7 files changed, 842 insertions, 371 deletions

diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index c3e1f760cac..72437065f6a 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_FUSE_FS) += fuse.o
 
-fuse-objs := dev.o dir.o file.o inode.o
+fuse-objs := dev.o dir.o file.o inode.o control.o
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
new file mode 100644
index 00000000000..a3bce3a7725
--- /dev/null
+++ b/fs/fuse/control.c
@@ -0,0 +1,218 @@
+/*
+  FUSE: Filesystem in Userspace
+  Copyright (C) 2001-2006  Miklos Szeredi <miklos@szeredi.hu>
+
+  This program can be distributed under the terms of the GNU GPL.
+  See the file COPYING.
+*/
+
+#include "fuse_i.h"
+
+#include <linux/init.h>
+#include <linux/module.h>
+
+#define FUSE_CTL_SUPER_MAGIC 0x65735543
+
+/*
+ * This is non-NULL when the single instance of the control filesystem
+ * exists.  Protected by fuse_mutex
+ */
+static struct super_block *fuse_control_sb;
+
+static struct fuse_conn *fuse_ctl_file_conn_get(struct file *file)
+{
+	struct fuse_conn *fc;
+	mutex_lock(&fuse_mutex);
+	fc = file->f_dentry->d_inode->u.generic_ip;
+	if (fc)
+		fc = fuse_conn_get(fc);
+	mutex_unlock(&fuse_mutex);
+	return fc;
+}
+
+static ssize_t fuse_conn_abort_write(struct file *file, const char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	struct fuse_conn *fc = fuse_ctl_file_conn_get(file);
+	if (fc) {
+		fuse_abort_conn(fc);
+		fuse_conn_put(fc);
+	}
+	return count;
+}
+
+static ssize_t fuse_conn_waiting_read(struct file *file, char __user *buf,
+				      size_t len, loff_t *ppos)
+{
+	char tmp[32];
+	size_t size;
+
+	if (!*ppos) {
+		struct fuse_conn *fc = fuse_ctl_file_conn_get(file);
+		if (!fc)
+			return 0;
+
+		file->private_data=(void *)(long)atomic_read(&fc->num_waiting);
+		fuse_conn_put(fc);
+	}
+	size = sprintf(tmp, "%ld\n", (long)file->private_data);
+	return simple_read_from_buffer(buf, len, ppos, tmp, size);
+}
+
+static const struct file_operations fuse_ctl_abort_ops = {
+	.open = nonseekable_open,
+	.write = fuse_conn_abort_write,
+};
+
+static const struct file_operations fuse_ctl_waiting_ops = {
+	.open = nonseekable_open,
+	.read = fuse_conn_waiting_read,
+};
+
+static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
+					  struct fuse_conn *fc,
+					  const char *name,
+					  int mode, int nlink,
+					  struct inode_operations *iop,
+					  const struct file_operations *fop)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	BUG_ON(fc->ctl_ndents >= FUSE_CTL_NUM_DENTRIES);
+	dentry = d_alloc_name(parent, name);
+	if (!dentry)
+		return NULL;
+
+	fc->ctl_dentry[fc->ctl_ndents++] = dentry;
+	inode = new_inode(fuse_control_sb);
+	if (!inode)
+		return NULL;
+
+	inode->i_mode = mode;
+	inode->i_uid = fc->user_id;
+	inode->i_gid = fc->group_id;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	/* setting ->i_op to NULL is not allowed */
+	if (iop)
+		inode->i_op = iop;
+	inode->i_fop = fop;
+	inode->i_nlink = nlink;
+	inode->u.generic_ip = fc;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+/*
+ * Add a connection to the control filesystem (if it exists).  Caller
+ * must host fuse_mutex
+ */
+int fuse_ctl_add_conn(struct fuse_conn *fc)
+{
+	struct dentry *parent;
+	char name[32];
+
+	if (!fuse_control_sb)
+		return 0;
+
+	parent = fuse_control_sb->s_root;
+	parent->d_inode->i_nlink++;
+	sprintf(name, "%llu", (unsigned long long) fc->id);
+	parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2,
+				     &simple_dir_inode_operations,
+				     &simple_dir_operations);
+	if (!parent)
+		goto err;
+
+	if (!fuse_ctl_add_dentry(parent, fc, "waiting", S_IFREG | 0400, 1,
+				NULL, &fuse_ctl_waiting_ops) ||
+	    !fuse_ctl_add_dentry(parent, fc, "abort", S_IFREG | 0200, 1,
+				 NULL, &fuse_ctl_abort_ops))
+		goto err;
+
+	return 0;
+
+ err:
+	fuse_ctl_remove_conn(fc);
+	return -ENOMEM;
+}
+
+/*
+ * Remove a connection from the control filesystem (if it exists).
+ * Caller must host fuse_mutex
+ */
+void fuse_ctl_remove_conn(struct fuse_conn *fc)
+{
+	int i;
+
+	if (!fuse_control_sb)
+		return;
+
+	for (i = fc->ctl_ndents - 1; i >= 0; i--) {
+		struct dentry *dentry = fc->ctl_dentry[i];
+		dentry->d_inode->u.generic_ip = NULL;
+		d_drop(dentry);
+		dput(dentry);
+	}
+	fuse_control_sb->s_root->d_inode->i_nlink--;
+}
+
+static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct tree_descr empty_descr = {""};
+	struct fuse_conn *fc;
+	int err;
+
+	err = simple_fill_super(sb, FUSE_CTL_SUPER_MAGIC, &empty_descr);
+	if (err)
+		return err;
+
+	mutex_lock(&fuse_mutex);
+	BUG_ON(fuse_control_sb);
+	fuse_control_sb = sb;
+	list_for_each_entry(fc, &fuse_conn_list, entry) {
+		err = fuse_ctl_add_conn(fc);
+		if (err) {
+			fuse_control_sb = NULL;
+			mutex_unlock(&fuse_mutex);
+			return err;
+		}
+	}
+	mutex_unlock(&fuse_mutex);
+
+	return 0;
+}
+
+static int fuse_ctl_get_sb(struct file_system_type *fs_type, int flags,
+			const char *dev_name, void *raw_data,
+			struct vfsmount *mnt)
+{
+	return get_sb_single(fs_type, flags, raw_data,
+				fuse_ctl_fill_super, mnt);
+}
+
+static void fuse_ctl_kill_sb(struct super_block *sb)
+{
+	mutex_lock(&fuse_mutex);
+	fuse_control_sb = NULL;
+	mutex_unlock(&fuse_mutex);
+
+	kill_litter_super(sb);
+}
+
+static struct file_system_type fuse_ctl_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "fusectl",
+	.get_sb		= fuse_ctl_get_sb,
+	.kill_sb	= fuse_ctl_kill_sb,
+};
+
+int __init fuse_ctl_init(void)
+{
+	return register_filesystem(&fuse_ctl_fs_type);
+}
+
+void fuse_ctl_cleanup(void)
+{
+	unregister_filesystem(&fuse_ctl_fs_type);
+}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 104a62dadb9..1e2006caf15 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -34,6 +34,7 @@ static void fuse_request_init(struct fuse_req *req)
 {
 	memset(req, 0, sizeof(*req));
 	INIT_LIST_HEAD(&req->list);
+	INIT_LIST_HEAD(&req->intr_entry);
 	init_waitqueue_head(&req->waitq);
 	atomic_set(&req->count, 1);
 }
@@ -64,18 +65,6 @@ static void restore_sigs(sigset_t *oldset)
 	sigprocmask(SIG_SETMASK, oldset, NULL);
 }
 
-/*
- * Reset request, so that it can be reused
- *
- * The caller must be _very_ careful to make sure, that it is holding
- * the only reference to req
- */
-void fuse_reset_request(struct fuse_req *req)
-{
-	BUG_ON(atomic_read(&req->count) != 1);
-	fuse_request_init(req);
-}
-
 static void __fuse_get_request(struct fuse_req *req)
 {
 	atomic_inc(&req->count);
@@ -88,6 +77,13 @@ static void __fuse_put_request(struct fuse_req *req)
 	atomic_dec(&req->count);
 }
 
+static void fuse_req_init_context(struct fuse_req *req)
+{
+	req->in.h.uid = current->fsuid;
+	req->in.h.gid = current->fsgid;
+	req->in.h.pid = current->pid;
+}
+
 struct fuse_req *fuse_get_req(struct fuse_conn *fc)
 {
 	struct fuse_req *req;
@@ -103,14 +99,16 @@ struct fuse_req *fuse_get_req(struct fuse_conn *fc)
 	if (intr)
 		goto out;
 
+	err = -ENOTCONN;
+	if (!fc->connected)
+		goto out;
+
 	req = fuse_request_alloc();
 	err = -ENOMEM;
 	if (!req)
 		goto out;
 
-	req->in.h.uid = current->fsuid;
-	req->in.h.gid = current->fsgid;
-	req->in.h.pid = current->pid;
+	fuse_req_init_context(req);
 	req->waiting = 1;
 	return req;
 
@@ -119,142 +117,183 @@ struct fuse_req *fuse_get_req(struct fuse_conn *fc)
 	return ERR_PTR(err);
 }
 
-void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
+/*
+ * Return request in fuse_file->reserved_req.  However that may
+ * currently be in use.  If that is the case, wait for it to become
+ * available.
+ */
+static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
+					 struct file *file)
 {
-	if (atomic_dec_and_test(&req->count)) {
-		if (req->waiting)
-			atomic_dec(&fc->num_waiting);
-		fuse_request_free(req);
-	}
+	struct fuse_req *req = NULL;
+	struct fuse_file *ff = file->private_data;
+
+	do {
+		wait_event(fc->blocked_waitq, ff->reserved_req);
+		spin_lock(&fc->lock);
+		if (ff->reserved_req) {
+			req = ff->reserved_req;
+			ff->reserved_req = NULL;
+			get_file(file);
+			req->stolen_file = file;
+		}
+		spin_unlock(&fc->lock);
+	} while (!req);
+
+	return req;
 }
 
 /*
- * Called with sbput_sem held for read (request_end) or write
- * (fuse_put_super).  By the time fuse_put_super() is finished, all
- * inodes belonging to background requests must be released, so the
- * iputs have to be done within the locked region.
+ * Put stolen request back into fuse_file->reserved_req
  */
-void fuse_release_background(struct fuse_conn *fc, struct fuse_req *req)
+static void put_reserved_req(struct fuse_conn *fc, struct fuse_req *req)
 {
-	iput(req->inode);
-	iput(req->inode2);
+	struct file *file = req->stolen_file;
+	struct fuse_file *ff = file->private_data;
+
 	spin_lock(&fc->lock);
-	list_del(&req->bg_entry);
-	if (fc->num_background == FUSE_MAX_BACKGROUND) {
-		fc->blocked = 0;
-		wake_up_all(&fc->blocked_waitq);
-	}
-	fc->num_background--;
+	fuse_request_init(req);
+	BUG_ON(ff->reserved_req);
+	ff->reserved_req = req;
+	wake_up(&fc->blocked_waitq);
 	spin_unlock(&fc->lock);
+	fput(file);
 }
 
 /*
- * This function is called when a request is finished.  Either a reply
- * has arrived or it was interrupted (and not yet sent) or some error
- * occurred during communication with userspace, or the device file
- * was closed.  In case of a background request the reference to the
- * stored objects are released.  The requester thread is woken up (if
- * still waiting), the 'end' callback is called if given, else the
- * reference to the request is released
+ * Gets a requests for a file operation, always succeeds
  *
- * Releasing extra reference for foreground requests must be done
- * within the same locked region as setting state to finished.  This
- * is because fuse_reset_request() may be called after request is
- * finished and it must be the sole possessor.  If request is
- * interrupted and put in the background, it will return with an error
- * and hence never be reset and reused.
+ * This is used for sending the FLUSH request, which must get to
+ * userspace, due to POSIX locks which may need to be unlocked.
  *
- * Called with fc->lock, unlocks it
+ * If allocation fails due to OOM, use the reserved request in
+ * fuse_file.
+ *
+ * This is very unlikely to deadlock accidentally, since the
+ * filesystem should not have it's own file open.  If deadlock is
+ * intentional, it can still be broken by "aborting" the filesystem.
  */
-static void request_end(struct fuse_conn *fc, struct fuse_req *req)
+struct fuse_req *fuse_get_req_nofail(struct fuse_conn *fc, struct file *file)
 {
-	list_del(&req->list);
-	req->state = FUSE_REQ_FINISHED;
-	if (!req->background) {
-		spin_unlock(&fc->lock);
-		wake_up(&req->waitq);
-		fuse_put_request(fc, req);
-	} else {
-		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
-		req->end = NULL;
-		spin_unlock(&fc->lock);
-		down_read(&fc->sbput_sem);
-		if (fc->mounted)
-			fuse_release_background(fc, req);
-		up_read(&fc->sbput_sem);
+	struct fuse_req *req;
 
-		/* fput must go outside sbput_sem, otherwise it can deadlock */
-		if (req->file)
-			fput(req->file);
+	atomic_inc(&fc->num_waiting);
+	wait_event(fc->blocked_waitq, !fc->blocked);
+	req = fuse_request_alloc();
+	if (!req)
+		req = get_reserved_req(fc, file);
 
-		if (end)
-			end(fc, req);
+	fuse_req_init_context(req);
+	req->waiting = 1;
+	return req;
+}
+
+void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
+{
+	if (atomic_dec_and_test(&req->count)) {
+		if (req->waiting)
+			atomic_dec(&fc->num_waiting);
+
+		if (req->stolen_file)
+			put_reserved_req(fc, req);
 		else
-			fuse_put_request(fc, req);
+			fuse_request_free(req);
 	}
 }
 
 /*
- * Unfortunately request interruption not just solves the deadlock
- * problem, it causes problems too.  These stem from the fact, that an
- * interrupted request is continued to be processed in userspace,
- * while all the locks and object references (inode and file) held
- * during the operation are released.
- *
- * To release the locks is exactly why there's a need to interrupt the
- * request, so there's not a lot that can be done about this, except
- * introduce additional locking in userspace.
- *
- * More important is to keep inode and file references until userspace
- * has replied, otherwise FORGET and RELEASE could be sent while the
- * inode/file is still used by the filesystem.
- *
- * For this reason the concept of "background" request is introduced.
- * An interrupted request is backgrounded if it has been already sent
- * to userspace.  Backgrounding involves getting an extra reference to
- * inode(s) or file used in the request, and adding the request to
- * fc->background list.  When a reply is received for a background
- * request, the object references are released, and the request is
- * removed from the list.  If the filesystem is unmounted while there
- * are still background requests, the list is walked and references
- * are released as if a reply was received.
+ * This function is called when a request is finished.  Either a reply
+ * has arrived or it was aborted (and not yet sent) or some error
+ * occurred during communication with userspace, or the device file
+ * was closed.  The requester thread is woken up (if still waiting),
+ * the 'end' callback is called if given, else the reference to the
+ * request is released
  *
- * There's one more use for a background request.  The RELEASE message is
- * always sent as background, since it doesn't return an error or
- * data.
+ * Called with fc->lock, unlocks it
  */
-static void background_request(struct fuse_conn *fc, struct fuse_req *req)
-{
-	req->background = 1;
-	list_add(&req->bg_entry, &fc->background);
-	fc->num_background++;
-	if (fc->num_background == FUSE_MAX_BACKGROUND)
-		fc->blocked = 1;
-	if (req->inode)
-		req->inode = igrab(req->inode);
-	if (req->inode2)
-		req->inode2 = igrab(req->inode2);
+static void request_end(struct fuse_conn *fc, struct fuse_req *req)
+{
+	void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
+	req->end = NULL;
+	list_del(&req->list);
+	list_del(&req->intr_entry);
+	req->state = FUSE_REQ_FINISHED;
+	if (req->background) {
+		if (fc->num_background == FUSE_MAX_BACKGROUND) {
+			fc->blocked = 0;
+			wake_up_all(&fc->blocked_waitq);
+		}
+		fc->num_background--;
+	}
+	spin_unlock(&fc->lock);
+	dput(req->dentry);
+	mntput(req->vfsmount);
 	if (req->file)
-		get_file(req->file);
+		fput(req->file);
+	wake_up(&req->waitq);
+	if (end)
+		end(fc, req);
+	else
+		fuse_put_request(fc, req);
 }
 
-/* Called with fc->lock held.  Releases, and then reacquires it. */
-static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
+static void wait_answer_interruptible(struct fuse_conn *fc,
+				      struct fuse_req *req)
 {
-	sigset_t oldset;
+	if (signal_pending(current))
+		return;
 
 	spin_unlock(&fc->lock);
-	block_sigs(&oldset);
 	wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED);
-	restore_sigs(&oldset);
 	spin_lock(&fc->lock);
-	if (req->state == FUSE_REQ_FINISHED && !req->interrupted)
-		return;
+}
+
+static void queue_interrupt(struct fuse_conn *fc, struct fuse_req *req)
+{
+	list_add_tail(&req->intr_entry, &fc->interrupts);
+	wake_up(&fc->waitq);
+	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+}
+
+/* Called with fc->lock held.  Releases, and then reacquires it. */
+static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
+{
+	if (!fc->no_interrupt) {
+		/* Any signal may interrupt this */
+		wait_answer_interruptible(fc, req);
+
+		if (req->aborted)
+			goto aborted;
+		if (req->state == FUSE_REQ_FINISHED)
+			return;
 
-	if (!req->interrupted) {
-		req->out.h.error = -EINTR;
 		req->interrupted = 1;
+		if (req->state == FUSE_REQ_SENT)
+			queue_interrupt(fc, req);
+	}
+
+	if (req->force) {
+		spin_unlock(&fc->lock);
+		wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+		spin_lock(&fc->lock);
+	} else {
+		sigset_t oldset;
+
+		/* Only fatal signals may interrupt this */
+		block_sigs(&oldset);
+		wait_answer_interruptible(fc, req);
+		restore_sigs(&oldset);
 	}
+
+	if (req->aborted)
+		goto aborted;
+	if (req->state == FUSE_REQ_FINISHED)
+ 		return;
+
+	req->out.h.error = -EINTR;
+	req->aborted = 1;
+
+ aborted:
 	if (req->locked) {
 		/* This is uninterruptible sleep, because data is
 		   being copied to/from the buffers of req.  During
@@ -268,8 +307,11 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
 	if (req->state == FUSE_REQ_PENDING) {
 		list_del(&req->list);
 		__fuse_put_request(req);
-	} else if (req->state == FUSE_REQ_SENT)
-		background_request(fc, req);
+	} else if (req->state == FUSE_REQ_SENT) {
+		spin_unlock(&fc->lock);
+		wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+		spin_lock(&fc->lock);
+	}
 }
 
 static unsigned len_args(unsigned numargs, struct fuse_arg *args)
@@ -283,13 +325,19 @@ static unsigned len_args(unsigned numargs, struct fuse_arg *args)
 	return nbytes;
 }
 
+static u64 fuse_get_unique(struct fuse_conn *fc)
+ {
+ 	fc->reqctr++;
+ 	/* zero is special */
+ 	if (fc->reqctr == 0)
+ 		fc->reqctr = 1;
+
+	return fc->reqctr;
+}
+
 static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
 {
-	fc->reqctr++;
-	/* zero is special */
-	if (fc->reqctr == 0)
-		fc->reqctr = 1;
-	req->in.h.unique = fc->reqctr;
+	req->in.h.unique = fuse_get_unique(fc);
 	req->in.h.len = sizeof(struct fuse_in_header) +
 		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
 	list_add_tail(&req->list, &fc->pending);
@@ -302,9 +350,6 @@ static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
 	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
 }
 
-/*
- * This can only be interrupted by a SIGKILL
- */
 void request_send(struct fuse_conn *fc, struct fuse_req *req)
 {
 	req->isreply = 1;
@@ -327,8 +372,12 @@ void request_send(struct fuse_conn *fc, struct fuse_req *req)
 static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
 {
 	spin_lock(&fc->lock);
-	background_request(fc, req);
 	if (fc->connected) {
+		req->background = 1;
+		fc->num_background++;
+		if (fc->num_background == FUSE_MAX_BACKGROUND)
+			fc->blocked = 1;
+
 		queue_request(fc, req);
 		spin_unlock(&fc->lock);
 	} else {
@@ -352,14 +401,14 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req)
 /*
  * Lock the request.  Up to the next unlock_request() there mustn't be
  * anything that could cause a page-fault.  If the request was already
- * interrupted bail out.
+ * aborted bail out.
  */
 static int lock_request(struct fuse_conn *fc, struct fuse_req *req)
 {
 	int err = 0;
 	if (req) {
 		spin_lock(&fc->lock);
-		if (req->interrupted)
+		if (req->aborted)
 			err = -ENOENT;
 		else
 			req->locked = 1;
@@ -369,7 +418,7 @@ static int lock_request(struct fuse_conn *fc, struct fuse_req *req)
 }
 
 /*
- * Unlock request.  If it was interrupted during being locked, the
+ * Unlock request.  If it was aborted during being locked, the
  * requester thread is currently waiting for it to be unlocked, so
  * wake it up.
  */
@@ -378,7 +427,7 @@ static void unlock_request(struct fuse_conn *fc, struct fuse_req *req)
 	if (req) {
 		spin_lock(&fc->lock);
 		req->locked = 0;
-		if (req->interrupted)
+		if (req->aborted)
 			wake_up(&req->waitq);
 		spin_unlock(&fc->lock);
 	}
@@ -557,13 +606,18 @@ static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
 	return err;
 }
 
+static int request_pending(struct fuse_conn *fc)
+{
+	return !list_empty(&fc->pending) || !list_empty(&fc->interrupts);
+}
+
 /* Wait until a request is available on the pending list */
 static void request_wait(struct fuse_conn *fc)
 {
 	DECLARE_WAITQUEUE(wait, current);
 
 	add_wait_queue_exclusive(&fc->waitq, &wait);
-	while (fc->connected && list_empty(&fc->pending)) {
+	while (fc->connected && !request_pending(fc)) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (signal_pending(current))
 			break;
@@ -577,11 +631,50 @@ static void request_wait(struct fuse_conn *fc)
 }
 
 /*
+ * Transfer an interrupt request to userspace
+ *
+ * Unlike other requests this is assembled on demand, without a need
+ * to allocate a separate fuse_req structure.
+ *
+ * Called with fc->lock held, releases it
+ */
+static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req,
+			       const struct iovec *iov, unsigned long nr_segs)
+{
+	struct fuse_copy_state cs;
+	struct fuse_in_header ih;
+	struct fuse_interrupt_in arg;
+	unsigned reqsize = sizeof(ih) + sizeof(arg);
+	int err;
+
+	list_del_init(&req->intr_entry);
+	req->intr_unique = fuse_get_unique(fc);
+	memset(&ih, 0, sizeof(ih));
+	memset(&arg, 0, sizeof(arg));
+	ih.len = reqsize;
+	ih.opcode = FUSE_INTERRUPT;
+	ih.unique = req->intr_unique;
+	arg.unique = req->in.h.unique;
+
+	spin_unlock(&fc->lock);
+	if (iov_length(iov, nr_segs) < reqsize)
+		return -EINVAL;
+
+	fuse_copy_init(&cs, fc, 1, NULL, iov, nr_segs);
+	err = fuse_copy_one(&cs, &ih, sizeof(ih));
+	if (!err)
+		err = fuse_copy_one(&cs, &arg, sizeof(arg));
+	fuse_copy_finish(&cs);
+
+	return err ? err : reqsize;
+}
+
+/*
  * Read a single request into the userspace filesystem's buffer.  This
  * function waits until a request is available, then removes it from
  * the pending list and copies request data to userspace buffer.  If
- * no reply is needed (FORGET) or request has been interrupted or
- * there was an error during the copying then it's finished by calling
+ * no reply is needed (FORGET) or request has been aborted or there
+ * was an error during the copying then it's finished by calling
  * request_end().  Otherwise add it to the processing list, and set
  * the 'sent' flag.
  */
@@ -601,7 +694,7 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
 	spin_lock(&fc->lock);
 	err = -EAGAIN;
 	if ((file->f_flags & O_NONBLOCK) && fc->connected &&
-	    list_empty(&fc->pending))
+	    !request_pending(fc))
 		goto err_unlock;
 
 	request_wait(fc);
@@ -609,9 +702,15 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
 	if (!fc->connected)
 		goto err_unlock;
 	err = -ERESTARTSYS;
-	if (list_empty(&fc->pending))
+	if (!request_pending(fc))
 		goto err_unlock;
 
+	if (!list_empty(&fc->interrupts)) {
+		req = list_entry(fc->interrupts.next, struct fuse_req,
+				 intr_entry);
+		return fuse_read_interrupt(fc, req, iov, nr_segs);
+	}
+
 	req = list_entry(fc->pending.next, struct fuse_req, list);
 	req->state = FUSE_REQ_READING;
 	list_move(&req->list, &fc->io);
@@ -636,10 +735,10 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
 	fuse_copy_finish(&cs);
 	spin_lock(&fc->lock);
 	req->locked = 0;
-	if (!err && req->interrupted)
+	if (!err && req->aborted)
 		err = -ENOENT;
 	if (err) {
-		if (!req->interrupted)
+		if (!req->aborted)
 			req->out.h.error = -EIO;
 		request_end(fc, req);
 		return err;
@@ -649,6 +748,8 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
 	else {
 		req->state = FUSE_REQ_SENT;
 		list_move_tail(&req->list, &fc->processing);
+		if (req->interrupted)
+			queue_interrupt(fc, req);
 		spin_unlock(&fc->lock);
 	}
 	return reqsize;
@@ -675,7 +776,7 @@ static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique)
 	list_for_each(entry, &fc->processing) {
 		struct fuse_req *req;
 		req = list_entry(entry, struct fuse_req, list);
-		if (req->in.h.unique == unique)
+		if (req->in.h.unique == unique || req->intr_unique == unique)
 			return req;
 	}
 	return NULL;
@@ -741,17 +842,33 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov,
 		goto err_unlock;
 
 	req = request_find(fc, oh.unique);
-	err = -EINVAL;
 	if (!req)
 		goto err_unlock;
 
-	if (req->interrupted) {
+	if (req->aborted) {
 		spin_unlock(&fc->lock);
 		fuse_copy_finish(&cs);
 		spin_lock(&fc->lock);
 		request_end(fc, req);
 		return -ENOENT;
 	}
+	/* Is it an interrupt reply? */
+	if (req->intr_unique == oh.unique) {
+		err = -EINVAL;
+		if (nbytes != sizeof(struct fuse_out_header))
+			goto err_unlock;
+
+		if (oh.error == -ENOSYS)
+			fc->no_interrupt = 1;
+		else if (oh.error == -EAGAIN)
+			queue_interrupt(fc, req);
+
+		spin_unlock(&fc->lock);
+		fuse_copy_finish(&cs);
+		return nbytes;
+	}
+
+	req->state = FUSE_REQ_WRITING;
 	list_move(&req->list, &fc->io);
 	req->out.h = oh;
 	req->locked = 1;
@@ -764,9 +881,9 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov,
 	spin_lock(&fc->lock);
 	req->locked = 0;
 	if (!err) {
-		if (req->interrupted)
+		if (req->aborted)
 			err = -ENOENT;
-	} else if (!req->interrupted)
+	} else if (!req->aborted)
 		req->out.h.error = -EIO;
 	request_end(fc, req);
 
@@ -800,7 +917,7 @@ static unsigned fuse_dev_poll(struct file *file, poll_table *wait)
 	spin_lock(&fc->lock);
 	if (!fc->connected)
 		mask = POLLERR;
-	else if (!list_empty(&fc->pending))
+	else if (request_pending(fc))
 		mask |= POLLIN | POLLRDNORM;
 	spin_unlock(&fc->lock);
 
@@ -826,7 +943,7 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
 /*
  * Abort requests under I/O
  *
- * The requests are set to interrupted and finished, and the request
+ * The requests are set to aborted and finished, and the request
  * waiter is woken up.  This will make request_wait_answer() wait
  * until the request is unlocked and then return.
  *
@@ -841,7 +958,7 @@ static void end_io_requests(struct fuse_conn *fc)
 			list_entry(fc->io.next, struct fuse_req, list);
 		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
 
-		req->interrupted = 1;
+		req->aborted = 1;
 		req->out.h.error = -ECONNABORTED;
 		req->state = FUSE_REQ_FINISHED;
 		list_del_init(&req->list);
@@ -874,19 +991,20 @@ static void end_io_requests(struct fuse_conn *fc)
  * onto the pending list is prevented by req->connected being false.
  *
  * Progression of requests under I/O to the processing list is
- * prevented by the req->interrupted flag being true for these
- * requests.  For this reason requests on the io list must be aborted
- * first.
+ * prevented by the req->aborted flag being true for these requests.
+ * For this reason requests on the io list must be aborted first.
  */
 void fuse_abort_conn(struct fuse_conn *fc)
 {
 	spin_lock(&fc->lock);
 	if (fc->connected) {
 		fc->connected = 0;
+		fc->blocked = 0;
 		end_io_requests(fc);
 		end_requests(fc, &fc->pending);
 		end_requests(fc, &fc->processing);
 		wake_up_all(&fc->waitq);
+		wake_up_all(&fc->blocked_waitq);
 		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
 	}
 	spin_unlock(&fc->lock);
@@ -902,7 +1020,7 @@ static int fuse_dev_release(struct inode *inode, struct file *file)
 		end_requests(fc, &fc->processing);
 		spin_unlock(&fc->lock);
 		fasync_helper(-1, file, 0, &fc->fasync);
-		kobject_put(&fc->kobj);
+		fuse_conn_put(fc);
 	}
 
 	return 0;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 8d7546e832e..72a74cde6de 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1,6 +1,6 @@
 /*
   FUSE: Filesystem in Userspace
-  Copyright (C) 2001-2005  Miklos Szeredi <miklos@szeredi.hu>
+  Copyright (C) 2001-2006  Miklos Szeredi <miklos@szeredi.hu>
 
   This program can be distributed under the terms of the GNU GPL.
   See the file COPYING.
@@ -79,7 +79,6 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir,
 {
 	req->in.h.opcode = FUSE_LOOKUP;
 	req->in.h.nodeid = get_node_id(dir);
-	req->inode = dir;
 	req->in.numargs = 1;
 	req->in.args[0].size = entry->d_name.len + 1;
 	req->in.args[0].value = entry->d_name.name;
@@ -225,6 +224,20 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 }
 
 /*
+ * Synchronous release for the case when something goes wrong in CREATE_OPEN
+ */
+static void fuse_sync_release(struct fuse_conn *fc, struct fuse_file *ff,
+			      u64 nodeid, int flags)
+{
+	struct fuse_req *req;
+
+	req = fuse_release_fill(ff, nodeid, flags, FUSE_RELEASE);
+	req->force = 1;
+	request_send(fc, req);
+	fuse_put_request(fc, req);
+}
+
+/*
  * Atomic create+open operation
  *
  * If the filesystem doesn't support this, then fall back to separate
@@ -237,6 +250,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	struct inode *inode;
 	struct fuse_conn *fc = get_fuse_conn(dir);
 	struct fuse_req *req;
+	struct fuse_req *forget_req;
 	struct fuse_open_in inarg;
 	struct fuse_open_out outopen;
 	struct fuse_entry_out outentry;
@@ -247,9 +261,14 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	if (fc->no_create)
 		return -ENOSYS;
 
+	forget_req = fuse_get_req(fc);
+	if (IS_ERR(forget_req))
+		return PTR_ERR(forget_req);
+
 	req = fuse_get_req(fc);
+	err = PTR_ERR(req);
 	if (IS_ERR(req))
-		return PTR_ERR(req);
+		goto out_put_forget_req;
 
 	err = -ENOMEM;
 	ff = fuse_file_alloc();
@@ -262,7 +281,6 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	inarg.mode = mode;
 	req->in.h.opcode = FUSE_CREATE;
 	req->in.h.nodeid = get_node_id(dir);
-	req->inode = dir;
 	req->in.numargs = 2;
 	req->in.args[0].size = sizeof(inarg);
 	req->in.args[0].value = &inarg;
@@ -285,25 +303,23 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
 		goto out_free_ff;
 
+	fuse_put_request(fc, req);
 	inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
 			  &outentry.attr);
-	err = -ENOMEM;
 	if (!inode) {
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		ff->fh = outopen.fh;
-		/* Special release, with inode = NULL, this will
-		   trigger a 'forget' request when the release is
-		   complete */
-		fuse_send_release(fc, ff, outentry.nodeid, NULL, flags, 0);
-		goto out_put_request;
+		fuse_sync_release(fc, ff, outentry.nodeid, flags);
+		fuse_send_forget(fc, forget_req, outentry.nodeid, 1);
+		return -ENOMEM;
 	}
-	fuse_put_request(fc, req);
+	fuse_put_request(fc, forget_req);
 	d_instantiate(entry, inode);
 	fuse_change_timeout(entry, &outentry);
 	file = lookup_instantiate_filp(nd, entry, generic_file_open);
 	if (IS_ERR(file)) {
 		ff->fh = outopen.fh;
-		fuse_send_release(fc, ff, outentry.nodeid, inode, flags, 0);
+		fuse_sync_release(fc, ff, outentry.nodeid, flags);
 		return PTR_ERR(file);
 	}
 	fuse_finish_open(inode, file, ff, &outopen);
@@ -313,6 +329,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	fuse_file_free(ff);
  out_put_request:
 	fuse_put_request(fc, req);
+ out_put_forget_req:
+	fuse_put_request(fc, forget_req);
 	return err;
 }
 
@@ -328,7 +346,6 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
 	int err;
 
 	req->in.h.nodeid = get_node_id(dir);
-	req->inode = dir;
 	req->out.numargs = 1;
 	req->out.args[0].size = sizeof(outarg);
 	req->out.args[0].value = &outarg;
@@ -448,7 +465,6 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry)
 
 	req->in.h.opcode = FUSE_UNLINK;
 	req->in.h.nodeid = get_node_id(dir);
-	req->inode = dir;
 	req->in.numargs = 1;
 	req->in.args[0].size = entry->d_name.len + 1;
 	req->in.args[0].value = entry->d_name.name;
@@ -480,7 +496,6 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
 
 	req->in.h.opcode = FUSE_RMDIR;
 	req->in.h.nodeid = get_node_id(dir);
-	req->inode = dir;
 	req->in.numargs = 1;
 	req->in.args[0].size = entry->d_name.len + 1;
 	req->in.args[0].value = entry->d_name.name;
@@ -510,8 +525,6 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
 	inarg.newdir = get_node_id(newdir);
 	req->in.h.opcode = FUSE_RENAME;
 	req->in.h.nodeid = get_node_id(olddir);
-	req->inode = olddir;
-	req->inode2 = newdir;
 	req->in.numargs = 3;
 	req->in.args[0].size = sizeof(inarg);