Merge tag 'fuse-update-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Add page -> folio conversions (Joanne Koong, Josef Bacik)

 - Allow max size of fuse requests to be configurable with a sysctl
   (Joanne Koong)

 - Allow FOPEN_DIRECT_IO to take advantage of async code path (yangyun)

 - Fix large kernel reads (like a module load) in virtio_fs (Hou Tao)

 - Fix attribute inconsistency in case readdirplus (and plain lookup in
   corner cases) is racing with inode eviction (Zhang Tianci)

 - Fix a WARN_ON triggered by virtio_fs (Asahi Lina)

* tag 'fuse-update-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (30 commits)
  virtiofs: dax: remove ->writepages() callback
  fuse: check attributes staleness on fuse_iget()
  fuse: remove pages for requests and exclusively use folios
  fuse: convert direct io to use folios
  mm/writeback: add folio_mark_dirty_lock()
  fuse: convert writebacks to use folios
  fuse: convert retrieves to use folios
  fuse: convert ioctls to use folios
  fuse: convert writes (non-writeback) to use folios
  fuse: convert reads to use folios
  fuse: convert readdir to use folios
  fuse: convert readlink to use folios
  fuse: convert cuse to use folios
  fuse: add support in virtio for requests using folios
  fuse: support folios in struct fuse_args_pages and fuse_copy_pages()
  fuse: convert fuse_notify_store to use folios
  fuse: convert fuse_retrieve to use folios
  fuse: use the folio based vmstat helpers
  fuse: convert fuse_writepage_need_send to take a folio
  fuse: convert fuse_do_readpage to use folios
  ...

Author: torvalds

Documentation/admin-guide/sysctl/fs.rst

@@ -337,3 +337,13 @@ Each "watch" costs roughly 90 bytes on a 32-bit kernel, and roughly 160 bytes
 on a 64-bit one.
 The current default value for ``max_user_watches`` is 4% of the
 available low memory, divided by the "watch" cost in bytes.
+
+5. /proc/sys/fs/fuse - Configuration options for FUSE filesystems
+=====================================================================
+
+This directory contains the following configuration options for FUSE
+filesystems:
+
+``/proc/sys/fs/fuse/max_pages_limit`` is a read/write file for
+setting/getting the maximum number of pages that can be used for servicing
+requests in FUSE.

fs/fuse/Makefile

@@ -14,5 +14,6 @@ fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o
 fuse-y += iomode.o
 fuse-$(CONFIG_FUSE_DAX) += dax.o
 fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
+fuse-$(CONFIG_SYSCTL) += sysctl.o
 
 virtiofs-y := virtio_fs.o

fs/fuse/cuse.c

@@ -303,8 +303,8 @@ struct cuse_init_args {
 	struct fuse_args_pages ap;
 	struct cuse_init_in in;
 	struct cuse_init_out out;
-	struct page *page;
-	struct fuse_page_desc desc;
+	struct folio *folio;
+	struct fuse_folio_desc desc;
 };
 
 /**
@@ -326,7 +326,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	struct fuse_args_pages *ap = &ia->ap;
 	struct cuse_conn *cc = fc_to_cc(fc), *pos;
 	struct cuse_init_out *arg = &ia->out;
-	struct page *page = ap->pages[0];
+	struct folio *folio = ap->folios[0];
 	struct cuse_devinfo devinfo = { };
 	struct device *dev;
 	struct cdev *cdev;
@@ -343,7 +343,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	/* parse init reply */
 	cc->unrestricted_ioctl = arg->flags & CUSE_UNRESTRICTED_IOCTL;
 
-	rc = cuse_parse_devinfo(page_address(page), ap->args.out_args[1].size,
+	rc = cuse_parse_devinfo(folio_address(folio), ap->args.out_args[1].size,
 				&devinfo);
 	if (rc)
 		goto err;
@@ -411,7 +411,7 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 	kobject_uevent(&dev->kobj, KOBJ_ADD);
 out:
 	kfree(ia);
-	__free_page(page);
+	folio_put(folio);
 	return;
 
 err_cdev:
@@ -429,21 +429,22 @@ static void cuse_process_init_reply(struct fuse_mount *fm,
 static int cuse_send_init(struct cuse_conn *cc)
 {
 	int rc;
-	struct page *page;
+	struct folio *folio;
 	struct fuse_mount *fm = &cc->fm;
 	struct cuse_init_args *ia;
 	struct fuse_args_pages *ap;
 
 	BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
 
 	rc = -ENOMEM;
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page)
+
+	folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, 0);
+	if (!folio)
 		goto err;
 
 	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
 	if (!ia)
-		goto err_free_page;
+		goto err_free_folio;
 
 	ap = &ia->ap;
 	ia->in.major = FUSE_KERNEL_VERSION;
@@ -459,18 +460,18 @@ static int cuse_send_init(struct cuse_conn *cc)
 	ap->args.out_args[1].size = CUSE_INIT_INFO_MAX;
 	ap->args.out_argvar = true;
 	ap->args.out_pages = true;
-	ap->num_pages = 1;
-	ap->pages = &ia->page;
+	ap->num_folios = 1;
+	ap->folios = &ia->folio;
 	ap->descs = &ia->desc;
-	ia->page = page;
+	ia->folio = folio;
 	ia->desc.length = ap->args.out_args[1].size;
 	ap->args.end = cuse_process_init_reply;
 
 	rc = fuse_simple_background(fm, &ap->args, GFP_KERNEL);
 	if (rc) {
 		kfree(ia);
-err_free_page:
-		__free_page(page);
+err_free_folio:
+		folio_put(folio);
 	}
 err:
 	return rc;

fs/fuse/dax.c

@@ -774,16 +774,6 @@ ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 
-static int fuse_dax_writepages(struct address_space *mapping,
-			       struct writeback_control *wbc)
-{
-
-	struct inode *inode = mapping->host;
-	struct fuse_conn *fc = get_fuse_conn(inode);
-
-	return dax_writeback_mapping_range(mapping, fc->dax->dev, wbc);
-}
-
 static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf, unsigned int order,
 		bool write)
 {
@@ -1323,7 +1313,6 @@ bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi)
 }
 
 static const struct address_space_operations fuse_dax_file_aops  = {
-	.writepages	= fuse_dax_writepages,
 	.direct_IO	= noop_direct_IO,
 	.dirty_folio	= noop_dirty_folio,
 };

fs/fuse/dev.c

@@ -1028,17 +1028,27 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
 	struct fuse_req *req = cs->req;
 	struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args);
 
-
-	for (i = 0; i < ap->num_pages && (nbytes || zeroing); i++) {
+	for (i = 0; i < ap->num_folios && (nbytes || zeroing); i++) {
 		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, &ap->pages[i], offset, count, zeroing);
+		err = fuse_copy_page(cs, &pagep, 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;
 }
@@ -1654,24 +1664,25 @@ 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;
 
-		err = -ENOMEM;
-		page = find_or_create_page(mapping, index,
-					   mapping_gfp_mask(mapping));
-		if (!page)
+		folio = filemap_grab_folio(mapping, index);
+		err = PTR_ERR(folio);
+		if (IS_ERR(folio))
 			goto out_iput;
 
-		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
+		page = &folio->page;
+		this_num = min_t(unsigned, num, folio_size(folio) - offset);
 		err = fuse_copy_page(cs, &page, offset, this_num, 0);
-		if (!PageUptodate(page) && !err && offset == 0 &&
-		    (this_num == PAGE_SIZE || file_size == end)) {
-			zero_user_segment(page, this_num, PAGE_SIZE);
-			SetPageUptodate(page);
+		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));
+			folio_mark_uptodate(folio);
 		}
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 
 		if (err)
 			goto out_iput;
@@ -1703,7 +1714,7 @@ static void fuse_retrieve_end(struct fuse_mount *fm, struct fuse_args *args,
 	struct fuse_retrieve_args *ra =
 		container_of(args, typeof(*ra), ap.args);
 
-	release_pages(ra->ap.pages, ra->ap.num_pages);
+	release_pages(ra->ap.folios, ra->ap.num_folios);
 	kfree(ra);
 }
 
@@ -1717,7 +1728,7 @@ 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;
+	unsigned int num_pages, cur_pages = 0;
 	struct fuse_conn *fc = fm->fc;
 	struct fuse_retrieve_args *ra;
 	size_t args_size = sizeof(*ra);
@@ -1736,15 +1747,15 @@ 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);
 
-	args_size += num_pages * (sizeof(ap->pages[0]) + sizeof(ap->descs[0]));
+	args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->descs[0]));
 
 	ra = kzalloc(args_size, GFP_KERNEL);
 	if (!ra)
 		return -ENOMEM;
 
 	ap = &ra->ap;
-	ap->pages = (void *) (ra + 1);
-	ap->descs = (void *) (ap->pages + num_pages);
+	ap->folios = (void *) (ra + 1);
+	ap->descs = (void *) (ap->folios + num_pages);
 
 	args = &ap->args;
 	args->nodeid = outarg->nodeid;
@@ -1755,19 +1766,20 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	index = outarg->offset >> PAGE_SHIFT;
 
-	while (num && ap->num_pages < num_pages) {
-		struct page *page;
+	while (num && cur_pages < num_pages) {
+		struct folio *folio;
 		unsigned int this_num;
 
-		page = find_get_page(mapping, index);
-		if (!page)
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio))
 			break;
 
 		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
-		ap->pages[ap->num_pages] = page;
-		ap->descs[ap->num_pages].offset = offset;
-		ap->descs[ap->num_pages].length = this_num;
-		ap->num_pages++;
+		ap->folios[ap->num_folios] = folio;
+		ap->descs[ap->num_folios].offset = offset;
+		ap->descs[ap->num_folios].length = this_num;
+		ap->num_folios++;
+		cur_pages++;
 
 		offset = 0;
 		num -= this_num;

fs/fuse/dir.c

@@ -366,7 +366,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 	struct fuse_mount *fm = get_fuse_mount_super(sb);
 	FUSE_ARGS(args);
 	struct fuse_forget_link *forget;
-	u64 attr_version;
+	u64 attr_version, evict_ctr;
 	int err;
 
 	*inode = NULL;
@@ -381,6 +381,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 		goto out;
 
 	attr_version = fuse_get_attr_version(fm->fc);
+	evict_ctr = fuse_get_evict_ctr(fm->fc);
 
 	fuse_lookup_init(fm->fc, &args, nodeid, name, outarg);
 	err = fuse_simple_request(fm, &args);
@@ -398,7 +399,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 
 	*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
 			   &outarg->attr, ATTR_TIMEOUT(outarg),
-			   attr_version);
+			   attr_version, evict_ctr);
 	err = -ENOMEM;
 	if (!*inode) {
 		fuse_queue_forget(fm->fc, forget, outarg->nodeid, 1);
@@ -691,7 +692,7 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	ff->nodeid = outentry.nodeid;
 	ff->open_flags = outopenp->open_flags;
 	inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
-			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0);
+			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0, 0);
 	if (!inode) {
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(NULL, ff, flags);
@@ -822,7 +823,7 @@ static int create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm,
 		goto out_put_forget_req;
 
 	inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
-			  &outarg.attr, ATTR_TIMEOUT(&outarg), 0);
+			  &outarg.attr, ATTR_TIMEOUT(&outarg), 0, 0);
 	if (!inode) {
 		fuse_queue_forget(fm->fc, forget, outarg.nodeid, 1);
 		return -ENOMEM;
@@ -1585,13 +1586,13 @@ static int fuse_permission(struct mnt_idmap *idmap,
 	return err;
 }
 
-static int fuse_readlink_page(struct inode *inode, struct page *page)
+static int fuse_readlink_page(struct inode *inode, struct folio *folio)
 {
 	struct fuse_mount *fm = get_fuse_mount(inode);
-	struct fuse_page_desc desc = { .length = PAGE_SIZE - 1 };
+	struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
 	struct fuse_args_pages ap = {
-		.num_pages = 1,
-		.pages = &page,
+		.num_folios = 1,
+		.folios = &folio,
 		.descs = &desc,
 	};
 	char *link;
@@ -1614,7 +1615,7 @@ static int fuse_readlink_page(struct inode *inode, struct page *page)
 	if (WARN_ON(res >= PAGE_SIZE))
 		return -EIO;
 
-	link = page_address(page);
+	link = folio_address(folio);
 	link[res] = '\0';
 
 	return 0;
@@ -1624,7 +1625,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 				 struct delayed_call *callback)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
-	struct page *page;
+	struct folio *folio;
 	int err;
 
 	err = -EIO;
@@ -1638,20 +1639,20 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 	if (!dentry)
 		goto out_err;
 
-	page = alloc_page(GFP_KERNEL);
+	folio = folio_alloc(GFP_KERNEL, 0);
 	err = -ENOMEM;
-	if (!page)
+	if (!folio)
 		goto out_err;
 
-	err = fuse_readlink_page(inode, page);
+	err = fuse_readlink_page(inode, folio);
 	if (err) {
-		__free_page(page);
+		folio_put(folio);
 		goto out_err;
 	}
 
-	set_delayed_call(callback, page_put_link, page);
+	set_delayed_call(callback, page_put_link, &folio->page);
 
-	return page_address(page);
+	return folio_address(folio);
 
 out_err:
 	return ERR_PTR(err);
@@ -2028,7 +2029,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 
 	fuse_change_attributes_common(inode, &outarg.attr, NULL,
 				      ATTR_TIMEOUT(&outarg),
-				      fuse_get_cache_mask(inode));
+				      fuse_get_cache_mask(inode), 0);
 	oldsize = inode->i_size;
 	/* see the comment in fuse_change_attributes() */
 	if (!is_wb || is_truncate)
@@ -2231,7 +2232,7 @@ 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->page);
+	int err = fuse_readlink_page(folio->mapping->host, folio);
 
 	if (!err)
 		folio_mark_uptodate(folio);