1 files changed, 655 insertions, 180 deletions

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 033f7bdd47e..03246cd9d47 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1,6 +1,6 @@
 /*
   FUSE: Filesystem in Userspace
-  Copyright (C) 2001-2006  Miklos Szeredi <miklos@szeredi.hu>
+  Copyright (C) 2001-2008  Miklos Szeredi <miklos@szeredi.hu>
 
   This program can be distributed under the terms of the GNU GPL.
   See the file COPYING.
@@ -14,10 +14,12 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/parser.h>
 #include <linux/statfs.h>
 #include <linux/random.h>
 #include <linux/sched.h>
+#include <linux/exportfs.h>
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -27,24 +29,53 @@ static struct kmem_cache *fuse_inode_cachep;
 struct list_head fuse_conn_list;
 DEFINE_MUTEX(fuse_mutex);
 
+static int set_global_limit(const char *val, struct kernel_param *kp);
+
+unsigned 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");
+MODULE_PARM_DESC(max_user_bgreq,
+ "Global limit for the maximum number of backgrounded requests an "
+ "unprivileged user can set");
+
+unsigned 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");
+MODULE_PARM_DESC(max_user_congthresh,
+ "Global limit for the maximum congestion threshold an "
+ "unprivileged user can set");
+
 #define FUSE_SUPER_MAGIC 0x65735546
 
 #define FUSE_DEFAULT_BLKSIZE 512
 
+/** Maximum number of outstanding background requests */
+#define FUSE_DEFAULT_MAX_BACKGROUND 12
+
+/** Congestion starts at 75% of maximum */
+#define FUSE_DEFAULT_CONGESTION_THRESHOLD (FUSE_DEFAULT_MAX_BACKGROUND * 3 / 4)
+
 struct fuse_mount_data {
 	int fd;
 	unsigned rootmode;
-	unsigned user_id;
-	unsigned group_id;
-	unsigned fd_present : 1;
-	unsigned rootmode_present : 1;
-	unsigned user_id_present : 1;
-	unsigned group_id_present : 1;
+	kuid_t user_id;
+	kgid_t group_id;
+	unsigned fd_present:1;
+	unsigned rootmode_present:1;
+	unsigned user_id_present:1;
+	unsigned group_id_present:1;
 	unsigned flags;
 	unsigned max_read;
 	unsigned blksize;
 };
 
+struct fuse_forget_link *fuse_alloc_forget(void)
+{
+	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL);
+}
+
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
 	struct inode *inode;
@@ -59,9 +90,15 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	fi->nodeid = 0;
 	fi->nlookup = 0;
 	fi->attr_version = 0;
+	fi->writectr = 0;
+	fi->orig_ino = 0;
+	fi->state = 0;
 	INIT_LIST_HEAD(&fi->write_files);
-	fi->forget_req = fuse_request_alloc();
-	if (!fi->forget_req) {
+	INIT_LIST_HEAD(&fi->queued_writes);
+	INIT_LIST_HEAD(&fi->writepages);
+	init_waitqueue_head(&fi->page_waitq);
+	fi->forget = fuse_alloc_forget();
+	if (!fi->forget) {
 		kmem_cache_free(fuse_inode_cachep, inode);
 		return NULL;
 	}
@@ -69,82 +106,78 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	return inode;
 }
 
-static void fuse_destroy_inode(struct inode *inode)
+static void fuse_i_callback(struct rcu_head *head)
 {
-	struct fuse_inode *fi = get_fuse_inode(inode);
-	BUG_ON(!list_empty(&fi->write_files));
-	if (fi->forget_req)
-		fuse_request_free(fi->forget_req);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(fuse_inode_cachep, inode);
 }
 
-void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req,
-		      unsigned long nodeid, u64 nlookup)
+static void fuse_destroy_inode(struct inode *inode)
 {
-	struct fuse_forget_in *inarg = &req->misc.forget_in;
-	inarg->nlookup = nlookup;
-	req->in.h.opcode = FUSE_FORGET;
-	req->in.h.nodeid = nodeid;
-	req->in.numargs = 1;
-	req->in.args[0].size = sizeof(struct fuse_forget_in);
-	req->in.args[0].value = inarg;
-	request_send_noreply(fc, req);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	BUG_ON(!list_empty(&fi->write_files));
+	BUG_ON(!list_empty(&fi->queued_writes));
+	kfree(fi->forget);
+	call_rcu(&inode->i_rcu, fuse_i_callback);
 }
 
-static void fuse_clear_inode(struct inode *inode)
+static void fuse_evict_inode(struct inode *inode)
 {
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
 	if (inode->i_sb->s_flags & MS_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
 		struct fuse_inode *fi = get_fuse_inode(inode);
-		fuse_send_forget(fc, fi->forget_req, fi->nodeid, fi->nlookup);
-		fi->forget_req = NULL;
+		fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
+		fi->forget = NULL;
 	}
 }
 
 static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
 {
+	sync_filesystem(sb);
 	if (*flags & MS_MANDLOCK)
 		return -EINVAL;
 
 	return 0;
 }
 
-static void fuse_truncate(struct address_space *mapping, loff_t offset)
+/*
+ * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
+ * so that it will fit.
+ */
+static ino_t fuse_squash_ino(u64 ino64)
 {
-	/* See vmtruncate() */
-	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-	truncate_inode_pages(mapping, offset);
-	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+	ino_t ino = (ino_t) ino64;
+	if (sizeof(ino_t) < sizeof(u64))
+		ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
+	return ino;
 }
 
-
-void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
-			    u64 attr_valid, u64 attr_version)
+void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
+				   u64 attr_valid)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	loff_t oldsize;
 
-	spin_lock(&fc->lock);
-	if (attr_version != 0 && fi->attr_version > attr_version) {
-		spin_unlock(&fc->lock);
-		return;
-	}
 	fi->attr_version = ++fc->attr_version;
 	fi->i_time = attr_valid;
 
-	inode->i_ino     = attr->ino;
+	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
-	inode->i_nlink   = attr->nlink;
-	inode->i_uid     = attr->uid;
-	inode->i_gid     = attr->gid;
+	set_nlink(inode, attr->nlink);
+	inode->i_uid     = make_kuid(&init_user_ns, attr->uid);
+	inode->i_gid     = make_kgid(&init_user_ns, attr->gid);
 	inode->i_blocks  = attr->blocks;
 	inode->i_atime.tv_sec   = attr->atime;
 	inode->i_atime.tv_nsec  = attr->atimensec;
-	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;
+	/* mtime from server may be stale due to local buffered write */
+	if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) {
+		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;
+	}
 
 	if (attr->blksize != 0)
 		inode->i_blkbits = ilog2(attr->blksize);
@@ -160,14 +193,60 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 	if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
 		inode->i_mode &= ~S_ISVTX;
 
+	fi->orig_ino = attr->ino;
+}
+
+void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
+			    u64 attr_valid, u64 attr_version)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	bool is_wb = fc->writeback_cache;
+	loff_t oldsize;
+	struct timespec old_mtime;
+
+	spin_lock(&fc->lock);
+	if ((attr_version != 0 && fi->attr_version > attr_version) ||
+	    test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
+		spin_unlock(&fc->lock);
+		return;
+	}
+
+	old_mtime = inode->i_mtime;
+	fuse_change_attributes_common(inode, attr, attr_valid);
+
 	oldsize = inode->i_size;
-	i_size_write(inode, attr->size);
+	/*
+	 * In case of writeback_cache enabled, the cached writes beyond EOF
+	 * extend local i_size without keeping userspace server in sync. So,
+	 * attr->size coming from server can be stale. We cannot trust it.
+	 */
+	if (!is_wb || !S_ISREG(inode->i_mode))
+		i_size_write(inode, attr->size);
 	spin_unlock(&fc->lock);
 
-	if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
-		if (attr->size < oldsize)
-			fuse_truncate(inode->i_mapping, attr->size);
-		invalidate_inode_pages2(inode->i_mapping);
+	if (!is_wb && S_ISREG(inode->i_mode)) {
+		bool inval = false;
+
+		if (oldsize != attr->size) {
+			truncate_pagecache(inode, attr->size);
+			inval = true;
+		} else if (fc->auto_inval_data) {
+			struct timespec new_mtime = {
+				.tv_sec = attr->mtime,
+				.tv_nsec = attr->mtimensec,
+			};
+
+			/*
+			 * Auto inval mode also checks and invalidates if mtime
+			 * has changed.
+			 */
+			if (!timespec_equal(&old_mtime, &new_mtime))
+				inval = true;
+		}
+
+		if (inval)
+			invalidate_inode_pages2(inode->i_mapping);
 	}
 }
 
@@ -175,6 +254,10 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
 {
 	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;
 	if (S_ISREG(inode->i_mode)) {
 		fuse_init_common(inode);
 		fuse_init_file_inode(inode);
@@ -191,9 +274,9 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
 		BUG();
 }
 
-static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
+int fuse_inode_eq(struct inode *inode, void *_nodeidp)
 {
-	unsigned long nodeid = *(unsigned long *) _nodeidp;
+	u64 nodeid = *(u64 *) _nodeidp;
 	if (get_node_id(inode) == nodeid)
 		return 1;
 	else
@@ -202,12 +285,12 @@ static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
 
 static int fuse_inode_set(struct inode *inode, void *_nodeidp)
 {
-	unsigned long nodeid = *(unsigned long *) _nodeidp;
+	u64 nodeid = *(u64 *) _nodeidp;
 	get_fuse_inode(inode)->nodeid = nodeid;
 	return 0;
 }
 
-struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
+struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 			int generation, struct fuse_attr *attr,
 			u64 attr_valid, u64 attr_version)
 {
@@ -221,7 +304,9 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
 		return NULL;
 
 	if ((inode->i_state & I_NEW)) {
-		inode->i_flags |= S_NOATIME|S_NOCMTIME;
+		inode->i_flags |= S_NOATIME;
+		if (!fc->writeback_cache || !S_ISREG(attr->mode))
+			inode->i_flags |= S_NOCMTIME;
 		inode->i_generation = generation;
 		inode->i_data.backing_dev_info = &fc->bdi;
 		fuse_init_inode(inode, attr);
@@ -235,17 +320,41 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
 
 	fi = get_fuse_inode(inode);
 	spin_lock(&fc->lock);
-	fi->nlookup ++;
+	fi->nlookup++;
 	spin_unlock(&fc->lock);
 	fuse_change_attributes(inode, attr, attr_valid, attr_version);
 
 	return inode;
 }
 
-static void fuse_umount_begin(struct vfsmount *vfsmnt, int flags)
+int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
+			     loff_t offset, loff_t len)
+{
+	struct inode *inode;
+	pgoff_t pg_start;
+	pgoff_t pg_end;
+
+	inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid);
+	if (!inode)
+		return -ENOENT;
+
+	fuse_invalidate_attr(inode);
+	if (offset >= 0) {
+		pg_start = offset >> PAGE_CACHE_SHIFT;
+		if (len <= 0)
+			pg_end = -1;
+		else
+			pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pg_start, pg_end);
+	}
+	iput(inode);
+	return 0;
+}
+
+static void fuse_umount_begin(struct super_block *sb)
 {
-	if (flags & MNT_FORCE)
-		fuse_abort_conn(get_fuse_conn_super(vfsmnt->mnt_sb));
+	fuse_abort_conn(get_fuse_conn_super(sb));
 }
 
 static void fuse_send_destroy(struct fuse_conn *fc)
@@ -255,29 +364,46 @@ static void fuse_send_destroy(struct fuse_conn *fc)
 		fc->destroy_req = NULL;
 		req->in.h.opcode = FUSE_DESTROY;
 		req->force = 1;
-		request_send(fc, req);
+		req->background = 0;
+		fuse_request_send(fc, req);
 		fuse_put_request(fc, req);
 	}
 }
 
-static void fuse_put_super(struct super_block *sb)
+static void fuse_bdi_destroy(struct fuse_conn *fc)
 {
-	struct fuse_conn *fc = get_fuse_conn_super(sb);
+	if (fc->bdi_initialized)
+		bdi_destroy(&fc->bdi);
+}
 
-	fuse_send_destroy(fc);
+void fuse_conn_kill(struct fuse_conn *fc)
+{
 	spin_lock(&fc->lock);
 	fc->connected = 0;
 	fc->blocked = 0;
+	fc->initialized = 1;
 	spin_unlock(&fc->lock);
 	/* Flush all readers on this fs */
 	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
 	wake_up_all(&fc->waitq);
 	wake_up_all(&fc->blocked_waitq);
 	wake_up_all(&fc->reserved_req_waitq);
+}
+EXPORT_SYMBOL_GPL(fuse_conn_kill);
+
+static void fuse_put_super(struct super_block *sb)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	fuse_send_destroy(fc);
+
+	fuse_conn_kill(fc);
 	mutex_lock(&fuse_mutex);
 	list_del(&fc->entry);
 	fuse_ctl_remove_conn(fc);
 	mutex_unlock(&fuse_mutex);
+	fuse_bdi_destroy(fc);
+
 	fuse_conn_put(fc);
 }
 
@@ -303,12 +429,12 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct fuse_statfs_out outarg;
 	int err;
 
-	if (!fuse_allow_task(fc, current)) {
+	if (!fuse_allow_current_process(fc)) {
 		buf->f_type = FUSE_SUPER_MAGIC;
 		return 0;
 	}
 
-	req = fuse_get_req(fc);
+	req = fuse_get_req_nopages(fc);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -320,7 +446,7 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
 	req->out.args[0].size =
 		fc->minor < 4 ? FUSE_COMPAT_STATFS_SIZE : sizeof(outarg);
 	req->out.args[0].value = &outarg;
-	request_send(fc, req);
+	fuse_request_send(fc, req);
 	err = req->out.h.error;
 	if (!err)
 		convert_fuse_statfs(buf, &outarg.st);
@@ -340,7 +466,7 @@ enum {
 	OPT_ERR
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
 	{OPT_FD,			"fd=%u"},
 	{OPT_ROOTMODE,			"rootmode=%o"},
 	{OPT_USER_ID,			"user_id=%u"},
@@ -352,6 +478,17 @@ static match_table_t tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+	int err = -ENOMEM;
+	char *buf = match_strdup(s);
+	if (buf) {
+		err = kstrtouint(buf, 10, res);
+		kfree(buf);
+	}
+	return err;
+}
+
 static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 {
 	char *p;
@@ -362,6 +499,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	while ((p = strsep(&opt, ",")) != NULL) {
 		int token;
 		int value;
+		unsigned uv;
 		substring_t args[MAX_OPT_ARGS];
 		if (!*p)
 			continue;
@@ -385,16 +523,20 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 			break;
 
 		case OPT_USER_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
+				return 0;
+			d->user_id = make_kuid(current_user_ns(), uv);
+			if (!uid_valid(d->user_id))
 				return 0;
-			d->user_id = value;
 			d->user_id_present = 1;
 			break;
 
 		case OPT_GROUP_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
+				return 0;
+			d->group_id = make_kgid(current_user_ns(), uv);
+			if (!gid_valid(d->group_id))
 				return 0;
-			d->group_id = value;
 			d->group_id_present = 1;
 			break;
 
@@ -430,78 +572,71 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	return 1;
 }
 
-static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt)
+static int fuse_show_options(struct seq_file *m, struct dentry *root)
 {
-	struct fuse_conn *fc = get_fuse_conn_super(mnt->mnt_sb);
+	struct super_block *sb = root->d_sb;
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
 
-	seq_printf(m, ",user_id=%u", fc->user_id);
-	seq_printf(m, ",group_id=%u", fc->group_id);
+	seq_printf(m, ",user_id=%u", from_kuid_munged(&init_user_ns, fc->user_id));
+	seq_printf(m, ",group_id=%u", from_kgid_munged(&init_user_ns, fc->group_id));
 	if (fc->flags & FUSE_DEFAULT_PERMISSIONS)
 		seq_puts(m, ",default_permissions");
 	if (fc->flags & FUSE_ALLOW_OTHER)
 		seq_puts(m, ",allow_other");
 	if (fc->max_read != ~0)
 		seq_printf(m, ",max_read=%u", fc->max_read);
-	if (mnt->mnt_sb->s_bdev &&
-	    mnt->mnt_sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
-		seq_printf(m, ",blksize=%lu", mnt->mnt_sb->s_blocksize);
+	if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
+		seq_printf(m, ",blksize=%lu", sb->s_blocksize);
 	return 0;
 }
 
-static struct fuse_conn *new_conn(void)
+void fuse_conn_init(struct fuse_conn *fc)
 {
-	struct fuse_conn *fc;
-	int err;
-
-	fc = kzalloc(sizeof(*fc), GFP_KERNEL);
-	if (fc) {
-		spin_lock_init(&fc->lock);
-		mutex_init(&fc->inst_mutex);
-		atomic_set(&fc->count, 1);
-		init_waitqueue_head(&fc->waitq);
-		init_waitqueue_head(&fc->blocked_waitq);
-		init_waitqueue_head(&fc->reserved_req_waitq);
-		INIT_LIST_HEAD(&fc->pending);
-		INIT_LIST_HEAD(&fc->processing);
-		INIT_LIST_HEAD(&fc->io);
-		INIT_LIST_HEAD(&fc->interrupts);
-		INIT_LIST_HEAD(&fc->bg_queue);
-		atomic_set(&fc->num_waiting, 0);
-		fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
-		fc->bdi.unplug_io_fn = default_unplug_io_fn;
-		err = bdi_init(&fc->bdi);
-		if (err) {
-			kfree(fc);
-			fc = NULL;
-			goto out;
-		}
-		fc->reqctr = 0;
-		fc->blocked = 1;
-		fc->attr_version = 1;
-		get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
-	}
-out:
-	return fc;
+	memset(fc, 0, sizeof(*fc));
+	spin_lock_init(&fc->lock);
+	init_rwsem(&fc->killsb);
+	atomic_set(&fc->count, 1);
+	init_waitqueue_head(&fc->waitq);
+	init_waitqueue_head(&fc->blocked_waitq);
+	init_waitqueue_head(&fc->reserved_req_waitq);
+	INIT_LIST_HEAD(&fc->pending);
+	INIT_LIST_HEAD(&fc->processing);
+	INIT_LIST_HEAD(&fc->io);
+	INIT_LIST_HEAD(&fc->interrupts);
+	INIT_LIST_HEAD(&fc->bg_queue);
+	INIT_LIST_HEAD(&fc->entry);
+	fc->forget_list_tail = &fc->forget_list_head;
+	atomic_set(&fc->num_waiting, 0);
+	fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND;
+	fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD;
+	fc->khctr = 0;
+	fc->polled_files = RB_ROOT;
+	fc->reqctr = 0;
+	fc->blocked = 0;
+	fc->initialized = 0;
+	fc->attr_version = 1;
+	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 }
+EXPORT_SYMBOL_GPL(fuse_conn_init);
 
 void fuse_conn_put(struct fuse_conn *fc)
 {
 	if (atomic_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
-		mutex_destroy(&fc->inst_mutex);
-		bdi_destroy(&fc->bdi);
-		kfree(fc);
+		fc->release(fc);
 	}
 }
+EXPORT_SYMBOL_GPL(fuse_conn_put);
 
 struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
 {
 	atomic_inc(&fc->count);
 	return fc;
 }
+EXPORT_SYMBOL_GPL(fuse_conn_get);
 
-static struct inode *get_root_inode(struct super_block *sb, unsigned mode)
+static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
 {
 	struct fuse_attr attr;
 	memset(&attr, 0, sizeof(attr));
@@ -512,10 +647,162 @@ static struct inode *get_root_inode(struct super_block *sb, unsigned mode)
 	return fuse_iget(sb, 1, 0, &attr, 0, 0);
 }
 
+struct fuse_inode_handle {
+	u64 nodeid;
+	u32 generation;
+};
+
+static struct dentry *fuse_get_dentry(struct super_block *sb,
+				      struct fuse_inode_handle *handle)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+	struct inode *inode;
+	struct dentry *entry;
+	int err = -ESTALE;
+
+	if (handle->nodeid == 0)
+		goto out_err;
+
+	inode = ilookup5(sb, handle->nodeid, fuse_inode_eq, &handle->nodeid);
+	if (!inode) {
+		struct fuse_entry_out outarg;
+		struct qstr name;
+
+		if (!fc->export_support)
+			goto out_err;
+
+		name.len = 1;
+		name.name = ".";
+		err = fuse_lookup_name(sb, handle->nodeid, &name, &outarg,
+				       &inode);
+		if (err && err != -ENOENT)
+			goto out_err;
+		if (err || !inode) {
+			err = -ESTALE;
+			goto out_err;
+		}
+		err = -EIO;
+		if (get_node_id(inode) != handle->nodeid)
+			goto out_iput;
+	}
+	err = -ESTALE;
+	if (inode->i_generation != handle->generation)
+		goto out_iput;
+
+	entry = d_obtain_alias(inode);
+	if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID)
+		fuse_invalidate_entry_cache(entry);
+
+	return entry;
+
+ out_iput:
+	iput(inode);
+ out_err:
+	return ERR_PTR(err);
+}
+
+static int fuse_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+			   struct inode *parent)
+{
+	int len = parent ? 6 : 3;
+	u64 nodeid;
+	u32 generation;
+
+	if (*max_len < len) {
+		*max_len = len;
+		return  FILEID_INVALID;
+	}
+
+	nodeid = get_fuse_inode(inode)->nodeid;
+	generation = inode->i_generation;
+
+	fh[0] = (u32)(nodeid >> 32);
+	fh[1] = (u32)(nodeid & 0xffffffff);
+	fh[2] = generation;
+
+	if (parent) {
+		nodeid = get_fuse_inode(parent)->nodeid;
+		generation = parent->i_generation;
+
+		fh[3] = (u32)(nodeid >> 32);
+		fh[4] = (u32)(nodeid & 0xffffffff);
+		fh[5] = generation;
+	}
+
+	*max_len = len;
+	return parent ? 0x82 : 0x81;
+}
+
+static struct dentry *fuse_fh_to_dentry(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	struct fuse_inode_handle handle;
+
+	if ((fh_type != 0x81 && fh_type != 0x82) || fh_len < 3)
+		return NULL;
+
+	handle.nodeid = (u64) fid->raw[0] << 32;
+	handle.nodeid |= (u64) fid->raw[1];
+	handle.generation = fid->raw[2];
+	return fuse_get_dentry(sb, &handle);
+}
+
+static struct dentry *fuse_fh_to_parent(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	struct fuse_inode_handle parent;
+
+	if (fh_type != 0x82 || fh_len < 6)
+		return NULL;
+
+	parent.nodeid = (u64) fid->raw[3] << 32;
+	parent.nodeid |= (u64) fid->raw[4];
+	parent.generation = fid->raw[5];
+	return fuse_get_dentry(sb, &parent);
+}
+
+static struct dentry *fuse_get_parent(struct dentry *child)
+{
+	struct inode *child_inode = child->d_inode;
+	struct fuse_conn *fc = get_fuse_conn(child_inode);
+	struct inode *inode;
+	struct dentry *parent;
+	struct fuse_entry_out outarg;
+	struct qstr name;
+	int err;
+
+	if (!fc->export_support)
+		return ERR_PTR(-ESTALE);
+
+	name.len = 2;
+	name.name = "..";
+	err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode),
+			       &name, &outarg, &inode);
+	if (err) {
+		if (err == -ENOENT)
+			return ERR_PTR(-ESTALE);
+		return ERR_PTR(err);
+	}
+
+	parent = d_obtain_alias(inode);
+	if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID)
+		fuse_invalidate_entry_cache(parent);
+
+	return parent;
+}
+
+static const struct export_operations fuse_export_operations = {
+	.fh_to_dentry	= fuse_fh_to_dentry,
+	.fh_to_parent	= fuse_fh_to_parent,
+	.encode_fh	= fuse_encode_fh,
+	.get_parent	= fuse_get_parent,
+};
+
 static const struct super_operations fuse_super_operations = {
 	.alloc_inode    = fuse_alloc_inode,
 	.destroy_inode  = fuse_destroy_inode,
-	.clear_inode	= fuse_clear_inode,
+	.evict_inode	= fuse_evict_inode,
+	.write_inode	= fuse_write_inode,
 	.drop_inode	= generic_delete_inode,
 	.remount_fs	= fuse_remount_fs,
 	.put_super	= fuse_put_super,
@@ -524,6 +811,54 @@ static const struct super_operations fuse_super_operations = {
 	.show_options	= fuse_show_options,
 };
 
+static void sanitize_global_limit(unsigned *limit)
+{
+	if (*limit == 0)
+		*limit = ((totalram_pages << PAGE_SHIFT) >> 13) /
+			 sizeof(struct fuse_req);
+
+	if (*limit >= 1 << 16)
+		*limit = (1 << 16) - 1;
+}
+
+static int set_global_limit(const char *val, struct kernel_param *kp)
+{
+	int rv;
+
+	rv = param_set_uint(val, kp);
+	if (rv)
+		return rv;
+
+	sanitize_global_limit((unsigned *)kp->arg);
+
+	return 0;
+}
+
+static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
+{
+	int cap_sys_admin = capable(CAP_SYS_ADMIN);
+
+	if (arg->minor < 13)
+		return;
+
+	sanitize_global_limit(&max_user_bgreq);
+	sanitize_global_limit(&max_user_congthresh);
+
+	if (arg->max_background) {
+		fc->max_background = arg->max_background;
+
+		if (!cap_sys_admin && fc->max_background > max_user_bgreq)
+			fc->max_background = max_user_bgreq;
+	}
+	if (arg->congestion_threshold) {
+		fc->congestion_threshold = arg->congestion_threshold;
+
+		if (!cap_sys_admin &&
+		    fc->congestion_threshold > max_user_congthresh)
+			fc->congestion_threshold = max_user_congthresh;
+	}
+}
+
 static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct fuse_init_out *arg = &req->misc.init_out;
@@ -533,26 +868,58 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 	else {
 		unsigned long ra_pages;
 
+		process_init_limits(fc, arg);
+
 		if (arg->minor >= 6) {
 			ra_pages = arg->max_readahead / PAGE_CACHE_SIZE;
 			if (arg->flags & FUSE_ASYNC_READ)
 				fc->async_read = 1;
 			if (!(arg->flags & FUSE_POSIX_LOCKS))
 				fc->no_lock = 1;
+			if (arg->minor >= 17) {
+				if (!(arg->flags & FUSE_FLOCK_LOCKS))
+					fc->no_flock = 1;
+			} else {
+				if (!(arg->flags & FUSE_POSIX_LOCKS))
+					fc->no_flock = 1;
+			}
 			if (arg->flags & FUSE_ATOMIC_O_TRUNC)
 				fc->atomic_o_trunc = 1;
+			if (arg->minor >= 9) {
+				/* LOOKUP has dependency on proto version */
+				if (arg->flags & FUSE_EXPORT_SUPPORT)
+					fc->export_support = 1;
+			}
+			if (arg->flags & FUSE_BIG_WRITES)
+				fc->big_writes = 1;
+			if (arg->flags & FUSE_DONT_MASK)
+				fc->dont_mask = 1;
+			if (arg->flags & FUSE_AUTO_INVAL_DATA)
+				fc->auto_inval_data = 1;
+			if (arg->flags & FUSE_DO_READDIRPLUS) {
+				fc->do_readdirplus = 1;
+				if (arg->flags & FUSE_READDIRPLUS_AUTO)
+					fc->readdirplus_auto = 1;
+			}
+			if (arg->flags & FUSE_ASYNC_DIO)
+				fc->async_dio = 1;
+			if (arg->flags & FUSE_WRITEBACK_CACHE)
+				fc->writeback_cache = 1;
+			if (arg->time_gran && arg->time_gran <= 1000000000)
+				fc->sb->s_time_gran = arg->time_gran;
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
+			fc->no_flock = 1;
 		}
 
 		fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
 		fc->minor = arg->minor;
 		fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
+		fc->max_write = max_t(unsigned, 4096, fc->max_write);
 		fc->conn_init = 1;
 	}
-	fuse_put_request(fc, req);
-	fc->blocked = 0;
+	fc->initialized = 1;
 	wake_up_all(&fc->blocked_waitq);
 }
 
@@ -563,26 +930,72 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->major = FUSE_KERNEL_VERSION;
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
 	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
-	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC;
+	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
+		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
+		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
+		FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
+		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
+		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
 	req->in.args[0].value = arg;
 	req->out.numargs = 1;
-	/* Variable length arguement used for backward compatibility
+	/* Variable length argument used for backward compatibility
 	   with interface version < 7.5.  Rest of init_out is zeroed
 	   by do_get_request(), so a short reply is not a problem */
 	req->out.argvar = 1;
 	req->out.args[0].size = sizeof(struct fuse_init_out);
 	req->out.args[0].value = &req->misc.init_out;
 	req->end = process_init_reply;
-	request_send_background(fc, req);
+	fuse_request_send_background(fc, req);
 }
 
-static u64 conn_id(void)
+static void fuse_free_conn(struct fuse_conn *fc)
 {
-	static u64 ctr = 1;
-	return ctr++;
+	kfree_rcu(fc, rcu);
+}
+
+static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
+{
+	int err;
+
+	fc->bdi.name = "fuse";
+	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+	/* fuse does it's own writeback accounting */
+	fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
+
+	err = bdi_init(&fc->bdi);
+	if (err)
+		return err;
+
+	fc->bdi_initialized = 1;
+
+	if (sb->s_bdev) {
+		err =  bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
+				    MAJOR(fc->dev), MINOR(fc->dev));
+	} else {
+		err = bdi_register_dev(&fc->bdi, fc->dev);
+	}
+
+	if (err)
+		return err;
+
+	/*
+	 * For a single fuse filesystem use max 1% of dirty +
+	 * writeback threshold.
+	 *
+	 * This gives about 1M of write buffer for memory maps on a
+	 * machine with 1G and 10% dirty_ratio, which should be more
+	 * than enough.
+	 *
+	 * Privileged users can raise it by writing to
+	 *
+	 *    /sys/class/bdi/<bdi>/max_ratio
+	 */
+	bdi_set_max_ratio(&fc->bdi, 1);
+
+	return 0;
 }
 
 static int fuse_fill_super(struct super_block *sb, void *data, int silent)
@@ -596,16 +1009,20 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	int err;
 	int is_bdev = sb->s_bdev != NULL;
 
+	err = -EINVAL;
 	if (sb->s_flags & MS_MANDLOCK)
-		return -EINVAL;
+		goto err;
 
-	if (!parse_fuse_opt((char *) data, &d, is_bdev))
-		return -EINVAL;
+	sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
+
+	if (!parse_fuse_opt(data, &d, is_bdev))
+		goto err;
 
 	if (is_bdev) {
 #ifdef CONFIG_BLOCK
+		err = -EINVAL;
 		if (!sb_set_blocksize(sb, d.blksize))
-			return -EINVAL;
+			goto err;
 #endif
 	} else {
 		sb->s_blocksize = PAGE_CACHE_SIZE;
@@ -614,45 +1031,64 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = FUSE_SUPER_MAGIC;
 	sb->s_op = &fuse_super_operations;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_time_gran = 1;
+	sb->s_export_op = &fuse_export_operations;
 
 	file = fget(d.fd);
+	err = -EINVAL;
 	if (!file)
-		return -EINVAL;
+		goto err;
 
-	if (file->f_op != &fuse_dev_operations)
-		return -EINVAL;
+	if ((file->f_op != &fuse_dev_operations) ||
+	    (file->f_cred->user_ns != &init_user_ns))
+		goto err_fput;
 
-	fc = new_conn();
+	fc = kmalloc(sizeof(*fc), GFP_KERNEL);
+	err = -ENOMEM;
 	if (!fc)
-		return -ENOMEM;
+		goto err_fput;
+
+	fuse_conn_init(fc);
+
+	fc->dev = sb->s_dev;
+	fc->sb = sb;
+	err = fuse_bdi_init(fc, sb);
+	if (err)
+		goto err_put_conn;
+
+	sb->s_bdi = &fc->bdi;
+
+	/* Handle umasking inside the fuse code */
+	if (sb->s_flags & MS_POSIXACL)
+		fc->dont_mask = 1;
+	sb->s_flags |= MS_POSIXACL;
 
+	fc->release = fuse_free_conn;
 	fc->flags = d.flags;
 	fc->user_id = d.user_id;
 	fc->group_id = d.group_id;
-	fc->max_read = d.max_read;
+	fc->max_read = max_t(unsigned, 4096, d.max_read);
 
 	/* Used by get_root_inode() */
 	sb->s_fs_info = fc;
 
 	err = -ENOMEM;
-	root = get_root_inode(sb, d.rootmode);
-	if (!root)
-		goto err;
-
-	root_dentry = d_alloc_root(root);
-	if (!root_dentry) {
-		iput(root);
-		goto err;
-	}
-
-	init_req = fuse_request_alloc();
+	root = fuse_get_root_inode(sb, d.rootmode);
+	root_dentry = d_make_root(root);
+	if (!root_dentry)
+		goto err_put_conn;
+	/* only now - we want root dentry with NULL ->d_op */
+	sb->s_d_op = &fuse_dentry_operations;
+
+	init_req = fuse_request_alloc(0);
 	if (!init_req)
 		goto err_put_root;
+	init_req->background = 1;
 
 	if (is_bdev) {
-		fc->destroy_req = fuse_request_alloc();
+		fc->destroy_req = fuse_request_alloc(0);
 		if (!fc->destroy_req)
-			goto err_put_root;
+			goto err_free_init_req;
 	}
 
 	mutex_lock(&fuse_mutex);
@@ -660,7 +1096,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (file->private_data)
 		goto err_unlock;
 
-	fc->id = conn_id();
 	err = fuse_ctl_add_conn(fc);
 	if (err)
 		goto err_unlock;
@@ -683,46 +1118,77 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
  err_unlock:
 	mutex_unlock(&fuse_mutex);
+ err_free_init_req:
 	fuse_request_free(init_req);
  err_put_root:
 	dput(root_dentry);
- err:
-	fput(file);
+ err_put_conn:
+	fuse_bdi_destroy(fc);
 	fuse_conn_put(fc);
+ err_fput:
+	fput(file);
+ err:
 	return err;
 }
 
-static int fuse_get_sb(struct file_system_type *fs_type,
+static struct dentry *fuse_mount(struct file_system_type *fs_type,
 		       int flags, const char *dev_name,
-		       void *raw_data, struct vfsmount *mnt)
+		       void *raw_data)
+{
+	return mount_nodev(fs_type, flags, raw_data, fuse_fill_super);
+}
+
+static void fuse_kill_sb_anon(struct super_block *sb)
 {
-	return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt);
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	if (fc) {
+		down_write(&fc->killsb);
+		fc->sb = NULL;
+		up_write(&fc->killsb);
+	}
+
+	kill_anon_super(sb);
 }
 
 static struct file_system_type fuse_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuse",
 	.fs_flags	= FS_HAS_SUBTYPE,
-	.get_sb		= fuse_get_sb,
-	.kill_sb	= kill_anon_super,
+	.mount		= fuse_mount,
+	.kill_sb	= fuse_kill_sb_anon,
 };
+MODULE_ALIAS_FS("fuse");
 
 #ifdef CONFIG_BLOCK
-static int fuse_get_sb_blk(struct file_system_type *fs_type,
+static struct dentry *fuse_mount_blk(struct file_system_type *fs_type,
 			   int flags, const char *dev_name,
-			   void *raw_data, struct vfsmount *mnt)
+			   void *raw_data)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super,
-			   mnt);
+	return mount_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super);
+}
+
+static void fuse_kill_sb_blk(struct super_block *sb)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	if (fc) {
+		down_write(&fc->killsb);
+		fc->sb = NULL;
+		up_write(&fc->killsb);
+	}
+
+	kill_block_super(sb);
 }
 
 static struct file_system_type fuseblk_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuseblk",
-	.get_sb		= fuse_get_sb_blk,
-	.kill_sb	= kill_block_super,
+	.mount		= fuse_mount_blk,
+	.kill_sb	= fuse_kill_sb_blk,
 	.fs_flags	= FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
 };
+MODULE_ALIAS_FS("fuseblk");
 
 static inline int register_fuseblk(void)
 {
@@ -744,9 +1210,9 @@ static inline void unregister_fuseblk(void)
 }
 #endif
 
-static void fuse_inode_init_once(struct kmem_cache *cachep, void *foo)
+static void fuse_inode_init_once(void *foo)
 {
-	struct inode * inode = foo;
+	struct inode *inode = foo;
 
 	inode_init_once(inode);
 }
@@ -755,28 +1221,28 @@ static int __init fuse_fs_init(void)
 {
 	int err;
 
-	err = register_filesystem(&fuse_fs_type);
-	if (err)
-		goto out;
-
-	err = register_fuseblk();
-	if (err)
-		goto out_unreg;
-
 	fuse_inode_cachep = kmem_cache_create("fuse_inode",
 					      sizeof(struct fuse_inode),
 					      0, SLAB_HWCACHE_ALIGN,
 					      fuse_inode_init_once);
 	err = -ENOMEM;
 	if (!fuse_inode_cachep)
-		goto out_unreg2;
+		goto out;
+
+	err = register_fuseblk();
+	if (err)
+		goto out2;
+
+	err = register_filesystem(&fuse_fs_type);
+	if (err)
+		goto out3;
 
 	return 0;
 
- out_unreg2:
+ out3:
 	unregister_fuseblk();
- out_unreg:
-	unregister_filesystem(&fuse_fs_type);
+ out2:
+	kmem_cache_destroy(fuse_inode_cachep);
  out:
 	return err;
 }
@@ -785,6 +1251,12 @@ static void fuse_fs_cleanup(void)
 {
 	unregister_filesystem(&fuse_fs_type);
 	unregister_fuseblk();
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(fuse_inode_cachep);
 }
 
@@ -825,7 +1297,7 @@ static int __init fuse_init(void)
 {
 	int res;
 
-	printk("fuse init (API version %i.%i)\n",
+	printk(KERN_INFO "fuse init (API version %i.%i)\n",
 	       FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION);
 
 	INIT_LIST_HEAD(&fuse_conn_list);
@@ -845,6 +1317,9 @@ static int __init fuse_init(void)
 	if (res)
 		goto err_sysfs_cleanup;
 
+	sanitize_global_limit(&max_user_bgreq);
+	sanitize_global_limit(&max_user_congthresh);
+
 	return 0;
 
  err_sysfs_cleanup: