1 files changed, 421 insertions, 104 deletions

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f19d748890f0..819e50d66622 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -7,7 +7,10 @@
 */
 
 #include "fuse_i.h"
+#include "fuse_dev_i.h"
+#include "dev_uring_i.h"
 
+#include <linux/dax.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -32,10 +35,16 @@ MODULE_LICENSE("GPL");
 static struct kmem_cache *fuse_inode_cachep;
 struct list_head fuse_conn_list;
 DEFINE_MUTEX(fuse_mutex);
+DECLARE_WAIT_QUEUE_HEAD(fuse_dev_waitq);
 
 static int set_global_limit(const char *val, const struct kernel_param *kp);
 
-unsigned max_user_bgreq;
+unsigned int fuse_max_pages_limit = 256;
+/* default is no timeout */
+unsigned int fuse_default_req_timeout;
+unsigned int fuse_max_req_timeout;
+
+unsigned int max_user_bgreq;
 module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
 		  &max_user_bgreq, 0644);
 __MODULE_PARM_TYPE(max_user_bgreq, "uint");
@@ -43,7 +52,7 @@ MODULE_PARM_DESC(max_user_bgreq,
  "Global limit for the maximum number of backgrounded requests an "
  "unprivileged user can set");
 
-unsigned max_user_congthresh;
+unsigned int max_user_congthresh;
 module_param_call(max_user_congthresh, set_global_limit, param_get_uint,
 		  &max_user_congthresh, 0644);
 __MODULE_PARM_TYPE(max_user_congthresh, "uint");
@@ -68,6 +77,24 @@ struct fuse_forget_link *fuse_alloc_forget(void)
 	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT);
 }
 
+static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void)
+{
+	struct fuse_submount_lookup *sl;
+
+	sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT);
+	if (!sl)
+		return NULL;
+	sl->forget = fuse_alloc_forget();
+	if (!sl->forget)
+		goto out_free;
+
+	return sl;
+
+out_free:
+	kfree(sl);
+	return NULL;
+}
+
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
 	struct fuse_inode *fi;
@@ -76,13 +103,11 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	if (!fi)
 		return NULL;
 
-	fi->i_time = 0;
-	fi->inval_mask = 0;
-	fi->nodeid = 0;
-	fi->nlookup = 0;
-	fi->attr_version = 0;
-	fi->orig_ino = 0;
-	fi->state = 0;
+	/* Initialize private data (i.e. everything except fi->inode) */
+	BUILD_BUG_ON(offsetof(struct fuse_inode, inode) != 0);
+	memset((void *) fi + sizeof(fi->inode), 0, sizeof(*fi) - sizeof(fi->inode));
+
+	fi->inval_mask = ~0;
 	mutex_init(&fi->mutex);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
@@ -92,6 +117,9 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi))
 		goto out_free_forget;
 
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_inode_backing_set(fi, NULL);
+
 	return &fi->inode;
 
 out_free_forget:
@@ -110,15 +138,32 @@ static void fuse_free_inode(struct inode *inode)
 #ifdef CONFIG_FUSE_DAX
 	kfree(fi->dax);
 #endif
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_put(fuse_inode_backing(fi));
+
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
+static void fuse_cleanup_submount_lookup(struct fuse_conn *fc,
+					 struct fuse_submount_lookup *sl)
+{
+	if (!refcount_dec_and_test(&sl->count))
+		return;
+
+	fuse_queue_forget(fc, sl->forget, sl->nodeid, 1);
+	sl->forget = NULL;
+	kfree(sl);
+}
+
 static void fuse_evict_inode(struct inode *inode)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	/* Will write inode on close/munmap and in all other dirtiers */
-	WARN_ON(inode->i_state & I_DIRTY_INODE);
+	WARN_ON(inode_state_read_once(inode) & I_DIRTY_INODE);
+
+	if (FUSE_IS_DAX(inode))
+		dax_break_layout_final(inode);
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
@@ -132,8 +177,22 @@ static void fuse_evict_inode(struct inode *inode)
 					  fi->nlookup);
 			fi->forget = NULL;
 		}
+
+		if (fi->submount_lookup) {
+			fuse_cleanup_submount_lookup(fc, fi->submount_lookup);
+			fi->submount_lookup = NULL;
+		}
+		/*
+		 * Evict of non-deleted inode may race with outstanding
+		 * LOOKUP/READDIRPLUS requests and result in inconsistency when
+		 * the request finishes.  Deal with that here by bumping a
+		 * counter that can be compared to the starting value.
+		 */
+		if (inode->i_nlink > 0)
+			atomic64_inc(&fc->evict_ctr);
 	}
 	if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
+		WARN_ON(fi->iocachectr != 0);
 		WARN_ON(!list_empty(&fi->write_files));
 		WARN_ON(!list_empty(&fi->queued_writes));
 	}
@@ -163,16 +222,31 @@ static ino_t fuse_squash_ino(u64 ino64)
 }
 
 void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
-				   u64 attr_valid, u32 cache_mask)
+				   struct fuse_statx *sx,
+				   u64 attr_valid, u32 cache_mask,
+				   u64 evict_ctr)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	lockdep_assert_held(&fi->lock);
 
+	/*
+	 * Clear basic stats from invalid mask.
+	 *
+	 * Don't do this if this is coming from a fuse_iget() call and there
+	 * might have been a racing evict which would've invalidated the result
+	 * if the attr_version would've been preserved.
+	 *
+	 * !evict_ctr -> this is create
+	 * fi->attr_version != 0 -> this is not a new inode
+	 * evict_ctr == fuse_get_evict_ctr() -> no evicts while during request
+	 */
+	if (!evict_ctr || fi->attr_version || evict_ctr == fuse_get_evict_ctr(fc))
+		set_mask_bits(&fi->inval_mask, STATX_BASIC_STATS, 0);
+
 	fi->attr_version = atomic64_inc_return(&fc->attr_version);
 	fi->i_time = attr_valid;
-	WRITE_ONCE(fi->inval_mask, 0);
 
 	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -186,22 +260,38 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1);
 	attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1);
 
-	inode->i_atime.tv_sec   = attr->atime;
-	inode->i_atime.tv_nsec  = attr->atimensec;
+	inode_set_atime(inode, attr->atime, attr->atimensec);
 	/* mtime from server may be stale due to local buffered write */
 	if (!(cache_mask & STATX_MTIME)) {
-		inode->i_mtime.tv_sec   = attr->mtime;
-		inode->i_mtime.tv_nsec  = attr->mtimensec;
+		inode_set_mtime(inode, attr->mtime, attr->mtimensec);
 	}
 	if (!(cache_mask & STATX_CTIME)) {
-		inode->i_ctime.tv_sec   = attr->ctime;
-		inode->i_ctime.tv_nsec  = attr->ctimensec;
+		inode_set_ctime(inode, attr->ctime, attr->ctimensec);
+	}
+	if (sx) {
+		/* Sanitize nsecs */
+		sx->btime.tv_nsec =
+			min_t(u32, sx->btime.tv_nsec, NSEC_PER_SEC - 1);
+
+		/*
+		 * Btime has been queried, cache is valid (whether or not btime
+		 * is available or not) so clear STATX_BTIME from inval_mask.
+		 *
+		 * Availability of the btime attribute is indicated in
+		 * FUSE_I_BTIME
+		 */
+		set_mask_bits(&fi->inval_mask, STATX_BTIME, 0);
+		if (sx->mask & STATX_BTIME) {
+			set_bit(FUSE_I_BTIME, &fi->state);
+			fi->i_btime.tv_sec = sx->btime.tv_sec;
+			fi->i_btime.tv_nsec = sx->btime.tv_nsec;
+		}
 	}
 
-	if (attr->blksize != 0)
-		inode->i_blkbits = ilog2(attr->blksize);
+	if (attr->blksize)
+		fi->cached_i_blkbits = ilog2(attr->blksize);
 	else
-		inode->i_blkbits = inode->i_sb->s_blocksize_bits;
+		fi->cached_i_blkbits = inode->i_sb->s_blocksize_bits;
 
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
@@ -235,8 +325,9 @@ u32 fuse_get_cache_mask(struct inode *inode)
 	return STATX_MTIME | STATX_CTIME | STATX_SIZE;
 }
 
-void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
-			    u64 attr_valid, u64 attr_version)
+static void fuse_change_attributes_i(struct inode *inode, struct fuse_attr *attr,
+				     struct fuse_statx *sx, u64 attr_valid,
+				     u64 attr_version, u64 evict_ctr)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
@@ -255,12 +346,12 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		attr->size = i_size_read(inode);
 
 	if (cache_mask & STATX_MTIME) {
-		attr->mtime = inode->i_mtime.tv_sec;
-		attr->mtimensec = inode->i_mtime.tv_nsec;
+		attr->mtime = inode_get_mtime_sec(inode);
+		attr->mtimensec = inode_get_mtime_nsec(inode);
 	}
 	if (cache_mask & STATX_CTIME) {
-		attr->ctime = inode->i_ctime.tv_sec;
-		attr->ctimensec = inode->i_ctime.tv_nsec;
+		attr->ctime = inode_get_ctime_sec(inode);
+		attr->ctimensec = inode_get_ctime_nsec(inode);
 	}
 
 	if ((attr_version != 0 && fi->attr_version > attr_version) ||
@@ -269,8 +360,9 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		return;
 	}
 
-	old_mtime = inode->i_mtime;
-	fuse_change_attributes_common(inode, attr, attr_valid, cache_mask);
+	old_mtime = inode_get_mtime(inode);
+	fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask,
+				      evict_ctr);
 
 	oldsize = inode->i_size;
 	/*
@@ -311,15 +403,27 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		fuse_dax_dontcache(inode, attr->flags);
 }
 
+void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
+			    struct fuse_statx *sx, u64 attr_valid,
+			    u64 attr_version)
+{
+	fuse_change_attributes_i(inode, attr, sx, attr_valid, attr_version, 0);
+}
+
+static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl,
+				      u64 nodeid)
+{
+	sl->nodeid = nodeid;
+	refcount_set(&sl->count, 1);
+}
+
 static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
 			    struct fuse_conn *fc)
 {
 	inode->i_mode = attr->mode & S_IFMT;
 	inode->i_size = attr->size;
-	inode->i_mtime.tv_sec  = attr->mtime;
-	inode->i_mtime.tv_nsec = attr->mtimensec;
-	inode->i_ctime.tv_sec  = attr->ctime;
-	inode->i_ctime.tv_nsec = attr->ctimensec;
+	inode_set_mtime(inode, attr->mtime, attr->mtimensec);
+	inode_set_ctime(inode, attr->ctime, attr->ctimensec);
 	if (S_ISREG(inode->i_mode)) {
 		fuse_init_common(inode);
 		fuse_init_file_inode(inode, attr->flags);
@@ -360,7 +464,8 @@ static int fuse_inode_set(struct inode *inode, void *_nodeidp)
 
 struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 			int generation, struct fuse_attr *attr,
-			u64 attr_valid, u64 attr_version)
+			u64 attr_valid, u64 attr_version,
+			u64 evict_ctr)
 {
 	struct inode *inode;
 	struct fuse_inode *fi;
@@ -375,12 +480,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	 */
 	if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) &&
 	    S_ISDIR(attr->mode)) {
+		struct fuse_inode *fi;
+
 		inode = new_inode(sb);
 		if (!inode)
 			return NULL;
 
 		fuse_init_inode(inode, attr, fc);
-		get_fuse_inode(inode)->nodeid = nodeid;
+		fi = get_fuse_inode(inode);
+		fi->nodeid = nodeid;
+		fi->submount_lookup = fuse_alloc_submount_lookup();
+		if (!fi->submount_lookup) {
+			iput(inode);
+			return NULL;
+		}
+		/* Sets nlookup = 1 on fi->submount_lookup->nlookup */
+		fuse_init_submount_lookup(fi->submount_lookup, nodeid);
 		inode->i_flags |= S_AUTOMOUNT;
 		goto done;
 	}
@@ -390,7 +505,7 @@ retry:
 	if (!inode)
 		return NULL;
 
-	if ((inode->i_state & I_NEW)) {
+	if ((inode_state_read_once(inode) & I_NEW)) {
 		inode->i_flags |= S_NOATIME;
 		if (!fc->writeback_cache || !S_ISREG(attr->mode))
 			inode->i_flags |= S_NOCMTIME;
@@ -400,16 +515,19 @@ retry:
 	} else if (fuse_stale_inode(inode, generation, attr)) {
 		/* nodeid was reused, any I/O on the old inode should fail */
 		fuse_make_bad(inode);
-		iput(inode);
-		goto retry;
+		if (inode != d_inode(sb->s_root)) {
+			remove_inode_hash(inode);
+			iput(inode);
+			goto retry;
+		}
 	}
-done:
 	fi = get_fuse_inode(inode);
 	spin_lock(&fi->lock);
 	fi->nlookup++;
 	spin_unlock(&fi->lock);
-	fuse_change_attributes(inode, attr, attr_valid, attr_version);
-
+done:
+	fuse_change_attributes_i(inode, attr, NULL, attr_valid, attr_version,
+				 evict_ctr);
 	return inode;
 }
 
@@ -467,6 +585,17 @@ int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid,
 	return 0;
 }
 
+void fuse_try_prune_one_inode(struct fuse_conn *fc, u64 nodeid)
+{
+	struct inode *inode;
+
+	inode = fuse_ilookup(fc, nodeid,  NULL);
+	if (!inode)
+		return;
+	d_prune_aliases(inode);
+	iput(inode);
+}
+
 bool fuse_lock_inode(struct inode *inode)
 {
 	bool locked = false;
@@ -661,8 +790,8 @@ static const struct fs_parameter_spec fuse_fs_parameters[] = {
 	fsparam_string	("source",		OPT_SOURCE),
 	fsparam_u32	("fd",			OPT_FD),
 	fsparam_u32oct	("rootmode",		OPT_ROOTMODE),
-	fsparam_u32	("user_id",		OPT_USER_ID),
-	fsparam_u32	("group_id",		OPT_GROUP_ID),
+	fsparam_uid	("user_id",		OPT_USER_ID),
+	fsparam_gid	("group_id",		OPT_GROUP_ID),
 	fsparam_flag	("default_permissions",	OPT_DEFAULT_PERMISSIONS),
 	fsparam_flag	("allow_other",		OPT_ALLOW_OTHER),
 	fsparam_u32	("max_read",		OPT_MAX_READ),
@@ -676,6 +805,8 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
 	struct fs_parse_result result;
 	struct fuse_fs_context *ctx = fsc->fs_private;
 	int opt;
+	kuid_t kuid;
+	kgid_t kgid;
 
 	if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
 		/*
@@ -720,16 +851,26 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
 		break;
 
 	case OPT_USER_ID:
-		ctx->user_id = make_kuid(fsc->user_ns, result.uint_32);
-		if (!uid_valid(ctx->user_id))
+		kuid = result.uid;
+		/*
+		 * The requested uid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kuid_has_mapping(fsc->user_ns, kuid))
 			return invalfc(fsc, "Invalid user_id");
+		ctx->user_id = kuid;
 		ctx->user_id_present = true;
 		break;
 
 	case OPT_GROUP_ID:
-		ctx->group_id = make_kgid(fsc->user_ns, result.uint_32);
-		if (!gid_valid(ctx->group_id))
+		kgid = result.gid;
+		/*
+		 * The requested gid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kgid_has_mapping(fsc->user_ns, kgid))
 			return invalfc(fsc, "Invalid group_id");
+		ctx->group_id = kgid;
 		ctx->group_id_present = true;
 		break;
 
@@ -814,7 +955,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq,
 	fiq->priv = priv;
 }
 
-static void fuse_pqueue_init(struct fuse_pqueue *fpq)
+void fuse_pqueue_init(struct fuse_pqueue *fpq)
 {
 	unsigned int i;
 
@@ -835,6 +976,8 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	init_rwsem(&fc->killsb);
 	refcount_set(&fc->count, 1);
 	atomic_set(&fc->dev_count, 1);
+	atomic_set(&fc->epoch, 1);
+	INIT_WORK(&fc->epoch_work, fuse_epoch_work);
 	init_waitqueue_head(&fc->blocked_waitq);
 	fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv);
 	INIT_LIST_HEAD(&fc->bg_queue);
@@ -849,11 +992,17 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->initialized = 0;
 	fc->connected = 1;
 	atomic64_set(&fc->attr_version, 1);
+	atomic64_set(&fc->evict_ctr, 1);
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 	fc->user_ns = get_user_ns(user_ns);
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
-	fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
+	fc->max_pages_limit = fuse_max_pages_limit;
+	fc->name_max = FUSE_NAME_LOW_MAX;
+	fc->timeout.req_timeout = 0;
+
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_files_init(fc);
 
 	INIT_LIST_HEAD(&fc->mounts);
 	list_add(&fm->fc_entry, &fc->mounts);
@@ -861,25 +1010,40 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
+static void delayed_release(struct rcu_head *p)
+{
+	struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu);
+
+	fuse_uring_destruct(fc);
+
+	put_user_ns(fc->user_ns);
+	fc->release(fc);
+}
+
 void fuse_conn_put(struct fuse_conn *fc)
 {
-	if (refcount_dec_and_test(&fc->count)) {
-		struct fuse_iqueue *fiq = &fc->iq;
-		struct fuse_sync_bucket *bucket;
-
-		if (IS_ENABLED(CONFIG_FUSE_DAX))
-			fuse_dax_conn_free(fc);
-		if (fiq->ops->release)
-			fiq->ops->release(fiq);
-		put_pid_ns(fc->pid_ns);
-		put_user_ns(fc->user_ns);
-		bucket = rcu_dereference_protected(fc->curr_bucket, 1);
-		if (bucket) {
-			WARN_ON(atomic_read(&bucket->count) != 1);
-			kfree(bucket);
-		}
-		fc->release(fc);
+	struct fuse_iqueue *fiq = &fc->iq;
+	struct fuse_sync_bucket *bucket;
+
+	if (!refcount_dec_and_test(&fc->count))
+		return;
+
+	if (IS_ENABLED(CONFIG_FUSE_DAX))
+		fuse_dax_conn_free(fc);
+	if (fc->timeout.req_timeout)
+		cancel_delayed_work_sync(&fc->timeout.work);
+	cancel_work_sync(&fc->epoch_work);
+	if (fiq->ops->release)
+		fiq->ops->release(fiq);
+	put_pid_ns(fc->pid_ns);
+	bucket = rcu_dereference_protected(fc->curr_bucket, 1);
+	if (bucket) {
+		WARN_ON(atomic_read(&bucket->count) != 1);
+		kfree(bucket);
 	}
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_files_free(fc);
+	call_rcu(&fc->rcu, delayed_release);
 }
 EXPORT_SYMBOL_GPL(fuse_conn_put);
 
@@ -890,7 +1054,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
 }
 EXPORT_SYMBOL_GPL(fuse_conn_get);
 
-static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
+static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned int mode)
 {
 	struct fuse_attr attr;
 	memset(&attr, 0, sizeof(attr));
@@ -898,7 +1062,7 @@ static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
 	attr.mode = mode;
 	attr.ino = FUSE_ROOT_ID;
 	attr.nlink = 1;
-	return fuse_iget(sb, 1, 0, &attr, 0, 0);
+	return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0, 0);
 }
 
 struct fuse_inode_handle {
@@ -982,7 +1146,7 @@ static int fuse_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 	}
 
 	*max_len = len;
-	return parent ? 0x82 : 0x81;
+	return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN;
 }
 
 static struct dentry *fuse_fh_to_dentry(struct super_block *sb,
@@ -990,7 +1154,8 @@ static struct dentry *fuse_fh_to_dentry(struct super_block *sb,
 {
 	struct fuse_inode_handle handle;
 
-	if ((fh_type != 0x81 && fh_type != 0x82) || fh_len < 3)
+	if ((fh_type != FILEID_INO64_GEN &&
+	     fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3)
 		return NULL;
 
 	handle.nodeid = (u64) fid->raw[0] << 32;
@@ -1004,7 +1169,7 @@ static struct dentry *fuse_fh_to_parent(struct super_block *sb,
 {
 	struct fuse_inode_handle parent;
 
-	if (fh_type != 0x82 || fh_len < 6)
+	if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6)
 		return NULL;
 
 	parent.nodeid = (u64) fid->raw[3] << 32;
@@ -1040,6 +1205,11 @@ static struct dentry *fuse_get_parent(struct dentry *child)
 	return parent;
 }
 
+/* only for fid encoding; no support for file handle */
+static const struct export_operations fuse_export_fid_operations = {
+	.encode_fh	= fuse_encode_fh,
+};
+
 static const struct export_operations fuse_export_operations = {
 	.fh_to_dentry	= fuse_fh_to_dentry,
 	.fh_to_parent	= fuse_fh_to_parent,
@@ -1052,14 +1222,14 @@ static const struct super_operations fuse_super_operations = {
 	.free_inode     = fuse_free_inode,
 	.evict_inode	= fuse_evict_inode,
 	.write_inode	= fuse_write_inode,
-	.drop_inode	= generic_delete_inode,
+	.drop_inode	= inode_just_drop,
 	.umount_begin	= fuse_umount_begin,
 	.statfs		= fuse_statfs,
 	.sync_fs	= fuse_sync_fs,
 	.show_options	= fuse_show_options,
 };
 
-static void sanitize_global_limit(unsigned *limit)
+static void sanitize_global_limit(unsigned int *limit)
 {
 	/*
 	 * The default maximum number of async requests is calculated to consume
@@ -1080,7 +1250,7 @@ static int set_global_limit(const char *val, const struct kernel_param *kp)
 	if (rv)
 		return rv;
 
-	sanitize_global_limit((unsigned *)kp->arg);
+	sanitize_global_limit((unsigned int *)kp->arg);
 
 	return 0;
 }
@@ -1112,6 +1282,34 @@ static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
 	spin_unlock(&fc->bg_lock);
 }
 
+static void set_request_timeout(struct fuse_conn *fc, unsigned int timeout)
+{
+	fc->timeout.req_timeout = secs_to_jiffies(timeout);
+	INIT_DELAYED_WORK(&fc->timeout.work, fuse_check_timeout);
+	queue_delayed_work(system_percpu_wq, &fc->timeout.work,
+			   fuse_timeout_timer_freq);
+}
+
+static void init_server_timeout(struct fuse_conn *fc, unsigned int timeout)
+{
+	if (!timeout && !fuse_max_req_timeout && !fuse_default_req_timeout)
+		return;
+
+	if (!timeout)
+		timeout = fuse_default_req_timeout;
+
+	if (fuse_max_req_timeout) {
+		if (timeout)
+			timeout = min(fuse_max_req_timeout, timeout);
+		else
+			timeout = fuse_max_req_timeout;
+	}
+
+	timeout = max(FUSE_TIMEOUT_TIMER_FREQ, timeout);
+
+	set_request_timeout(fc, timeout);
+}
+
 struct fuse_init_args {
 	struct fuse_args args;
 	struct fuse_init_in in;
@@ -1130,6 +1328,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 		ok = false;
 	else {
 		unsigned long ra_pages;
+		unsigned int timeout = 0;
 
 		process_init_limits(fc, arg);
 
@@ -1193,6 +1392,13 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->max_pages =
 					min_t(unsigned int, fc->max_pages_limit,
 					max_t(unsigned int, arg->max_pages, 1));
+
+				/*
+				 * PATH_MAX file names might need two pages for
+				 * ops like rename
+				 */
+				if (fc->max_pages > 1)
+					fc->name_max = FUSE_NAME_MAX;
 			}
 			if (IS_ENABLED(CONFIG_FUSE_DAX)) {
 				if (flags & FUSE_MAP_ALIGNMENT &&
@@ -1212,12 +1418,52 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->init_security = 1;
 			if (flags & FUSE_CREATE_SUPP_GROUP)
 				fc->create_supp_group = 1;
+			if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
+				fc->direct_io_allow_mmap = 1;
+			/*
+			 * max_stack_depth is the max stack depth of FUSE fs,
+			 * so it has to be at least 1 to support passthrough
+			 * to backing files.
+			 *
+			 * with max_stack_depth > 1, the backing files can be
+			 * on a stacked fs (e.g. overlayfs) themselves and with
+			 * max_stack_depth == 1, FUSE fs can be stacked as the
+			 * underlying fs of a stacked fs (e.g. overlayfs).
+			 *
+			 * Also don't allow the combination of FUSE_PASSTHROUGH
+			 * and FUSE_WRITEBACK_CACHE, current design doesn't handle
+			 * them together.
+			 */
+			if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) &&
+			    (flags & FUSE_PASSTHROUGH) &&
+			    arg->max_stack_depth > 0 &&
+			    arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH &&
+			    !(flags & FUSE_WRITEBACK_CACHE))  {
+				fc->passthrough = 1;
+				fc->max_stack_depth = arg->max_stack_depth;
+				fm->sb->s_stack_depth = arg->max_stack_depth;
+			}
+			if (flags & FUSE_NO_EXPORT_SUPPORT)
+				fm->sb->s_export_op = &fuse_export_fid_operations;
+			if (flags & FUSE_ALLOW_IDMAP) {
+				if (fc->default_permissions)
+					fm->sb->s_iflags &= ~SB_I_NOIDMAP;
+				else
+					ok = false;
+			}
+			if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled())
+				fc->io_uring = 1;
+
+			if (flags & FUSE_REQUEST_TIMEOUT)
+				timeout = arg->request_timeout;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
 			fc->no_flock = 1;
 		}
 
+		init_server_timeout(fc, timeout);
+
 		fm->sb->s_bdi->ra_pages =
 				min(fm->sb->s_bdi->ra_pages, ra_pages);
 		fc->minor = arg->minor;
@@ -1236,7 +1482,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 	wake_up_all(&fc->blocked_waitq);
 }
 
-void fuse_send_init(struct fuse_mount *fm)
+static struct fuse_init_args *fuse_new_init(struct fuse_mount *fm)
 {
 	struct fuse_init_args *ia;
 	u64 flags;
@@ -1258,7 +1504,9 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
 		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
 		FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
-		FUSE_HAS_EXPIRE_ONLY;
+		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP |
+		FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND | FUSE_ALLOW_IDMAP |
+		FUSE_REQUEST_TIMEOUT;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		flags |= FUSE_MAP_ALIGNMENT;
@@ -1267,6 +1515,15 @@ void fuse_send_init(struct fuse_mount *fm)
 #endif
 	if (fm->fc->auto_submounts)
 		flags |= FUSE_SUBMOUNTS;
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		flags |= FUSE_PASSTHROUGH;
+
+	/*
+	 * This is just an information flag for fuse server. No need to check
+	 * the reply - server is either sending IORING_OP_URING_CMD or not.
+	 */
+	if (fuse_uring_enabled())
+		flags |= FUSE_OVER_IO_URING;
 
 	ia->in.flags = flags;
 	ia->in.flags2 = flags >> 32;
@@ -1284,17 +1541,37 @@ void fuse_send_init(struct fuse_mount *fm)
 	ia->args.out_args[0].value = &ia->out;
 	ia->args.force = true;
 	ia->args.nocreds = true;
-	ia->args.end = process_init_reply;
 
-	if (fuse_simple_background(fm, &ia->args, GFP_KERNEL) != 0)
-		process_init_reply(fm, &ia->args, -ENOTCONN);
+	return ia;
+}
+
+int fuse_send_init(struct fuse_mount *fm)
+{
+	struct fuse_init_args *ia = fuse_new_init(fm);
+	int err;
+
+	if (fm->fc->sync_init) {
+		err = fuse_simple_request(fm, &ia->args);
+		/* Ignore size of init reply */
+		if (err > 0)
+			err = 0;
+	} else {
+		ia->args.end = process_init_reply;
+		err = fuse_simple_background(fm, &ia->args, GFP_KERNEL);
+		if (!err)
+			return 0;
+	}
+	process_init_reply(fm, &ia->args, err);
+	if (fm->fc->conn_error)
+		return -ENOTCONN;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(fuse_send_init);
 
 void fuse_free_conn(struct fuse_conn *fc)
 {
 	WARN_ON(!list_empty(&fc->devices));
-	kfree_rcu(fc, rcu);
+	kfree(fc);
 }
 EXPORT_SYMBOL_GPL(fuse_free_conn);
 
@@ -1317,8 +1594,6 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	if (err)
 		return err;
 
-	/* fuse does it's own writeback accounting */
-	sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT;
 	sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT;
 
 	/*
@@ -1401,20 +1676,24 @@ EXPORT_SYMBOL_GPL(fuse_dev_free);
 static void fuse_fill_attr_from_inode(struct fuse_attr *attr,
 				      const struct fuse_inode *fi)
 {
+	struct timespec64 atime = inode_get_atime(&fi->inode);
+	struct timespec64 mtime = inode_get_mtime(&fi->inode);
+	struct timespec64 ctime = inode_get_ctime(&fi->inode);
+
 	*attr = (struct fuse_attr){
 		.ino		= fi->inode.i_ino,
 		.size		= fi->inode.i_size,
 		.blocks		= fi->inode.i_blocks,
-		.atime		= fi->inode.i_atime.tv_sec,
-		.mtime		= fi->inode.i_mtime.tv_sec,
-		.ctime		= fi->inode.i_ctime.tv_sec,
-		.atimensec	= fi->inode.i_atime.tv_nsec,
-		.mtimensec	= fi->inode.i_mtime.tv_nsec,
-		.ctimensec	= fi->inode.i_ctime.tv_nsec,
+		.atime		= atime.tv_sec,
+		.mtime		= mtime.tv_sec,
+		.ctime		= ctime.tv_sec,
+		.atimensec	= atime.tv_nsec,
+		.mtimensec	= mtime.tv_nsec,
+		.ctimensec	= ctime.tv_nsec,
 		.mode		= fi->inode.i_mode,
 		.nlink		= fi->inode.i_nlink,
-		.uid		= fi->inode.i_uid.val,
-		.gid		= fi->inode.i_gid.val,
+		.uid		= __kuid_val(fi->inode.i_uid),
+		.gid		= __kgid_val(fi->inode.i_gid),
 		.rdev		= fi->inode.i_rdev,
 		.blksize	= 1u << fi->inode.i_blkbits,
 	};
@@ -1429,6 +1708,7 @@ static void fuse_sb_defaults(struct super_block *sb)
 	sb->s_time_gran = 1;
 	sb->s_export_op = &fuse_export_operations;
 	sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE;
+	sb->s_iflags |= SB_I_NOIDMAP;
 	if (sb->s_user_ns != &init_user_ns)
 		sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER;
 	sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
@@ -1441,6 +1721,8 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	struct super_block *parent_sb = parent_fi->inode.i_sb;
 	struct fuse_attr root_attr;
 	struct inode *root;
+	struct fuse_submount_lookup *sl;
+	struct fuse_inode *fi;
 
 	fuse_sb_defaults(sb);
 	fm->sb = sb;
@@ -1449,6 +1731,7 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	sb->s_bdi = bdi_get(parent_sb->s_bdi);
 
 	sb->s_xattr = parent_sb->s_xattr;
+	sb->s_export_op = parent_sb->s_export_op;
 	sb->s_time_gran = parent_sb->s_time_gran;
 	sb->s_blocksize = parent_sb->s_blocksize;
 	sb->s_blocksize_bits = parent_sb->s_blocksize_bits;
@@ -1457,18 +1740,34 @@ static int fuse_fill_super_submount(struct super_block *sb,
 		return -ENOMEM;
 
 	fuse_fill_attr_from_inode(&root_attr, parent_fi);
-	root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0);
+	root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0,
+			 fuse_get_evict_ctr(fm->fc));
 	/*
 	 * This inode is just a duplicate, so it is not looked up and
 	 * its nlookup should not be incremented.  fuse_iget() does
 	 * that, though, so undo it here.
 	 */
-	get_fuse_inode(root)->nlookup--;
-	sb->s_d_op = &fuse_dentry_operations;
+	fi = get_fuse_inode(root);
+	fi->nlookup--;
+
+	set_default_d_op(sb, &fuse_dentry_operations);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root)
 		return -ENOMEM;
 
+	/*
+	 * Grab the parent's submount_lookup pointer and take a
+	 * reference on the shared nlookup from the parent.  This is to
+	 * prevent the last forget for this nodeid from getting
+	 * triggered until all users have finished with it.
+	 */
+	sl = parent_fi->submount_lookup;
+	WARN_ON(!sl);
+	if (sl) {
+		refcount_inc(&sl->count);
+		fi->submount_lookup = sl;
+	}
+
 	return 0;
 }
 
@@ -1543,6 +1842,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 		if (!sb_set_blocksize(sb, ctx->blksize))
 			goto err;
 #endif
+		fc->sync_fs = 1;
 	} else {
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
@@ -1586,17 +1886,19 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 
 	err = -ENOMEM;
 	root = fuse_get_root_inode(sb, ctx->rootmode);
-	sb->s_d_op = &fuse_root_dentry_operations;
+	set_default_d_op(sb, &fuse_dentry_operations);
 	root_dentry = d_make_root(root);
 	if (!root_dentry)
 		goto err_dev_free;
-	/* Root dentry doesn't have .d_revalidate */
-	sb->s_d_op = &fuse_dentry_operations;
 
 	mutex_lock(&fuse_mutex);
 	err = -EINVAL;
-	if (ctx->fudptr && *ctx->fudptr)
-		goto err_unlock;
+	if (ctx->fudptr && *ctx->fudptr) {
+		if (*ctx->fudptr == FUSE_DEV_SYNC_INIT)
+			fc->sync_init = 1;
+		else
+			goto err_unlock;
+	}
 
 	err = fuse_ctl_add_conn(fc);
 	if (err)
@@ -1604,8 +1906,10 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 
 	list_add_tail(&fc->entry, &fuse_conn_list);
 	sb->s_root = root_dentry;
-	if (ctx->fudptr)
+	if (ctx->fudptr) {
 		*ctx->fudptr = fud;
+		wake_up_all(&fuse_dev_waitq);
+	}
 	mutex_unlock(&fuse_mutex);
 	return 0;
 
@@ -1626,6 +1930,7 @@ EXPORT_SYMBOL_GPL(fuse_fill_super_common);
 static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc)
 {
 	struct fuse_fs_context *ctx = fsc->fs_private;
+	struct fuse_mount *fm;
 	int err;
 
 	if (!ctx->file || !ctx->rootmode_present ||
@@ -1646,8 +1951,10 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc)
 		return err;
 	/* file->private_data shall be visible on all CPUs after this */
 	smp_mb();
-	fuse_send_init(get_fuse_mount_super(sb));
-	return 0;
+
+	fm = get_fuse_mount_super(sb);
+
+	return fuse_send_init(fm);
 }
 
 /*
@@ -1708,7 +2015,7 @@ static int fuse_get_tree(struct fs_context *fsc)
 	 * Allow creating a fuse mount with an already initialized fuse
 	 * connection
 	 */
-	fud = READ_ONCE(ctx->file->private_data);
+	fud = __fuse_get_dev(ctx->file);
 	if (ctx->file->f_op == &fuse_dev_operations && fud) {
 		fsc->sget_key = fud->fc;
 		sb = sget_fc(fsc, fuse_test_super, fuse_set_no_super);
@@ -1809,7 +2116,7 @@ static void fuse_sb_destroy(struct super_block *sb)
 void fuse_mount_destroy(struct fuse_mount *fm)
 {
 	fuse_conn_put(fm->fc);
-	kfree(fm);
+	kfree_rcu(fm, rcu);
 }
 EXPORT_SYMBOL(fuse_mount_destroy);
 
@@ -1823,7 +2130,7 @@ static void fuse_kill_sb_anon(struct super_block *sb)
 static struct file_system_type fuse_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuse",
-	.fs_flags	= FS_HAS_SUBTYPE | FS_USERNS_MOUNT,
+	.fs_flags	= FS_HAS_SUBTYPE | FS_USERNS_MOUNT | FS_ALLOW_IDMAP,
 	.init_fs_context = fuse_init_fs_context,
 	.parameters	= fuse_fs_parameters,
 	.kill_sb	= fuse_kill_sb_anon,
@@ -1844,7 +2151,7 @@ static struct file_system_type fuseblk_fs_type = {
 	.init_fs_context = fuse_init_fs_context,
 	.parameters	= fuse_fs_parameters,
 	.kill_sb	= fuse_kill_sb_blk,
-	.fs_flags	= FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
+	.fs_flags	= FS_REQUIRES_DEV | FS_HAS_SUBTYPE | FS_ALLOW_IDMAP,
 };
 MODULE_ALIAS_FS("fuseblk");
 
@@ -1895,8 +2202,14 @@ static int __init fuse_fs_init(void)
 	if (err)
 		goto out3;
 
+	err = fuse_sysctl_register();
+	if (err)
+		goto out4;
+
 	return 0;
 
+ out4:
+	unregister_filesystem(&fuse_fs_type);
  out3:
 	unregister_fuseblk();
  out2:
@@ -1907,6 +2220,7 @@ static int __init fuse_fs_init(void)
 
 static void fuse_fs_cleanup(void)
 {
+	fuse_sysctl_unregister();
 	unregister_filesystem(&fuse_fs_type);
 	unregister_fuseblk();
 
@@ -1972,6 +2286,8 @@ static int __init fuse_init(void)
 	if (res)
 		goto err_sysfs_cleanup;
 
+	fuse_dentry_tree_init();
+
 	sanitize_global_limit(&max_user_bgreq);
 	sanitize_global_limit(&max_user_congthresh);
 
@@ -1991,6 +2307,7 @@ static void __exit fuse_exit(void)
 {
 	pr_debug("exit\n");
 
+	fuse_dentry_tree_cleanup();
 	fuse_ctl_cleanup();
 	fuse_sysfs_cleanup();
 	fuse_fs_cleanup();