fuse: add prune notification

Some fuse servers need to prune their caches, which can only be done if the
kernel's own dentry/inode caches are pruned first to avoid dangling
references.

Add FUSE_NOTIFY_PRUNE, which takes an array of node ID's to try and get rid
of.  Inodes with active references are skipped.

A similar functionality is already provided by FUSE_NOTIFY_INVAL_ENTRY with
the FUSE_EXPIRE_ONLY flag.  Differences in the interface are

FUSE_NOTIFY_INVAL_ENTRY:

  - can only prune one dentry

  - dentry is determined by parent ID and name

  - if inode has multiple aliases (cached hard links), then they would have
    to be invalidated individually to be able to get rid of the inode

FUSE_NOTIFY_PRUNE:

  - can prune multiple inodes

  - inodes determined by their node ID

  - aliases are taken care of automatically

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/dev.c

@@ -2034,6 +2034,42 @@ static int fuse_notify_inc_epoch(struct fuse_conn *fc)
 	return 0;
 }
 
+static int fuse_notify_prune(struct fuse_conn *fc, unsigned int size,
+			     struct fuse_copy_state *cs)
+{
+	struct fuse_notify_prune_out outarg;
+	const unsigned int batch = 512;
+	u64 *nodeids __free(kfree) = kmalloc(sizeof(u64) * batch, GFP_KERNEL);
+	unsigned int num, i;
+	int err;
+
+	if (!nodeids)
+		return -ENOMEM;
+
+	if (size < sizeof(outarg))
+		return -EINVAL;
+
+	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
+	if (err)
+		return err;
+
+	if (size - sizeof(outarg) != outarg.count * sizeof(u64))
+		return -EINVAL;
+
+	for (; outarg.count; outarg.count -= num) {
+		num = min(batch, outarg.count);
+		err = fuse_copy_one(cs, nodeids, num * sizeof(u64));
+		if (err)
+			return err;
+
+		scoped_guard(rwsem_read, &fc->killsb) {
+			for (i = 0; i < num; i++)
+				fuse_try_prune_one_inode(fc, nodeids[i]);
+		}
+	}
+	return 0;
+}
+
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
@@ -2065,6 +2101,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 	case FUSE_NOTIFY_INC_EPOCH:
 		return fuse_notify_inc_epoch(fc);
 
+	case FUSE_NOTIFY_PRUNE:
+		return fuse_notify_prune(fc, size, cs);
+
 	default:
 		return -EINVAL;
 	}

fs/fuse/fuse_i.h

@@ -1413,6 +1413,12 @@ int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid,
 int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid,
 			     u64 child_nodeid, struct qstr *name, u32 flags);
 
+/*
+ * Try to prune this inode.  If neither the inode itself nor dentries associated
+ * with this inode have any external reference, then the inode can be freed.
+ */
+void fuse_try_prune_one_inode(struct fuse_conn *fc, u64 nodeid);
+
 int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
 		 bool isdir);
 

fs/fuse/inode.c

@@ -585,6 +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;

include/uapi/linux/fuse.h

@@ -239,6 +239,7 @@
  *  7.45
  *  - add FUSE_COPY_FILE_RANGE_64
  *  - add struct fuse_copy_file_range_out
+ *  - add FUSE_NOTIFY_PRUNE
  */
 
 #ifndef _LINUX_FUSE_H
@@ -680,6 +681,7 @@ enum fuse_notify_code {
 	FUSE_NOTIFY_DELETE = 6,
 	FUSE_NOTIFY_RESEND = 7,
 	FUSE_NOTIFY_INC_EPOCH = 8,
+	FUSE_NOTIFY_PRUNE = 9,
 };
 
 /* The read buffer is required to be at least 8k, but may be much larger */
@@ -1118,6 +1120,12 @@ struct fuse_notify_retrieve_in {
 	uint64_t	dummy4;
 };
 
+struct fuse_notify_prune_out {
+	uint32_t	count;
+	uint32_t	padding;
+	uint64_t	spare;
+};
+
 struct fuse_backing_map {
 	int32_t		fd;
 	uint32_t	flags;