Re: [RFC PATCH net-next v1 1/2] net: add SO_NO_RFS to exclude a socket from RFS and aRFS

[Kuniyuki Iwashima <kuniyu@google.com>]

On Sat, 31 Oct 2026 11:33:29 +0000, Vitaly Zuevsky wrote:
> RFS and accelerated RFS are enabled per host and per rx queue, but
> whether steering helps is a property of the flow. A host that carries
> a few long-lived flows which benefit from steering alongside a large
> churn of short-lived flows has no way to express that today.

FWIW, we have the exact same option in our kernel since 2019,
it was named SO_BYPASS_RFS with skc_bypass_rfs:1.


> 
> Add a boolean socket option, SO_NO_RFS. When set, sock_rps_record_flow()
> does not record the socket in rps_sock_flow_table, so get_rps_cpu()
> finds no match and neither software RFS nor ndo_rx_flow_steer() acts
> on the flow; it stays on the CPU chosen by RSS or RPS.
> 
> The option is kept in sk_flags so that sk_clone_lock() copies it to

I posted this so that you don't need to access to cold cacheline.
https://lore.kernel.org/netdev/20261103044213.1336347-1-kuniyu@google.com/T/#u


> accepted children: setting it on a listening socket excludes every
> connection accepted from it, while sockets the same process connects
> itself remain eligible.
> 
> sock_rps_delete_flow() is skipped as well, because a socket that never
> recorded itself must not clear a table slot that may belong to another
> flow.
> 
> The test sits after the TCP_ESTABLISHED check and inside the
> rfs_needed static branch, so hosts without RFS pay nothing and hosts
> with RFS pay one test_bit() on a cache line tcp_recvmsg() already
> touches.
> 
> Signed-off-by: Vitaly Zuevsky <vitaly.zuevsky@gcore.com>
> ---
>  arch/alpha/include/uapi/asm/socket.h  |  2 ++
>  arch/mips/include/uapi/asm/socket.h   |  2 ++
>  arch/parisc/include/uapi/asm/socket.h |  2 ++
>  arch/sparc/include/uapi/asm/socket.h  |  2 ++
>  include/net/rps.h                     | 13 +++++++++++++
>  include/net/sock.h                    |  1 +
>  include/uapi/asm-generic/socket.h     |  2 ++
>  net/core/sock.c                       |  8 ++++++++
>  8 files changed, 32 insertions(+)
> 
> diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
> index 5d3524c26b2b..256d37f5b9b0 100644
> --- a/arch/alpha/include/uapi/asm/socket.h
> +++ b/arch/alpha/include/uapi/asm/socket.h
> @@ -161,6 +161,8 @@
>  
>  #define SO_PEERPIDFD_THREAD    87
>  
> +#define SO_NO_RFS              88
> +
>  #if !defined(__KERNEL__)
>  
>  #if __BITS_PER_LONG == 64
> diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
> index 245a43f52fb1..5b477de463a3 100644
> --- a/arch/mips/include/uapi/asm/socket.h
> +++ b/arch/mips/include/uapi/asm/socket.h
> @@ -172,6 +172,8 @@
>  
>  #define SO_PEERPIDFD_THREAD    87
>  
> +#define SO_NO_RFS              88
> +
>  #if !defined(__KERNEL__)
>  
>  #if __BITS_PER_LONG == 64
> diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
> index f23710e1c671..b3a4cc2cbc50 100644
> --- a/arch/parisc/include/uapi/asm/socket.h
> +++ b/arch/parisc/include/uapi/asm/socket.h
> @@ -153,6 +153,8 @@
>  
>  #define SO_PEERPIDFD_THREAD	0x4055
>  
> +#define SO_NO_RFS		0x4056
> +
>  #if !defined(__KERNEL__)
>  
>  #if __BITS_PER_LONG == 64
> diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
> index b35b25bdefc2..ba5ed7942570 100644
> --- a/arch/sparc/include/uapi/asm/socket.h
> +++ b/arch/sparc/include/uapi/asm/socket.h
> @@ -154,6 +154,8 @@
>  
>  #define SO_PEERPIDFD_THREAD      0x0060
>  
> +#define SO_NO_RFS                0x0061
> +
>  #if !defined(__KERNEL__)
>  
>  
> diff --git a/include/net/rps.h b/include/net/rps.h
> index e33c6a2fa8bb..5afa48868236 100644
> --- a/include/net/rps.h
> +++ b/include/net/rps.h
> @@ -98,6 +98,13 @@ static inline void _sock_rps_record_flow(const struct sock *sk)
>  	 * [1] : sk_state and sk_prot are in the same cache line.
>  	 */
>  	if (sk->sk_state == TCP_ESTABLISHED) {
> +		/* SO_NO_RFS: application asked us to never steer this flow.
> +		 * Tested after sk_state so the common case stays on one
> +		 * cache line.
> +		 */
> +		if (unlikely(sock_flag(sk, SOCK_NO_RFS)))

Move this to just after rfs_is_needed().

With skc_bypss_rfs in the hot bit, access to it and skc_state
adds no cost.


> +			return;
> +
>  		/* This READ_ONCE() is paired with the WRITE_ONCE()
>  		 * from sock_rps_save_rxhash() and sock_rps_reset_rxhash().
>  		 */
> @@ -111,6 +118,12 @@ static inline void _sock_rps_delete_flow(const struct sock *sk)
>  	rps_tag_ptr tag_ptr;
>  	u32 hash, index;
>  
> +	/* Never recorded, so never clear a slot that may belong to
> +	 * another flow.
> +	 */
> +	if (sock_flag(sk, SOCK_NO_RFS))
> +		return;

Same.


> +
>  	hash = READ_ONCE(sk->sk_rxhash);
>  	if (!hash)
>  		return;
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 173b37b2b8bb..4472dc4ed28e 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1024,6 +1024,7 @@ enum sock_flags {
>  	SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
>  	SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
>  	SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */
> +	SOCK_NO_RFS, /* SO_NO_RFS: never record this flow for RFS/aRFS */
>  };
>  
>  #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
> index 56fed7ab27ab..9bf415b0d470 100644
> --- a/include/uapi/asm-generic/socket.h
> +++ b/include/uapi/asm-generic/socket.h
> @@ -156,6 +156,8 @@
>  
>  #define SO_PEERPIDFD_THREAD	87
>  
> +#define SO_NO_RFS		88
> +
>  #if !defined(__KERNEL__)
>  
>  #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
> diff --git a/net/core/sock.c b/net/core/sock.c
> index e7405be8941f..02b8cc4bc1c4 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -1597,6 +1597,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
>  		reuseport_update_incoming_cpu(sk, val);
>  		break;
>  
> +	case SO_NO_RFS:
> +		sock_valbool_flag(sk, SOCK_NO_RFS, valbool);
> +		break;

Guard this with CONFIG_RPS.


> +
>  	case SO_CNX_ADVICE:
>  		if (val == 1)
>  			dst_negative_advice(sk);
> @@ -2118,6 +2122,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
>  		v.val = READ_ONCE(sk->sk_incoming_cpu);
>  		break;
>  
> +	case SO_NO_RFS:
> +		v.val = sock_flag(sk, SOCK_NO_RFS);
> +		break;

Same here.


> +
>  	case SO_MEMINFO:
>  	{
>  		u32 meminfo[SK_MEMINFO_VARS];
> 
> base-commit: 734bef548a96e8774d6eef5dfa2026c6edc4e80b
> -- 
> 2.34.1
>