Merge tag 'fuse-update-5.17' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Fix a regression introduced in 5.15

 - Extend the size of the FUSE_INIT request to accommodate for more
   flags. There's a slight possibility of a regression for obscure fuse
   servers; if this happens, then more complexity will need to be added
   to the protocol

 - Allow the DAX property to be controlled by the server on a per-inode
   basis in virtiofs

 - Allow sending security context to the server when creating a file or
   directory

* tag 'fuse-update-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  Documentation/filesystem/dax: DAX on virtiofs
  fuse: mark inode DONT_CACHE when per inode DAX hint changes
  fuse: negotiate per inode DAX in FUSE_INIT
  fuse: enable per inode DAX
  fuse: support per inode DAX in fuse protocol
  fuse: make DAX mount option a tri-state
  fuse: add fuse_should_enable_dax() helper
  fuse: Pass correct lend value to filemap_write_and_wait_range()
  fuse: send security context of inode on file
  fuse: extend init flags

Documentation/filesystems/dax.rst

@@ -23,8 +23,8 @@ on it as usual.  The `DAX` code currently only supports files with a block
 size equal to your kernel's `PAGE_SIZE`, so you may need to specify a block
 size when creating the filesystem.
 
-Currently 3 filesystems support `DAX`: ext2, ext4 and xfs.  Enabling `DAX` on them
-is different.
+Currently 4 filesystems support `DAX`: ext2, ext4, xfs and virtiofs.
+Enabling `DAX` on them is different.
 
 Enabling DAX on ext2
 --------------------
@@ -168,6 +168,22 @@ if the underlying media does not support dax and/or the filesystem is
 overridden with a mount option.
 
 
+Enabling DAX on virtiofs
+----------------------------
+The semantic of DAX on virtiofs is basically equal to that on ext4 and xfs,
+except that when '-o dax=inode' is specified, virtiofs client derives the hint
+whether DAX shall be enabled or not from virtiofs server through FUSE protocol,
+rather than the persistent `FS_XFLAG_DAX` flag. That is, whether DAX shall be
+enabled or not is completely determined by virtiofs server, while virtiofs
+server itself may deploy various algorithm making this decision, e.g. depending
+on the persistent `FS_XFLAG_DAX` flag on the host.
+
+It is still supported to set or clear persistent `FS_XFLAG_DAX` flag inside
+guest, but it is not guaranteed that DAX will be enabled or disabled for
+corresponding file then. Users inside guest still need to call statx(2) and
+check the statx flag `STATX_ATTR_DAX` to see if DAX is enabled for this file.
+
+
 Implementation Tips for Block Driver Writers
 --------------------------------------------
 

fs/fuse/dax.c

@@ -1279,11 +1279,14 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
 	return ret;
 }
 
-int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
+int fuse_dax_conn_alloc(struct fuse_conn *fc, enum fuse_dax_mode dax_mode,
+			struct dax_device *dax_dev)
 {
 	struct fuse_conn_dax *fcd;
 	int err;
 
+	fc->dax_mode = dax_mode;
+
 	if (!dax_dev)
 		return 0;
 
@@ -1327,17 +1330,46 @@ static const struct address_space_operations fuse_dax_file_aops  = {
 	.invalidatepage	= noop_invalidatepage,
 };
 
-void fuse_dax_inode_init(struct inode *inode)
+static bool fuse_should_enable_dax(struct inode *inode, unsigned int flags)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
+	enum fuse_dax_mode dax_mode = fc->dax_mode;
+
+	if (dax_mode == FUSE_DAX_NEVER)
+		return false;
 
+	/*
+	 * fc->dax may be NULL in 'inode' mode when filesystem device doesn't
+	 * support DAX, in which case it will silently fallback to 'never' mode.
+	 */
 	if (!fc->dax)
+		return false;
+
+	if (dax_mode == FUSE_DAX_ALWAYS)
+		return true;
+
+	/* dax_mode is FUSE_DAX_INODE* */
+	return fc->inode_dax && (flags & FUSE_ATTR_DAX);
+}
+
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags)
+{
+	if (!fuse_should_enable_dax(inode, flags))
 		return;
 
 	inode->i_flags |= S_DAX;
 	inode->i_data.a_ops = &fuse_dax_file_aops;
 }
 
+void fuse_dax_dontcache(struct inode *inode, unsigned int flags)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+
+	if (fuse_is_inode_dax_mode(fc->dax_mode) &&
+	    ((bool) IS_DAX(inode) != (bool) (flags & FUSE_ATTR_DAX)))
+		d_mark_dontcache(inode);
+}
+
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment)
 {
 	if (fc->dax && (map_alignment > FUSE_DAX_SHIFT)) {

fs/fuse/dir.c

@@ -17,6 +17,9 @@
 #include <linux/xattr.h>
 #include <linux/iversion.h>
 #include <linux/posix_acl.h>
+#include <linux/security.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
 
 static void fuse_advise_use_readdirplus(struct inode *dir)
 {
@@ -456,6 +459,62 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	return ERR_PTR(err);
 }
 
+static int get_security_context(struct dentry *entry, umode_t mode,
+				void **security_ctx, u32 *security_ctxlen)
+{
+	struct fuse_secctx *fctx;
+	struct fuse_secctx_header *header;
+	void *ctx = NULL, *ptr;
+	u32 ctxlen, total_len = sizeof(*header);
+	int err, nr_ctx = 0;
+	const char *name;
+	size_t namelen;
+
+	err = security_dentry_init_security(entry, mode, &entry->d_name,
+					    &name, &ctx, &ctxlen);
+	if (err) {
+		if (err != -EOPNOTSUPP)
+			goto out_err;
+		/* No LSM is supporting this security hook. Ignore error */
+		ctxlen = 0;
+		ctx = NULL;
+	}
+
+	if (ctxlen) {
+		nr_ctx = 1;
+		namelen = strlen(name) + 1;
+		err = -EIO;
+		if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX))
+			goto out_err;
+		total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen);
+	}
+
+	err = -ENOMEM;
+	header = ptr = kzalloc(total_len, GFP_KERNEL);
+	if (!ptr)
+		goto out_err;
+
+	header->nr_secctx = nr_ctx;
+	header->size = total_len;
+	ptr += sizeof(*header);
+	if (nr_ctx) {
+		fctx = ptr;
+		fctx->size = ctxlen;
+		ptr += sizeof(*fctx);
+
+		strcpy(ptr, name);
+		ptr += namelen;
+
+		memcpy(ptr, ctx, ctxlen);
+	}
+	*security_ctxlen = total_len;
+	*security_ctx = header;
+	err = 0;
+out_err:
+	kfree(ctx);
+	return err;
+}
+
 /*
  * Atomic create+open operation
  *
@@ -476,6 +535,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	struct fuse_entry_out outentry;
 	struct fuse_inode *fi;
 	struct fuse_file *ff;
+	void *security_ctx = NULL;
+	u32 security_ctxlen;
 
 	/* Userspace expects S_IFREG in create mode */
 	BUG_ON((mode & S_IFMT) != S_IFREG);
@@ -517,7 +578,20 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	args.out_args[0].value = &outentry;
 	args.out_args[1].size = sizeof(outopen);
 	args.out_args[1].value = &outopen;
+
+	if (fm->fc->init_security) {
+		err = get_security_context(entry, mode, &security_ctx,
+					   &security_ctxlen);
+		if (err)
+			goto out_put_forget_req;
+
+		args.in_numargs = 3;
+		args.in_args[2].size = security_ctxlen;
+		args.in_args[2].value = security_ctx;
+	}
+
 	err = fuse_simple_request(fm, &args);
+	kfree(security_ctx);
 	if (err)
 		goto out_free_ff;
 
@@ -620,6 +694,8 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
 	struct dentry *d;
 	int err;
 	struct fuse_forget_link *forget;
+	void *security_ctx = NULL;
+	u32 security_ctxlen;
 
 	if (fuse_is_bad(dir))
 		return -EIO;
@@ -633,7 +709,22 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
 	args->out_numargs = 1;
 	args->out_args[0].size = sizeof(outarg);
 	args->out_args[0].value = &outarg;
+
+	if (fm->fc->init_security && args->opcode != FUSE_LINK) {
+		err = get_security_context(entry, mode, &security_ctx,
+					   &security_ctxlen);
+		if (err)
+			goto out_put_forget_req;
+
+		BUG_ON(args->in_numargs != 2);
+
+		args->in_numargs = 3;
+		args->in_args[2].size = security_ctxlen;
+		args->in_args[2].value = security_ctx;
+	}
+
 	err = fuse_simple_request(fm, args);
+	kfree(security_ctx);
 	if (err)
 		goto out_put_forget_req;
 

fs/fuse/file.c

@@ -2910,7 +2910,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static int fuse_writeback_range(struct inode *inode, loff_t start, loff_t end)
 {
-	int err = filemap_write_and_wait_range(inode->i_mapping, start, -1);
+	int err = filemap_write_and_wait_range(inode->i_mapping, start, LLONG_MAX);
 
 	if (!err)
 		fuse_sync_writes(inode);
@@ -3169,7 +3169,7 @@ static const struct address_space_operations fuse_file_aops  = {
 	.write_end	= fuse_write_end,
 };
 
-void fuse_init_file_inode(struct inode *inode)
+void fuse_init_file_inode(struct inode *inode, unsigned int flags)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
@@ -3183,5 +3183,5 @@ void fuse_init_file_inode(struct inode *inode)
 	fi->writepages = RB_ROOT;
 
 	if (IS_ENABLED(CONFIG_FUSE_DAX))
-		fuse_dax_inode_init(inode);
+		fuse_dax_inode_init(inode, flags);
 }

fs/fuse/fuse_i.h

@@ -480,6 +480,18 @@ struct fuse_dev {
 	struct list_head entry;
 };
 
+enum fuse_dax_mode {
+	FUSE_DAX_INODE_DEFAULT,	/* default */
+	FUSE_DAX_ALWAYS,	/* "-o dax=always" */
+	FUSE_DAX_NEVER,		/* "-o dax=never" */
+	FUSE_DAX_INODE_USER,	/* "-o dax=inode" */
+};
+
+static inline bool fuse_is_inode_dax_mode(enum fuse_dax_mode mode)
+{
+	return mode == FUSE_DAX_INODE_DEFAULT || mode == FUSE_DAX_INODE_USER;
+}
+
 struct fuse_fs_context {
 	int fd;
 	struct file *file;
@@ -497,7 +509,7 @@ struct fuse_fs_context {
 	bool no_control:1;
 	bool no_force_umount:1;
 	bool legacy_opts_show:1;
-	bool dax:1;
+	enum fuse_dax_mode dax_mode;
 	unsigned int max_read;
 	unsigned int blksize;
 	const char *subtype;
@@ -765,6 +777,12 @@ struct fuse_conn {
 	/* Propagate syncfs() to server */
 	unsigned int sync_fs:1;
 
+	/* Initialize security xattrs when creating a new inode */
+	unsigned int init_security:1;
+
+	/* Does the filesystem support per inode DAX? */
+	unsigned int inode_dax:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
@@ -802,6 +820,9 @@ struct fuse_conn {
 	struct list_head devices;
 
 #ifdef CONFIG_FUSE_DAX
+	/* Dax mode */
+	enum fuse_dax_mode dax_mode;
+
 	/* Dax specific conn data, non-NULL if DAX is enabled */
 	struct fuse_conn_dax *dax;
 #endif
@@ -1007,7 +1028,7 @@ int fuse_notify_poll_wakeup(struct fuse_conn *fc,
 /**
  * Initialize file operations on a regular file
  */
-void fuse_init_file_inode(struct inode *inode);
+void fuse_init_file_inode(struct inode *inode, unsigned int flags);
 
 /**
  * Initialize inode operations on regular files and special files
@@ -1269,11 +1290,13 @@ ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
 ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
 int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma);
 int fuse_dax_break_layouts(struct inode *inode, u64 dmap_start, u64 dmap_end);
-int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
+int fuse_dax_conn_alloc(struct fuse_conn *fc, enum fuse_dax_mode mode,
+			struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
 bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi);
-void fuse_dax_inode_init(struct inode *inode);
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags);
 void fuse_dax_inode_cleanup(struct inode *inode);
+void fuse_dax_dontcache(struct inode *inode, unsigned int flags);
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 void fuse_dax_cancel_work(struct fuse_conn *fc);