From 3b885787ea4112eaa80945999ea0901bf742707f Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 12 Oct 2009 13:26:31 -0700 Subject: net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/mips/include/asm/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h index ae05accd9fe..9de5190f248 100644 --- a/arch/mips/include/asm/socket.h +++ b/arch/mips/include/asm/socket.h @@ -80,6 +80,8 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ #define SO_TIMESTAMPING 37 #define SCM_TIMESTAMPING SO_TIMESTAMPING +#define SO_RXQ_OVFL 40 + #ifdef __KERNEL__ /** sock_type - Socket types -- cgit v1.2.3 From a2e2725541fad72416326798c2d7fa4dafb7d337 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 Oct 2009 23:40:10 -0700 Subject: net: Introduce recvmmsg socket syscall MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Meaning receive multiple messages, reducing the number of syscalls and net stack entry/exit operations. Next patches will introduce mechanisms where protocols that want to optimize this operation will provide an unlocked_recvmsg operation. This takes into account comments made by: . Paul Moore: sock_recvmsg is called only for the first datagram, sock_recvmsg_nosec is used for the rest. . Caitlin Bestler: recvmmsg now has a struct timespec timeout, that works in the same fashion as the ppoll one. If the underlying protocol returns a datagram with MSG_OOB set, this will make recvmmsg return right away with as many datagrams (+ the OOB one) it has received so far. . Rémi Denis-Courmont & Steven Whitehouse: If we receive N < vlen datagrams and then recvmsg returns an error, recvmmsg will return the successfully received datagrams, store the error and return it in the next call. This paves the way for a subsequent optimization, sk_prot->unlocked_recvmsg, where we will be able to acquire the lock only at batch start and end, not at every underlying recvmsg call. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- arch/mips/kernel/scall32-o32.S | 1 + arch/mips/kernel/scall64-64.S | 1 + arch/mips/kernel/scall64-n32.S | 1 + arch/mips/kernel/scall64-o32.S | 1 + 4 files changed, 4 insertions(+) (limited to 'arch/mips') diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index fd2a9bb620d..17202bbe843 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -583,6 +583,7 @@ einval: li v0, -ENOSYS sys sys_rt_tgsigqueueinfo 4 sys sys_perf_event_open 5 sys sys_accept4 4 + sys sys_recvmmsg 5 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 18bf7f32c5e..a8a6c596eb0 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -420,4 +420,5 @@ sys_call_table: PTR sys_rt_tgsigqueueinfo PTR sys_perf_event_open PTR sys_accept4 + PTR sys_recvmmsg .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 6ebc0797669..5154e64f7cf 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -418,4 +418,5 @@ EXPORT(sysn32_call_table) PTR compat_sys_rt_tgsigqueueinfo /* 5295 */ PTR sys_perf_event_open PTR sys_accept4 + PTR compat_sys_recvmmsg .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 9bbf9775e0b..d0eff53d7cb 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -538,4 +538,5 @@ sys_call_table: PTR compat_sys_rt_tgsigqueueinfo PTR sys_perf_event_open PTR sys_accept4 + PTR compat_sys_recvmmsg .size sys_call_table,.-sys_call_table -- cgit v1.2.3 From 5a5b6f6f62ac684a5856121d8cffd3c3253dc890 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Nov 2009 13:02:23 -0800 Subject: MIPS: Wire up recvmmsg syscall Reported-by: Jean-Mickael Guerin Signed-off-by: Arnaldo Carvalho de Melo Acked-by: Ralf Baechle Signed-off-by: David S. Miller --- arch/mips/include/asm/unistd.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 8c9dfa9e901..65c679ecbe6 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -355,16 +355,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 332) #define __NR_perf_event_open (__NR_Linux + 333) #define __NR_accept4 (__NR_Linux + 334) +#define __NR_recvmmsg (__NR_Linux + 335) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 334 +#define __NR_Linux_syscalls 335 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 334 +#define __NR_O32_Linux_syscalls 335 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -666,16 +667,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 291) #define __NR_perf_event_open (__NR_Linux + 292) #define __NR_accept4 (__NR_Linux + 293) +#define __NR_recvmmsg (__NR_Linux + 294) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 293 +#define __NR_Linux_syscalls 294 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 293 +#define __NR_64_Linux_syscalls 294 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -981,16 +983,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 295) #define __NR_perf_event_open (__NR_Linux + 296) #define __NR_accept4 (__NR_Linux + 297) +#define __NR_recvmmsg (__NR_Linux + 298) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 297 +#define __NR_Linux_syscalls 298 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 297 +#define __NR_N32_Linux_syscalls 298 #ifdef __KERNEL__ -- cgit v1.2.3