf, &count);
 			kunmap_local(mapaddr);
 		} else
 			offset += fuse_copy_do(cs, NULL, &count);
 	}
-	if (page && !cs->write)
-		flush_dcache_page(page);
+	if (folio && !cs->write)
+		flush_dcache_folio(folio);
 	return 0;
 }
 
-/* Copy pages in the request to/from userspace buffer */
-static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
-			   int zeroing)
+/* Copy folios in the request to/from userspace buffer */
+static int fuse_copy_folios(struct fuse_copy_state *cs, unsigned nbytes,
+			    int zeroing)
 {
 	unsigned i;
 	struct fuse_req *req = cs->req;
@@ -1151,23 +1152,12 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
 		int err;
 		unsigned int offset = ap->descs[i].offset;
 		unsigned int count = min(nbytes, ap->descs[i].length);
-		struct page *orig, *pagep;
-
-		orig = pagep = &ap->folios[i]->page;
 
-		err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
+		err = fuse_copy_folio(cs, &ap->folios[i], offset, count, zeroing);
 		if (err)
 			return err;
 
 		nbytes -= count;
-
-		/*
-		 *  fuse_copy_page may have moved a page from a pipe instead of
-		 *  copying into our given page, so update the folios if it was
-		 *  replaced.
-		 */
-		if (pagep != orig)
-			ap->folios[i] = page_folio(pagep);
 	}
 	return 0;
 }
@@ -1197,7 +1187,7 @@ int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
 	for (i = 0; !err && i < numargs; i++)  {
 		struct fuse_arg *arg = &args[i];
 		if (i == numargs - 1 && argpages)
-			err = fuse_copy_pages(cs, arg->size, zeroing);
+			err = fuse_copy_folios(cs, arg->size, zeroing);
 		else
 			err = fuse_copy_one(cs, arg->value, arg->size);
 	}
@@ -1786,7 +1776,6 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 	num = outarg.size;
 	while (num) {
 		struct folio *folio;
-		struct page *page;
 		unsigned int this_num;
 
 		folio = filemap_grab_folio(mapping, index);
@@ -1794,9 +1783,8 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 		if (IS_ERR(folio))
 			goto out_iput;
 
-		page = &folio->page;
 		this_num = min_t(unsigned, num, folio_size(folio) - offset);
-		err = fuse_copy_page(cs, &page, offset, this_num, 0);
+		err = fuse_copy_folio(cs, &folio, offset, this_num, 0);
 		if (!folio_test_uptodate(folio) && !err && offset == 0 &&
 		    (this_num == folio_size(folio) || file_size == end)) {
 			folio_zero_segment(folio, this_num, folio_size(folio));
@@ -2037,8 +2025,8 @@ static int fuse_notify_inc_epoch(struct fuse_conn *fc)
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
-	/* Don't try to move pages (yet) */
-	cs->move_pages = false;
+	/* Don't try to move folios (yet) */
+	cs->move_folios = false;
 
 	switch (code) {
 	case FUSE_NOTIFY_POLL:
@@ -2189,7 +2177,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	spin_unlock(&fpq->lock);
 	cs->req = req;
 	if (!req->args->page_replace)
-		cs->move_pages = false;
+		cs->move_folios = false;
 
 	if (oh.error)
 		err = nbytes != sizeof(oh) ? -EINVAL : 0;
@@ -2307,7 +2295,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 	cs.pipe = pipe;
 
 	if (flags & SPLICE_F_MOVE)
-		cs.move_pages = true;
+		cs.move_folios = true;
 
 	ret = fuse_dev_do_write(fud, &cs, len);
 
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
index db136e045925..5a9bd771a319 100644
--- a/fs/fuse/fuse_dev_i.h
+++ b/fs/fuse/fuse_dev_i.h
@@ -30,7 +30,7 @@ struct fuse_copy_state {
 	unsigned int len;
 	unsigned int offset;
 	bool write:1;
-	bool move_pages:1;
+	bool move_folios:1;
 	bool is_uring:1;
 	struct {
 		unsigned int copied_sz; /* copied size into the user buffer */
-- 
2.47.1

[PATCH v5 02/11] fuse: support large folios for retrieves

[Joanne Koong]

Add support for folios larger than one page size for retrieves.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/dev.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 7b0e3a394480..fb81c0a1c6cd 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1837,7 +1837,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	unsigned int num;
 	unsigned int offset;
 	size_t total_len = 0;
-	unsigned int num_pages, cur_pages = 0;
+	unsigned int num_pages;
 	struct fuse_conn *fc = fm->fc;
 	struct fuse_retrieve_args *ra;
 	size_t args_size = sizeof(*ra);
@@ -1855,6 +1855,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	num_pages = min(num_pages, fc->max_pages);
+	num = min(num, num_pages << PAGE_SHIFT);
 
 	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->descs[0]));
 
@@ -1875,25 +1876,29 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	index = outarg->offset >> PAGE_SHIFT;
 
-	while (num && cur_pages < num_pages) {
+	while (num) {
 		struct folio *folio;
-		unsigned int this_num;
+		unsigned int folio_offset;
+		unsigned int nr_bytes;
+		unsigned int nr_pages;
 
 		folio = filemap_get_folio(mapping, index);
 		if (IS_ERR(folio))
 			break;
 
-		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
+		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+		nr_bytes = min(folio_size(folio) - folio_offset, num);
+		nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
 		ap->folios[ap->num_folios] = folio;
-		ap->descs[ap->num_folios].offset = offset;
-		ap->descs[ap->num_folios].length = this_num;
+		ap->descs[ap->num_folios].offset = folio_offset;
+		ap->descs[ap->num_folios].length = nr_bytes;
 		ap->num_folios++;
-		cur_pages++;
 
 		offset = 0;
-		num -= this_num;
-		total_len += this_num;
-		index++;
+		num -= nr_bytes;
+		total_len += nr_bytes;
+		index += nr_pages;
 	}
 	ra->inarg.offset = outarg->offset;
 	ra->inarg.size = total_len;
-- 
2.47.1

[PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()

[Joanne Koong]

Refactor the logic in fuse_fill_write_pages() for copying out write
data. This will make the future change for supporting large folios for
writes easier. No functional changes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e203dd4fcc0f..edc86485065e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1132,21 +1132,21 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 	struct fuse_args_pages *ap = &ia->ap;
 	struct fuse_conn *fc = get_fuse_conn(mapping->host);
 	unsigned offset = pos & (PAGE_SIZE - 1);
-	unsigned int nr_pages = 0;
 	size_t count = 0;
+	unsigned int num;
 	int err;
 
+	num = min(iov_iter_count(ii), fc->max_write);
+	num = min(num, max_pages << PAGE_SHIFT);
+
 	ap->args.in_pages = true;
 	ap->descs[0].offset = offset;
 
-	do {
+	while (num) {
 		size_t tmp;
 		struct folio *folio;
 		pgoff_t index = pos >> PAGE_SHIFT;
-		size_t bytes = min_t(size_t, PAGE_SIZE - offset,
-				     iov_iter_count(ii));
-
-		bytes = min_t(size_t, bytes, fc->max_write - count);
+		unsigned bytes = min(PAGE_SIZE - offset, num);
 
  again:
 		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
@@ -1182,10 +1182,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		ap->folios[ap->num_folios] = folio;
 		ap->descs[ap->num_folios].length = tmp;
 		ap->num_folios++;
-		nr_pages++;
 
 		count += tmp;
 		pos += tmp;
+		num -= tmp;
 		offset += tmp;
 		if (offset == PAGE_SIZE)
 			offset = 0;
@@ -1200,10 +1200,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 			ia->write.folio_locked = true;
 			break;
 		}
-		if (!fc->big_writes)
+		if (!fc->big_writes || offset != 0)
 			break;
-	} while (iov_iter_count(ii) && count < fc->max_write &&
-		 nr_pages < max_pages && offset == 0);
+	}
 
 	return count > 0 ? count : err;
 }
-- 
2.47.1

[PATCH v5 04/11] fuse: support large folios for writethrough writes

[Joanne Koong]

Add support for folios larger than one page size for writethrough
writes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index edc86485065e..e44b6d26c1c6 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1146,7 +1146,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		size_t tmp;
 		struct folio *folio;
 		pgoff_t index = pos >> PAGE_SHIFT;
-		unsigned bytes = min(PAGE_SIZE - offset, num);
+		unsigned int bytes;
+		unsigned int folio_offset;
 
  again:
 		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
@@ -1159,7 +1160,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_folio(folio);
 
-		tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
+		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+		bytes = min(folio_size(folio) - folio_offset, num);
+
+		tmp = copy_folio_from_iter_atomic(folio, folio_offset, bytes, ii);
 		flush_dcache_folio(folio);
 
 		if (!tmp) {
@@ -1180,6 +1184,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 
 		err = 0;
 		ap->folios[ap->num_folios] = folio;
+		ap->descs[ap->num_folios].offset = folio_offset;
 		ap->descs[ap->num_folios].length = tmp;
 		ap->num_folios++;
 
@@ -1187,11 +1192,11 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 		pos += tmp;
 		num -= tmp;
 		offset += tmp;
-		if (offset == PAGE_SIZE)
+		if (offset == folio_size(folio))
 			offset = 0;
 
-		/* If we copied full page, mark it uptodate */
-		if (tmp == PAGE_SIZE)
+		/* If we copied full folio, mark it uptodate */
+		if (tmp == folio_size(folio))
 			folio_mark_uptodate(folio);
 
 		if (folio_test_uptodate(folio)) {
-- 
2.47.1

[PATCH v5 05/11] fuse: support large folios for folio reads

[Joanne Koong]

Add support for folios larger than one page size for folio reads into
the page cache.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e44b6d26c1c6..0ca3b31c59f9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -793,7 +793,7 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
 	struct inode *inode = folio->mapping->host;
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	loff_t pos = folio_pos(folio);
-	struct fuse_folio_desc desc = { .length = PAGE_SIZE };
+	struct fuse_folio_desc desc = { .length = folio_size(folio) };
 	struct fuse_io_args ia = {
 		.ap.args.page_zeroing = true,
 		.ap.args.out_pages = true,
-- 
2.47.1

[PATCH v5 06/11] fuse: support large folios for symlinks

[Joanne Koong]

Support large folios for symlinks and change the name from
fuse_getlink_page() to fuse_getlink_folio().

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/dir.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 1fb0b15a6088..3003119559e8 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1629,10 +1629,10 @@ static int fuse_permission(struct mnt_idmap *idmap,
 	return err;
 }
 
-static int fuse_readlink_page(struct inode *inode, struct folio *folio)
+static int fuse_readlink_folio(struct inode *inode, struct folio *folio)
 {
 	struct fuse_mount *fm = get_fuse_mount(inode);
-	struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
+	struct fuse_folio_desc desc = { .length = folio_size(folio) - 1 };
 	struct fuse_args_pages ap = {
 		.num_folios = 1,
 		.folios = &folio,
@@ -1687,7 +1687,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 	if (!folio)
 		goto out_err;
 
-	err = fuse_readlink_page(inode, folio);
+	err = fuse_readlink_folio(inode, folio);
 	if (err) {
 		folio_put(folio);
 		goto out_err;
@@ -2277,7 +2277,7 @@ void fuse_init_dir(struct inode *inode)
 
 static int fuse_symlink_read_folio(struct file *null, struct folio *folio)
 {
-	int err = fuse_readlink_page(folio->mapping->host, folio);
+	int err = fuse_readlink_folio(folio->mapping->host, folio);
 
 	if (!err)
 		folio_mark_uptodate(folio);
-- 
2.47.1

[PATCH v5 07/11] fuse: support large folios for stores

[Joanne Koong]

Add support for folios larger than one page size for stores.
Also change variable naming from "this_num" to "nr_bytes".

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/dev.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index fb81c0a1c6cd..a6ee8cd0f5cb 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1776,18 +1776,23 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 	num = outarg.size;
 	while (num) {
 		struct folio *folio;
-		unsigned int this_num;
+		unsigned int folio_offset;
+		unsigned int nr_bytes;
+		unsigned int nr_pages;
 
 		folio = filemap_grab_folio(mapping, index);
 		err = PTR_ERR(folio);
 		if (IS_ERR(folio))
 			goto out_iput;
 
-		this_num = min_t(unsigned, num, folio_size(folio) - offset);
-		err = fuse_copy_folio(cs, &folio, offset, this_num, 0);
+		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+		nr_bytes = min_t(unsigned, num, folio_size(folio) - folio_offset);
+		nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+		err = fuse_copy_folio(cs, &folio, folio_offset, nr_bytes, 0);
 		if (!folio_test_uptodate(folio) && !err && offset == 0 &&
-		    (this_num == folio_size(folio) || file_size == end)) {
-			folio_zero_segment(folio, this_num, folio_size(folio));
+		    (nr_bytes == folio_size(folio) || file_size == end)) {
+			folio_zero_segment(folio, nr_bytes, folio_size(folio));
 			folio_mark_uptodate(folio);
 		}
 		folio_unlock(folio);
@@ -1796,9 +1801,9 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 		if (err)
 			goto out_iput;
 
-		num -= this_num;
+		num -= nr_bytes;
 		offset = 0;
-		index++;
+		index += nr_pages;
 	}
 
 	err = 0;
-- 
2.47.1

[PATCH v5 08/11] fuse: support large folios for queued writes

[Joanne Koong]

Add support for folios larger than one page size for queued writes.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0ca3b31c59f9..1d38486fae50 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1790,11 +1790,14 @@ __releases(fi->lock)
 __acquires(fi->lock)
 {
 	struct fuse_inode *fi = get_fuse_inode(wpa->inode);
+	struct fuse_args_pages *ap = &wpa->ia.ap;
 	struct fuse_write_in *inarg = &wpa->ia.write.in;
-	struct fuse_args *args = &wpa->ia.ap.args;
-	/* Currently, all folios in FUSE are one page */
-	__u64 data_size = wpa->ia.ap.num_folios * PAGE_SIZE;
-	int err;
+	struct fuse_args *args = &ap->args;
+	__u64 data_size = 0;
+	int err, i;
+
+	for (i = 0; i < ap->num_folios; i++)
+		data_size += ap->descs[i].length;
 
 	fi->writectr++;
 	if (inarg->offset + data_size <= size) {
-- 
2.47.1

[PATCH v5 09/11] fuse: support large folios for readahead

[Joanne Koong]

Add support for folios larger than one page size for readahead.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1d38486fae50..9a31f2a516b9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 	fuse_io_free(ia);
 }
 
-static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
+static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
+				unsigned int count)
 {
 	struct fuse_file *ff = file->private_data;
 	struct fuse_mount *fm = ff->fm;
 	struct fuse_args_pages *ap = &ia->ap;
 	loff_t pos = folio_pos(ap->folios[0]);
-	/* Currently, all folios in FUSE are one page */
-	size_t count = ap->num_folios << PAGE_SHIFT;
 	ssize_t res;
 	int err;
 
@@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
 	struct inode *inode = rac->mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	unsigned int max_pages, nr_pages;
+	struct folio *folio = NULL;
 
 	if (fuse_is_bad(inode))
 		return;
@@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
 	while (nr_pages) {
 		struct fuse_io_args *ia;
 		struct fuse_args_pages *ap;
-		struct folio *folio;
 		unsigned cur_pages = min(max_pages, nr_pages);
+		unsigned int pages = 0;
 
 		if (fc->num_background >= fc->congestion_threshold &&
 		    rac->ra->async_size >= readahead_count(rac))
@@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
 
 		ia = fuse_io_alloc(NULL, cur_pages);
 		if (!ia)
-			return;
+			break;
 		ap = &ia->ap;
 
-		while (ap->num_folios < cur_pages) {
+		while (pages < cur_pages) {
+			unsigned int folio_pages;
+
 			/*
 			 * This returns a folio with a ref held on it.
 			 * The ref needs to be held until the request is
@@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
 			 * fuse_try_move_page()) drops the ref after it's
 			 * replaced in the page cache.
 			 */
-			folio = __readahead_folio(rac);
+			if (!folio)
+				folio =  __readahead_folio(rac);
+
+			folio_pages = folio_nr_pages(folio);
+			if (folio_pages > cur_pages - pages)
+				break;
+
 			ap->folios[ap->num_folios] = folio;
 			ap->descs[ap->num_folios].length = folio_size(folio);
 			ap->num_folios++;
+			pages += folio_pages;
+			folio = NULL;
+		}
+		if (!pages) {
+			fuse_io_free(ia);
+			break;
 		}
-		fuse_send_readpages(ia, rac->file);
-		nr_pages -= cur_pages;
+		fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
+		nr_pages -= pages;
+	}
+	if (folio) {
+		folio_end_read(folio, false);
+		folio_put(folio);
 	}
 }
 
-- 
2.47.1

[PATCH v5 10/11] fuse: optimize direct io large folios processing

[Joanne Koong]

Optimize processing folios larger than one page size for the direct io
case. If contiguous pages are part of the same folio, collate the
processing instead of processing each page in the folio separately.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 41 insertions(+), 14 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9a31f2a516b9..61eaec1c993b 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 	}
 
 	while (nbytes < *nbytesp && nr_pages < max_pages) {
-		unsigned nfolios, i;
+		struct folio *prev_folio = NULL;
+		unsigned npages, i;
 		size_t start;
 
 		ret = iov_iter_extract_pages(ii, &pages,
@@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 
 		nbytes += ret;
 
-		nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
+		npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
 
-		for (i = 0; i < nfolios; i++) {
-			struct folio *folio = page_folio(pages[i]);
-			unsigned int offset = start +
-				(folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
-			unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
+		/*
+		 * We must check each extracted page. We can't assume every page
+		 * in a large folio is used. For example, userspace may mmap() a
+		 * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
+		 * a large folio, in which case the extracted pages could be
+		 *
+		 * folio A page 0
+		 * folio A page 1
+		 * folio B page 0
+		 * folio A page 3
+		 *
+		 * where folio A belongs to the file and folio B is an anonymous
+		 * COW page.
+		 */
+		for (i = 0; i < npages && ret; i++) {
+			struct folio *folio;
+			unsigned int offset;
+			unsigned int len;
+
+			WARN_ON(!pages[i]);
+			folio = page_folio(pages[i]);
+
+			len = min_t(unsigned int, ret, PAGE_SIZE - start);
+
+			if (folio == prev_folio && pages[i] != pages[i - 1]) {
+				WARN_ON(ap->folios[ap->num_folios - 1] != folio);
+				ap->descs[ap->num_folios - 1].length += len;
+				WARN_ON(ap->descs[ap->num_folios - 1].length > folio_size(folio));
+			} else {
+				offset = start + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
+				ap->descs[ap->num_folios].offset = offset;
+				ap->descs[ap->num_folios].length = len;
+				ap->folios[ap->num_folios] = folio;
+				start = 0;
+				ap->num_folios++;
+				prev_folio = folio;
+			}
 
-			ap->descs[ap->num_folios].offset = offset;
-			ap->descs[ap->num_folios].length = len;
-			ap->folios[ap->num_folios] = folio;
-			start = 0;
 			ret -= len;
-			ap->num_folios++;
 		}
-
-		nr_pages += nfolios;
+		nr_pages += npages;
 	}
 	kfree(pages);
 
-- 
2.47.1

[PATCH v5 11/11] fuse: support large folios for writeback

[Joanne Koong]

Add support for folios larger than one page size for writeback.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/fuse/file.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 61eaec1c993b..5e7187446730 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2014,7 +2014,7 @@ static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struc
 
 	ap->folios[folio_index] = folio;
 	ap->descs[folio_index].offset = 0;
-	ap->descs[folio_index].length = PAGE_SIZE;
+	ap->descs[folio_index].length = folio_size(folio);
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 }
@@ -2088,6 +2088,7 @@ struct fuse_fill_wb_data {
 	struct fuse_file *ff;
 	struct inode *inode;
 	unsigned int max_folios;
+	unsigned int nr_pages;
 };
 
 static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
@@ -2135,15 +2136,15 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
 	WARN_ON(!ap->num_folios);
 
 	/* Reached max pages */
-	if (ap->num_folios == fc->max_pages)
+	if (data->nr_pages + folio_nr_pages(folio) > fc->max_pages)
 		return true;
 
 	/* Reached max write bytes */
-	if ((ap->num_folios + 1) * PAGE_SIZE > fc->max_write)
+	if ((data->nr_pages * PAGE_SIZE) + folio_size(folio) > fc->max_write)
 		return true;
 
 	/* Discontinuity */
-	if (ap->folios[ap->num_folios - 1]->index + 1 != folio_index(folio))
+	if (folio_next_index(ap->folios[ap->num_folios - 1]) != folio_index(folio))
 		return true;
 
 	/* Need to grow the pages array?  If so, did the expansion fail? */
@@ -2174,6 +2175,7 @@ static int fuse_writepages_fill(struct folio *folio,
 	if (wpa && fuse_writepage_need_send(fc, folio, ap, data)) {
 		fuse_writepages_send(data);
 		data->wpa = NULL;
+		data->nr_pages = 0;
 	}
 
 	if (data->wpa == NULL) {
@@ -2188,6 +2190,7 @@ static int fuse_writepages_fill(struct folio *folio,
 	folio_start_writeback(folio);
 
 	fuse_writepage_args_page_fill(wpa, folio, ap->num_folios);
+	data->nr_pages += folio_nr_pages(folio);
 
 	err = 0;
 	ap->num_folios++;
@@ -2218,6 +2221,7 @@ static int fuse_writepages(struct address_space *mapping,
 	data.inode = inode;
 	data.wpa = NULL;
 	data.ff = NULL;
+	data.nr_pages = 0;
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.wpa) {
-- 
2.47.1

Re: [PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()

[Dan Carpenter]

Hi Joanne,

kernel test robot noticed the following build warnings:

https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Joanne-Koong/fuse-support-copying-large-folios/20250426-081219
base:   https://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git for-next
patch link:    https://lore.kernel.org/r/20250426000828.3216220-4-joannelkoong%40gmail.com
patch subject: [PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()
config: i386-randconfig-141-20250426 (https://download.01.org/0day-ci/archive/20250427/202504270319.GmkEM1Xg-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
| Closes: https://lore.kernel.org/r/202504270319.GmkEM1Xg-lkp@intel.com/

smatch warnings:
fs/fuse/file.c:1207 fuse_fill_write_pages() error: uninitialized symbol 'err'.

vim +/err +1207 fs/fuse/file.c

4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1127  static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1128  				     struct address_space *mapping,
338f2e3f3341a9 Miklos Szeredi     2019-09-10  1129  				     struct iov_iter *ii, loff_t pos,
338f2e3f3341a9 Miklos Szeredi     2019-09-10  1130  				     unsigned int max_pages)
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1131  {
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1132  	struct fuse_args_pages *ap = &ia->ap;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1133  	struct fuse_conn *fc = get_fuse_conn(mapping->host);
09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1134  	unsigned offset = pos & (PAGE_SIZE - 1);
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1135  	size_t count = 0;
dfda790dfda452 Joanne Koong       2025-04-25  1136  	unsigned int num;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1137  	int err;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1138  
dfda790dfda452 Joanne Koong       2025-04-25  1139  	num = min(iov_iter_count(ii), fc->max_write);

Can iov_iter_count() return zero here?

dfda790dfda452 Joanne Koong       2025-04-25  1140  	num = min(num, max_pages << PAGE_SHIFT);
dfda790dfda452 Joanne Koong       2025-04-25  1141  
338f2e3f3341a9 Miklos Szeredi     2019-09-10  1142  	ap->args.in_pages = true;
68bfb7eb7f7de3 Joanne Koong       2024-10-24  1143  	ap->descs[0].offset = offset;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1144  
dfda790dfda452 Joanne Koong       2025-04-25  1145  	while (num) {
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1146  		size_t tmp;
9bafbe7ae01321 Josef Bacik        2024-09-30  1147  		struct folio *folio;
09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1148  		pgoff_t index = pos >> PAGE_SHIFT;
dfda790dfda452 Joanne Koong       2025-04-25  1149  		unsigned bytes = min(PAGE_SIZE - offset, num);
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1150  
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1151   again:
9bafbe7ae01321 Josef Bacik        2024-09-30  1152  		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
9bafbe7ae01321 Josef Bacik        2024-09-30  1153  					    mapping_gfp_mask(mapping));
9bafbe7ae01321 Josef Bacik        2024-09-30  1154  		if (IS_ERR(folio)) {
9bafbe7ae01321 Josef Bacik        2024-09-30  1155  			err = PTR_ERR(folio);
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1156  			break;
9bafbe7ae01321 Josef Bacik        2024-09-30  1157  		}
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1158  
931e80e4b3263d anfei zhou         2010-02-02  1159  		if (mapping_writably_mapped(mapping))
9bafbe7ae01321 Josef Bacik        2024-09-30  1160  			flush_dcache_folio(folio);
931e80e4b3263d anfei zhou         2010-02-02  1161  
9bafbe7ae01321 Josef Bacik        2024-09-30  1162  		tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
9bafbe7ae01321 Josef Bacik        2024-09-30  1163  		flush_dcache_folio(folio);
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1164  
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1165  		if (!tmp) {
9bafbe7ae01321 Josef Bacik        2024-09-30  1166  			folio_unlock(folio);
9bafbe7ae01321 Josef Bacik        2024-09-30  1167  			folio_put(folio);
faa794dd2e17e7 Dave Hansen        2025-01-29  1168  
faa794dd2e17e7 Dave Hansen        2025-01-29  1169  			/*
faa794dd2e17e7 Dave Hansen        2025-01-29  1170  			 * Ensure forward progress by faulting in
faa794dd2e17e7 Dave Hansen        2025-01-29  1171  			 * while not holding the folio lock:
faa794dd2e17e7 Dave Hansen        2025-01-29  1172  			 */
faa794dd2e17e7 Dave Hansen        2025-01-29  1173  			if (fault_in_iov_iter_readable(ii, bytes)) {
faa794dd2e17e7 Dave Hansen        2025-01-29  1174  				err = -EFAULT;
faa794dd2e17e7 Dave Hansen        2025-01-29  1175  				break;
faa794dd2e17e7 Dave Hansen        2025-01-29  1176  			}
faa794dd2e17e7 Dave Hansen        2025-01-29  1177  
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1178  			goto again;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1179  		}
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1180  
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1181  		err = 0;
f2ef459bab7326 Joanne Koong       2024-10-24  1182  		ap->folios[ap->num_folios] = folio;
68bfb7eb7f7de3 Joanne Koong       2024-10-24  1183  		ap->descs[ap->num_folios].length = tmp;
f2ef459bab7326 Joanne Koong       2024-10-24  1184  		ap->num_folios++;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1185  
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1186  		count += tmp;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1187  		pos += tmp;
dfda790dfda452 Joanne Koong       2025-04-25  1188  		num -= tmp;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1189  		offset += tmp;
09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1190  		if (offset == PAGE_SIZE)
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1191  			offset = 0;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1192  
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1193  		/* If we copied full page, mark it uptodate */
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1194  		if (tmp == PAGE_SIZE)
9bafbe7ae01321 Josef Bacik        2024-09-30  1195  			folio_mark_uptodate(folio);
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1196  
9bafbe7ae01321 Josef Bacik        2024-09-30  1197  		if (folio_test_uptodate(folio)) {
9bafbe7ae01321 Josef Bacik        2024-09-30  1198  			folio_unlock(folio);
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1199  		} else {
f2ef459bab7326 Joanne Koong       2024-10-24  1200  			ia->write.folio_locked = true;
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1201  			break;
4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1202  		}
dfda790dfda452 Joanne Koong       2025-04-25  1203  		if (!fc->big_writes || offset != 0)
78bb6cb9a890d3 Miklos Szeredi     2008-05-12  1204  			break;
dfda790dfda452 Joanne Koong       2025-04-25  1205  	}
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1206  
ea9b9907b82a09 Nicholas Piggin    2008-04-30 @1207  	return count > 0 ? count : err;
ea9b9907b82a09 Nicholas Piggin    2008-04-30  1208  }

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()

[Joanne Koong]

On Sun, Apr 27, 2025 at 10:32 PM Dan Carpenter <dan.carpenter@linaro.org> wrote:
>
> Hi Joanne,
>
> kernel test robot noticed the following build warnings:
>
> https://git-scm.com/docs/git-format-patch#_base_tree_information]
>
> url:    https://github.com/intel-lab-lkp/linux/commits/Joanne-Koong/fuse-support-copying-large-folios/20250426-081219
> base:   https://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git for-next
> patch link:    https://lore.kernel.org/r/20250426000828.3216220-4-joannelkoong%40gmail.com
> patch subject: [PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()
> config: i386-randconfig-141-20250426 (https://download.01.org/0day-ci/archive/20250427/202504270319.GmkEM1Xg-lkp@intel.com/config)
> compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
>
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <lkp@intel.com>
> | Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
> | Closes: https://lore.kernel.org/r/202504270319.GmkEM1Xg-lkp@intel.com/
>
> smatch warnings:
> fs/fuse/file.c:1207 fuse_fill_write_pages() error: uninitialized symbol 'err'.
>
> vim +/err +1207 fs/fuse/file.c
>
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1127  static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1128                                   struct address_space *mapping,
> 338f2e3f3341a9 Miklos Szeredi     2019-09-10  1129                                   struct iov_iter *ii, loff_t pos,
> 338f2e3f3341a9 Miklos Szeredi     2019-09-10  1130                                   unsigned int max_pages)
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1131  {
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1132      struct fuse_args_pages *ap = &ia->ap;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1133      struct fuse_conn *fc = get_fuse_conn(mapping->host);
> 09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1134      unsigned offset = pos & (PAGE_SIZE - 1);
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1135      size_t count = 0;
> dfda790dfda452 Joanne Koong       2025-04-25  1136      unsigned int num;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1137      int err;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1138
> dfda790dfda452 Joanne Koong       2025-04-25  1139      num = min(iov_iter_count(ii), fc->max_write);
>
> Can iov_iter_count() return zero here?
>
> dfda790dfda452 Joanne Koong       2025-04-25  1140      num = min(num, max_pages << PAGE_SHIFT);
> dfda790dfda452 Joanne Koong       2025-04-25  1141
> 338f2e3f3341a9 Miklos Szeredi     2019-09-10  1142      ap->args.in_pages = true;
> 68bfb7eb7f7de3 Joanne Koong       2024-10-24  1143      ap->descs[0].offset = offset;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1144
> dfda790dfda452 Joanne Koong       2025-04-25  1145      while (num) {
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1146              size_t tmp;
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1147              struct folio *folio;
> 09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1148              pgoff_t index = pos >> PAGE_SHIFT;
> dfda790dfda452 Joanne Koong       2025-04-25  1149              unsigned bytes = min(PAGE_SIZE - offset, num);
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1150
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1151   again:
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1152              folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1153                                          mapping_gfp_mask(mapping));
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1154              if (IS_ERR(folio)) {
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1155                      err = PTR_ERR(folio);
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1156                      break;
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1157              }
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1158
> 931e80e4b3263d anfei zhou         2010-02-02  1159              if (mapping_writably_mapped(mapping))
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1160                      flush_dcache_folio(folio);
> 931e80e4b3263d anfei zhou         2010-02-02  1161
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1162              tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1163              flush_dcache_folio(folio);
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1164
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1165              if (!tmp) {
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1166                      folio_unlock(folio);
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1167                      folio_put(folio);
> faa794dd2e17e7 Dave Hansen        2025-01-29  1168
> faa794dd2e17e7 Dave Hansen        2025-01-29  1169                      /*
> faa794dd2e17e7 Dave Hansen        2025-01-29  1170                       * Ensure forward progress by faulting in
> faa794dd2e17e7 Dave Hansen        2025-01-29  1171                       * while not holding the folio lock:
> faa794dd2e17e7 Dave Hansen        2025-01-29  1172                       */
> faa794dd2e17e7 Dave Hansen        2025-01-29  1173                      if (fault_in_iov_iter_readable(ii, bytes)) {
> faa794dd2e17e7 Dave Hansen        2025-01-29  1174                              err = -EFAULT;
> faa794dd2e17e7 Dave Hansen        2025-01-29  1175                              break;
> faa794dd2e17e7 Dave Hansen        2025-01-29  1176                      }
> faa794dd2e17e7 Dave Hansen        2025-01-29  1177
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1178                      goto again;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1179              }
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1180
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1181              err = 0;
> f2ef459bab7326 Joanne Koong       2024-10-24  1182              ap->folios[ap->num_folios] = folio;
> 68bfb7eb7f7de3 Joanne Koong       2024-10-24  1183              ap->descs[ap->num_folios].length = tmp;
> f2ef459bab7326 Joanne Koong       2024-10-24  1184              ap->num_folios++;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1185
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1186              count += tmp;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1187              pos += tmp;
> dfda790dfda452 Joanne Koong       2025-04-25  1188              num -= tmp;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1189              offset += tmp;
> 09cbfeaf1a5a67 Kirill A. Shutemov 2016-04-01  1190              if (offset == PAGE_SIZE)
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1191                      offset = 0;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1192
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1193              /* If we copied full page, mark it uptodate */
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1194              if (tmp == PAGE_SIZE)
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1195                      folio_mark_uptodate(folio);
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1196
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1197              if (folio_test_uptodate(folio)) {
> 9bafbe7ae01321 Josef Bacik        2024-09-30  1198                      folio_unlock(folio);
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1199              } else {
> f2ef459bab7326 Joanne Koong       2024-10-24  1200                      ia->write.folio_locked = true;
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1201                      break;
> 4f06dd92b5d0a6 Vivek Goyal        2020-10-21  1202              }
> dfda790dfda452 Joanne Koong       2025-04-25  1203              if (!fc->big_writes || offset != 0)
> 78bb6cb9a890d3 Miklos Szeredi     2008-05-12  1204                      break;
> dfda790dfda452 Joanne Koong       2025-04-25  1205      }
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1206
> ea9b9907b82a09 Nicholas Piggin    2008-04-30 @1207      return count > 0 ? count : err;
> ea9b9907b82a09 Nicholas Piggin    2008-04-30  1208  }
>

I'll initialize err to 0 in v6. I'll wait for more reviews/comments on
the patchset before sending that out.

Thanks,
Joanne

> --
> 0-DAY CI Kernel Test Service
> https://github.com/intel/lkp-tests/wiki
>

Re: [PATCH v5 01/11] fuse: support copying large folios

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Currently, all folios associated with fuse are one page size. As part of
> the work to enable large folios, this commit adds support for copying
> to/from folios larger than one page size.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/dev.c        | 84 +++++++++++++++++++-------------------------
>  fs/fuse/fuse_dev_i.h |  2 +-
>  2 files changed, 37 insertions(+), 49 deletions(-)
> 
> diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
> index 155bb6aeaef5..7b0e3a394480 100644
> --- a/fs/fuse/dev.c
> +++ b/fs/fuse/dev.c
> @@ -955,10 +955,10 @@ static int fuse_check_folio(struct folio *folio)
>   * folio that was originally in @pagep will lose a reference and the new
>   * folio returned in @pagep will carry a reference.
>   */
> -static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
> +static int fuse_try_move_folio(struct fuse_copy_state *cs, struct folio **foliop)
>  {
>  	int err;
> -	struct folio *oldfolio = page_folio(*pagep);
> +	struct folio *oldfolio = *foliop;
>  	struct folio *newfolio;
>  	struct pipe_buffer *buf = cs->pipebufs;
>  
> @@ -979,7 +979,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
>  	cs->pipebufs++;
>  	cs->nr_segs--;
>  
> -	if (cs->len != PAGE_SIZE)
> +	if (cs->len != folio_size(oldfolio))
>  		goto out_fallback;
>  
>  	if (!pipe_buf_try_steal(cs->pipe, buf))
> @@ -1025,7 +1025,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
>  	if (test_bit(FR_ABORTED, &cs->req->flags))
>  		err = -ENOENT;
>  	else
> -		*pagep = &newfolio->page;
> +		*foliop = newfolio;
>  	spin_unlock(&cs->req->waitq.lock);
>  
>  	if (err) {
> @@ -1058,8 +1058,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
>  	goto out_put_old;
>  }
>  
> -static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
> -			 unsigned offset, unsigned count)
> +static int fuse_ref_folio(struct fuse_copy_state *cs, struct folio *folio,
> +			  unsigned offset, unsigned count)
>  {
>  	struct pipe_buffer *buf;
>  	int err;
> @@ -1067,17 +1067,17 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
>  	if (cs->nr_segs >= cs->pipe->max_usage)
>  		return -EIO;
>  
> -	get_page(page);
> +	folio_get(folio);
>  	err = unlock_request(cs->req);
>  	if (err) {
> -		put_page(page);
> +		folio_put(folio);
>  		return err;
>  	}
>  
>  	fuse_copy_finish(cs);
>  
>  	buf = cs->pipebufs;
> -	buf->page = page;
> +	buf->page = &folio->page;
>  	buf->offset = offset;
>  	buf->len = count;
>  
> @@ -1089,20 +1089,21 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
>  }
>  
>  /*
> - * Copy a page in the request to/from the userspace buffer.  Must be
> + * Copy a folio in the request to/from the userspace buffer.  Must be
>   * done atomically
>   */
> -static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
> -			  unsigned offset, unsigned count, int zeroing)
> +static int fuse_copy_folio(struct fuse_copy_state *cs, struct folio **foliop,
> +			   unsigned offset, unsigned count, int zeroing)
>  {
>  	int err;
> -	struct page *page = *pagep;
> +	struct folio *folio = *foliop;
> +	size_t size = folio_size(folio);
>  
> -	if (page && zeroing && count < PAGE_SIZE)
> -		clear_highpage(page);
> +	if (folio && zeroing && count < size)
> +		folio_zero_range(folio, 0, size);
>  
>  	while (count) {
> -		if (cs->write && cs->pipebufs && page) {
> +		if (cs->write && cs->pipebufs && folio) {
>  			/*
>  			 * Can't control lifetime of pipe buffers, so always
>  			 * copy user pages.
> @@ -1112,12 +1113,12 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
>  				if (err)
>  					return err;
>  			} else {
> -				return fuse_ref_page(cs, page, offset, count);
> +				return fuse_ref_folio(cs, folio, offset, count);
>  			}
>  		} else if (!cs->len) {
> -			if (cs->move_pages && page &&
> -			    offset == 0 && count == PAGE_SIZE) {
> -				err = fuse_try_move_page(cs, pagep);
> +			if (cs->move_folios && folio &&
> +			    offset == 0 && count == folio_size(folio)) {
> +				err = fuse_try_move_folio(cs, foliop);
>  				if (err <= 0)
>  					return err;
>  			} else {
> @@ -1126,22 +1127,22 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
>  					return err;
>  			}
>  		}
> -		if (page) {
> -			void *mapaddr = kmap_local_page(page);
> -			void *buf = mapaddr + offset;
> +		if (folio) {
> +			void *mapaddr = kmap_local_folio(folio, offset);
> +			void *buf = mapaddr;
>  			offset += fuse_copy_do(cs, &buf, &count);
>  			kunmap_local(mapaddr);
>  		} else
>  			offset += fuse_copy_do(cs, NULL, &count);
>  	}
> -	if (page && !cs->write)
> -		flush_dcache_page(page);
> +	if (folio && !cs->write)
> +		flush_dcache_folio(folio);
>  	return 0;
>  }
>  
> -/* Copy pages in the request to/from userspace buffer */
> -static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
> -			   int zeroing)
> +/* Copy folios in the request to/from userspace buffer */
> +static int fuse_copy_folios(struct fuse_copy_state *cs, unsigned nbytes,
> +			    int zeroing)
>  {
>  	unsigned i;
>  	struct fuse_req *req = cs->req;
> @@ -1151,23 +1152,12 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
>  		int err;
>  		unsigned int offset = ap->descs[i].offset;
>  		unsigned int count = min(nbytes, ap->descs[i].length);
> -		struct page *orig, *pagep;
> -
> -		orig = pagep = &ap->folios[i]->page;
>  
> -		err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
> +		err = fuse_copy_folio(cs, &ap->folios[i], offset, count, zeroing);
>  		if (err)
>  			return err;
>  
>  		nbytes -= count;
> -
> -		/*
> -		 *  fuse_copy_page may have moved a page from a pipe instead of
> -		 *  copying into our given page, so update the folios if it was
> -		 *  replaced.
> -		 */
> -		if (pagep != orig)
> -			ap->folios[i] = page_folio(pagep);
>  	}
>  	return 0;
>  }
> @@ -1197,7 +1187,7 @@ int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
>  	for (i = 0; !err && i < numargs; i++)  {
>  		struct fuse_arg *arg = &args[i];
>  		if (i == numargs - 1 && argpages)
> -			err = fuse_copy_pages(cs, arg->size, zeroing);
> +			err = fuse_copy_folios(cs, arg->size, zeroing);
>  		else
>  			err = fuse_copy_one(cs, arg->value, arg->size);
>  	}
> @@ -1786,7 +1776,6 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
>  	num = outarg.size;
>  	while (num) {
>  		struct folio *folio;
> -		struct page *page;
>  		unsigned int this_num;
>  
>  		folio = filemap_grab_folio(mapping, index);
> @@ -1794,9 +1783,8 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
>  		if (IS_ERR(folio))
>  			goto out_iput;
>  
> -		page = &folio->page;
>  		this_num = min_t(unsigned, num, folio_size(folio) - offset);
> -		err = fuse_copy_page(cs, &page, offset, this_num, 0);
> +		err = fuse_copy_folio(cs, &folio, offset, this_num, 0);
>  		if (!folio_test_uptodate(folio) && !err && offset == 0 &&
>  		    (this_num == folio_size(folio) || file_size == end)) {
>  			folio_zero_segment(folio, this_num, folio_size(folio));
> @@ -2037,8 +2025,8 @@ static int fuse_notify_inc_epoch(struct fuse_conn *fc)
>  static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
>  		       unsigned int size, struct fuse_copy_state *cs)
>  {
> -	/* Don't try to move pages (yet) */
> -	cs->move_pages = false;
> +	/* Don't try to move folios (yet) */
> +	cs->move_folios = false;
>  
>  	switch (code) {
>  	case FUSE_NOTIFY_POLL:
> @@ -2189,7 +2177,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
>  	spin_unlock(&fpq->lock);
>  	cs->req = req;
>  	if (!req->args->page_replace)
> -		cs->move_pages = false;
> +		cs->move_folios = false;
>  
>  	if (oh.error)
>  		err = nbytes != sizeof(oh) ? -EINVAL : 0;
> @@ -2307,7 +2295,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
>  	cs.pipe = pipe;
>  
>  	if (flags & SPLICE_F_MOVE)
> -		cs.move_pages = true;
> +		cs.move_folios = true;
>  
>  	ret = fuse_dev_do_write(fud, &cs, len);
>  
> diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
> index db136e045925..5a9bd771a319 100644
> --- a/fs/fuse/fuse_dev_i.h
> +++ b/fs/fuse/fuse_dev_i.h
> @@ -30,7 +30,7 @@ struct fuse_copy_state {
>  	unsigned int len;
>  	unsigned int offset;
>  	bool write:1;
> -	bool move_pages:1;
> +	bool move_folios:1;
>  	bool is_uring:1;
>  	struct {
>  		unsigned int copied_sz; /* copied size into the user buffer */

Re: [PATCH v5 02/11] fuse: support large folios for retrieves

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Add support for folios larger than one page size for retrieves.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/dev.c | 25 +++++++++++++++----------
>  1 file changed, 15 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
> index 7b0e3a394480..fb81c0a1c6cd 100644
> --- a/fs/fuse/dev.c
> +++ b/fs/fuse/dev.c
> @@ -1837,7 +1837,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
>  	unsigned int num;
>  	unsigned int offset;
>  	size_t total_len = 0;
> -	unsigned int num_pages, cur_pages = 0;
> +	unsigned int num_pages;
>  	struct fuse_conn *fc = fm->fc;
>  	struct fuse_retrieve_args *ra;
>  	size_t args_size = sizeof(*ra);
> @@ -1855,6 +1855,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
>  
>  	num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
>  	num_pages = min(num_pages, fc->max_pages);
> +	num = min(num, num_pages << PAGE_SHIFT);
>  
>  	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->descs[0]));
>  
> @@ -1875,25 +1876,29 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
>  
>  	index = outarg->offset >> PAGE_SHIFT;
>  
> -	while (num && cur_pages < num_pages) {
> +	while (num) {
>  		struct folio *folio;
> -		unsigned int this_num;
> +		unsigned int folio_offset;
> +		unsigned int nr_bytes;
> +		unsigned int nr_pages;
>  
>  		folio = filemap_get_folio(mapping, index);
>  		if (IS_ERR(folio))
>  			break;
>  
> -		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
> +		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
> +		nr_bytes = min(folio_size(folio) - folio_offset, num);
> +		nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
> +
>  		ap->folios[ap->num_folios] = folio;
> -		ap->descs[ap->num_folios].offset = offset;
> -		ap->descs[ap->num_folios].length = this_num;
> +		ap->descs[ap->num_folios].offset = folio_offset;
> +		ap->descs[ap->num_folios].length = nr_bytes;
>  		ap->num_folios++;
> -		cur_pages++;
>  
>  		offset = 0;
> -		num -= this_num;
> -		total_len += this_num;
> -		index++;
> +		num -= nr_bytes;
> +		total_len += nr_bytes;
> +		index += nr_pages;
>  	}
>  	ra->inarg.offset = outarg->offset;
>  	ra->inarg.size = total_len;

Re: [PATCH v5 03/11] fuse: refactor fuse_fill_write_pages()

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Refactor the logic in fuse_fill_write_pages() for copying out write
> data. This will make the future change for supporting large folios for
> writes easier. No functional changes.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpandewa.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/file.c | 19 +++++++++----------
>  1 file changed, 9 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index e203dd4fcc0f..edc86485065e 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1132,21 +1132,21 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  	struct fuse_args_pages *ap = &ia->ap;
>  	struct fuse_conn *fc = get_fuse_conn(mapping->host);
>  	unsigned offset = pos & (PAGE_SIZE - 1);
> -	unsigned int nr_pages = 0;
>  	size_t count = 0;
> +	unsigned int num;
>  	int err;
>  
> +	num = min(iov_iter_count(ii), fc->max_write);
> +	num = min(num, max_pages << PAGE_SHIFT);
> +
>  	ap->args.in_pages = true;
>  	ap->descs[0].offset = offset;
>  
> -	do {
> +	while (num) {
>  		size_t tmp;
>  		struct folio *folio;
>  		pgoff_t index = pos >> PAGE_SHIFT;
> -		size_t bytes = min_t(size_t, PAGE_SIZE - offset,
> -				     iov_iter_count(ii));
> -
> -		bytes = min_t(size_t, bytes, fc->max_write - count);
> +		unsigned bytes = min(PAGE_SIZE - offset, num);
>  
>   again:
>  		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
> @@ -1182,10 +1182,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  		ap->folios[ap->num_folios] = folio;
>  		ap->descs[ap->num_folios].length = tmp;
>  		ap->num_folios++;
> -		nr_pages++;
>  
>  		count += tmp;
>  		pos += tmp;
> +		num -= tmp;
>  		offset += tmp;
>  		if (offset == PAGE_SIZE)
>  			offset = 0;
> @@ -1200,10 +1200,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  			ia->write.folio_locked = true;
>  			break;
>  		}
> -		if (!fc->big_writes)
> +		if (!fc->big_writes || offset != 0)
>  			break;
> -	} while (iov_iter_count(ii) && count < fc->max_write &&
> -		 nr_pages < max_pages && offset == 0);
> +	}
>  
>  	return count > 0 ? count : err;
>  }

Re: [PATCH v5 04/11] fuse: support large folios for writethrough writes

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Add support for folios larger than one page size for writethrough
> writes.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>
> ---
>  fs/fuse/file.c | 15 ++++++++++-----
>  1 file changed, 10 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index edc86485065e..e44b6d26c1c6 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1146,7 +1146,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  		size_t tmp;
>  		struct folio *folio;
>  		pgoff_t index = pos >> PAGE_SHIFT;
> -		unsigned bytes = min(PAGE_SIZE - offset, num);
> +		unsigned int bytes;
> +		unsigned int folio_offset;
>  
>   again:
>  		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
> @@ -1159,7 +1160,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  		if (mapping_writably_mapped(mapping))
>  			flush_dcache_folio(folio);
>  
> -		tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
> +		folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
> +		bytes = min(folio_size(folio) - folio_offset, num);
> +
> +		tmp = copy_folio_from_iter_atomic(folio, folio_offset, bytes, ii);
>  		flush_dcache_folio(folio);
>  
>  		if (!tmp) {f 
> @@ -1180,6 +1184,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  
>  		err = 0;
>  		ap->folios[ap->num_folios] = folio;
> +		ap->descs[ap->num_folios].offset = folio_offset;
>  		ap->descs[ap->num_folios].length = tmp;
>  		ap->num_folios++;
>  
> @@ -1187,11 +1192,11 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
>  		pos += tmp;
>  		num -= tmp;
>  		offset += tmp;
> -		if (offset == PAGE_SIZE)
> +		if (offset == folio_size(folio))
>  			offset = 0;
>  
> -		/* If we copied full page, mark it uptodate */
> -		if (tmp == PAGE_SIZE)
> +		/* If we copied full folio, mark it uptodate */
> +		if (tmp == folio_size(folio))
>  			folio_mark_uptodate(folio);

Here am I confused. I think tmp can be a subpart of the folio, let's say
the folio is 2MB and somehow the again loop would iterate through the
folio in smaller steps. So the folio would be entirely written out, but
tmp might not be folio_size? Doesn't this need to sum up tmp for per
folio and then use that value?  And I actually wonder if we could use
the above "(offset == folio_size(folio)" as well. At least if the
initial offset for a folio is 0 it should work.


Thanks,
Bernd

>  
>  		if (folio_test_uptodate(folio)) {

Re: [PATCH v5 05/11] fuse: support large folios for folio reads

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Add support for folios larger than one page size for folio reads into
> the page cache.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/file.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index e44b6d26c1c6..0ca3b31c59f9 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -793,7 +793,7 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
>  	struct inode *inode = folio->mapping->host;
>  	struct fuse_mount *fm = get_fuse_mount(inode);
>  	loff_t pos = folio_pos(folio);
> -	struct fuse_folio_desc desc = { .length = PAGE_SIZE };
> +	struct fuse_folio_desc desc = { .length = folio_size(folio) };
>  	struct fuse_io_args ia = {
>  		.ap.args.page_zeroing = true,
>  		.ap.args.out_pages = true,

Re: [PATCH v5 06/11] fuse: support large folios for symlinks

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Support large folios for symlinks and change the name from
> fuse_getlink_page() to fuse_getlink_folio().
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/dir.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
> index 1fb0b15a6088..3003119559e8 100644
> --- a/fs/fuse/dir.c
> +++ b/fs/fuse/dir.c
> @@ -1629,10 +1629,10 @@ static int fuse_permission(struct mnt_idmap *idmap,
>  	return err;
>  }
>  
> -static int fuse_readlink_page(struct inode *inode, struct folio *folio)
> +static int fuse_readlink_folio(struct inode *inode, struct folio *folio)
>  {
>  	struct fuse_mount *fm = get_fuse_mount(inode);
> -	struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
> +	struct fuse_folio_desc desc = { .length = folio_size(folio) - 1 };
>  	struct fuse_args_pages ap = {
>  		.num_folios = 1,
>  		.folios = &folio,
> @@ -1687,7 +1687,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
>  	if (!folio)
>  		goto out_err;
>  
> -	err = fuse_readlink_page(inode, folio);
> +	err = fuse_readlink_folio(inode, folio);
>  	if (err) {
>  		folio_put(folio);
>  		goto out_err;
> @@ -2277,7 +2277,7 @@ void fuse_init_dir(struct inode *inode)
>  
>  static int fuse_symlink_read_folio(struct file *null, struct folio *folio)
>  {
> -	int err = fuse_readlink_page(folio->mapping->host, folio);
> +	int err = fuse_readlink_folio(folio->mapping->host, folio);
>  
>  	if (!err)
>  		folio_mark_uptodate(folio);

Re: [PATCH v5 08/11] fuse: support large folios for queued writes

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Add support for folios larger than one page size for queued writes.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>


> ---
>  fs/fuse/file.c | 11 +++++++----
>  1 file changed, 7 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 0ca3b31c59f9..1d38486fae50 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1790,11 +1790,14 @@ __releases(fi->lock)
>  __acquires(fi->lock)
>  {
>  	struct fuse_inode *fi = get_fuse_inode(wpa->inode);
> +	struct fuse_args_pages *ap = &wpa->ia.ap;
>  	struct fuse_write_in *inarg = &wpa->ia.write.in;
> -	struct fuse_args *args = &wpa->ia.ap.args;
> -	/* Currently, all folios in FUSE are one page */
> -	__u64 data_size = wpa->ia.ap.num_folios * PAGE_SIZE;
> -	int err;
> +	struct fuse_args *args = &ap->args;
> +	__u64 data_size = 0;
> +	int err, i;
> +
> +	for (i = 0; i < ap->num_folios; i++)
> +		data_size += ap->descs[i].length;
>  
>  	fi->writectr++;
>  	if (inarg->offset + data_size <= size) {

Re: [PATCH v5 09/11] fuse: support large folios for readahead

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Add support for folios larger than one page size for readahead.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>
> ---
>  fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
>  1 file changed, 27 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 1d38486fae50..9a31f2a516b9 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
>  	fuse_io_free(ia);
>  }
>  
> -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
> +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
> +				unsigned int count)
>  {
>  	struct fuse_file *ff = file->private_data;
>  	struct fuse_mount *fm = ff->fm;
>  	struct fuse_args_pages *ap = &ia->ap;
>  	loff_t pos = folio_pos(ap->folios[0]);
> -	/* Currently, all folios in FUSE are one page */
> -	size_t count = ap->num_folios << PAGE_SHIFT;
>  	ssize_t res;
>  	int err;
>  
> @@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
>  	struct inode *inode = rac->mapping->host;
>  	struct fuse_conn *fc = get_fuse_conn(inode);
>  	unsigned int max_pages, nr_pages;
> +	struct folio *folio = NULL;
>  
>  	if (fuse_is_bad(inode))
>  		return;
> @@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
>  	while (nr_pages) {
>  		struct fuse_io_args *ia;
>  		struct fuse_args_pages *ap;
> -		struct folio *folio;
>  		unsigned cur_pages = min(max_pages, nr_pages);
> +		unsigned int pages = 0;
>  
>  		if (fc->num_background >= fc->congestion_threshold &&
>  		    rac->ra->async_size >= readahead_count(rac))
> @@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
>  
>  		ia = fuse_io_alloc(NULL, cur_pages);
>  		if (!ia)
> -			return;
> +			break;
>  		ap = &ia->ap;
>  
> -		while (ap->num_folios < cur_pages) {
> +		while (pages < cur_pages) {
> +			unsigned int folio_pages;
> +
>  			/*
>  			 * This returns a folio with a ref held on it.
>  			 * The ref needs to be held until the request is
> @@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
>  			 * fuse_try_move_page()) drops the ref after it's
>  			 * replaced in the page cache.
>  			 */
> -			folio = __readahead_folio(rac);
> +			if (!folio)
> +				folio =  __readahead_folio(rac);
> +
> +			folio_pages = folio_nr_pages(folio);
> +			if (folio_pages > cur_pages - pages)
> +				break;
> +

Hmm, so let's assume this would be a 2MB folio, but fc->max_pages is
limited to 1MB - we not do read-ahead anymore?

Thanks,
Bernd


>  			ap->folios[ap->num_folios] = folio;
>  			ap->descs[ap->num_folios].length = folio_size(folio);
>  			ap->num_folios++;
> +			pages += folio_pages;
> +			folio = NULL;
> +		}
> +		if (!pages) {
> +			fuse_io_free(ia);
> +			break;
>  		}
> -		fuse_send_readpages(ia, rac->file);
> -		nr_pages -= cur_pages;
> +		fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
> +		nr_pages -= pages;
> +	}
> +	if (folio) {
> +		folio_end_read(folio, false);
> +		folio_put(folio);
>  	}
>  }
>  

Re: [PATCH v5 10/11] fuse: optimize direct io large folios processing

[Bernd Schubert]

On 4/26/25 02:08, Joanne Koong wrote:
> Optimize processing folios larger than one page size for the direct io
> case. If contiguous pages are part of the same folio, collate the
> processing instead of processing each page in the folio separately.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>

Reviewed-by: Bernd Schubert <bschubert@ddn.com>

> ---
>  fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
>  1 file changed, 41 insertions(+), 14 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 9a31f2a516b9..61eaec1c993b 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>  	}
>  
>  	while (nbytes < *nbytesp && nr_pages < max_pages) {
> -		unsigned nfolios, i;
> +		struct folio *prev_folio = NULL;
> +		unsigned npages, i;
>  		size_t start;
>  
>  		ret = iov_iter_extract_pages(ii, &pages,
> @@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>  
>  		nbytes += ret;
>  
> -		nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> +		npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
>  
> -		for (i = 0; i < nfolios; i++) {
> -			struct folio *folio = page_folio(pages[i]);
> -			unsigned int offset = start +
> -				(folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
> -			unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
> +		/*
> +		 * We must check each extracted page. We can't assume every page
> +		 * in a large folio is used. For example, userspace may mmap() a
> +		 * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
> +		 * a large folio, in which case the extracted pages could be
> +		 *
> +		 * folio A page 0
> +		 * folio A page 1
> +		 * folio B page 0
> +		 * folio A page 3
> +		 *
> +		 * where folio A belongs to the file and folio B is an anonymous
> +		 * COW page.
> +		 */
> +		for (i = 0; i < npages && ret; i++) {
> +			struct folio *folio;
> +			unsigned int offset;
> +			unsigned int len;
> +
> +			WARN_ON(!pages[i]);
> +			folio = page_folio(pages[i]);
> +
> +			len = min_t(unsigned int, ret, PAGE_SIZE - start);
> +
> +			if (folio == prev_folio && pages[i] != pages[i - 1]) {
> +				WARN_ON(ap->folios[ap->num_folios - 1] != folio);
> +				ap->descs[ap->num_folios - 1].length += len;
> +				WARN_ON(ap->descs[ap->num_folios - 1].length > folio_size(folio));
> +			} else {
> +				offset = start + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
> +				ap->descs[ap->num_folios].offset = offset;
> +				ap->descs[ap->num_folios].length = len;
> +				ap->folios[ap->num_folios] = folio;
> +				start = 0;
> +				ap->num_folios++;
> +				prev_folio = folio;
> +			}
>  
> -			ap->descs[ap->num_folios].offset = offset;
> -			ap->descs[ap->num_folios].length = len;
> -			ap->folios[ap->num_folios] = folio;
> -			start = 0;
>  			ret -= len;
> -			ap->num_folios++;
>  		}
> -
> -		nr_pages += nfolios;
> +		nr_pages += npages;
>  	}
>  	kfree(pages);
>  

Re: [PATCH v5 09/11] fuse: support large folios for readahead

[Darrick J. Wong]

On Sun, May 04, 2025 at 09:13:44PM +0200, Bernd Schubert wrote:
> 
> 
> On 4/26/25 02:08, Joanne Koong wrote:
> > Add support for folios larger than one page size for readahead.
> > 
> > Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> > Reviewed-by: Jeff Layton <jlayton@kernel.org>
> > ---
> >  fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
> >  1 file changed, 27 insertions(+), 9 deletions(-)
> > 
> > diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> > index 1d38486fae50..9a31f2a516b9 100644
> > --- a/fs/fuse/file.c
> > +++ b/fs/fuse/file.c
> > @@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
> >  	fuse_io_free(ia);
> >  }
> >  
> > -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
> > +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
> > +				unsigned int count)
> >  {
> >  	struct fuse_file *ff = file->private_data;
> >  	struct fuse_mount *fm = ff->fm;
> >  	struct fuse_args_pages *ap = &ia->ap;
> >  	loff_t pos = folio_pos(ap->folios[0]);
> > -	/* Currently, all folios in FUSE are one page */
> > -	size_t count = ap->num_folios << PAGE_SHIFT;
> >  	ssize_t res;
> >  	int err;
> >  
> > @@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
> >  	struct inode *inode = rac->mapping->host;
> >  	struct fuse_conn *fc = get_fuse_conn(inode);
> >  	unsigned int max_pages, nr_pages;
> > +	struct folio *folio = NULL;
> >  
> >  	if (fuse_is_bad(inode))
> >  		return;
> > @@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
> >  	while (nr_pages) {
> >  		struct fuse_io_args *ia;
> >  		struct fuse_args_pages *ap;
> > -		struct folio *folio;
> >  		unsigned cur_pages = min(max_pages, nr_pages);
> > +		unsigned int pages = 0;
> >  
> >  		if (fc->num_background >= fc->congestion_threshold &&
> >  		    rac->ra->async_size >= readahead_count(rac))
> > @@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
> >  
> >  		ia = fuse_io_alloc(NULL, cur_pages);
> >  		if (!ia)
> > -			return;
> > +			break;
> >  		ap = &ia->ap;
> >  
> > -		while (ap->num_folios < cur_pages) {
> > +		while (pages < cur_pages) {
> > +			unsigned int folio_pages;
> > +
> >  			/*
> >  			 * This returns a folio with a ref held on it.
> >  			 * The ref needs to be held until the request is
> > @@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
> >  			 * fuse_try_move_page()) drops the ref after it's
> >  			 * replaced in the page cache.
> >  			 */
> > -			folio = __readahead_folio(rac);
> > +			if (!folio)
> > +				folio =  __readahead_folio(rac);
> > +
> > +			folio_pages = folio_nr_pages(folio);
> > +			if (folio_pages > cur_pages - pages)
> > +				break;
> > +
> 
> Hmm, so let's assume this would be a 2MB folio, but fc->max_pages is
> limited to 1MB - we not do read-ahead anymore?

It's hard for me to say without seeing the actual enablement patches,
but filesystems are supposed to call mapping_set_folio_order_range to
constrain the sizes of the folios that the pagecache requests.

--D

> Thanks,
> Bernd
> 
> 
> >  			ap->folios[ap->num_folios] = folio;
> >  			ap->descs[ap->num_folios].length = folio_size(folio);
> >  			ap->num_folios++;
> > +			pages += folio_pages;
> > +			folio = NULL;
> > +		}
> > +		if (!pages) {
> > +			fuse_io_free(ia);
> > +			break;
> >  		}
> > -		fuse_send_readpages(ia, rac->file);
> > -		nr_pages -= cur_pages;
> > +		fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
> > +		nr_pages -= pages;
> > +	}
> > +	if (folio) {
> > +		folio_end_read(folio, false);
> > +		folio_put(folio);
> >  	}
> >  }
> >  
> 
> 

Re: [PATCH v5 09/11] fuse: support large folios for readahead

[Bernd Schubert]

On 5/5/25 16:40, Darrick J. Wong wrote:
> On Sun, May 04, 2025 at 09:13:44PM +0200, Bernd Schubert wrote:
>>
>>
>> On 4/26/25 02:08, Joanne Koong wrote:
>>> Add support for folios larger than one page size for readahead.
>>>
>>> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
>>> Reviewed-by: Jeff Layton <jlayton@kernel.org>
>>> ---
>>>  fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
>>>  1 file changed, 27 insertions(+), 9 deletions(-)
>>>
>>> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
>>> index 1d38486fae50..9a31f2a516b9 100644
>>> --- a/fs/fuse/file.c
>>> +++ b/fs/fuse/file.c
>>> @@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
>>>  	fuse_io_free(ia);
>>>  }
>>>  
>>> -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
>>> +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
>>> +				unsigned int count)
>>>  {
>>>  	struct fuse_file *ff = file->private_data;
>>>  	struct fuse_mount *fm = ff->fm;
>>>  	struct fuse_args_pages *ap = &ia->ap;
>>>  	loff_t pos = folio_pos(ap->folios[0]);
>>> -	/* Currently, all folios in FUSE are one page */
>>> -	size_t count = ap->num_folios << PAGE_SHIFT;
>>>  	ssize_t res;
>>>  	int err;
>>>  
>>> @@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
>>>  	struct inode *inode = rac->mapping->host;
>>>  	struct fuse_conn *fc = get_fuse_conn(inode);
>>>  	unsigned int max_pages, nr_pages;
>>> +	struct folio *folio = NULL;
>>>  
>>>  	if (fuse_is_bad(inode))
>>>  		return;
>>> @@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
>>>  	while (nr_pages) {
>>>  		struct fuse_io_args *ia;
>>>  		struct fuse_args_pages *ap;
>>> -		struct folio *folio;
>>>  		unsigned cur_pages = min(max_pages, nr_pages);
>>> +		unsigned int pages = 0;
>>>  
>>>  		if (fc->num_background >= fc->congestion_threshold &&
>>>  		    rac->ra->async_size >= readahead_count(rac))
>>> @@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
>>>  
>>>  		ia = fuse_io_alloc(NULL, cur_pages);
>>>  		if (!ia)
>>> -			return;
>>> +			break;
>>>  		ap = &ia->ap;
>>>  
>>> -		while (ap->num_folios < cur_pages) {
>>> +		while (pages < cur_pages) {
>>> +			unsigned int folio_pages;
>>> +
>>>  			/*
>>>  			 * This returns a folio with a ref held on it.
>>>  			 * The ref needs to be held until the request is
>>> @@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
>>>  			 * fuse_try_move_page()) drops the ref after it's
>>>  			 * replaced in the page cache.
>>>  			 */
>>> -			folio = __readahead_folio(rac);
>>> +			if (!folio)
>>> +				folio =  __readahead_folio(rac);
>>> +
>>> +			folio_pages = folio_nr_pages(folio);
>>> +			if (folio_pages > cur_pages - pages)
>>> +				break;
>>> +
>>
>> Hmm, so let's assume this would be a 2MB folio, but fc->max_pages is
>> limited to 1MB - we not do read-ahead anymore?
> 
> It's hard for me to say without seeing the actual enablement patches,
> but filesystems are supposed to call mapping_set_folio_order_range to
> constrain the sizes of the folios that the pagecache requests.

I think large folios do not get enabled ye in this series. Could we have
a comment here that folio size is supposed to be restricted to
fc->max_pages? And wouldn't that be a case for unlikely()?


Thanks,
Bernd

Re: [PATCH v5 04/11] fuse: support large folios for writethrough writes

[Joanne Koong]

On Sun, May 4, 2025 at 11:40 AM Bernd Schubert
<bernd.schubert@fastmail.fm> wrote:
>
>
>
> On 4/26/25 02:08, Joanne Koong wrote:
> > Add support for folios larger than one page size for writethrough
> > writes.
> >
> > Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> > Reviewed-by: Jeff Layton <jlayton@kernel.org>
> > ---
> >  fs/fuse/file.c | 15 ++++++++++-----
> >  1 file changed, 10 insertions(+), 5 deletions(-)
> >
> > diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> > index edc86485065e..e44b6d26c1c6 100644
> > --- a/fs/fuse/file.c
> > +++ b/fs/fuse/file.c
> > @@ -1146,7 +1146,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
> >               size_t tmp;
> >               struct folio *folio;
> >               pgoff_t index = pos >> PAGE_SHIFT;
> > -             unsigned bytes = min(PAGE_SIZE - offset, num);
> > +             unsigned int bytes;
> > +             unsigned int folio_offset;
> >
> >   again:
> >               folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
> > @@ -1159,7 +1160,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
> >               if (mapping_writably_mapped(mapping))
> >                       flush_dcache_folio(folio);
> >
> > -             tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
> > +             folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
> > +             bytes = min(folio_size(folio) - folio_offset, num);
> > +
> > +             tmp = copy_folio_from_iter_atomic(folio, folio_offset, bytes, ii);
> >               flush_dcache_folio(folio);
> >
> >               if (!tmp) {f
> > @@ -1180,6 +1184,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
> >
> >               err = 0;
> >               ap->folios[ap->num_folios] = folio;
> > +             ap->descs[ap->num_folios].offset = folio_offset;
> >               ap->descs[ap->num_folios].length = tmp;
> >               ap->num_folios++;
> >
> > @@ -1187,11 +1192,11 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
> >               pos += tmp;
> >               num -= tmp;
> >               offset += tmp;
> > -             if (offset == PAGE_SIZE)
> > +             if (offset == folio_size(folio))
> >                       offset = 0;
> >
> > -             /* If we copied full page, mark it uptodate */
> > -             if (tmp == PAGE_SIZE)
> > +             /* If we copied full folio, mark it uptodate */
> > +             if (tmp == folio_size(folio))
> >                       folio_mark_uptodate(folio);
>
> Here am I confused. I think tmp can be a subpart of the folio, let's say
> the folio is 2MB and somehow the again loop would iterate through the
> folio in smaller steps. So the folio would be entirely written out, but
> tmp might not be folio_size? Doesn't this need to sum up tmp for per
> folio and then use that value?  And I actually wonder if we could use
> the above "(offset == folio_size(folio)" as well. At least if the
> initial offset for a folio is 0 it should work.
>

Hi Bernd,

Thanks for taking a look at this series and reviewing.

I don't think this scenario is possible. In copy_folio_iter_atomic()
which ends up calling into __copy_from_iter(), I don't see anywhere
where only the subpart of the folio can be copied out. The iter is a
ubuf, and from what I see, either copy_folio_iter_atomic() will return
0 or memcpy all requested bytes (unless bytes is greater than the
bytes contained in the iter, which isn't possible here) into the
folio.

Thanks,
Joanne

>
> Thanks,
> Bernd
>
> >
> >               if (folio_test_uptodate(folio)) {
>

Re: [PATCH v5 09/11] fuse: support large folios for readahead

[Joanne Koong]

On Mon, May 5, 2025 at 8:23 AM Bernd Schubert
<bernd.schubert@fastmail.fm> wrote:
>
>
>
> On 5/5/25 16:40, Darrick J. Wong wrote:
> > On Sun, May 04, 2025 at 09:13:44PM +0200, Bernd Schubert wrote:
> >>
> >>
> >> On 4/26/25 02:08, Joanne Koong wrote:
> >>> Add support for folios larger than one page size for readahead.
> >>>
> >>> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> >>> Reviewed-by: Jeff Layton <jlayton@kernel.org>
> >>> ---
> >>>  fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
> >>>  1 file changed, 27 insertions(+), 9 deletions(-)
> >>>
> >>> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> >>> index 1d38486fae50..9a31f2a516b9 100644
> >>> --- a/fs/fuse/file.c
> >>> +++ b/fs/fuse/file.c
> >>> @@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
> >>>     fuse_io_free(ia);
> >>>  }
> >>>
> >>> -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
> >>> +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
> >>> +                           unsigned int count)
> >>>  {
> >>>     struct fuse_file *ff = file->private_data;
> >>>     struct fuse_mount *fm = ff->fm;
> >>>     struct fuse_args_pages *ap = &ia->ap;
> >>>     loff_t pos = folio_pos(ap->folios[0]);
> >>> -   /* Currently, all folios in FUSE are one page */
> >>> -   size_t count = ap->num_folios << PAGE_SHIFT;
> >>>     ssize_t res;
> >>>     int err;
> >>>
> >>> @@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
> >>>     struct inode *inode = rac->mapping->host;
> >>>     struct fuse_conn *fc = get_fuse_conn(inode);
> >>>     unsigned int max_pages, nr_pages;
> >>> +   struct folio *folio = NULL;
> >>>
> >>>     if (fuse_is_bad(inode))
> >>>             return;
> >>> @@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
> >>>     while (nr_pages) {
> >>>             struct fuse_io_args *ia;
> >>>             struct fuse_args_pages *ap;
> >>> -           struct folio *folio;
> >>>             unsigned cur_pages = min(max_pages, nr_pages);
> >>> +           unsigned int pages = 0;
> >>>
> >>>             if (fc->num_background >= fc->congestion_threshold &&
> >>>                 rac->ra->async_size >= readahead_count(rac))
> >>> @@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
> >>>
> >>>             ia = fuse_io_alloc(NULL, cur_pages);
> >>>             if (!ia)
> >>> -                   return;
> >>> +                   break;
> >>>             ap = &ia->ap;
> >>>
> >>> -           while (ap->num_folios < cur_pages) {
> >>> +           while (pages < cur_pages) {
> >>> +                   unsigned int folio_pages;
> >>> +
> >>>                     /*
> >>>                      * This returns a folio with a ref held on it.
> >>>                      * The ref needs to be held until the request is
> >>> @@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
> >>>                      * fuse_try_move_page()) drops the ref after it's
> >>>                      * replaced in the page cache.
> >>>                      */
> >>> -                   folio = __readahead_folio(rac);
> >>> +                   if (!folio)
> >>> +                           folio =  __readahead_folio(rac);
> >>> +
> >>> +                   folio_pages = folio_nr_pages(folio);
> >>> +                   if (folio_pages > cur_pages - pages)
> >>> +                           break;
> >>> +
> >>
> >> Hmm, so let's assume this would be a 2MB folio, but fc->max_pages is
> >> limited to 1MB - we not do read-ahead anymore?
> >
> > It's hard for me to say without seeing the actual enablement patches,
> > but filesystems are supposed to call mapping_set_folio_order_range to
> > constrain the sizes of the folios that the pagecache requests.

Yes, exactly. For enabling fuse, I envision adding something like this
in fuse_init_file_inode():

max_pages = min(min(fc->max_write, fc->max_read) >> PAGE_SHIFT, fc->max_pages);
max_order = ilog2(max_pages);
mapping_set_folio_order_range(inode->i_mapping, 0, max_order);

>
> I think large folios do not get enabled ye in this series. Could we have
> a comment here that folio size is supposed to be restricted to
> fc->max_pages? And wouldn't that be a case for unlikely()?

Large folios are not enabled yet in this series. The cover letter
explains a bit why,

"This does not yet switch fuse to using large folios. Using large folios in
fuse is dependent on adding granular dirty-page tracking. This will be done
in a separate patchset that will have fuse use iomap [1]. There also needs
to be a followup (also part of future work) for having dirty page balancing
not tank performance for unprivileged servers where bdi limits lead to subpar
throttling [1], before enabling large folios for fuse."

[1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a38pv3OgFZRfdTiDMXuPWuBgN8KY47XfOsYHj=N2wxAg@mail.gmail.com/#t

I'll add a comment about this in v6.

Thanks,
Joanne
>
>
> Thanks,
> Bernd

Re: [PATCH v5 10/11] fuse: optimize direct io large folios processing

[David Hildenbrand]

On 26.04.25 02:08, Joanne Koong wrote:
> Optimize processing folios larger than one page size for the direct io
> case. If contiguous pages are part of the same folio, collate the
> processing instead of processing each page in the folio separately.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Jeff Layton <jlayton@kernel.org>
> ---
>   fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
>   1 file changed, 41 insertions(+), 14 deletions(-)
> 
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 9a31f2a516b9..61eaec1c993b 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>   	}
>   
>   	while (nbytes < *nbytesp && nr_pages < max_pages) {
> -		unsigned nfolios, i;
> +		struct folio *prev_folio = NULL;
> +		unsigned npages, i;
>   		size_t start;
>   
>   		ret = iov_iter_extract_pages(ii, &pages,
> @@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>   
>   		nbytes += ret;
>   
> -		nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> +		npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
>   
> -		for (i = 0; i < nfolios; i++) {
> -			struct folio *folio = page_folio(pages[i]);
> -			unsigned int offset = start +
> -				(folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
> -			unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
> +		/*
> +		 * We must check each extracted page. We can't assume every page
> +		 * in a large folio is used. For example, userspace may mmap() a
> +		 * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
> +		 * a large folio, in which case the extracted pages could be
> +		 *
> +		 * folio A page 0
> +		 * folio A page 1
> +		 * folio B page 0
> +		 * folio A page 3
> +		 *
> +		 * where folio A belongs to the file and folio B is an anonymous
> +		 * COW page.
> +		 */
> +		for (i = 0; i < npages && ret; i++) {
> +			struct folio *folio;
> +			unsigned int offset;
> +			unsigned int len;
> +
> +			WARN_ON(!pages[i]);
> +			folio = page_folio(pages[i]);
> +
> +			len = min_t(unsigned int, ret, PAGE_SIZE - start);
> +
> +			if (folio == prev_folio && pages[i] != pages[i - 1]) {

I don't really understand the "pages[i] != pages[i - 1]" part.

Why would you have to equal page pointers in there?


Something that might be simpler to understand and implement would be using

	num_pages_contiguous()

from

	https://lore.kernel.org/all/20250704062602.33500-2-lizhe.67@bytedance.com/T/#u

and then just making sure that we don't exceed the current folio, if we 
ever get contiguous pages that cross a folio.


-- 
Cheers,

David / dhildenb

Re: [PATCH v5 10/11] fuse: optimize direct io large folios processing

[Joanne Koong]

On Fri, Jul 4, 2025 at 3:24 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 26.04.25 02:08, Joanne Koong wrote:
> > Optimize processing folios larger than one page size for the direct io
> > case. If contiguous pages are part of the same folio, collate the
> > processing instead of processing each page in the folio separately.
> >
> > Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> > Reviewed-by: Jeff Layton <jlayton@kernel.org>
> > ---
> >   fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
> >   1 file changed, 41 insertions(+), 14 deletions(-)
> >
> > diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> > index 9a31f2a516b9..61eaec1c993b 100644
> > --- a/fs/fuse/file.c
> > +++ b/fs/fuse/file.c
> > @@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
> >       }
> >
> >       while (nbytes < *nbytesp && nr_pages < max_pages) {
> > -             unsigned nfolios, i;
> > +             struct folio *prev_folio = NULL;
> > +             unsigned npages, i;
> >               size_t start;
> >
> >               ret = iov_iter_extract_pages(ii, &pages,
> > @@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
> >
> >               nbytes += ret;
> >
> > -             nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> > +             npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> >
> > -             for (i = 0; i < nfolios; i++) {
> > -                     struct folio *folio = page_folio(pages[i]);
> > -                     unsigned int offset = start +
> > -                             (folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
> > -                     unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
> > +             /*
> > +              * We must check each extracted page. We can't assume every page
> > +              * in a large folio is used. For example, userspace may mmap() a
> > +              * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
> > +              * a large folio, in which case the extracted pages could be
> > +              *
> > +              * folio A page 0
> > +              * folio A page 1
> > +              * folio B page 0
> > +              * folio A page 3
> > +              *
> > +              * where folio A belongs to the file and folio B is an anonymous
> > +              * COW page.
> > +              */
> > +             for (i = 0; i < npages && ret; i++) {
> > +                     struct folio *folio;
> > +                     unsigned int offset;
> > +                     unsigned int len;
> > +
> > +                     WARN_ON(!pages[i]);
> > +                     folio = page_folio(pages[i]);
> > +
> > +                     len = min_t(unsigned int, ret, PAGE_SIZE - start);
> > +
> > +                     if (folio == prev_folio && pages[i] != pages[i - 1]) {
>
> I don't really understand the "pages[i] != pages[i - 1]" part.
>
> Why would you have to equal page pointers in there?
>

The pages extracted are user pages from a userspace iovec. AFAICT,
there's the possibility, eg if userspace mmaps() the file with
copy-on-write, that the same physical page could back multiple
contiguous virtual addresses.

>
> Something that might be simpler to understand and implement would be using
>
>         num_pages_contiguous()
>
> from
>
>         https://lore.kernel.org/all/20250704062602.33500-2-lizhe.67@bytedance.com/T/#u
>
> and then just making sure that we don't exceed the current folio, if we
> ever get contiguous pages that cross a folio.

Thanks for the link. I think here it's common that the pages array
would hold pages from multiple different folios, so maybe a new helper
num_pages_contiguous_folio() would be useful to return back the number
of contiguous pages that are within the scope of the same folio.


Thanks,
Joanne
>
>
> --
> Cheers,
>
> David / dhildenb
>

Re: [PATCH v5 10/11] fuse: optimize direct io large folios processing

[David Hildenbrand]

On 08.07.25 01:27, Joanne Koong wrote:
> On Fri, Jul 4, 2025 at 3:24 AM David Hildenbrand <david@redhat.com> wrote:
>>
>> On 26.04.25 02:08, Joanne Koong wrote:
>>> Optimize processing folios larger than one page size for the direct io
>>> case. If contiguous pages are part of the same folio, collate the
>>> processing instead of processing each page in the folio separately.
>>>
>>> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
>>> Reviewed-by: Jeff Layton <jlayton@kernel.org>
>>> ---
>>>    fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
>>>    1 file changed, 41 insertions(+), 14 deletions(-)
>>>
>>> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
>>> index 9a31f2a516b9..61eaec1c993b 100644
>>> --- a/fs/fuse/file.c
>>> +++ b/fs/fuse/file.c
>>> @@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>>>        }
>>>
>>>        while (nbytes < *nbytesp && nr_pages < max_pages) {
>>> -             unsigned nfolios, i;
>>> +             struct folio *prev_folio = NULL;
>>> +             unsigned npages, i;
>>>                size_t start;
>>>
>>>                ret = iov_iter_extract_pages(ii, &pages,
>>> @@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
>>>
>>>                nbytes += ret;
>>>
>>> -             nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
>>> +             npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
>>>
>>> -             for (i = 0; i < nfolios; i++) {
>>> -                     struct folio *folio = page_folio(pages[i]);
>>> -                     unsigned int offset = start +
>>> -                             (folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
>>> -                     unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
>>> +             /*
>>> +              * We must check each extracted page. We can't assume every page
>>> +              * in a large folio is used. For example, userspace may mmap() a
>>> +              * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
>>> +              * a large folio, in which case the extracted pages could be
>>> +              *
>>> +              * folio A page 0
>>> +              * folio A page 1
>>> +              * folio B page 0
>>> +              * folio A page 3
>>> +              *
>>> +              * where folio A belongs to the file and folio B is an anonymous
>>> +              * COW page.
>>> +              */
>>> +             for (i = 0; i < npages && ret; i++) {
>>> +                     struct folio *folio;
>>> +                     unsigned int offset;
>>> +                     unsigned int len;
>>> +
>>> +                     WARN_ON(!pages[i]);
>>> +                     folio = page_folio(pages[i]);
>>> +
>>> +                     len = min_t(unsigned int, ret, PAGE_SIZE - start);
>>> +
>>> +                     if (folio == prev_folio && pages[i] != pages[i - 1]) {
>>
>> I don't really understand the "pages[i] != pages[i - 1]" part.
>>
>> Why would you have to equal page pointers in there?
>>
> 
> The pages extracted are user pages from a userspace iovec. AFAICT,
> there's the possibility, eg if userspace mmaps() the file with
> copy-on-write, that the same physical page could back multiple
> contiguous virtual addresses.

Yes, I but I was rather curious why that would be a condition we are 
checking. It's quite the ... corner case :)

> 
>>
>> Something that might be simpler to understand and implement would be using
>>
>>          num_pages_contiguous()
>>
>> from
>>
>>          https://lore.kernel.org/all/20250704062602.33500-2-lizhe.67@bytedance.com/T/#u
>>
>> and then just making sure that we don't exceed the current folio, if we
>> ever get contiguous pages that cross a folio.
> 
> Thanks for the link. I think here it's common that the pages array
> would hold pages from multiple different folios, so maybe a new helper
> num_pages_contiguous_folio() would be useful to return back the number
> of contiguous pages that are within the scope of the same folio.

Yes, something like that can be useful.

-- 
Cheers,

David / dhildenb

Re: [PATCH v5 10/11] fuse: optimize direct io large folios processing

[Joanne Koong]

On Tue, Jul 8, 2025 at 9:05 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 08.07.25 01:27, Joanne Koong wrote:
> > On Fri, Jul 4, 2025 at 3:24 AM David Hildenbrand <david@redhat.com> wrote:
> >>
> >> On 26.04.25 02:08, Joanne Koong wrote:
> >>> Optimize processing folios larger than one page size for the direct io
> >>> case. If contiguous pages are part of the same folio, collate the
> >>> processing instead of processing each page in the folio separately.
> >>>
> >>> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> >>> Reviewed-by: Jeff Layton <jlayton@kernel.org>
> >>> ---
> >>>    fs/fuse/file.c | 55 +++++++++++++++++++++++++++++++++++++-------------
> >>>    1 file changed, 41 insertions(+), 14 deletions(-)
> >>>
> >>> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> >>> index 9a31f2a516b9..61eaec1c993b 100644
> >>> --- a/fs/fuse/file.c
> >>> +++ b/fs/fuse/file.c
> >>> @@ -1490,7 +1490,8 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
> >>>        }
> >>>
> >>>        while (nbytes < *nbytesp && nr_pages < max_pages) {
> >>> -             unsigned nfolios, i;
> >>> +             struct folio *prev_folio = NULL;
> >>> +             unsigned npages, i;
> >>>                size_t start;
> >>>
> >>>                ret = iov_iter_extract_pages(ii, &pages,
> >>> @@ -1502,23 +1503,49 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
> >>>
> >>>                nbytes += ret;
> >>>
> >>> -             nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> >>> +             npages = DIV_ROUND_UP(ret + start, PAGE_SIZE);
> >>>
> >>> -             for (i = 0; i < nfolios; i++) {
> >>> -                     struct folio *folio = page_folio(pages[i]);
> >>> -                     unsigned int offset = start +
> >>> -                             (folio_page_idx(folio, pages[i]) << PAGE_SHIFT);
> >>> -                     unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start);
> >>> +             /*
> >>> +              * We must check each extracted page. We can't assume every page
> >>> +              * in a large folio is used. For example, userspace may mmap() a
> >>> +              * file PROT_WRITE, MAP_PRIVATE, and then store to the middle of
> >>> +              * a large folio, in which case the extracted pages could be
> >>> +              *
> >>> +              * folio A page 0
> >>> +              * folio A page 1
> >>> +              * folio B page 0
> >>> +              * folio A page 3
> >>> +              *
> >>> +              * where folio A belongs to the file and folio B is an anonymous
> >>> +              * COW page.
> >>> +              */
> >>> +             for (i = 0; i < npages && ret; i++) {
> >>> +                     struct folio *folio;
> >>> +                     unsigned int offset;
> >>> +                     unsigned int len;
> >>> +
> >>> +                     WARN_ON(!pages[i]);
> >>> +                     folio = page_folio(pages[i]);
> >>> +
> >>> +                     len = min_t(unsigned int, ret, PAGE_SIZE - start);
> >>> +
> >>> +                     if (folio == prev_folio && pages[i] != pages[i - 1]) {
> >>
> >> I don't really understand the "pages[i] != pages[i - 1]" part.
> >>
> >> Why would you have to equal page pointers in there?
> >>
> >
> > The pages extracted are user pages from a userspace iovec. AFAICT,
> > there's the possibility, eg if userspace mmaps() the file with
> > copy-on-write, that the same physical page could back multiple
> > contiguous virtual addresses.
>
> Yes, I but I was rather curious why that would be a condition we are
> checking. It's quite the ... corner case :)
>

Agreed, definitely the corner case :)

In the fuse code, later on when the buffer gets copied to/from the
server, it'll use ap->descs[index].length as the number of bytes to
copy. If we don't check for this duplicate page corner case, then
it'll copy the wrong offsets in the folio, which may even lead to a
page fault if the folio is only one page. This buffer copying logic if
you're curious happens in fuse_copy_args() -> fuse_copy_folios() ->
fuse_copy_folio().

> >
> >>
> >> Something that might be simpler to understand and implement would be using
> >>
> >>          num_pages_contiguous()
> >>
> >> from
> >>
> >>          https://lore.kernel.org/all/20250704062602.33500-2-lizhe.67@bytedance.com/T/#u
> >>
> >> and then just making sure that we don't exceed the current folio, if we
> >> ever get contiguous pages that cross a folio.
> >
> > Thanks for the link. I think here it's common that the pages array
> > would hold pages from multiple different folios, so maybe a new helper
> > num_pages_contiguous_folio() would be useful to return back the number
> > of contiguous pages that are within the scope of the same folio.
>
> Yes, something like that can be useful.
>
> --
> Cheers,
>
> David / dhildenb
>
>