diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 281 |
1 files changed, 273 insertions, 8 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index abb6e0f0c3c3..bb972d254dff 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -53,6 +53,8 @@ #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/memcontrol.h> +#include <linux/res_counter.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> @@ -62,6 +64,22 @@ #include <net/dst.h> #include <net/checksum.h> +struct cgroup; +struct cgroup_subsys; +#ifdef CONFIG_NET +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss); +#else +static inline +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + return 0; +} +static inline +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ +} +#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -167,6 +185,7 @@ struct sock_common { /* public: */ }; +struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -227,6 +246,7 @@ 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 @@ -306,8 +326,8 @@ struct sock { kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; - int sk_route_caps; - int sk_route_nocaps; + netdev_features_t sk_route_caps; + netdev_features_t sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; @@ -320,6 +340,9 @@ 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; @@ -338,6 +361,7 @@ 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); @@ -563,6 +587,7 @@ 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) @@ -637,12 +662,14 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) /* * Take into account size of receive queue and backlog queue + * Do not take into account this skb truesize, + * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); - return qsize + skb->truesize > sk->sk_rcvbuf; + return qsize > sk->sk_rcvbuf; } /* The per-socket spinlock must be held here. */ @@ -833,6 +860,37 @@ 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); @@ -851,7 +909,7 @@ 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", @@ -863,6 +921,208 @@ 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; +} + +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; +} + +static inline void sk_leave_memory_pressure(struct sock *sk) +{ + int *memory_pressure = sk->sk_prot->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) + 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, 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, 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); +} + +static inline int +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); +} + +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 */ @@ -1089,8 +1349,8 @@ extern struct sock *sk_alloc(struct net *net, int family, struct proto *prot); extern void sk_free(struct sock *sk); extern void sk_release_kernel(struct sock *sk); -extern struct sock *sk_clone(const struct sock *sk, - const gfp_t priority); +extern struct sock *sk_clone_lock(const struct sock *sk, + const gfp_t priority); extern struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, @@ -1393,7 +1653,7 @@ static inline int sk_can_gso(const struct sock *sk) extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst); -static inline void sk_nocaps_add(struct sock *sk, int flags) +static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) { sk->sk_route_nocaps |= flags; sk->sk_route_caps &= ~flags; @@ -1670,7 +1930,7 @@ 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; @@ -1714,6 +1974,8 @@ 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 +2003,9 @@ 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, |