1 files changed, 131 insertions, 53 deletions

diff --git a/io_uring/napi.c b/io_uring/napi.c
index d0cf694d0172..b1ade3fda30f 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -38,67 +38,88 @@ static inline ktime_t net_to_ktime(unsigned long t)
 	return ns_to_ktime(t << 10);
 }
 
-void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id)
 {
 	struct hlist_head *hash_list;
-	unsigned int napi_id;
-	struct sock *sk;
 	struct io_napi_entry *e;
 
-	sk = sock->sk;
-	if (!sk)
-		return;
-
-	napi_id = READ_ONCE(sk->sk_napi_id);
-
 	/* Non-NAPI IDs can be rejected. */
 	if (napi_id < MIN_NAPI_ID)
-		return;
+		return -EINVAL;
 
 	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
 
-	rcu_read_lock();
-	e = io_napi_hash_find(hash_list, napi_id);
-	if (e) {
-		e->timeout = jiffies + NAPI_TIMEOUT;
-		rcu_read_unlock();
-		return;
+	scoped_guard(rcu) {
+		e = io_napi_hash_find(hash_list, napi_id);
+		if (e) {
+			WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT);
+			return -EEXIST;
+		}
 	}
-	rcu_read_unlock();
 
 	e = kmalloc(sizeof(*e), GFP_NOWAIT);
 	if (!e)
-		return;
+		return -ENOMEM;
 
 	e->napi_id = napi_id;
 	e->timeout = jiffies + NAPI_TIMEOUT;
 
+	/*
+	 * guard(spinlock) is not used to manually unlock it before calling
+	 * kfree()
+	 */
 	spin_lock(&ctx->napi_lock);
 	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
 		spin_unlock(&ctx->napi_lock);
 		kfree(e);
-		return;
+		return -EEXIST;
 	}
 
 	hlist_add_tail_rcu(&e->node, hash_list);
-	list_add_tail(&e->list, &ctx->napi_list);
+	list_add_tail_rcu(&e->list, &ctx->napi_list);
 	spin_unlock(&ctx->napi_lock);
+	return 0;
+}
+
+static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id)
+{
+	struct hlist_head *hash_list;
+	struct io_napi_entry *e;
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return -EINVAL;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+	guard(spinlock)(&ctx->napi_lock);
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (!e)
+		return -ENOENT;
+
+	list_del_rcu(&e->list);
+	hash_del_rcu(&e->node);
+	kfree_rcu(e, rcu);
+	return 0;
 }
 
 static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
 {
 	struct io_napi_entry *e;
-	unsigned int i;
 
-	spin_lock(&ctx->napi_lock);
-	hash_for_each(ctx->napi_ht, i, e, node) {
-		if (time_after(jiffies, e->timeout)) {
-			list_del(&e->list);
+	guard(spinlock)(&ctx->napi_lock);
+	/*
+	 * list_for_each_entry_safe() is not required as long as:
+	 * 1. list_del_rcu() does not reset the deleted node next pointer
+	 * 2. kfree_rcu() delays the memory freeing until the next quiescent
+	 *    state
+	 */
+	list_for_each_entry(e, &ctx->napi_list, list) {
+		if (time_after(jiffies, READ_ONCE(e->timeout))) {
+			list_del_rcu(&e->list);
 			hash_del_rcu(&e->node);
 			kfree_rcu(e, rcu);
 		}
 	}
-	spin_unlock(&ctx->napi_lock);
 }
 
 static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
@@ -136,45 +157,73 @@ static bool io_napi_busy_loop_should_end(void *data,
 	return false;
 }
 
-static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
-				   void *loop_end_arg)
+/*
+ * never report stale entries
+ */
+static bool static_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					 bool (*loop_end)(void *, unsigned long),
+					 void *loop_end_arg)
 {
 	struct io_napi_entry *e;
-	bool (*loop_end)(void *, unsigned long) = NULL;
-	bool is_stale = false;
 
-	if (loop_end_arg)
-		loop_end = io_napi_busy_loop_should_end;
+	list_for_each_entry_rcu(e, &ctx->napi_list, list)
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+	return false;
+}
+
+static bool
+dynamic_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+			      bool (*loop_end)(void *, unsigned long),
+			      void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool is_stale = false;
 
 	list_for_each_entry_rcu(e, &ctx->napi_list, list) {
 		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
 				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
 
-		if (time_after(jiffies, e->timeout))
+		if (time_after(jiffies, READ_ONCE(e->timeout)))
 			is_stale = true;
 	}
 
 	return is_stale;
 }
 
+static inline bool
+__io_napi_do_busy_loop(struct io_ring_ctx *ctx,
+		       bool (*loop_end)(void *, unsigned long),
+		       void *loop_end_arg)
+{
+	if (READ_ONCE(ctx->napi_track_mode) == IO_URING_NAPI_TRACKING_STATIC)
+		return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg);
+	return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg);
+}
+
 static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
 				       struct io_wait_queue *iowq)
 {
 	unsigned long start_time = busy_loop_current_time();
+	bool (*loop_end)(void *, unsigned long) = NULL;
 	void *loop_end_arg = NULL;
 	bool is_stale = false;
 
 	/* Singular lists use a different napi loop end check function and are
 	 * only executed once.
 	 */
-	if (list_is_singular(&ctx->napi_list))
+	if (list_is_singular(&ctx->napi_list)) {
+		loop_end = io_napi_busy_loop_should_end;
 		loop_end_arg = iowq;
+	}
 
-	rcu_read_lock();
-	do {
-		is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg);
-	} while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg);
-	rcu_read_unlock();
+	scoped_guard(rcu) {
+		do {
+			is_stale = __io_napi_do_busy_loop(ctx, loop_end,
+							  loop_end_arg);
+		} while (!io_napi_busy_loop_should_end(iowq, start_time) &&
+			 !loop_end_arg);
+	}
 
 	io_napi_remove_stale(ctx, is_stale);
 }
@@ -193,6 +242,7 @@ void io_napi_init(struct io_ring_ctx *ctx)
 	spin_lock_init(&ctx->napi_lock);
 	ctx->napi_prefer_busy_poll = false;
 	ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt);
+	ctx->napi_track_mode = IO_URING_NAPI_TRACKING_INACTIVE;
 }
 
 /*
@@ -204,14 +254,31 @@ void io_napi_init(struct io_ring_ctx *ctx)
 void io_napi_free(struct io_ring_ctx *ctx)
 {
 	struct io_napi_entry *e;
-	unsigned int i;
 
-	spin_lock(&ctx->napi_lock);
-	hash_for_each(ctx->napi_ht, i, e, node) {
+	guard(spinlock)(&ctx->napi_lock);
+	list_for_each_entry(e, &ctx->napi_list, list) {
 		hash_del_rcu(&e->node);
 		kfree_rcu(e, rcu);
 	}
-	spin_unlock(&ctx->napi_lock);
+	INIT_LIST_HEAD_RCU(&ctx->napi_list);
+}
+
+static int io_napi_register_napi(struct io_ring_ctx *ctx,
+				 struct io_uring_napi *napi)
+{
+	switch (napi->op_param) {
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+	case IO_URING_NAPI_TRACKING_STATIC:
+		break;
+	default:
+		return -EINVAL;
+	}
+	/* clean the napi list for new settings */
+	io_napi_free(ctx);
+	WRITE_ONCE(ctx->napi_track_mode, napi->op_param);
+	WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll);
+	return 0;
 }
 
 /*
@@ -225,7 +292,8 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 {
 	const struct io_uring_napi curr = {
 		.busy_poll_to 	  = ktime_to_us(ctx->napi_busy_poll_dt),
-		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll,
+		.op_param	  = ctx->napi_track_mode
 	};
 	struct io_uring_napi napi;
 
@@ -233,16 +301,26 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 		return -EINVAL;
 	if (copy_from_user(&napi, arg, sizeof(napi)))
 		return -EFAULT;
-	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+	if (napi.pad[0] || napi.pad[1] || napi.resv)
 		return -EINVAL;
 
 	if (copy_to_user(arg, &curr, sizeof(curr)))
 		return -EFAULT;
 
-	WRITE_ONCE(ctx->napi_busy_poll_dt, napi.busy_poll_to * NSEC_PER_USEC);
-	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
-	WRITE_ONCE(ctx->napi_enabled, true);
-	return 0;
+	switch (napi.opcode) {
+	case IO_URING_NAPI_REGISTER_OP:
+		return io_napi_register_napi(ctx, &napi);
+	case IO_URING_NAPI_STATIC_ADD_ID:
+		if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC)
+			return -EINVAL;
+		return __io_napi_add_id(ctx, napi.op_param);
+	case IO_URING_NAPI_STATIC_DEL_ID:
+		if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC)
+			return -EINVAL;
+		return __io_napi_del_id(ctx, napi.op_param);
+	default:
+		return -EINVAL;
+	}
 }
 
 /*
@@ -265,7 +343,7 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 
 	WRITE_ONCE(ctx->napi_busy_poll_dt, 0);
 	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
-	WRITE_ONCE(ctx->napi_enabled, false);
+	WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE);
 	return 0;
 }
 
@@ -307,9 +385,9 @@ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
 	if (list_empty_careful(&ctx->napi_list))
 		return 0;
 
-	rcu_read_lock();
-	is_stale = __io_napi_do_busy_loop(ctx, NULL);
-	rcu_read_unlock();
+	scoped_guard(rcu) {
+		is_stale = __io_napi_do_busy_loop(ctx, NULL, NULL);
+	}
 
 	io_napi_remove_stale(ctx, is_stale);
 	return 1;