From e56c57d0d3fdbbdf583d3af96bfb803b8dfa713e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Nov 2011 17:07:07 -0500 Subject: net: rename sk_clone to sk_clone_lock Make clear that sk_clone() and inet_csk_clone() return a locked socket. Add _lock() prefix and kerneldoc. Suggested-by: Linus Torvalds Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 4ed7b1d12f5e..2de9dc295956 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1204,7 +1204,14 @@ void sk_release_kernel(struct sock *sk) } EXPORT_SYMBOL(sk_release_kernel); -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; @@ -1297,7 +1304,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) out: return newsk; } -EXPORT_SYMBOL_GPL(sk_clone); +EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { -- cgit v1.2.3 From 6e3e939f3b1bf8534b32ad09ff199d88800835a0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 9 Nov 2011 10:15:42 +0100 Subject: net: add wireless TX status socket option The 802.1X EAPOL handshake hostapd does requires knowing whether the frame was ack'ed by the peer. Currently, we fudge this pretty badly by not even transmitting the frame as a normal data frame but injecting it with radiotap and getting the status out of radiotap monitor as well. This is rather complex, confuses users (mon.wlan0 presence) and doesn't work with all hardware. To get rid of that hack, introduce a real wifi TX status option for data frame transmissions. This works similar to the existing TX timestamping in that it reflects the SKB back to the socket's error queue with a SCM_WIFI_STATUS cmsg that has an int indicating ACK status (0/1). Since it is possible that at some point we will want to have TX timestamping and wifi status in a single errqueue SKB (there's little point in not doing that), redefine SO_EE_ORIGIN_TIMESTAMPING to SO_EE_ORIGIN_TXSTATUS which can collect more than just the timestamp; keep the old constant as an alias of course. Currently the internal APIs don't make that possible, but it wouldn't be hard to split them up in a way that makes it possible. Thanks to Neil Horman for helping me figure out the functions that add the control messages. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- arch/alpha/include/asm/socket.h | 3 +++ arch/arm/include/asm/socket.h | 3 +++ arch/avr32/include/asm/socket.h | 3 +++ arch/cris/include/asm/socket.h | 3 +++ arch/frv/include/asm/socket.h | 3 +++ arch/h8300/include/asm/socket.h | 3 +++ arch/ia64/include/asm/socket.h | 3 +++ arch/m32r/include/asm/socket.h | 3 +++ arch/m68k/include/asm/socket.h | 3 +++ arch/mips/include/asm/socket.h | 3 +++ arch/mn10300/include/asm/socket.h | 3 +++ arch/parisc/include/asm/socket.h | 3 +++ arch/powerpc/include/asm/socket.h | 3 +++ arch/s390/include/asm/socket.h | 3 +++ arch/sparc/include/asm/socket.h | 3 +++ arch/xtensa/include/asm/socket.h | 3 +++ include/asm-generic/socket.h | 3 +++ include/linux/errqueue.h | 3 ++- include/linux/skbuff.h | 19 +++++++++++++++++-- include/net/sock.h | 6 ++++++ net/core/skbuff.c | 20 ++++++++++++++++++++ net/core/sock.c | 9 +++++++++ net/socket.c | 18 ++++++++++++++++++ 23 files changed, 123 insertions(+), 3 deletions(-) (limited to 'net/core/sock.c') diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h index 06edfefc3373..082355f159e6 100644 --- a/arch/alpha/include/asm/socket.h +++ b/arch/alpha/include/asm/socket.h @@ -69,6 +69,9 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + /* 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/arm/include/asm/socket.h b/arch/arm/include/asm/socket.h index 90ffd04b8e74..dec6f9afb3cf 100644 --- a/arch/arm/include/asm/socket.h +++ b/arch/arm/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/avr32/include/asm/socket.h b/arch/avr32/include/asm/socket.h index c8d1fae49476..247b88c760be 100644 --- a/arch/avr32/include/asm/socket.h +++ b/arch/avr32/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h index 1a4a61909ca8..e269264df7c4 100644 --- a/arch/cris/include/asm/socket.h +++ b/arch/cris/include/asm/socket.h @@ -64,6 +64,9 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/asm/socket.h b/arch/frv/include/asm/socket.h index a6b26880c1ec..ce80fdadcce5 100644 --- a/arch/frv/include/asm/socket.h +++ b/arch/frv/include/asm/socket.h @@ -62,5 +62,8 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h index 04c0f4596eb5..cf1daab6f27e 100644 --- a/arch/h8300/include/asm/socket.h +++ b/arch/h8300/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h index 51427eaa51ba..4b03664e3fb5 100644 --- a/arch/ia64/include/asm/socket.h +++ b/arch/ia64/include/asm/socket.h @@ -71,4 +71,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/asm/socket.h b/arch/m32r/include/asm/socket.h index 469787c30098..e8b8c5bb053c 100644 --- a/arch/m32r/include/asm/socket.h +++ b/arch/m32r/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h index 9bf49c87d954..d4708ce466e0 100644 --- a/arch/m68k/include/asm/socket.h +++ b/arch/m68k/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h index 9de5190f2487..ad5c0a7a02a7 100644 --- a/arch/mips/include/asm/socket.h +++ b/arch/mips/include/asm/socket.h @@ -82,6 +82,9 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #ifdef __KERNEL__ /** sock_type - Socket types diff --git a/arch/mn10300/include/asm/socket.h b/arch/mn10300/include/asm/socket.h index 4e60c4281288..876356d78522 100644 --- a/arch/mn10300/include/asm/socket.h +++ b/arch/mn10300/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h index 225b7d6a1a0a..d28c51b61067 100644 --- a/arch/parisc/include/asm/socket.h +++ b/arch/parisc/include/asm/socket.h @@ -61,6 +61,9 @@ #define SO_RXQ_OVFL 0x4021 +#define SO_WIFI_STATUS 0x4022 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + /* 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/asm/socket.h b/arch/powerpc/include/asm/socket.h index 866f7606da68..2fc2af8fbf59 100644 --- a/arch/powerpc/include/asm/socket.h +++ b/arch/powerpc/include/asm/socket.h @@ -69,4 +69,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index fdff1e995c73..67b5c1b14b51 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -70,4 +70,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h index 9d3fefcff2f5..8af1b64168b3 100644 --- a/arch/sparc/include/asm/socket.h +++ b/arch/sparc/include/asm/socket.h @@ -58,6 +58,9 @@ #define SO_RXQ_OVFL 0x0024 +#define SO_WIFI_STATUS 0x0025 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + /* 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/asm/socket.h b/arch/xtensa/include/asm/socket.h index cbdf2ffaacff..bb06968be227 100644 --- a/arch/xtensa/include/asm/socket.h +++ b/arch/xtensa/include/asm/socket.h @@ -73,4 +73,7 @@ #define SO_RXQ_OVFL 40 +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/asm-generic/socket.h b/include/asm-generic/socket.h index 9a6115e7cf63..49c1704173e7 100644 --- a/include/asm-generic/socket.h +++ b/include/asm-generic/socket.h @@ -64,4 +64,7 @@ #define SO_DOMAIN 39 #define SO_RXQ_OVFL 40 + +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index 034072cea853..c9f522bd17e4 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -17,7 +17,8 @@ struct sock_extended_err { #define SO_EE_ORIGIN_LOCAL 1 #define SO_EE_ORIGIN_ICMP 2 #define SO_EE_ORIGIN_ICMP6 3 -#define SO_EE_ORIGIN_TIMESTAMPING 4 +#define SO_EE_ORIGIN_TXSTATUS 4 +#define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6a6b352326d7..ff7e1306a2d2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -218,6 +218,9 @@ enum { /* device driver supports TX zero-copy buffers */ SKBTX_DEV_ZEROCOPY = 1 << 4, + + /* generate wifi status information (where possible) */ + SKBTX_WIFI_STATUS = 1 << 5, }; /* @@ -352,6 +355,8 @@ typedef unsigned char *sk_buff_data_t; * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport * ports. + * @wifi_acked_valid: wifi_acked was set + * @wifi_acked: whether frame was acked on wifi or not * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions * @secmark: security marking @@ -445,10 +450,11 @@ struct sk_buff { #endif __u8 ooo_okay:1; __u8 l4_rxhash:1; + __u8 wifi_acked_valid:1; + __u8 wifi_acked:1; + /* 10/12 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); - /* 0/13 bit hole */ - #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; #endif @@ -2263,6 +2269,15 @@ static inline void skb_tx_timestamp(struct sk_buff *skb) sw_tx_timestamp(skb); } +/** + * skb_complete_wifi_ack - deliver skb with wifi status + * + * @skb: the original outgoing packet + * @acked: ack status + * + */ +void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); + extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); extern __sum16 __skb_checksum_complete(struct sk_buff *skb); diff --git a/include/net/sock.h b/include/net/sock.h index 5ac682f73d63..fa6f5381c5d6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -564,6 +564,7 @@ enum sock_flags { SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ + SOCK_WIFI_STATUS, /* push wifi status to userspace */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -1714,6 +1715,8 @@ static inline int sock_intr_errno(long timeo) extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); +extern void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); static __inline__ void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) @@ -1741,6 +1744,9 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) __sock_recv_timestamp(msg, sk, skb); else sk->sk_stamp = kt; + + if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) + __sock_recv_wifi_status(msg, sk, skb); } extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ca4db40e75b8..2f6babd5a570 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3168,6 +3168,26 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, } EXPORT_SYMBOL_GPL(skb_tstamp_tx); +void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) +{ + struct sock *sk = skb->sk; + struct sock_exterr_skb *serr; + int err; + + skb->wifi_acked_valid = 1; + skb->wifi_acked = acked; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; + + err = sock_queue_err_skb(sk, skb); + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); + /** * skb_partial_csum_set - set up and verify partial csum values for packet diff --git a/net/core/sock.c b/net/core/sock.c index 4ed7b1d12f5e..cbdf51c0d5ac 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -740,6 +740,11 @@ set_rcvbuf: case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; + + case SO_WIFI_STATUS: + sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); + break; + default: ret = -ENOPROTOOPT; break; @@ -961,6 +966,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = !!sock_flag(sk, SOCK_RXQ_OVFL); break; + case SO_WIFI_STATUS: + v.val = !!sock_flag(sk, SOCK_WIFI_STATUS); + break; + default: return -ENOPROTOOPT; } diff --git a/net/socket.c b/net/socket.c index 2877647f347b..425ef4270460 100644 --- a/net/socket.c +++ b/net/socket.c @@ -538,6 +538,8 @@ int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags) *tx_flags |= SKBTX_HW_TSTAMP; if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) *tx_flags |= SKBTX_SW_TSTAMP; + if (sock_flag(sk, SOCK_WIFI_STATUS)) + *tx_flags |= SKBTX_WIFI_STATUS; return 0; } EXPORT_SYMBOL(sock_tx_timestamp); @@ -674,6 +676,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); +void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + int ack; + + if (!sock_flag(sk, SOCK_WIFI_STATUS)) + return; + if (!skb->wifi_acked_valid) + return; + + ack = skb->wifi_acked; + + put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); +} +EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); + static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { -- cgit v1.2.3 From 5bc1421e34ecfe0bd4b26dc3232b7d5e25179144 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 22 Nov 2011 05:10:51 +0000 Subject: net: add network priority cgroup infrastructure (v4) This patch adds in the infrastructure code to create the network priority cgroup. The cgroup, in addition to the standard processes file creates two control files: 1) prioidx - This is a read-only file that exports the index of this cgroup. This is a value that is both arbitrary and unique to a cgroup in this subsystem, and is used to index the per-device priority map 2) priomap - This is a writeable file. On read it reports a table of 2-tuples where name is the name of a network interface and priority is indicates the priority assigned to frames egresessing on the named interface and originating from a pid in this cgroup This cgroup allows for skb priority to be set prior to a root qdisc getting selected. This is benenficial for DCB enabled systems, in that it allows for any application to use dcb configured priorities so without application modification Signed-off-by: Neil Horman Signed-off-by: John Fastabend CC: Robert Love CC: "David S. Miller" Signed-off-by: David S. Miller --- include/linux/cgroup_subsys.h | 8 + include/linux/netdevice.h | 4 + include/net/netprio_cgroup.h | 65 ++++++++ include/net/sock.h | 3 + net/Kconfig | 7 + net/core/Makefile | 1 + net/core/dev.c | 14 ++ net/core/netprio_cgroup.c | 344 ++++++++++++++++++++++++++++++++++++++++++ net/core/sock.c | 22 ++- net/socket.c | 2 + 10 files changed, 469 insertions(+), 1 deletion(-) create mode 100644 include/net/netprio_cgroup.h create mode 100644 net/core/netprio_cgroup.c (limited to 'net/core/sock.c') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index ac663c18776c..0bd390ce98b2 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -59,8 +59,16 @@ SUBSYS(net_cls) SUBSYS(blkio) #endif +/* */ + #ifdef CONFIG_CGROUP_PERF SUBSYS(perf) #endif /* */ + +#ifdef CONFIG_NETPRIO_CGROUP +SUBSYS(net_prio) +#endif + +/* */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3eb383a9b5ed..999bb264fe27 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -50,6 +50,7 @@ #ifdef CONFIG_DCB #include #endif +#include #include @@ -1244,6 +1245,9 @@ struct net_device { #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; +#endif +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) + struct netprio_map __rcu *priomap; #endif /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h new file mode 100644 index 000000000000..c432e99942af --- /dev/null +++ b/include/net/netprio_cgroup.h @@ -0,0 +1,65 @@ +/* + * netprio_cgroup.h Control Group Priority set + * + * + * Authors: Neil Horman + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _NETPRIO_CGROUP_H +#define _NETPRIO_CGROUP_H +#include +#include +#include +#include + +struct cgroup_netprio_state +{ + struct cgroup_subsys_state css; + u32 prioidx; +}; + +struct netprio_map { + struct rcu_head rcu; + u32 priomap_len; + u32 priomap[]; +}; + +#ifdef CONFIG_CGROUPS + +#ifndef CONFIG_NETPRIO_CGROUP +extern int net_prio_subsys_id; +#endif + +extern void sock_update_netprioidx(struct sock *sk); + +static inline struct cgroup_netprio_state + *task_netprio_state(struct task_struct *p) +{ +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) + return container_of(task_subsys_state(p, net_prio_subsys_id), + struct cgroup_netprio_state, css); +#else + return NULL; +#endif +} + +#else + +#define sock_update_netprioidx(sk) +#define skb_update_prio(skb) + +static inline struct cgroup_netprio_state + *task_netprio_state(struct task_struct *p) +{ + return NULL; +} + +#endif + +#endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 1c28f394d8ec..8ac338cb39ce 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -320,6 +320,9 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; +#ifdef CONFIG_CGROUPS + __u32 sk_cgrp_prioidx; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; diff --git a/net/Kconfig b/net/Kconfig index a07314844238..63d2c5dc36ff 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,13 @@ config XPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config NETPRIO_CGROUP + tristate "Network priority cgroup" + depends on CGROUPS + ---help--- + Cgroup subsystem for use in assigning processes to network priorities on + a per-interface basis + config HAVE_BPF_JIT bool diff --git a/net/core/Makefile b/net/core/Makefile index 0d357b1c4e57..3606d40aae62 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index f78959996148..8afb244b205f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2449,6 +2449,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference(skb->dev->priomap); + + if ((!skb->priority) && (skb->sk) && map) + skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; +} +#else +#define skb_update_prio(skb) +#endif + static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 @@ -2489,6 +2501,8 @@ int dev_queue_xmit(struct sk_buff *skb) */ rcu_read_lock_bh(); + skb_update_prio(skb); + txq = dev_pick_tx(dev, skb); q = rcu_dereference_bh(txq->qdisc); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 000000000000..72ad0bc6841e --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,344 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Neil Horman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp); +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp); + +struct cgroup_subsys net_prio_subsys = { + .name = "net_prio", + .create = cgrp_create, + .destroy = cgrp_destroy, + .populate = cgrp_populate, +#ifdef CONFIG_NETPRIO_CGROUP + .subsys_id = net_prio_subsys_id, +#endif + .module = THIS_MODULE +}; + +#define PRIOIDX_SZ 128 + +static unsigned long prioidx_map[PRIOIDX_SZ]; +static DEFINE_SPINLOCK(prioidx_map_lock); +static atomic_t max_prioidx = ATOMIC_INIT(0); + +static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id), + struct cgroup_netprio_state, css); +} + +static int get_prioidx(u32 *prio) +{ + unsigned long flags; + u32 prioidx; + + spin_lock_irqsave(&prioidx_map_lock, flags); + prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + set_bit(prioidx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) + return -ENOSPC; + + atomic_set(&max_prioidx, prioidx); + *prio = prioidx; + return 0; +} + +static void put_prioidx(u32 idx) +{ + unsigned long flags; + + spin_lock_irqsave(&prioidx_map_lock, flags); + clear_bit(idx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); +} + +static void extend_netdev_table(struct net_device *dev, u32 new_len) +{ + size_t new_size = sizeof(struct netprio_map) + + ((sizeof(u32) * new_len)); + struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL); + struct netprio_map *old_priomap; + int i; + + old_priomap = rtnl_dereference(dev->priomap); + + if (!new_priomap) { + printk(KERN_WARNING "Unable to alloc new priomap!\n"); + return; + } + + for (i = 0; + old_priomap && (i < old_priomap->priomap_len); + i++) + new_priomap->priomap[i] = old_priomap->priomap[i]; + + new_priomap->priomap_len = new_len; + + rcu_assign_pointer(dev->priomap, new_priomap); + if (old_priomap) + kfree_rcu(old_priomap, rcu); +} + +static void update_netdev_tables(void) +{ + struct net_device *dev; + u32 max_len = atomic_read(&max_prioidx); + struct netprio_map *map; + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if ((!map) || + (map->priomap_len < max_len)) + extend_netdev_table(dev, max_len); + } + rtnl_unlock(); +} + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + int ret; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { + kfree(cs); + return ERR_PTR(-EINVAL); + } + + ret = get_prioidx(&cs->prioidx); + if (ret != 0) { + printk(KERN_WARNING "No space in priority index array\n"); + kfree(cs); + return ERR_PTR(ret); + } + + return &cs->css; +} + +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + struct net_device *dev; + struct netprio_map *map; + + cs = cgrp_netprio_state(cgrp); + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if (map) + map->priomap[cs->prioidx] = 0; + } + rtnl_unlock(); + put_prioidx(cs->prioidx); + kfree(cs); +} + +static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) +{ + return (u64)cgrp_netprio_state(cgrp)->prioidx; +} + +static int read_priomap(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct net_device *dev; + u32 prioidx = cgrp_netprio_state(cont)->prioidx; + u32 priority; + struct netprio_map *map; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + map = rcu_dereference(dev->priomap); + priority = map ? map->priomap[prioidx] : 0; + cb->fill(cb, dev->name, priority); + } + rcu_read_unlock(); + return 0; +} + +static int write_priomap(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + char *devname = kstrdup(buffer, GFP_KERNEL); + int ret = -EINVAL; + u32 prioidx = cgrp_netprio_state(cgrp)->prioidx; + unsigned long priority; + char *priostr; + struct net_device *dev; + struct netprio_map *map; + + if (!devname) + return -ENOMEM; + + /* + * Minimally sized valid priomap string + */ + if (strlen(devname) < 3) + goto out_free_devname; + + priostr = strstr(devname, " "); + if (!priostr) + goto out_free_devname; + + /* + *Separate the devname from the associated priority + *and advance the priostr poitner to the priority value + */ + *priostr = '\0'; + priostr++; + + /* + * If the priostr points to NULL, we're at the end of the passed + * in string, and its not a valid write + */ + if (*priostr == '\0') + goto out_free_devname; + + ret = kstrtoul(priostr, 10, &priority); + if (ret < 0) + goto out_free_devname; + + ret = -ENODEV; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + goto out_free_devname; + + update_netdev_tables(); + ret = 0; + rcu_read_lock(); + map = rcu_dereference(dev->priomap); + if (map) + map->priomap[prioidx] = priority; + rcu_read_unlock(); + dev_put(dev); + +out_free_devname: + kfree(devname); + return ret; +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .read_map = read_priomap, + .write_string = write_priomap, + }, +}; + +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); +} + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct netprio_map *old; + u32 max_len = atomic_read(&max_prioidx); + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + + case NETDEV_REGISTER: + if (max_len) + extend_netdev_table(dev, max_len); + break; + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + rcu_assign_pointer(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + int ret; + + ret = cgroup_load_subsys(&net_prio_subsys); + if (ret) + goto out; +#ifndef CONFIG_NETPRIO_CGROUP + smp_wmb(); + net_prio_subsys_id = net_prio_subsys.subsys_id; +#endif + + register_netdevice_notifier(&netprio_device_notifier); + +out: + return ret; +} + +static void __exit exit_cgroup_netprio(void) +{ + struct netprio_map *old; + struct net_device *dev; + + unregister_netdevice_notifier(&netprio_device_notifier); + + cgroup_unload_subsys(&net_prio_subsys); + +#ifndef CONFIG_NETPRIO_CGROUP + net_prio_subsys_id = -1; + synchronize_rcu(); +#endif + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + old = rtnl_dereference(dev->priomap); + rcu_assign_pointer(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + } + rtnl_unlock(); +} + +module_init(init_cgroup_netprio); +module_exit(exit_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/sock.c b/net/core/sock.c index 9a8b3fac1401..16069139797c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -125,6 +125,7 @@ #include #include #include +#include #include @@ -221,10 +222,16 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); -#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP) +#if defined(CONFIG_CGROUPS) +#if !defined(CONFIG_NET_CLS_CGROUP) int net_cls_subsys_id = -1; EXPORT_SYMBOL_GPL(net_cls_subsys_id); #endif +#if !defined(CONFIG_NETPRIO_CGROUP) +int net_prio_subsys_id = -1; +EXPORT_SYMBOL_GPL(net_prio_subsys_id); +#endif +#endif static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -1120,6 +1127,18 @@ void sock_update_classid(struct sock *sk) sk->sk_classid = classid; } EXPORT_SYMBOL(sock_update_classid); + +void sock_update_netprioidx(struct sock *sk) +{ + struct cgroup_netprio_state *state; + if (in_interrupt()) + return; + rcu_read_lock(); + state = task_netprio_state(current); + sk->sk_cgrp_prioidx = state ? state->prioidx : 0; + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif /** @@ -1147,6 +1166,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; diff --git a/net/socket.c b/net/socket.c index 425ef4270460..e62b4f055071 100644 --- a/net/socket.c +++ b/net/socket.c @@ -551,6 +551,8 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, sock_update_classid(sock->sk); + sock_update_netprioidx(sock->sk); + si->sock = sock; si->scm = NULL; si->msg = msg; -- cgit v1.2.3 From 08e29af3a9096ffdff477e537daea67faefd3952 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 28 Nov 2011 12:04:18 +0000 Subject: net: optimize socket timestamping We can test/set multiple bits from sk_flags at once, to shorten a bit socket setup/dismantle phase. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 16069139797c..9777da86aeac 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -276,14 +276,14 @@ static void sock_warn_obsolete_bsdism(const char *name) } } -static void sock_disable_timestamp(struct sock *sk, int flag) +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + +static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { - if (sock_flag(sk, flag)) { - sock_reset_flag(sk, flag); - if (!sock_flag(sk, SOCK_TIMESTAMP) && - !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) { + if (sk->sk_flags & flags) { + sk->sk_flags &= ~flags; + if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); - } } } @@ -689,7 +689,7 @@ set_rcvbuf: SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, - SOCK_TIMESTAMPING_RX_SOFTWARE); + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, val & SOF_TIMESTAMPING_SOFTWARE); sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, @@ -1187,8 +1187,7 @@ static void __sk_free(struct sock *sk) RCU_INIT_POINTER(sk->sk_filter, NULL); } - sock_disable_timestamp(sk, SOCK_TIMESTAMP); - sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); + sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); if (atomic_read(&sk->sk_omem_alloc)) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", @@ -1326,8 +1325,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); - if (sock_flag(newsk, SOCK_TIMESTAMP) || - sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); } out: @@ -2165,16 +2163,15 @@ EXPORT_SYMBOL(sock_get_timestampns); void sock_enable_timestamp(struct sock *sk, int flag) { if (!sock_flag(sk, flag)) { + unsigned long previous_flags = sk->sk_flags; + sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ - if (!sock_flag(sk, - flag == SOCK_TIMESTAMP ? - SOCK_TIMESTAMPING_RX_SOFTWARE : - SOCK_TIMESTAMP)) + if (!(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } -- cgit v1.2.3 From 180d8cd942ce336b2c869d324855c40c5db478ad Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:02 +0000 Subject: foundations of per-cgroup memory pressure controlling. This patch replaces all uses of struct sock fields' memory_pressure, memory_allocated, sockets_allocated, and sysctl_mem to acessor macros. Those macros can either receive a socket argument, or a mem_cgroup argument, depending on the context they live in. Since we're only doing a macro wrapping here, no performance impact at all is expected in the case where we don't have cgroups disabled. Signed-off-by: Glauber Costa Reviewed-by: Hiroyouki Kamezawa CC: David S. Miller CC: Eric W. Biederman CC: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++- include/net/tcp.h | 3 +- net/core/sock.c | 57 ++++++++++++++++++------------ net/ipv4/proc.c | 6 ++-- net/ipv4/tcp_input.c | 12 +++---- net/ipv4/tcp_ipv4.c | 4 +-- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 145 insertions(+), 39 deletions(-) (limited to 'net/core/sock.c') diff --git a/include/net/sock.h b/include/net/sock.h index 8ac338cb39ce..ed0dbf034539 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -53,6 +53,7 @@ #include #include #include +#include #include #include @@ -867,6 +868,99 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +static inline bool sk_under_memory_pressure(const struct sock *sk) +{ + if (!sk->sk_prot->memory_pressure) + return false; + return !!*sk->sk_prot->memory_pressure; +} + +static inline void sk_leave_memory_pressure(struct sock *sk) +{ + int *memory_pressure = sk->sk_prot->memory_pressure; + + if (memory_pressure && *memory_pressure) + *memory_pressure = 0; +} + +static inline void sk_enter_memory_pressure(struct sock *sk) +{ + if (sk->sk_prot->enter_memory_pressure) + sk->sk_prot->enter_memory_pressure(sk); +} + +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long *prot = sk->sk_prot->sysctl_mem; + return prot[index]; +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + return atomic_long_read(prot->memory_allocated); +} + +static inline long +sk_memory_allocated_add(struct sock *sk, int amt) +{ + struct proto *prot = sk->sk_prot; + return atomic_long_add_return(amt, prot->memory_allocated); +} + +static inline void +sk_memory_allocated_sub(struct sock *sk, int amt) +{ + struct proto *prot = sk->sk_prot; + atomic_long_sub(amt, prot->memory_allocated); +} + +static inline void sk_sockets_allocated_dec(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + percpu_counter_dec(prot->sockets_allocated); +} + +static inline void sk_sockets_allocated_inc(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + percpu_counter_inc(prot->sockets_allocated); +} + +static inline int +sk_sockets_allocated_read_positive(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline int +proto_sockets_allocated_sum_positive(struct proto *prot) +{ + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline long +proto_memory_allocated(struct proto *prot) +{ + return atomic_long_read(prot->memory_allocated); +} + +static inline bool +proto_memory_pressure(struct proto *prot) +{ + if (!prot->memory_pressure) + return false; + return !!*prot->memory_pressure; +} + #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ @@ -1674,7 +1768,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk) page = alloc_pages(sk->sk_allocation, 0); if (!page) { - sk->sk_prot->enter_memory_pressure(sk); + sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return page; diff --git a/include/net/tcp.h b/include/net/tcp.h index 02f070d339ba..913473b4eda7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -44,6 +44,7 @@ #include #include +#include extern struct inet_hashinfo tcp_hashinfo; @@ -285,7 +286,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) } if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]) + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } diff --git a/net/core/sock.c b/net/core/sock.c index 9777da86aeac..a3d4205e7238 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1323,7 +1323,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_wq = NULL; if (newsk->sk_prot->sockets_allocated) - percpu_counter_inc(newsk->sk_prot->sockets_allocated); + sk_sockets_allocated_inc(newsk); if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); @@ -1713,28 +1713,28 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) long allocated; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = atomic_long_add_return(amt, prot->memory_allocated); + + allocated = sk_memory_allocated_add(sk, amt); /* Under limit. */ - if (allocated <= prot->sysctl_mem[0]) { - if (prot->memory_pressure && *prot->memory_pressure) - *prot->memory_pressure = 0; + if (allocated <= sk_prot_mem_limits(sk, 0)) { + sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ - if (allocated > prot->sysctl_mem[1]) - if (prot->enter_memory_pressure) - prot->enter_memory_pressure(sk); + if (allocated > sk_prot_mem_limits(sk, 1)) + sk_enter_memory_pressure(sk); /* Over hard limit. */ - if (allocated > prot->sysctl_mem[2]) + if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0]) return 1; + } else { /* SK_MEM_SEND */ if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) @@ -1744,13 +1744,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) return 1; } - if (prot->memory_pressure) { + if (sk_has_memory_pressure(sk)) { int alloc; - if (!*prot->memory_pressure) + if (!sk_under_memory_pressure(sk)) return 1; - alloc = percpu_counter_read_positive(prot->sockets_allocated); - if (prot->sysctl_mem[2] > alloc * + alloc = sk_sockets_allocated_read_positive(sk); + if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) @@ -1773,7 +1773,9 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - atomic_long_sub(amt, prot->memory_allocated); + + sk_memory_allocated_sub(sk, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -1784,15 +1786,13 @@ EXPORT_SYMBOL(__sk_mem_schedule); */ void __sk_mem_reclaim(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, - prot->memory_allocated); + sk_memory_allocated_sub(sk, + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; - if (prot->memory_pressure && *prot->memory_pressure && - (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0])) - *prot->memory_pressure = 0; + if (sk_under_memory_pressure(sk) && + (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) + sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -2507,16 +2507,27 @@ static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } +static long sock_prot_memory_allocated(struct proto *proto) +{ + return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L; +} + +static char *sock_prot_memory_pressure(struct proto *proto) +{ + return proto->memory_pressure != NULL ? + proto_memory_pressure(proto) ? "yes" : "no" : "NI"; +} static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), - proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L, - proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", + sock_prot_memory_allocated(proto), + sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 961eed4f510a..3569d8ecaeac 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_disable(); orphans = percpu_counter_sum_positive(&tcp_orphan_count); - sockets = percpu_counter_sum_positive(&tcp_sockets_allocated); + sockets = proto_sockets_allocated_sum_positive(&tcp_prot); local_bh_enable(); socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_long_read(&tcp_memory_allocated)); + proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_long_read(&udp_memory_allocated)); + proto_memory_allocated(&udp_prot)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b9cbc351c511..f131d92d25ee 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #1 */ if (tp->rcv_ssthresh < tp->window_clamp && (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_memory_pressure) { + !sk_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && - !tcp_memory_pressure && - atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + !sk_under_memory_pressure(sk) && + sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -4866,7 +4866,7 @@ static int tcp_prune_queue(struct sock *sk) if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); - else if (tcp_memory_pressure) + else if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); tcp_collapse_ofo_queue(sk); @@ -4932,11 +4932,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk) return 0; /* If we are under global TCP memory pressure, do not expand. */ - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) return 0; /* If we filled the congestion window, do not expand. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c4b8b09db9f5..f48bf312cfe8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1917,7 +1917,7 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; @@ -1973,7 +1973,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tp->cookie_values = NULL; } - percpu_counter_dec(&tcp_sockets_allocated); + sk_sockets_allocated_dec(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cf3068038942..8c8de2780c7a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1922,7 +1922,7 @@ u32 __tcp_select_window(struct sock *sk) if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index aa39a692f4c8..40a41f077981 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data) } out: - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); out_unlock: bh_unlock_sock(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9d74eee334d6..b69c7030aba9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1994,7 +1994,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; -- cgit v1.2.3 From e1aab161e0135aafcd439be20b4f35e4b0922d95 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:03 +0000 Subject: socket: initial cgroup code. The goal of this work is to move the memory pressure tcp controls to a cgroup, instead of just relying on global conditions. To avoid excessive overhead in the network fast paths, the code that accounts allocated memory to a cgroup is hidden inside a static_branch(). This branch is patched out until the first non-root cgroup is created. So when nobody is using cgroups, even if it is mounted, no significant performance penalty should be seen. This patch handles the generic part of the code, and has nothing tcp-specific. Signed-off-by: Glauber Costa Reviewed-by: KAMEZAWA Hiroyuki CC: Kirill A. Shutemov CC: David S. Miller CC: Eric W. Biederman CC: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/cgroups/memory.txt | 4 +- include/linux/memcontrol.h | 22 ++++++ include/net/sock.h | 156 +++++++++++++++++++++++++++++++++++++-- mm/memcontrol.c | 46 +++++++++++- net/core/sock.c | 24 ++++-- 5 files changed, 235 insertions(+), 17 deletions(-) (limited to 'net/core/sock.c') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index f2453241142b..23a8dc5319a3 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -289,7 +289,9 @@ to trigger slab reclaim when those limits are reached. 2.7.1 Current Kernel Memory resources accounted -None +* sockets memory pressure: some sockets protocols have memory pressure +thresholds. The Memory Controller allows them to be controlled individually +per cgroup, instead of globally. 3. User Interface diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b87068a1a09e..f15021b9f734 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,6 +85,8 @@ extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); +extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); + static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) { @@ -381,5 +383,25 @@ mem_cgroup_print_bad_page(struct page *page) } #endif +#ifdef CONFIG_INET +enum { + UNDER_LIMIT, + SOFT_LIMIT, + OVER_LIMIT, +}; + +struct sock; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +void sock_update_memcg(struct sock *sk); +void sock_release_memcg(struct sock *sk); +#else +static inline void sock_update_memcg(struct sock *sk) +{ +} +static inline void sock_release_memcg(struct sock *sk) +{ +} +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_INET */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/net/sock.h b/include/net/sock.h index ed0dbf034539..d5eab256167c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -168,6 +169,7 @@ struct sock_common { /* public: */ }; +struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -228,6 +230,7 @@ struct sock_common { * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_classid: this socket's cgroup classid + * @sk_cgrp: this socket's cgroup-specific proto data * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -342,6 +345,7 @@ struct sock { #endif __u32 sk_mark; u32 sk_classid; + struct cg_proto *sk_cgrp; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk, int bytes); void (*sk_write_space)(struct sock *sk); @@ -838,6 +842,37 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + /* + * cgroup specific init/deinit functions. Called once for all + * protocols that implement it, from cgroups populate function. + * This function has to setup any files the protocol want to + * appear in the kmem cgroup filesystem. + */ + int (*init_cgroup)(struct cgroup *cgrp, + struct cgroup_subsys *ss); + void (*destroy_cgroup)(struct cgroup *cgrp, + struct cgroup_subsys *ss); + struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); +#endif +}; + +struct cg_proto { + void (*enter_memory_pressure)(struct sock *sk); + struct res_counter *memory_allocated; /* Current allocated memory. */ + struct percpu_counter *sockets_allocated; /* Current number of sockets. */ + int *memory_pressure; + long *sysctl_mem; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; }; extern int proto_register(struct proto *prot, int alloc_slab); @@ -856,7 +891,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk) sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); } -static inline void sk_refcnt_debug_release(const struct sock *sk) +inline void sk_refcnt_debug_release(const struct sock *sk) { if (atomic_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", @@ -868,6 +903,24 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +extern struct jump_label_key memcg_socket_limit_enabled; +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); +} +#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled) +#else +#define mem_cgroup_sockets_enabled 0 +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return NULL; +} +#endif + + static inline bool sk_has_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure != NULL; @@ -877,6 +930,10 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) return false; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return !!*sk->sk_cgrp->memory_pressure; + return !!*sk->sk_prot->memory_pressure; } @@ -884,52 +941,136 @@ static inline void sk_leave_memory_pressure(struct sock *sk) { int *memory_pressure = sk->sk_prot->memory_pressure; - if (memory_pressure && *memory_pressure) + if (!memory_pressure) + return; + + if (*memory_pressure) *memory_pressure = 0; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + if (*cg_proto->memory_pressure) + *cg_proto->memory_pressure = 0; + } + } static inline void sk_enter_memory_pressure(struct sock *sk) { - if (sk->sk_prot->enter_memory_pressure) - sk->sk_prot->enter_memory_pressure(sk); + if (!sk->sk_prot->enter_memory_pressure) + return; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + cg_proto->enter_memory_pressure(sk); + } + + sk->sk_prot->enter_memory_pressure(sk); } static inline long sk_prot_mem_limits(const struct sock *sk, int index) { long *prot = sk->sk_prot->sysctl_mem; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + prot = sk->sk_cgrp->sysctl_mem; return prot[index]; } +static inline void memcg_memory_allocated_add(struct cg_proto *prot, + unsigned long amt, + int *parent_status) +{ + struct res_counter *fail; + int ret; + + ret = res_counter_charge(prot->memory_allocated, + amt << PAGE_SHIFT, &fail); + + if (ret < 0) + *parent_status = OVER_LIMIT; +} + +static inline void memcg_memory_allocated_sub(struct cg_proto *prot, + unsigned long amt) +{ + res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT); +} + +static inline u64 memcg_memory_allocated_read(struct cg_proto *prot) +{ + u64 ret; + ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE); + return ret >> PAGE_SHIFT; +} + static inline long sk_memory_allocated(const struct sock *sk) { struct proto *prot = sk->sk_prot; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return memcg_memory_allocated_read(sk->sk_cgrp); + return atomic_long_read(prot->memory_allocated); } static inline long -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) { struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); + /* update the root cgroup regardless */ + atomic_long_add_return(amt, prot->memory_allocated); + return memcg_memory_allocated_read(sk->sk_cgrp); + } + return atomic_long_add_return(amt, prot->memory_allocated); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status) { struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp && + parent_status != OVER_LIMIT) /* Otherwise was uncharged already */ + memcg_memory_allocated_sub(sk->sk_cgrp, amt); + atomic_long_sub(amt, prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) { struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_dec(cg_proto->sockets_allocated); + } + percpu_counter_dec(prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_inc(cg_proto->sockets_allocated); + } + percpu_counter_inc(prot->sockets_allocated); } @@ -938,6 +1079,9 @@ sk_sockets_allocated_read_positive(struct sock *sk) { struct proto *prot = sk->sk_prot; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated); + return percpu_counter_sum_positive(prot->sockets_allocated); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9fbcff71245e..3de3901ae0a7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -379,7 +379,48 @@ enum mem_type { static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); -static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); + +/* Writing them here to avoid exposing memcg's inner layout */ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_INET +#include + +static bool mem_cgroup_is_root(struct mem_cgroup *memcg); +void sock_update_memcg(struct sock *sk) +{ + /* A socket spends its whole life in the same cgroup */ + if (sk->sk_cgrp) { + WARN_ON(1); + return; + } + if (static_branch(&memcg_socket_limit_enabled)) { + struct mem_cgroup *memcg; + + BUG_ON(!sk->sk_prot->proto_cgroup); + + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + if (!mem_cgroup_is_root(memcg)) { + mem_cgroup_get(memcg); + sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg); + } + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(sock_update_memcg); + +void sock_release_memcg(struct sock *sk) +{ + if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) { + struct mem_cgroup *memcg; + WARN_ON(!sk->sk_cgrp->memcg); + memcg = sk->sk_cgrp->memcg; + mem_cgroup_put(memcg); + } +} +#endif /* CONFIG_INET */ +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ + static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * @@ -4932,12 +4973,13 @@ static void mem_cgroup_put(struct mem_cgroup *memcg) /* * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. */ -static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) +struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { if (!memcg->res.parent) return NULL; return mem_cgroup_from_res_counter(memcg->res.parent, res); } +EXPORT_SYMBOL(parent_mem_cgroup); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static void __init enable_swap_cgroup(void) diff --git a/net/core/sock.c b/net/core/sock.c index a3d4205e7238..6a871b8fdd20 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -111,6 +111,7 @@ #include #include #include +#include #include #include @@ -142,6 +143,9 @@ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +struct jump_label_key memcg_socket_limit_enabled; +EXPORT_SYMBOL(memcg_socket_limit_enabled); + /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket @@ -1711,23 +1715,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); long allocated; + int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = sk_memory_allocated_add(sk, amt); + allocated = sk_memory_allocated_add(sk, amt, &parent_status); /* Under limit. */ - if (allocated <= sk_prot_mem_limits(sk, 0)) { + if (parent_status == UNDER_LIMIT && + allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. */ - if (allocated > sk_prot_mem_limits(sk, 1)) + /* Under pressure. (we or our parents) */ + if ((parent_status > SOFT_LIMIT) || + allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); - /* Over hard limit. */ - if (allocated > sk_prot_mem_limits(sk, 2)) + /* Over hard limit (we or our parents) */ + if ((parent_status == OVER_LIMIT) || + (allocated > sk_prot_mem_limits(sk, 2))) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ @@ -1774,7 +1782,7 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - sk_memory_allocated_sub(sk, amt); + sk_memory_allocated_sub(sk, amt, parent_status); return 0; } @@ -1787,7 +1795,7 @@ EXPORT_SYMBOL(__sk_mem_schedule); void __sk_mem_reclaim(struct sock *sk) { sk_memory_allocated_sub(sk, - sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; if (sk_under_memory_pressure(sk) && -- cgit v1.2.3 From d1a4c0b37c296e600ffe08edb0db2dc1b8f550d7 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Sun, 11 Dec 2011 21:47:04 +0000 Subject: tcp memory pressure controls This patch introduces memory pressure controls for the tcp protocol. It uses the generic socket memory pressure code introduced in earlier patches, and fills in the necessary data in cg_proto struct. Signed-off-by: Glauber Costa Reviewed-by: KAMEZAWA Hiroyuki CC: Eric W. Biederman Signed-off-by: David S. Miller --- Documentation/cgroups/memory.txt | 2 ++ include/linux/memcontrol.h | 1 + include/net/sock.h | 2 ++ include/net/tcp_memcontrol.h | 17 +++++++++ mm/memcontrol.c | 40 +++++++++++++++++++++- net/core/sock.c | 43 +++++++++++++++++++++-- net/ipv4/Makefile | 1 + net/ipv4/tcp_ipv4.c | 9 ++++- net/ipv4/tcp_memcontrol.c | 74 ++++++++++++++++++++++++++++++++++++++++ net/ipv6/tcp_ipv6.c | 5 +++ 10 files changed, 189 insertions(+), 5 deletions(-) create mode 100644 include/net/tcp_memcontrol.h create mode 100644 net/ipv4/tcp_memcontrol.c (limited to 'net/core/sock.c') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 23a8dc5319a3..687dea5bf1fd 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -293,6 +293,8 @@ to trigger slab reclaim when those limits are reached. thresholds. The Memory Controller allows them to be controlled individually per cgroup, instead of globally. +* tcp memory pressure: sockets memory pressure for the tcp protocol. + 3. User Interface 0. Configuration diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f15021b9f734..1513994ce207 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -86,6 +86,7 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); +extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont); static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) diff --git a/include/net/sock.h b/include/net/sock.h index d5eab256167c..18ecc9919d29 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -64,6 +64,8 @@ #include #include +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss); /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h new file mode 100644 index 000000000000..5f5e1582d764 --- /dev/null +++ b/include/net/tcp_memcontrol.h @@ -0,0 +1,17 @@ +#ifndef _TCP_MEMCG_H +#define _TCP_MEMCG_H + +struct tcp_memcontrol { + struct cg_proto cg_proto; + /* per-cgroup tcp memory pressure knobs */ + struct res_counter tcp_memory_allocated; + struct percpu_counter tcp_sockets_allocated; + /* those two are read-mostly, leave them at the end */ + long tcp_prot_mem[3]; + int tcp_memory_pressure; +}; + +struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +#endif /* _TCP_MEMCG_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3de3901ae0a7..7266202fa7cf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -50,6 +50,8 @@ #include #include #include "internal.h" +#include +#include #include @@ -295,6 +297,10 @@ struct mem_cgroup { */ struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; + +#ifdef CONFIG_INET + struct tcp_memcontrol tcp_mem; +#endif }; /* Stuffs for move charges at task migration. */ @@ -384,6 +390,7 @@ static void mem_cgroup_put(struct mem_cgroup *memcg); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM #ifdef CONFIG_INET #include +#include static bool mem_cgroup_is_root(struct mem_cgroup *memcg); void sock_update_memcg(struct sock *sk) @@ -418,6 +425,15 @@ void sock_release_memcg(struct sock *sk) mem_cgroup_put(memcg); } } + +struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) +{ + if (!memcg || mem_cgroup_is_root(memcg)) + return NULL; + + return &memcg->tcp_mem.cg_proto; +} +EXPORT_SYMBOL(tcp_proto_cgroup); #endif /* CONFIG_INET */ #endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ @@ -800,7 +816,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) preempt_enable(); } -static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) +struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { return container_of(cgroup_subsys_state(cont, mem_cgroup_subsys_id), struct mem_cgroup, @@ -4732,14 +4748,34 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) ret = cgroup_add_files(cont, ss, kmem_cgroup_files, ARRAY_SIZE(kmem_cgroup_files)); + + /* + * Part of this would be better living in a separate allocation + * function, leaving us with just the cgroup tree population work. + * We, however, depend on state such as network's proto_list that + * is only initialized after cgroup creation. I found the less + * cumbersome way to deal with it to defer it all to populate time + */ + if (!ret) + ret = mem_cgroup_sockets_init(cont, ss); return ret; }; +static void kmem_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + mem_cgroup_sockets_destroy(cont, ss); +} #else static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) { return 0; } + +static void kmem_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ +} #endif static struct cftype mem_cgroup_files[] = { @@ -5098,6 +5134,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + kmem_cgroup_destroy(ss, cont); + mem_cgroup_put(memcg); } diff --git a/net/core/sock.c b/net/core/sock.c index 6a871b8fdd20..5a6a90620656 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -136,6 +136,46 @@ #include #endif +static DEFINE_RWLOCK(proto_list_lock); +static LIST_HEAD(proto_list); + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct proto *proto; + int ret = 0; + + read_lock(&proto_list_lock); + list_for_each_entry(proto, &proto_list, node) { + if (proto->init_cgroup) { + ret = proto->init_cgroup(cgrp, ss); + if (ret) + goto out; + } + } + + read_unlock(&proto_list_lock); + return ret; +out: + list_for_each_entry_continue_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(cgrp, ss); + read_unlock(&proto_list_lock); + return ret; +} + +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct proto *proto; + + read_lock(&proto_list_lock); + list_for_each_entry_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(cgrp, ss); + read_unlock(&proto_list_lock); +} +#endif + /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -2291,9 +2331,6 @@ void sk_common_release(struct sock *sk) } EXPORT_SYMBOL(sk_common_release); -static DEFINE_RWLOCK(proto_list_lock); -static LIST_HEAD(proto_list); - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index e9d98e621112..ff75d3bbcd6a 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o +obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f48bf312cfe8..42714cb1fef3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include @@ -1917,6 +1918,7 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); @@ -1974,6 +1976,7 @@ void tcp_v4_destroy_sock(struct sock *sk) } sk_sockets_allocated_dec(sk); + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2634,10 +2637,14 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .init_cgroup = tcp_init_cgroup, + .destroy_cgroup = tcp_destroy_cgroup, + .proto_cgroup = tcp_proto_cgroup, +#endif }; EXPORT_SYMBOL(tcp_prot); - static int __net_init tcp_sk_init(struct net *net) { return inet_ctl_sock_create(&net->ipv4.tcp_sock, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c new file mode 100644 index 000000000000..4a68d2c24556 --- /dev/null +++ b/net/ipv4/tcp_memcontrol.c @@ -0,0 +1,74 @@ +#include +#include +#include +#include +#include + +static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) +{ + return container_of(cg_proto, struct tcp_memcontrol, cg_proto); +} + +static void memcg_tcp_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_cgrp->memory_pressure) + *sk->sk_cgrp->memory_pressure = 1; +} +EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); + +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + /* + * The root cgroup does not use res_counters, but rather, + * rely on the data already collected by the network + * subsystem + */ + struct res_counter *res_parent = NULL; + struct cg_proto *cg_proto, *parent_cg; + struct tcp_memcontrol *tcp; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return 0; + + tcp = tcp_from_cgproto(cg_proto); + + tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0]; + tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1]; + tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2]; + tcp->tcp_memory_pressure = 0; + + parent_cg = tcp_prot.proto_cgroup(parent); + if (parent_cg) + res_parent = parent_cg->memory_allocated; + + res_counter_init(&tcp->tcp_memory_allocated, res_parent); + percpu_counter_init(&tcp->tcp_sockets_allocated, 0); + + cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure; + cg_proto->memory_pressure = &tcp->tcp_memory_pressure; + cg_proto->sysctl_mem = tcp->tcp_prot_mem; + cg_proto->memory_allocated = &tcp->tcp_memory_allocated; + cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; + cg_proto->memcg = memcg; + + return 0; +} +EXPORT_SYMBOL(tcp_init_cgroup); + +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct cg_proto *cg_proto; + struct tcp_memcontrol *tcp; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return; + + tcp = tcp_from_cgproto(cg_proto); + percpu_counter_destroy(&tcp->tcp_sockets_allocated); +} +EXPORT_SYMBOL(tcp_destroy_cgroup); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b69c7030aba9..95d3cfb65d39 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -62,6 +62,7 @@ #include #include #include +#include #include @@ -1994,6 +1995,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); @@ -2227,6 +2229,9 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .proto_cgroup = tcp_proto_cgroup, +#endif }; static const struct inet6_protocol tcpv6_protocol = { -- cgit v1.2.3 From 36b77a52087a9fca4228c06e0730750f9b6468f0 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Fri, 16 Dec 2011 00:51:59 +0000 Subject: net: fix sleeping while atomic problem in sock mem_cgroup. We can't scan the proto_list to initialize sock cgroups, as it holds a rwlock, and we also want to keep the code generic enough to avoid calling the initialization functions of protocols directly, Convert proto_list_lock into a mutex, so we can sleep and do the necessary allocations. This lock is seldom taken, so there shouldn't be any performance penalties associated with that Signed-off-by: Glauber Costa CC: Hiroyouki Kamezawa CC: David S. Miller CC: Eric Dumazet CC: Stephen Rothwell CC: Randy Dunlap Signed-off-by: David S. Miller --- net/core/sock.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'net/core/sock.c') diff --git a/net/core/sock.c b/net/core/sock.c index 5a6a90620656..0c67facf42f3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -136,7 +136,7 @@ #include #endif -static DEFINE_RWLOCK(proto_list_lock); +static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM @@ -145,7 +145,7 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) struct proto *proto; int ret = 0; - read_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_for_each_entry(proto, &proto_list, node) { if (proto->init_cgroup) { ret = proto->init_cgroup(cgrp, ss); @@ -154,13 +154,13 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) } } - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); return ret; out: list_for_each_entry_continue_reverse(proto, &proto_list, node) if (proto->destroy_cgroup) proto->destroy_cgroup(cgrp, ss); - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); return ret; } @@ -168,11 +168,11 @@ void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct proto *proto; - read_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_for_each_entry_reverse(proto, &proto_list, node) if (proto->destroy_cgroup) proto->destroy_cgroup(cgrp, ss); - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); } #endif @@ -2479,10 +2479,10 @@ int proto_register(struct proto *prot, int alloc_slab) } } - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_add(&prot->node, &proto_list); assign_proto_idx(prot); - write_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); return 0; out_free_timewait_sock_slab_name: @@ -2505,10 +2505,10 @@ EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); - write_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); if (prot->slab != NULL) { kmem_cache_destroy(prot->slab); @@ -2531,9 +2531,9 @@ EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(proto_list_lock) + __acquires(proto_list_mutex) { - read_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } @@ -2543,9 +2543,9 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void proto_seq_stop(struct seq_file *seq, void *v) - __releases(proto_list_lock) + __releases(proto_list_mutex) { - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) -- cgit v1.2.3