net: Introduce preferred busy-polling

The existing busy-polling mode, enabled by the SO_BUSY_POLL socket
option or system-wide using the /proc/sys/net/core/busy_read knob, is
an opportunistic. That means that if the NAPI context is not
scheduled, it will poll it. If, after busy-polling, the budget is
exceeded the busy-polling logic will schedule the NAPI onto the
regular softirq handling.

One implication of the behavior above is that a busy/heavy loaded NAPI
context will never enter/allow for busy-polling. Some applications
prefer that most NAPI processing would be done by busy-polling.

This series adds a new socket option, SO_PREFER_BUSY_POLL, that works
in concert with the napi_defer_hard_irqs and gro_flush_timeout
knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were
introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral
feature"), and allows for a user to defer interrupts to be enabled and
instead schedule the NAPI context from a watchdog timer. When a user
enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled,
and the NAPI context is being processed by a softirq, the softirq NAPI
processing will exit early to allow the busy-polling to be performed.

If the application stops performing busy-polling via a system call,
the watchdog timer defined by gro_flush_timeout will timeout, and
regular softirq handling will resume.

In summary; Heavy traffic applications that prefer busy-polling over
softirq processing should use this option.

Example usage:

  $ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs
  $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout

Note that the timeout should be larger than the userspace processing
window, otherwise the watchdog will timeout and fall back to regular
softirq processing.

Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/bpf/20201130185205.196029-2-bjorn.topel@gmail.com

4 files changed, 30 insertions, 16 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ce648a564f7..52d1cc2bd8a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -350,23 +350,25 @@ struct napi_struct {
 };
 
 enum {
-	NAPI_STATE_SCHED,	/* Poll is scheduled */
-	NAPI_STATE_MISSED,	/* reschedule a napi */
-	NAPI_STATE_DISABLE,	/* Disable pending */
-	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
-	NAPI_STATE_LISTED,	/* NAPI added to system lists */
-	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_SCHED,		/* Poll is scheduled */
+	NAPI_STATE_MISSED,		/* reschedule a napi */
+	NAPI_STATE_DISABLE,		/* Disable pending */
+	NAPI_STATE_NPSVC,		/* Netpoll - don't dequeue from poll_list */
+	NAPI_STATE_LISTED,		/* NAPI added to system lists */
+	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_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 };
 
 enum {
-	NAPIF_STATE_SCHED	 = BIT(NAPI_STATE_SCHED),
-	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
-	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
-	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
-	NAPIF_STATE_LISTED	 = BIT(NAPI_STATE_LISTED),
-	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
-	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_SCHED		= BIT(NAPI_STATE_SCHED),
+	NAPIF_STATE_MISSED		= BIT(NAPI_STATE_MISSED),
+	NAPIF_STATE_DISABLE		= BIT(NAPI_STATE_DISABLE),
+	NAPIF_STATE_NPSVC		= BIT(NAPI_STATE_NPSVC),
+	NAPIF_STATE_LISTED		= BIT(NAPI_STATE_LISTED),
+	NAPIF_STATE_NO_BUSY_POLL	= BIT(NAPI_STATE_NO_BUSY_POLL),
+	NAPIF_STATE_IN_BUSY_POLL	= BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 };
 
 enum gro_result {
@@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n)
 	return test_bit(NAPI_STATE_DISABLE, &n->state);
 }
 
+static inline bool napi_prefer_busy_poll(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
+}
+
 bool napi_schedule_prep(struct napi_struct *n);
 
 /**
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index b001fa91c14e..0292b8353d7e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -43,7 +43,7 @@ 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);
+		    void *loop_end_arg, bool prefer_busy_poll);
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
@@ -105,7 +105,8 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
 
 	if (napi_id >= MIN_NAPI_ID)
-		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
+			       READ_ONCE(sk->sk_prefer_busy_poll));
 #endif
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index a5c6ae78df77..d49b89b071b6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -301,6 +301,7 @@ struct bpf_local_storage;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
   *	@sk_priority: %SO_PRIORITY setting
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
@@ -479,6 +480,9 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	u8			sk_prefer_busy_poll;
+#endif
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 77f7c1638eb1..7dd02408b7ce 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -119,6 +119,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))