fuse: add more control over cache invalidation behaviour

Currently userspace is able to notify the kernel to invalidate the cache
for an inode.  This means that, if all the inodes in a filesystem need to
be invalidated, then userspace needs to iterate through all of them and do
this kernel notification separately.

This patch adds the concept of 'epoch': each fuse connection will have the
current epoch initialized and every new dentry will have it's d_time set to
the current epoch value.  A new operation will then allow userspace to
increment the epoch value.  Every time a dentry is d_revalidate()'ed, it's
epoch is compared with the current connection epoch and invalidated if it's
value is different.

Signed-off-by: Luis Henriques <luis@igalia.com>
Tested-by: Laura Promberger <laura.promberger@cern.ch>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Author: luis-henrix

fs/fuse/dev.c

@@ -2021,6 +2021,19 @@ static int fuse_notify_resend(struct fuse_conn *fc)
 	return 0;
 }
 
+/*
+ * Increments the fuse connection epoch.  This will result of dentries from
+ * previous epochs to be invalidated.
+ *
+ * XXX optimization: add call to shrink_dcache_sb()?
+ */
+static int fuse_notify_inc_epoch(struct fuse_conn *fc)
+{
+	atomic_inc(&fc->epoch);
+
+	return 0;
+}
+
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
@@ -2049,6 +2062,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 	case FUSE_NOTIFY_RESEND:
 		return fuse_notify_resend(fc);
 
+	case FUSE_NOTIFY_INC_EPOCH:
+		return fuse_notify_inc_epoch(fc);
+
 	default:
 		fuse_copy_finish(cs);
 		return -EINVAL;

fs/fuse/dir.c

@@ -200,9 +200,14 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
 {
 	struct inode *inode;
 	struct fuse_mount *fm;
+	struct fuse_conn *fc;
 	struct fuse_inode *fi;
 	int ret;
 
+	fc = get_fuse_conn_super(dir->i_sb);
+	if (entry->d_time < atomic_read(&fc->epoch))
+		goto invalid;
+
 	inode = d_inode_rcu(entry);
 	if (inode && fuse_is_bad(inode))
 		goto invalid;
@@ -415,16 +420,20 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 				  unsigned int flags)
 {
-	int err;
 	struct fuse_entry_out outarg;
+	struct fuse_conn *fc;
 	struct inode *inode;
 	struct dentry *newent;
+	int err, epoch;
 	bool outarg_valid = true;
 	bool locked;
 
 	if (fuse_is_bad(dir))
 		return ERR_PTR(-EIO);
 
+	fc = get_fuse_conn_super(dir->i_sb);
+	epoch = atomic_read(&fc->epoch);
+
 	locked = fuse_lock_inode(dir);
 	err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
 			       &outarg, &inode);
@@ -446,6 +455,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 		goto out_err;
 
 	entry = newent ? newent : entry;
+	entry->d_time = epoch;
 	if (outarg_valid)
 		fuse_change_entry_timeout(entry, &outarg);
 	else
@@ -619,7 +629,6 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 			    struct dentry *entry, struct file *file,
 			    unsigned int flags, umode_t mode, u32 opcode)
 {
-	int err;
 	struct inode *inode;
 	struct fuse_mount *fm = get_fuse_mount(dir);
 	FUSE_ARGS(args);
@@ -629,11 +638,13 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	struct fuse_entry_out outentry;
 	struct fuse_inode *fi;
 	struct fuse_file *ff;
+	int epoch, err;
 	bool trunc = flags & O_TRUNC;
 
 	/* Userspace expects S_IFREG in create mode */
 	BUG_ON((mode & S_IFMT) != S_IFREG);
 
+	epoch = atomic_read(&fm->fc->epoch);
 	forget = fuse_alloc_forget();
 	err = -ENOMEM;
 	if (!forget)
@@ -702,6 +713,7 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	}
 	kfree(forget);
 	d_instantiate(entry, inode);
+	entry->d_time = epoch;
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_dir_changed(dir);
 	err = generic_file_open(inode, file);
@@ -788,12 +800,14 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun
 	struct fuse_entry_out outarg;
 	struct inode *inode;
 	struct dentry *d;
-	int err;
 	struct fuse_forget_link *forget;
+	int epoch, err;
 
 	if (fuse_is_bad(dir))
 		return ERR_PTR(-EIO);
 
+	epoch = atomic_read(&fm->fc->epoch);
+
 	forget = fuse_alloc_forget();
 	if (!forget)
 		return ERR_PTR(-ENOMEM);
@@ -835,10 +849,13 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun
 	if (IS_ERR(d))
 		return d;
 
-	if (d)
+	if (d) {
+		d->d_time = epoch;
 		fuse_change_entry_timeout(d, &outarg);
-	else
+	} else {
+		entry->d_time = epoch;
 		fuse_change_entry_timeout(entry, &outarg);
+	}
 	fuse_dir_changed(dir);
 	return d;
 

fs/fuse/fuse_i.h

@@ -636,6 +636,9 @@ struct fuse_conn {
 	/** Number of fuse_dev's */
 	atomic_t dev_count;
 
+	/** Current epoch for up-to-date dentries */
+	atomic_t epoch;
+
 	struct rcu_head rcu;
 
 	/** The user id for this mount */

fs/fuse/inode.c

@@ -962,6 +962,7 @@ 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_waitqueue_head(&fc->blocked_waitq);
 	fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv);
 	INIT_LIST_HEAD(&fc->bg_queue);

fs/fuse/readdir.c

@@ -161,6 +161,7 @@ static int fuse_direntplus_link(struct file *file,
 	struct fuse_conn *fc;
 	struct inode *inode;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	int epoch;
 
 	if (!o->nodeid) {
 		/*
@@ -190,6 +191,7 @@ static int fuse_direntplus_link(struct file *file,
 		return -EIO;
 
 	fc = get_fuse_conn(dir);
+	epoch = atomic_read(&fc->epoch);
 
 	name.hash = full_name_hash(parent, name.name, name.len);
 	dentry = d_lookup(parent, &name);
@@ -256,6 +258,7 @@ static int fuse_direntplus_link(struct file *file,
 	}
 	if (fc->readdirplus_auto)
 		set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
+	dentry->d_time = epoch;
 	fuse_change_entry_timeout(dentry, o);
 
 	dput(dentry);

include/uapi/linux/fuse.h

@@ -232,6 +232,9 @@
  *
  *  7.43
  *  - add FUSE_REQUEST_TIMEOUT
+ *
+ *  7.44
+ *  - add FUSE_NOTIFY_INC_EPOCH
  */
 
 #ifndef _LINUX_FUSE_H
@@ -267,7 +270,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 43
+#define FUSE_KERNEL_MINOR_VERSION 44
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -671,6 +674,7 @@ enum fuse_notify_code {
 	FUSE_NOTIFY_RETRIEVE = 5,
 	FUSE_NOTIFY_DELETE = 6,
 	FUSE_NOTIFY_RESEND = 7,
+	FUSE_NOTIFY_INC_EPOCH = 8,
 	FUSE_NOTIFY_CODE_MAX,
 };