4 files changed, 111 insertions, 43 deletions

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 334e0b1..324bc08 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -154,7 +154,7 @@ u64 fuse_get_attr_version(struct fuse_conn *fc)
  * the lookup once more.  If the lookup results in the same inode,
  * then refresh the attributes, timeouts and mark the dentry valid.
  */
-static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
+static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 {
 	struct inode *inode;
 
@@ -174,7 +174,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 		if (!inode)
 			return 0;
 
-		if (nd && (nd->flags & LOOKUP_RCU))
+		if (flags & LOOKUP_RCU)
 			return -ECHILD;
 
 		fc = get_fuse_conn(inode);
@@ -249,7 +249,7 @@ static struct dentry *fuse_d_add_directory(struct dentry *entry,
 		/* This tries to shrink the subtree below alias */
 		fuse_invalidate_entry(alias);
 		dput(alias);
-		if (!list_empty(&inode->i_dentry))
+		if (!hlist_empty(&inode->i_dentry))
 			return ERR_PTR(-EBUSY);
 	} else {
 		dput(alias);
@@ -316,7 +316,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 }
 
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	int err;
 	struct fuse_entry_out outarg;
@@ -370,7 +370,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  * 'mknod' + 'open' requests.
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
-			    umode_t mode, struct nameidata *nd)
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
 {
 	int err;
 	struct inode *inode;
@@ -381,15 +382,14 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	struct fuse_open_out outopen;
 	struct fuse_entry_out outentry;
 	struct fuse_file *ff;
-	struct file *file;
-	int flags = nd->intent.open.flags;
 
-	if (fc->no_create)
-		return -ENOSYS;
+	/* Userspace expects S_IFREG in create mode */
+	BUG_ON((mode & S_IFMT) != S_IFREG);
 
 	forget = fuse_alloc_forget();
+	err = -ENOMEM;
 	if (!forget)
-		return -ENOMEM;
+		goto out_err;
 
 	req = fuse_get_req(fc);
 	err = PTR_ERR(req);
@@ -428,11 +428,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	req->out.args[1].value = &outopen;
 	fuse_request_send(fc, req);
 	err = req->out.h.error;
-	if (err) {
-		if (err == -ENOSYS)
-			fc->no_create = 1;
+	if (err)
 		goto out_free_ff;
-	}
 
 	err = -EIO;
 	if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
@@ -448,30 +445,76 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(ff, flags);
 		fuse_queue_forget(fc, forget, outentry.nodeid, 1);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out_err;
 	}
 	kfree(forget);
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	file = lookup_instantiate_filp(nd, entry, generic_file_open);
-	if (IS_ERR(file)) {
+	err = finish_open(file, entry, generic_file_open, opened);
+	if (err) {
 		fuse_sync_release(ff, flags);
-		return PTR_ERR(file);
+	} else {
+		file->private_data = fuse_file_get(ff);
+		fuse_finish_open(inode, file);
 	}
-	file->private_data = fuse_file_get(ff);
-	fuse_finish_open(inode, file);
-	return 0;
+	return err;
 
- out_free_ff:
+out_free_ff:
 	fuse_file_free(ff);
- out_put_request:
+out_put_request:
 	fuse_put_request(fc, req);
- out_put_forget_req:
+out_put_forget_req:
 	kfree(forget);
+out_err:
 	return err;
 }
 
+static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
+{
+	int err;
+	struct fuse_conn *fc = get_fuse_conn(dir);
+	struct dentry *res = NULL;
+
+	if (d_unhashed(entry)) {
+		res = fuse_lookup(dir, entry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			entry = res;
+	}
+
+	if (!(flags & O_CREAT) || entry->d_inode)
+		goto no_open;
+
+	/* Only creates */
+	*opened |= FILE_CREATED;
+
+	if (fc->no_create)
+		goto mknod;
+
+	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	if (err == -ENOSYS) {
+		fc->no_create = 1;
+		goto mknod;
+	}
+out_dput:
+	dput(res);
+	return err;
+
+mknod:
+	err = fuse_mknod(dir, entry, mode, 0);
+	if (err)
+		goto out_dput;
+no_open:
+	return finish_no_open(file, res);
+}
+
 /*
  * Code shared between mknod, mkdir, symlink and link
  */
@@ -571,14 +614,8 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode,
 }
 
 static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
-	if (nd) {
-		int err = fuse_create_open(dir, entry, mode, nd);
-		if (err != -ENOSYS)
-			return err;
-		/* Fall back on mknod */
-	}
 	return fuse_mknod(dir, entry, mode, 0);
 }
 
@@ -1646,6 +1683,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
 	.link		= fuse_link,
 	.setattr	= fuse_setattr,
 	.create		= fuse_create,
+	.atomic_open	= fuse_atomic_open,
 	.mknod		= fuse_mknod,
 	.permission	= fuse_permission,
 	.getattr	= fuse_getattr,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b321a68..aba15f1 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -703,13 +703,16 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 				  unsigned long nr_segs, loff_t pos)
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	struct fuse_conn *fc = get_fuse_conn(inode);
 
-	if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) {
+	/*
+	 * In auto invalidate mode, always update attributes on read.
+	 * Otherwise, only update if we attempt to read past EOF (to ensure
+	 * i_size is up to date).
+	 */
+	if (fc->auto_inval_data ||
+	    (pos + iov_length(iov, nr_segs) > i_size_read(inode))) {
 		int err;
-		/*
-		 * If trying to read past EOF, make sure the i_size
-		 * attribute is up-to-date.
-		 */
 		err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
 		if (err)
 			return err;
@@ -944,9 +947,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-
+	sb_start_write(inode->i_sb);
 	mutex_lock(&inode->i_mutex);
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -1004,6 +1006,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 out:
 	current->backing_dev_info = NULL;
 	mutex_unlock(&inode->i_mutex);
+	sb_end_write(inode->i_sb);
 
 	return written ? written : err;
 }
@@ -1700,7 +1703,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count)
 	size_t n;
 	u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT;
 
-	for (n = 0; n < count; n++) {
+	for (n = 0; n < count; n++, iov++) {
 		if (iov->iov_len > (size_t) max)
 			return -ENOMEM;
 		max -= iov->iov_len;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 771fb63..e24dd74 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -484,6 +484,9 @@ struct fuse_conn {
 	/** Is fallocate not implemented by fs? */
 	unsigned no_fallocate:1;
 
+	/** Use enhanced/automatic page cache invalidation. */
+	unsigned auto_inval_data:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1cd6165..ce0a283 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -197,6 +197,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	loff_t oldsize;
+	struct timespec old_mtime;
 
 	spin_lock(&fc->lock);
 	if (attr_version != 0 && fi->attr_version > attr_version) {
@@ -204,15 +205,35 @@ 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);
 
 	oldsize = inode->i_size;
 	i_size_write(inode, attr->size);
 	spin_unlock(&fc->lock);
 
-	if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
-		truncate_pagecache(inode, oldsize, attr->size);
-		invalidate_inode_pages2(inode->i_mapping);
+	if (S_ISREG(inode->i_mode)) {
+		bool inval = false;
+
+		if (oldsize != attr->size) {
+			truncate_pagecache(inode, oldsize, 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);
 	}
 }
 
@@ -834,6 +855,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				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;
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
@@ -859,7 +882,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
-		FUSE_FLOCK_LOCKS;
+		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
+		FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);