From 62748f32d501f5d3712a7c372bbb92abc7c62bc7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Sep 2013 08:20:52 -0700 Subject: [PATCH] net: introduce SO_MAX_PACING_RATE As mentioned in commit afe4fd062416b ("pkt_sched: fq: Fair Queue packet scheduler"), this patch adds a new socket option. SO_MAX_PACING_RATE offers the application the ability to cap the rate computed by transport layer. Value is in bytes per second. u32 val = 1000000; setsockopt(sockfd, SOL_SOCKET, SO_MAX_PACING_RATE, &val, sizeof(val)); To be effectively paced, a flow must use FQ packet scheduler. Note that a packet scheduler takes into account the headers for its computations. The effective payload rate depends on MSS and retransmits if any. I chose to make this pacing rate a SOL_SOCKET option instead of a TCP one because this can be used by other protocols. Signed-off-by: Eric Dumazet Cc: Steinar H. Gunderson Cc: Michael Kerrisk Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 4 +++- arch/avr32/include/uapi/asm/socket.h | 2 ++ arch/cris/include/uapi/asm/socket.h | 2 ++ arch/frv/include/uapi/asm/socket.h | 2 ++ arch/h8300/include/uapi/asm/socket.h | 2 ++ arch/ia64/include/uapi/asm/socket.h | 2 ++ arch/m32r/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/mn10300/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/powerpc/include/uapi/asm/socket.h | 2 ++ arch/s390/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ arch/xtensa/include/uapi/asm/socket.h | 2 ++ include/net/sock.h | 1 + include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 12 ++++++++++++ net/ipv4/tcp_input.c | 2 +- 18 files changed, 45 insertions(+), 2 deletions(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 467de010ea7e..e3a1491d5073 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -81,6 +81,8 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_BUSY_POLL 46 +#define SO_BUSY_POLL 46 + +#define SO_MAX_PACING_RATE 47 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 11c4259c62fb..439936421434 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -76,4 +76,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index eb723e51554e..13829aaaeec5 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -78,6 +78,8 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index f0cb1c341163..5d4299762426 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -76,5 +76,7 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h index 9490758c5e2b..214ccaf3554a 100644 --- a/arch/h8300/include/uapi/asm/socket.h +++ b/arch/h8300/include/uapi/asm/socket.h @@ -76,4 +76,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 556d0701a155..c25302fb48d9 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -85,4 +85,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 24be7c8da86a..52966650114f 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -76,4 +76,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 61c01f054d1b..0df9787cd84d 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -94,4 +94,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index e2a2b203eb00..71dedcae55a6 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -76,4 +76,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 71700e636a8e..7c614d01f1fa 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -75,6 +75,8 @@ #define SO_BUSY_POLL 0x4027 +#define SO_MAX_PACING_RATE 0x4048 + /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. */ diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index a6d74467c9ed..fa698324a1fd 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -83,4 +83,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 92494494692e..c286c2e868f0 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -82,4 +82,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 4e1d66c3ce71..0f21e9a5ca18 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -72,6 +72,8 @@ #define SO_BUSY_POLL 0x0030 +#define SO_MAX_PACING_RATE 0x0031 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index c114483010c1..7db5c22faa68 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -87,4 +87,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 4625d2eff461..240aa3f08cd6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -363,6 +363,7 @@ struct sock { int sk_wmem_queued; gfp_t sk_allocation; u32 sk_pacing_rate; /* bytes per second */ + u32 sk_max_pacing_rate; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; int sk_gso_type; diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index f04b69b6abf2..38f14d0264c3 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -78,4 +78,6 @@ #define SO_BUSY_POLL 46 +#define SO_MAX_PACING_RATE 47 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 5b6beba494a3..2bd9b3faa0d0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -914,6 +914,13 @@ int sock_setsockopt(struct socket *sock, int level, int optname, } break; #endif + + case SO_MAX_PACING_RATE: + sk->sk_max_pacing_rate = val; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, + sk->sk_max_pacing_rate); + break; + default: ret = -ENOPROTOOPT; break; @@ -1177,6 +1184,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; #endif + case SO_MAX_PACING_RATE: + v.val = sk->sk_max_pacing_rate; + break; + default: return -ENOPROTOOPT; } @@ -2319,6 +2330,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_ll_usec = sysctl_net_busy_read; #endif + sk->sk_max_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5d083855c111..66aa816ad30b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -735,7 +735,7 @@ static void tcp_update_pacing_rate(struct sock *sk) if (tp->srtt > 8 + 2) do_div(rate, tp->srtt); - sk->sk_pacing_rate = min_t(u64, rate, ~0U); + sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate); } /* Calculate rto without backoff. This is the second half of Van Jacobson's