kernel: replace threaded NAPI implementation in 5.10 with upstream backport

This uses a kthread per NAPI instance instead of the workqueue approach

Signed-off-by: Felix Fietkau <nbd@nbd.name>

1 files changed, 93 insertions, 0 deletions

diff --git a/target/linux/generic/backport-5.10/603-v5.12-net-fix-race-between-napi-kthread-mode-and-busy-poll.patch b/target/linux/generic/backport-5.10/603-v5.12-net-fix-race-between-napi-kthread-mode-and-busy-poll.patch
new file mode 100644
index 0000000000..e0fd09b012
--- /dev/null
+++ b/target/linux/generic/backport-5.10/603-v5.12-net-fix-race-between-napi-kthread-mode-and-busy-poll.patch
@@ -0,0 +1,93 @@
+From: Wei Wang <weiwan@google.com>
+Date: Mon, 1 Mar 2021 17:21:13 -0800
+Subject: [PATCH] net: fix race between napi kthread mode and busy poll
+
+Currently, napi_thread_wait() checks for NAPI_STATE_SCHED bit to
+determine if the kthread owns this napi and could call napi->poll() on
+it. However, if socket busy poll is enabled, it is possible that the
+busy poll thread grabs this SCHED bit (after the previous napi->poll()
+invokes napi_complete_done() and clears SCHED bit) and tries to poll
+on the same napi. napi_disable() could grab the SCHED bit as well.
+This patch tries to fix this race by adding a new bit
+NAPI_STATE_SCHED_THREADED in napi->state. This bit gets set in
+____napi_schedule() if the threaded mode is enabled, and gets cleared
+in napi_complete_done(), and we only poll the napi in kthread if this
+bit is set. This helps distinguish the ownership of the napi between
+kthread and other scenarios and fixes the race issue.
+
+Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support")
+Reported-by: Martin Zaharinov <micron10@gmail.com>
+Suggested-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Wei Wang <weiwan@google.com>
+Cc: Alexander Duyck <alexanderduyck@fb.com>
+Cc: Eric Dumazet <edumazet@google.com>
+Cc: Paolo Abeni <pabeni@redhat.com>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+---
+
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -359,6 +359,7 @@ enum {
+ 	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
+ 	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+ 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
++	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
+ };
+ 
+ enum {
+@@ -370,6 +371,7 @@ enum {
+ 	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
+ 	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+ 	NAPIF_STATE_THREADED	 = BIT(NAPI_STATE_THREADED),
++	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
+ };
+ 
+ enum gro_result {
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -4275,6 +4275,8 @@ static inline void ____napi_schedule(str
+ 		 */
+ 		thread = READ_ONCE(napi->thread);
+ 		if (thread) {
++			if (thread->state != TASK_INTERRUPTIBLE)
++				set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
+ 			wake_up_process(thread);
+ 			return;
+ 		}
+@@ -6495,7 +6497,8 @@ bool napi_complete_done(struct napi_stru
+ 
+ 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
+ 
+-		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
++		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
++			      NAPIF_STATE_SCHED_THREADED);
+ 
+ 		/* If STATE_MISSED was set, leave STATE_SCHED set,
+ 		 * because we will call napi->poll() one more time.
+@@ -6931,16 +6934,25 @@ static int napi_poll(struct napi_struct
+ 
+ static int napi_thread_wait(struct napi_struct *napi)
+ {
++	bool woken = false;
++
+ 	set_current_state(TASK_INTERRUPTIBLE);
+ 
+ 	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
+-		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
++		/* Testing SCHED_THREADED bit here to make sure the current
++		 * kthread owns this napi and could poll on this napi.
++		 * Testing SCHED bit is not enough because SCHED bit might be
++		 * set by some other busy poll thread or by napi_disable().
++		 */
++		if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
+ 			WARN_ON(!list_empty(&napi->poll_list));
+ 			__set_current_state(TASK_RUNNING);
+ 			return 0;
+ 		}
+ 
+ 		schedule();
++		/* woken being true indicates this thread owns this napi. */
++		woken = true;
+ 		set_current_state(TASK_INTERRUPTIBLE);
+ 	}
+ 	__set_current_state(TASK_RUNNING);