[PATCH v4] fuse: add new function to invalidate cache for all inodes

[Luis Henriques]

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 a new option that allows userspace to invalidate all the
inodes with a single notification operation.  In addition to invalidate
all the inodes, it also shrinks the sb dcache.

Signed-off-by: Luis Henriques <luis@xxxxxxxxxx>
---
* Changes since v3
- Added comments to clarify semantic changes in fuse_reverse_inval_inode()
  when called with FUSE_INVAL_ALL_INODES (suggested by Bernd).
- Added comments to inodes iteration loop to clarify __iget/iput usage
  (suggested by Joanne)
- Dropped get_fuse_mount() call -- fuse_mount can be obtained from
  fuse_ilookup() directly (suggested by Joanne)

(Also dropped the RFC from the subject.)

* Changes since v2
- Use the new helper from fuse_reverse_inval_inode(), as suggested by Bernd.
- Also updated patch description as per checkpatch.pl suggestion.

* Changes since v1
As suggested by Bernd, this patch v2 simply adds an helper function that
will make it easier to replace most of it's code by a call to function
super_iter_inodes() when Dave Chinner's patch[1] eventually gets merged.

[1] https://lore.kernel.org/r/20241002014017.3801899-3-david@xxxxxxxxxxxxx

 fs/fuse/inode.c           | 83 +++++++++++++++++++++++++++++++++++----
 include/uapi/linux/fuse.h |  3 ++
 2 files changed, 79 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e9db2cb8c150..5aa49856731a 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -547,25 +547,94 @@ struct inode *fuse_ilookup(struct fuse_conn *fc, u64 nodeid,
 	return NULL;
 }
 
+static void inval_single_inode(struct inode *inode, struct fuse_conn *fc)
+{
+	struct fuse_inode *fi;
+
+	fi = get_fuse_inode(inode);
+	spin_lock(&fi->lock);
+	fi->attr_version = atomic64_inc_return(&fc->attr_version);
+	spin_unlock(&fi->lock);
+	fuse_invalidate_attr(inode);
+	forget_all_cached_acls(inode);
+}
+
+static int fuse_reverse_inval_all(struct fuse_conn *fc)
+{
+	struct fuse_mount *fm;
+	struct super_block *sb;
+	struct inode *inode, *old_inode = NULL;
+
+	inode = fuse_ilookup(fc, FUSE_ROOT_ID, &fm);
+	if (!inode || !fm)
+		return -ENOENT;
+
+	iput(inode);
+	sb = fm->sb;
+
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    !atomic_read(&inode->i_count)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+
+		/*
+		 * This __iget()/iput() dance is required so that we can release
+		 * the sb lock and continue the iteration on the previous
+		 * inode.  If we don't keep a ref to the old inode it could have
+		 * disappear.  This way we can safely call cond_resched() when
+		 * there's a huge amount of inodes to iterate.
+		 */
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&sb->s_inode_list_lock);
+		iput(old_inode);
+
+		inval_single_inode(inode, fc);
+
+		old_inode = inode;
+		cond_resched();
+		spin_lock(&sb->s_inode_list_lock);
+	}
+	spin_unlock(&sb->s_inode_list_lock);
+	iput(old_inode);
+
+	shrink_dcache_sb(sb);
+
+	return 0;
+}
+
+/*
+ * Notify to invalidate inodes cache.  It can be called with @nodeid set to
+ * either:
+ *
+ * - An inode number - Any pending writebacks within the rage [@offset @len]
+ *   will be triggered and the inode will be validated.  To invalidate the whole
+ *   cache @offset has to be set to '0' and @len needs to be <= '0'; if @offset
+ *   is negative, only the inode attributes are invalidated.
+ *
+ * - FUSE_INVAL_ALL_INODES - All the inodes in the superblock are invalidated
+ *   and the whole dcache is shrinked.
+ */
 int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid,
 			     loff_t offset, loff_t len)
 {
-	struct fuse_inode *fi;
 	struct inode *inode;
 	pgoff_t pg_start;
 	pgoff_t pg_end;
 
+	if (nodeid == FUSE_INVAL_ALL_INODES)
+		return fuse_reverse_inval_all(fc);
+
 	inode = fuse_ilookup(fc, nodeid, NULL);
 	if (!inode)
 		return -ENOENT;
 
-	fi = get_fuse_inode(inode);
-	spin_lock(&fi->lock);
-	fi->attr_version = atomic64_inc_return(&fc->attr_version);
-	spin_unlock(&fi->lock);
+	inval_single_inode(inode, fc);
 
-	fuse_invalidate_attr(inode);
-	forget_all_cached_acls(inode);
 	if (offset >= 0) {
 		pg_start = offset >> PAGE_SHIFT;
 		if (len <= 0)
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 5e0eb41d967e..e5852b63f99f 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -669,6 +669,9 @@ enum fuse_notify_code {
 	FUSE_NOTIFY_CODE_MAX,
 };
 
+/* The nodeid to request to invalidate all inodes */
+#define FUSE_INVAL_ALL_INODES 0
+
 /* The read buffer is required to be at least 8k, but may be much larger */
 #define FUSE_MIN_READ_BUFFER 8192