From 060212928670593fb89243640bf05cf89560b023 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Mon, 10 Jun 2013 11:39:50 +0300 Subject: net: add low latency socket poll Adds an ndo_ll_poll method and the code that supports it. This method can be used by low latency applications to busy-poll Ethernet device queues directly from the socket code. sysctl_net_ll_poll controls how many microseconds to poll. Default is zero (disabled). Individual protocol support will be added by subsequent patches. Signed-off-by: Alexander Duyck Signed-off-by: Jesse Brandeburg Signed-off-by: Eliezer Tamir Acked-by: Eric Dumazet Tested-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/sock.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 88868a9d21d..788c0da5eed 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include #endif +#include + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -2284,6 +2286,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); +#ifdef CONFIG_NET_LL_RX_POLL + sk->sk_napi_id = 0; +#endif + /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) -- cgit v1.2.3-18-g5258 From dafcc4380deec21d160c31411f33c8813f67f517 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Fri, 14 Jun 2013 16:33:57 +0300 Subject: net: add socket option for low latency polling adds a socket option for low latency polling. This allows overriding the global sysctl value with a per-socket one. Unexport sysctl_net_ll_poll since for now it's not needed in modules. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- net/core/sock.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 788c0da5eed..1e744b12fda 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -913,6 +913,19 @@ set_rcvbuf: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; +#ifdef CONFIG_NET_LL_RX_POLL + case SO_LL: + /* allow unprivileged users to decrease the value */ + if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else { + if (val < 0) + ret = -EINVAL; + else + sk->sk_ll_usec = val; + } + break; +#endif default: ret = -ENOPROTOOPT; break; @@ -1170,6 +1183,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; +#ifdef CONFIG_NET_LL_RX_POLL + case SO_LL: + v.val = sk->sk_ll_usec; + break; +#endif + default: return -ENOPROTOOPT; } @@ -2288,6 +2307,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; + sk->sk_ll_usec = sysctl_net_ll_poll; #endif /* -- cgit v1.2.3-18-g5258 From 2d48d67fa8cd129ea85ea02d91b4a793286866f8 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Mon, 24 Jun 2013 10:28:03 +0300 Subject: net: poll/select low latency socket support select/poll busy-poll support. Split sysctl value into two separate ones, one for read and one for poll. updated Documentation/sysctl/net.txt Add a new poll flag POLL_LL. When this flag is set, sock_poll will call sk_poll_ll if possible. sock_poll sets this flag in its return value to indicate to select/poll when a socket that can busy poll is found. When poll/select have nothing to report, call the low-level sock_poll again until we are out of time or we find something. Once the system call finds something, it stops setting POLL_LL, so it can return the result to the user ASAP. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 1e744b12fda..b6c619f4d47 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2307,7 +2307,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_ll_poll; + sk->sk_ll_usec = sysctl_net_ll_read; #endif /* -- cgit v1.2.3-18-g5258 From 076bb0c82a44fbe46fe2c8527a5b5b64b69f679d Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:17 +0300 Subject: net: rename include/net/ll_poll.h to include/net/busy_poll.h Rename the file and correct all the places where it is included. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index ab06b719f5b..9bfe83f4d67 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,7 +139,7 @@ #include #endif -#include +#include static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -- cgit v1.2.3-18-g5258 From 64b0dc517ea1b35d02565a779e6cb77ae9045685 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:36 +0300 Subject: net: rename busy poll socket op and globals Rename LL_SO to BUSY_POLL_SO Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll} Fix up users of these variables. Fix documentation for sysctl. a patch for the socket.7 man page will follow separately, because of limitations of my mail setup. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- net/core/sock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 9bfe83f4d67..548d716c5f6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -901,7 +901,7 @@ set_rcvbuf: break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; @@ -1171,7 +1171,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; #endif @@ -2294,7 +2294,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_ll_read; + sk->sk_ll_usec = sysctl_net_busy_read; #endif /* -- cgit v1.2.3-18-g5258 From e0d1095ae3405404d247afb00233ef837d58da83 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 1 Aug 2013 11:10:25 +0800 Subject: net: rename CONFIG_NET_LL_RX_POLL to CONFIG_NET_RX_BUSY_POLL Eliezer renames several *ll_poll to *busy_poll, but forgets CONFIG_NET_LL_RX_POLL, so in case of confusion, rename it too. Cc: Eliezer Tamir Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/sock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 548d716c5f6..2c097c5a35d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -900,7 +900,7 @@ set_rcvbuf: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) @@ -1170,7 +1170,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; @@ -2292,7 +2292,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = sysctl_net_busy_read; #endif -- cgit v1.2.3-18-g5258