[PATCH v7 08/15] net: add helper executing custom callback from napi

[David Wei <dw@davidwei.uk>]

From: Pavel Begunkov <asml.silence@gmail.com>

It's useful to have napi private bits and pieces like page pool's fast
allocating cache, so that the hot allocation path doesn't have to do any
additional synchronisation. In case of io_uring memory provider
introduced in following patches, we keep the consumer end of the
io_uring's refill queue private to napi as it's a hot path.

However, from time to time we need to synchronise with the napi, for
example to add more user memory or allocate fallback buffers. Add a
helper function napi_execute that allows to run a custom callback from
under napi context so that it can access and modify napi protected
parts of io_uring. It works similar to busy polling and stops napi from
running in the meantime, so it's supposed to be a slow control path.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
---
 include/net/busy_poll.h |  6 +++
 net/core/dev.c          | 81 ++++++++++++++++++++++++++++++++---------
 2 files changed, 70 insertions(+), 17 deletions(-)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index f03040baaefd..3fd9e65731e9 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -47,6 +47,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time);
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
 		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+void napi_execute(unsigned napi_id, void (*cb)(void *), void *cb_arg);
 
 void napi_busy_loop_rcu(unsigned int napi_id,
 			bool (*loop_end)(void *, unsigned long),
@@ -63,6 +64,11 @@ static inline bool sk_can_busy_loop(struct sock *sk)
 	return false;
 }
 
+static inline void napi_execute(unsigned napi_id,
+				void (*cb)(void *), void *cb_arg)
+{
+}
+
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 static inline unsigned long busy_loop_current_time(void)
diff --git a/net/core/dev.c b/net/core/dev.c
index c682173a7642..5ea455e64363 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6347,6 +6347,30 @@ enum {
 	NAPI_F_END_ON_RESCHED	= 2,
 };
 
+static inline bool napi_state_start_busy_polling(struct napi_struct *napi,
+						 unsigned flags)
+{
+	unsigned long val = READ_ONCE(napi->state);
+
+	/* If multiple threads are competing for this napi,
+	 * we avoid dirtying napi->state as much as we can.
+	 */
+	if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
+		   NAPIF_STATE_IN_BUSY_POLL))
+		goto fail;
+
+	if (cmpxchg(&napi->state, val,
+		    val | NAPIF_STATE_IN_BUSY_POLL |
+			  NAPIF_STATE_SCHED) != val)
+		goto fail;
+
+	return true;
+fail:
+	if (flags & NAPI_F_PREFER_BUSY_POLL)
+		set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
+	return false;
+}
+
 static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 			   unsigned flags, u16 budget)
 {
@@ -6422,24 +6446,8 @@ static void __napi_busy_loop(unsigned int napi_id,
 		local_bh_disable();
 		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 		if (!napi_poll) {
-			unsigned long val = READ_ONCE(napi->state);
-
-			/* If multiple threads are competing for this napi,
-			 * we avoid dirtying napi->state as much as we can.
-			 */
-			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
-				   NAPIF_STATE_IN_BUSY_POLL)) {
-				if (flags & NAPI_F_PREFER_BUSY_POLL)
-					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
+			if (!napi_state_start_busy_polling(napi, flags))
 				goto count;
-			}
-			if (cmpxchg(&napi->state, val,
-				    val | NAPIF_STATE_IN_BUSY_POLL |
-					  NAPIF_STATE_SCHED) != val) {
-				if (flags & NAPI_F_PREFER_BUSY_POLL)
-					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
-				goto count;
-			}
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
@@ -6503,6 +6511,45 @@ void napi_busy_loop(unsigned int napi_id,
 }
 EXPORT_SYMBOL(napi_busy_loop);
 
+void napi_execute(unsigned napi_id,
+		  void (*cb)(void *), void *cb_arg)
+{
+	unsigned flags = NAPI_F_PREFER_BUSY_POLL;
+	void *have_poll_lock = NULL;
+	struct napi_struct *napi;
+
+	rcu_read_lock();
+	napi = napi_by_id(napi_id);
+	if (!napi) {
+		rcu_read_unlock();
+		return;
+	}
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
+
+	for (;;) {
+		local_bh_disable();
+
+		if (napi_state_start_busy_polling(napi, flags)) {
+			have_poll_lock = netpoll_poll_lock(napi);
+			cb(cb_arg);
+			local_bh_enable();
+			busy_poll_stop(napi, have_poll_lock, flags, 1);
+			break;
+		}
+
+		local_bh_enable();
+		if (unlikely(need_resched()))
+			break;
+		cpu_relax();
+	}
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	rcu_read_unlock();
+}
+
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 static void __napi_hash_add_with_id(struct napi_struct *napi,
-- 
2.43.5