[PATCH v3 1/4] fuse: Make the fuse unique value a per-cpu counter

[Bernd Schubert <bschubert@xxxxxxx>]

No need to take lock, we can have that per cpu and
add in the current cpu as offset.

fuse-io-uring and virtiofs especially benefit from it
as they don't need the fiq lock at all.

Signed-off-by: Bernd Schubert <bschubert@xxxxxxx>
---
 fs/fuse/dev.c        | 24 +++---------------------
 fs/fuse/fuse_dev_i.h |  4 ----
 fs/fuse/fuse_i.h     | 21 ++++++++++++++++-----
 fs/fuse/inode.c      |  7 +++++++
 4 files changed, 26 insertions(+), 30 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 51e31df4c54613280a9c295f530b18e1d461a974..e9592ab092b948bacb5034018bd1f32c917d5c9f 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -204,24 +204,6 @@ unsigned int fuse_len_args(unsigned int numargs, struct fuse_arg *args)
 }
 EXPORT_SYMBOL_GPL(fuse_len_args);
 
-static u64 fuse_get_unique_locked(struct fuse_iqueue *fiq)
-{
-	fiq->reqctr += FUSE_REQ_ID_STEP;
-	return fiq->reqctr;
-}
-
-u64 fuse_get_unique(struct fuse_iqueue *fiq)
-{
-	u64 ret;
-
-	spin_lock(&fiq->lock);
-	ret = fuse_get_unique_locked(fiq);
-	spin_unlock(&fiq->lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(fuse_get_unique);
-
 unsigned int fuse_req_hash(u64 unique)
 {
 	return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS);
@@ -278,7 +260,7 @@ static void fuse_dev_queue_req(struct fuse_iqueue *fiq, struct fuse_req *req)
 	spin_lock(&fiq->lock);
 	if (fiq->connected) {
 		if (req->in.h.opcode != FUSE_NOTIFY_REPLY)
-			req->in.h.unique = fuse_get_unique_locked(fiq);
+			req->in.h.unique = fuse_get_unique(fiq);
 		list_add_tail(&req->list, &fiq->pending);
 		fuse_dev_wake_and_unlock(fiq);
 	} else {
@@ -1177,7 +1159,7 @@ __releases(fiq->lock)
 	struct fuse_in_header ih = {
 		.opcode = FUSE_FORGET,
 		.nodeid = forget->forget_one.nodeid,
-		.unique = fuse_get_unique_locked(fiq),
+		.unique = fuse_get_unique(fiq),
 		.len = sizeof(ih) + sizeof(arg),
 	};
 
@@ -1208,7 +1190,7 @@ __releases(fiq->lock)
 	struct fuse_batch_forget_in arg = { .count = 0 };
 	struct fuse_in_header ih = {
 		.opcode = FUSE_BATCH_FORGET,
-		.unique = fuse_get_unique_locked(fiq),
+		.unique = fuse_get_unique(fiq),
 		.len = sizeof(ih) + sizeof(arg),
 	};
 
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
index 3b2bfe1248d3573abe3b144a6d4bf6a502f56a40..e0afd837a8024450bab77312c7eebdcc7a39bd36 100644
--- a/fs/fuse/fuse_dev_i.h
+++ b/fs/fuse/fuse_dev_i.h
@@ -8,10 +8,6 @@
 
 #include <linux/types.h>
 
-/* Ordinary requests have even IDs, while interrupts IDs are odd */
-#define FUSE_INT_REQ_BIT (1ULL << 0)
-#define FUSE_REQ_ID_STEP (1ULL << 1)
-
 struct fuse_arg;
 struct fuse_args;
 struct fuse_pqueue;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fee96fe7887b30cd57b8a6bbda11447a228cf446..80a526eaba38aa97f6a6faa60e5276fcd7f2668f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -44,6 +44,10 @@
 /** Number of dentries for each connection in the control filesystem */
 #define FUSE_CTL_NUM_DENTRIES 5
 
+/* Ordinary requests have even IDs, while interrupts IDs are odd */
+#define FUSE_INT_REQ_BIT (1ULL << 0)
+#define FUSE_REQ_ID_STEP (1ULL << 1)
+
 /** Maximum of max_pages received in init_out */
 extern unsigned int fuse_max_pages_limit;
 
@@ -490,7 +494,7 @@ struct fuse_iqueue {
 	wait_queue_head_t waitq;
 
 	/** The next unique request id */
-	u64 reqctr;
+	u64 __percpu *reqctr;
 
 	/** The list of pending requests */
 	struct list_head pending;
@@ -1065,6 +1069,17 @@ static inline void fuse_sync_bucket_dec(struct fuse_sync_bucket *bucket)
 	rcu_read_unlock();
 }
 
+/**
+ * Get the next unique ID for a request
+ */
+static inline u64 fuse_get_unique(struct fuse_iqueue *fiq)
+{
+	int step = FUSE_REQ_ID_STEP * (task_cpu(current));
+	u64 cntr = this_cpu_inc_return(*fiq->reqctr);
+
+	return cntr * FUSE_REQ_ID_STEP * NR_CPUS + step;
+}
+
 /** Device operations */
 extern const struct file_operations fuse_dev_operations;
 
@@ -1415,10 +1430,6 @@ int fuse_readdir(struct file *file, struct dir_context *ctx);
  */
 unsigned int fuse_len_args(unsigned int numargs, struct fuse_arg *args);
 
-/**
- * Get the next unique ID for a request
- */
-u64 fuse_get_unique(struct fuse_iqueue *fiq);
 void fuse_free_conn(struct fuse_conn *fc);
 
 /* dax.c */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e9db2cb8c150878634728685af0fa15e7ade628f..d2d850cca4c7bc3cd7158e773c5e602e15afe4e3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -930,6 +930,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq,
 	memset(fiq, 0, sizeof(struct fuse_iqueue));
 	spin_lock_init(&fiq->lock);
 	init_waitqueue_head(&fiq->waitq);
+	fiq->reqctr = alloc_percpu(u64);
 	INIT_LIST_HEAD(&fiq->pending);
 	INIT_LIST_HEAD(&fiq->interrupts);
 	fiq->forget_list_tail = &fiq->forget_list_head;
@@ -938,6 +939,11 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq,
 	fiq->priv = priv;
 }
 
+static void fuse_iqueue_destroy(struct fuse_iqueue *fiq)
+{
+	free_percpu(fiq->reqctr);
+}
+
 void fuse_pqueue_init(struct fuse_pqueue *fpq)
 {
 	unsigned int i;
@@ -994,6 +1000,7 @@ static void delayed_release(struct rcu_head *p)
 	struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu);
 
 	fuse_uring_destruct(fc);
+	fuse_iqueue_destroy(&fc->iq);
 
 	put_user_ns(fc->user_ns);
 	fc->release(fc);

-- 
2.43.0