Merge tag 'fuse-update-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Support directly accessing host page cache from virtiofs. This can
   improve I/O performance for various workloads, as well as reducing
   the memory requirement by eliminating double caching. Thanks to Vivek
   Goyal for doing most of the work on this.

 - Allow automatic submounting inside virtiofs. This allows unique
   st_dev/ st_ino values to be assigned inside the guest to files
   residing on different filesystems on the host. Thanks to Max Reitz
   for the patches.

 - Fix an old use after free bug found by Pradeep P V K.

* tag 'fuse-update-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (25 commits)
  virtiofs: calculate number of scatter-gather elements accurately
  fuse: connection remove fix
  fuse: implement crossmounts
  fuse: Allow fuse_fill_super_common() for submounts
  fuse: split fuse_mount off of fuse_conn
  fuse: drop fuse_conn parameter where possible
  fuse: store fuse_conn in fuse_req
  fuse: add submount support to <uapi/linux/fuse.h>
  fuse: fix page dereference after free
  virtiofs: add logic to free up a memory range
  virtiofs: maintain a list of busy elements
  virtiofs: serialize truncate/punch_hole and dax fault path
  virtiofs: define dax address space operations
  virtiofs: add DAX mmap support
  virtiofs: implement dax read/write operations
  virtiofs: introduce setupmapping/removemapping commands
  virtiofs: implement FUSE_INIT map_alignment field
  virtiofs: keep a list of free dax memory ranges
  virtiofs: add a mount option to enable dax
  virtiofs: set up virtio_fs dax_device
  ...

Author: torvalds

Documentation/filesystems/fuse.rst

@@ -47,7 +47,7 @@ filesystems.  A good example is sshfs: a secure network filesystem
 using the sftp protocol.
 
 The userspace library and utilities are available from the
-`FUSE homepage: <http://fuse.sourceforge.net/>`_
+`FUSE homepage: <https://github.com/libfuse/>`_
 
 Filesystem type
 ===============

MAINTAINERS

@@ -7238,7 +7238,7 @@ FUSE: FILESYSTEM IN USERSPACE
 M:	Miklos Szeredi <[email protected]>
 L:	[email protected]
 S:	Maintained
-W:	http://fuse.sourceforge.net/
+W:	https://github.com/libfuse/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git
 F:	Documentation/filesystems/fuse.rst
 F:	fs/fuse/

drivers/dax/super.c

@@ -46,7 +46,8 @@ EXPORT_SYMBOL_GPL(dax_read_unlock);
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 		pgoff_t *pgoff)
 {
-	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
+	sector_t start_sect = bdev ? get_start_sect(bdev) : 0;
+	phys_addr_t phys_off = (start_sect + sector) * 512;
 
 	if (pgoff)
 		*pgoff = PHYS_PFN(phys_off);

fs/dax.c

@@ -559,8 +559,11 @@ static void *grab_mapping_entry(struct xa_state *xas,
 }
 
 /**
- * dax_layout_busy_page - find first pinned page in @mapping
+ * dax_layout_busy_page_range - find first pinned page in @mapping
  * @mapping: address space to scan for a page with ref count > 1
+ * @start: Starting offset. Page containing 'start' is included.
+ * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
+ *       pages from 'start' till the end of file are included.
  *
  * DAX requires ZONE_DEVICE mapped pages. These pages are never
  * 'onlined' to the page allocator so they are considered idle when
@@ -573,12 +576,15 @@ static void *grab_mapping_entry(struct xa_state *xas,
  * to be able to run unmap_mapping_range() and subsequently not race
  * mapping_mapped() becoming true.
  */
-struct page *dax_layout_busy_page(struct address_space *mapping)
+struct page *dax_layout_busy_page_range(struct address_space *mapping,
+					loff_t start, loff_t end)
 {
-	XA_STATE(xas, &mapping->i_pages, 0);
 	void *entry;
 	unsigned int scanned = 0;
 	struct page *page = NULL;
+	pgoff_t start_idx = start >> PAGE_SHIFT;
+	pgoff_t end_idx;
+	XA_STATE(xas, &mapping->i_pages, start_idx);
 
 	/*
 	 * In the 'limited' case get_user_pages() for dax is disabled.
@@ -589,22 +595,27 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
 		return NULL;
 
+	/* If end == LLONG_MAX, all pages from start to till end of file */
+	if (end == LLONG_MAX)
+		end_idx = ULONG_MAX;
+	else
+		end_idx = end >> PAGE_SHIFT;
 	/*
 	 * If we race get_user_pages_fast() here either we'll see the
 	 * elevated page count in the iteration and wait, or
 	 * get_user_pages_fast() will see that the page it took a reference
 	 * against is no longer mapped in the page tables and bail to the
 	 * get_user_pages() slow path.  The slow path is protected by
 	 * pte_lock() and pmd_lock(). New references are not taken without
-	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * holding those locks, and unmap_mapping_pages() will not zero the
 	 * pte or pmd without holding the respective lock, so we are
 	 * guaranteed to either see new references or prevent new
 	 * references from being established.
 	 */
-	unmap_mapping_range(mapping, 0, 0, 0);
+	unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);
 
 	xas_lock_irq(&xas);
-	xas_for_each(&xas, entry, ULONG_MAX) {
+	xas_for_each(&xas, entry, end_idx) {
 		if (WARN_ON_ONCE(!xa_is_value(entry)))
 			continue;
 		if (unlikely(dax_is_locked(entry)))
@@ -625,6 +636,12 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	xas_unlock_irq(&xas);
 	return page;
 }
+EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);
+
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
+}
 EXPORT_SYMBOL_GPL(dax_layout_busy_page);
 
 static int __dax_invalidate_entry(struct address_space *mapping,

fs/fuse/Kconfig

@@ -8,7 +8,7 @@ config FUSE_FS
 
 	  There's also a companion library: libfuse2.  This library is available
 	  from the FUSE homepage:
-	  <http://fuse.sourceforge.net/>
+	  <https://github.com/libfuse/>
 	  although chances are your distribution already has that library
 	  installed if you've installed the "fuse" package itself.
 
@@ -38,3 +38,17 @@ config VIRTIO_FS
 
 	  If you want to share files between guests or with the host, answer Y
 	  or M.
+
+config FUSE_DAX
+	bool "Virtio Filesystem Direct Host Memory Access support"
+	default y
+	select INTERVAL_TREE
+	depends on VIRTIO_FS
+	depends on FS_DAX
+	depends on DAX_DRIVER
+	help
+	  This allows bypassing guest page cache and allows mapping host page
+	  cache directly in guest address space.
+
+	  If you want to allow mounting a Virtio Filesystem with the "dax"
+	  option, answer Y.

fs/fuse/Makefile

@@ -7,5 +7,7 @@ obj-$(CONFIG_FUSE_FS) += fuse.o
 obj-$(CONFIG_CUSE) += cuse.o
 obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
 
-fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
-virtiofs-y += virtio_fs.o
+fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+fuse-$(CONFIG_FUSE_DAX) += dax.o
+
+virtiofs-y := virtio_fs.o

fs/fuse/control.c

@@ -164,6 +164,7 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
 {
 	unsigned val;
 	struct fuse_conn *fc;
+	struct fuse_mount *fm;
 	ssize_t ret;
 
 	ret = fuse_conn_limit_write(file, buf, count, ppos, &val,
@@ -174,18 +175,27 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
 	if (!fc)
 		goto out;
 
+	down_read(&fc->killsb);
 	spin_lock(&fc->bg_lock);
 	fc->congestion_threshold = val;
-	if (fc->sb) {
+
+	/*
+	 * Get any fuse_mount belonging to this fuse_conn; s_bdi is
+	 * shared between all of them
+	 */
+
+	if (!list_empty(&fc->mounts)) {
+		fm = list_first_entry(&fc->mounts, struct fuse_mount, fc_entry);
 		if (fc->num_background < fc->congestion_threshold) {
-			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
-			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
+			clear_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
+			clear_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
 		} else {
-			set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
-			set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
+			set_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
+			set_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
 		}
 	}
 	spin_unlock(&fc->bg_lock);
+	up_read(&fc->killsb);
 	fuse_conn_put(fc);
 out:
 	return ret;

fs/fuse/cuse.c

@@ -57,6 +57,7 @@
 
 struct cuse_conn {
 	struct list_head	list;	/* linked on cuse_conntbl */
+	struct fuse_mount	fm;	/* Dummy mount referencing fc */
 	struct fuse_conn	fc;	/* fuse connection */
 	struct cdev		*cdev;	/* associated character device */
 	struct device		*dev;	/* device representing @cdev */
@@ -134,7 +135,7 @@ static int cuse_open(struct inode *inode, struct file *file)
 	 * Generic permission check is already done against the chrdev
 	 * file, proceed to open.
 	 */
-	rc = fuse_do_open(&cc->fc, 0, file, 0);
+	rc = fuse_do_open(&cc->fm, 0, file, 0);
 	if (rc)
 		fuse_conn_put(&cc->fc);
 	return rc;
@@ -143,10 +144,10 @@ static int cuse_open(struct inode *inode, struct file *file)
 static int cuse_release(struct inode *inode, struct file *file)
 {
 	struct fuse_file *ff = file->private_data;
-	struct fuse_conn *fc = ff->fc;
+	struct fuse_mount *fm = ff->fm;
 
 	fuse_sync_release(NULL, ff, file->f_flags);
-	fuse_conn_put(fc);
+	fuse_conn_put(fm->fc);
 
 	return 0;
 }
@@ -155,7 +156,7 @@ static long cuse_file_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
 	struct fuse_file *ff = file->private_data;
-	struct cuse_conn *cc = fc_to_cc(ff->fc);
+	struct cuse_conn *cc = fc_to_cc(ff->fm->fc);
 	unsigned int flags = 0;
 
 	if (cc->unrestricted_ioctl)
@@ -168,7 +169,7 @@ static long cuse_file_compat_ioctl(struct file *file, unsigned int cmd,
 				   unsigned long arg)
 {
 	struct fuse_file *ff = file->private_data;
-	struct cuse_conn *cc = fc_to_cc(ff->fc);
+	struct cuse_conn *cc = fc_to_cc(ff->fm->fc);
 	unsigned int flags = FUSE_IOCTL_COMPAT;
 
 	if (cc->unrestricted_ioctl)
@@ -313,9 +314,10 @@ struct cuse_init_args {
  * required data structures for it.  Please read the comment at the
  * top of this file for high level overview.
  */
-static void cuse_process_init_reply(struct fuse_conn *fc,
+static void cuse_process_init_reply(struct fuse_mount *fm,
 				    struct fuse_args *args, int error)
 {
+	struct fuse_conn *fc = fm->fc;
 	struct cuse_init_args *ia = container_of(args, typeof(*ia), ap.args);
 	struct fuse_args_pages *ap = &ia->ap;
 	struct cuse_conn *cc = fc_to_cc(fc), *pos;
@@ -424,7 +426,7 @@ static int cuse_send_init(struct cuse_conn *cc)
 {
 	int rc;
 	struct page *page;
-	struct fuse_conn *fc = &cc->fc;
+	struct fuse_mount *fm = &cc->fm;
 	struct cuse_init_args *ia;
 	struct fuse_args_pages *ap;
 
@@ -460,7 +462,7 @@ static int cuse_send_init(struct cuse_conn *cc)
 	ia->desc.length = ap->args.out_args[1].size;
 	ap->args.end = cuse_process_init_reply;
 
-	rc = fuse_simple_background(fc, &ap->args, GFP_KERNEL);
+	rc = fuse_simple_background(fm, &ap->args, GFP_KERNEL);
 	if (rc) {
 		kfree(ia);
 err_free_page:
@@ -506,7 +508,8 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	 * Limit the cuse channel to requests that can
 	 * be represented in file->f_cred->user_ns.
 	 */
-	fuse_conn_init(&cc->fc, file->f_cred->user_ns, &fuse_dev_fiq_ops, NULL);
+	fuse_conn_init(&cc->fc, &cc->fm, file->f_cred->user_ns,
+		       &fuse_dev_fiq_ops, NULL);
 
 	fud = fuse_dev_alloc_install(&cc->fc);
 	if (!fud) {