net: Add SO_BUSY_POLL_BUDGET socket option

This option lets a user set a per socket NAPI budget for
busy-polling. If the options is not set, it will use the default of 8.

Signed-off-by: Björn Töpel <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Reviewed-by: Jakub Kicinski <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Björn Töpel

arch/alpha/include/uapi/asm/socket.h

@@ -125,6 +125,7 @@
 #define SO_DETACH_REUSEPORT_BPF 68
 
 #define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
 
 #if !defined(__KERNEL__)
 

arch/mips/include/uapi/asm/socket.h

@@ -136,6 +136,7 @@
 #define SO_DETACH_REUSEPORT_BPF 68
 
 #define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
 
 #if !defined(__KERNEL__)
 

arch/parisc/include/uapi/asm/socket.h

@@ -117,6 +117,7 @@
 #define SO_DETACH_REUSEPORT_BPF 0x4042
 
 #define SO_PREFER_BUSY_POLL	0x4043
+#define SO_BUSY_POLL_BUDGET	0x4044
 
 #if !defined(__KERNEL__)
 

arch/sparc/include/uapi/asm/socket.h

@@ -118,6 +118,7 @@
 #define SO_DETACH_REUSEPORT_BPF  0x0047
 
 #define SO_PREFER_BUSY_POLL	 0x0048
+#define SO_BUSY_POLL_BUDGET	 0x0049
 
 #if !defined(__KERNEL__)
 

fs/eventpoll.c

@@ -397,7 +397,8 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock)
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 
 	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
-		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false);
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false,
+			       BUSY_POLL_BUDGET);
 }
 
 static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)

include/net/busy_poll.h

@@ -23,6 +23,8 @@
  */
 #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
 
+#define BUSY_POLL_BUDGET 8
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 
 struct napi_struct;
@@ -43,7 +45,7 @@ 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);
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
@@ -106,7 +108,8 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 
 	if (napi_id >= MIN_NAPI_ID)
 		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
-			       READ_ONCE(sk->sk_prefer_busy_poll));
+			       READ_ONCE(sk->sk_prefer_busy_poll),
+			       READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET);
 #endif
 }
 

include/net/sock.h

@@ -302,6 +302,7 @@ struct bpf_local_storage;
   *	@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_busy_poll_budget: napi processing budget when busypolling
   *	@sk_priority: %SO_PRIORITY setting
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
@@ -482,6 +483,7 @@ struct sock {
 	kuid_t			sk_uid;
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	u8			sk_prefer_busy_poll;
+	u16			sk_busy_poll_budget;
 #endif
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;

include/uapi/asm-generic/socket.h

@@ -120,6 +120,7 @@
 #define SO_DETACH_REUSEPORT_BPF 68
 
 #define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
 
 #if !defined(__KERNEL__)
 

net/core/dev.c

@@ -6496,8 +6496,6 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 
 #if defined(CONFIG_NET_RX_BUSY_POLL)
 
-#define BUSY_POLL_BUDGET 8
-
 static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 {
 	if (!skip_schedule) {
@@ -6517,7 +6515,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll)
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
+			   u16 budget)
 {
 	bool skip_schedule = false;
 	unsigned long timeout;
@@ -6549,21 +6548,21 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 	/* All we really want here is to re-enable device interrupts.
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
-	rc = napi->poll(napi, BUSY_POLL_BUDGET);
+	rc = napi->poll(napi, budget);
 	/* We can't gro_normal_list() here, because napi->poll() might have
 	 * rearmed the napi (napi_complete_done()) in which case it could
 	 * already be running on another CPU.
 	 */
-	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+	trace_napi_poll(napi, rc, budget);
 	netpoll_poll_unlock(have_poll_lock);
-	if (rc == BUSY_POLL_BUDGET)
+	if (rc == budget)
 		__busy_poll_stop(napi, skip_schedule);
 	local_bh_enable();
 }
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg, bool prefer_busy_poll)
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6606,8 +6605,8 @@ void napi_busy_loop(unsigned int napi_id,
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		work = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, budget);
+		trace_napi_poll(napi, work, budget);
 		gro_normal_list(napi);
 count:
 		if (work > 0)
@@ -6620,7 +6619,7 @@ void napi_busy_loop(unsigned int napi_id,
 
 		if (unlikely(need_resched())) {
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
+				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
@@ -6631,7 +6630,7 @@ void napi_busy_loop(unsigned int napi_id,
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
+		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 	preempt_enable();
 out:
 	rcu_read_unlock();

net/core/sock.c

@@ -1165,6 +1165,16 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		else
 			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
 		break;
+	case SO_BUSY_POLL_BUDGET:
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+			ret = -EPERM;
+		} else {
+			if (val < 0 || val > U16_MAX)
+				ret = -EINVAL;
+			else
+				WRITE_ONCE(sk->sk_busy_poll_budget, val);
+		}
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE: