aboutsummaryrefslogtreecommitdiff
path: root/include/net/sock.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/net/sock.h')
-rw-r--r--include/net/sock.h492
1 files changed, 273 insertions, 219 deletions
diff --git a/include/net/sock.h b/include/net/sock.h
index c945fba4f54..15635074570 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -126,15 +126,21 @@ struct sock;
struct proto;
struct net;
+typedef __u32 __bitwise __portpair;
+typedef __u64 __bitwise __addrpair;
+
/**
* struct sock_common - minimal network layer representation of sockets
* @skc_daddr: Foreign IPv4 addr
* @skc_rcv_saddr: Bound local IPv4 addr
* @skc_hash: hash value used with various protocol lookup tables
* @skc_u16hashes: two u16 hash values used by UDP lookup tables
+ * @skc_dport: placeholder for inet_dport/tw_dport
+ * @skc_num: placeholder for inet_num/tw_num
* @skc_family: network address family
* @skc_state: Connection state
* @skc_reuse: %SO_REUSEADDR setting
+ * @skc_reuseport: %SO_REUSEPORT setting
* @skc_bound_dev_if: bound device index if != 0
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
@@ -149,19 +155,33 @@ struct net;
* for struct sock and struct inet_timewait_sock.
*/
struct sock_common {
- /* skc_daddr and skc_rcv_saddr must be grouped :
- * cf INET_MATCH() and INET_TW_MATCH()
+ /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
+ * address on 64bit arches : cf INET_MATCH()
*/
- __be32 skc_daddr;
- __be32 skc_rcv_saddr;
-
+ union {
+ __addrpair skc_addrpair;
+ struct {
+ __be32 skc_daddr;
+ __be32 skc_rcv_saddr;
+ };
+ };
union {
unsigned int skc_hash;
__u16 skc_u16hashes[2];
};
+ /* skc_dport && skc_num must be grouped as well */
+ union {
+ __portpair skc_portpair;
+ struct {
+ __be16 skc_dport;
+ __u16 skc_num;
+ };
+ };
+
unsigned short skc_family;
volatile unsigned char skc_state;
- unsigned char skc_reuse;
+ unsigned char skc_reuse:4;
+ unsigned char skc_reuseport:4;
int skc_bound_dev_if;
union {
struct hlist_node skc_bind_node;
@@ -171,6 +191,12 @@ struct sock_common {
#ifdef CONFIG_NET_NS
struct net *skc_net;
#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr skc_v6_daddr;
+ struct in6_addr skc_v6_rcv_saddr;
+#endif
+
/*
* fields between dontcopy_begin/dontcopy_end
* are not copied in sock_copy()
@@ -198,7 +224,7 @@ struct cg_proto;
* @sk_lock: synchronizer
* @sk_rcvbuf: size of receive buffer in bytes
* @sk_wq: sock wait queue and async head
- * @sk_rx_dst: receive input route used by early tcp demux
+ * @sk_rx_dst: receive input route used by early demux
* @sk_dst_cache: destination cache
* @sk_dst_lock: destination cache lock
* @sk_policy: flow policy
@@ -209,11 +235,16 @@ struct cg_proto;
* @sk_omem_alloc: "o" is "option" or "other"
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
+ * @sk_napi_id: id of the last napi context to receive data for sk
+ * @sk_ll_usec: usecs to busypoll when there is no data
* @sk_allocation: allocation mode
+ * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
+ * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
* @sk_sndbuf: size of send buffer in bytes
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
- * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
+ * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
+ * @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
@@ -276,13 +307,23 @@ struct sock {
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
#define sk_hash __sk_common.skc_hash
+#define sk_portpair __sk_common.skc_portpair
+#define sk_num __sk_common.skc_num
+#define sk_dport __sk_common.skc_dport
+#define sk_addrpair __sk_common.skc_addrpair
+#define sk_daddr __sk_common.skc_daddr
+#define sk_rcv_saddr __sk_common.skc_rcv_saddr
#define sk_family __sk_common.skc_family
#define sk_state __sk_common.skc_state
#define sk_reuse __sk_common.skc_reuse
+#define sk_reuseport __sk_common.skc_reuseport
#define sk_bound_dev_if __sk_common.skc_bound_dev_if
#define sk_bind_node __sk_common.skc_bind_node
#define sk_prot __sk_common.skc_prot
#define sk_net __sk_common.skc_net
+#define sk_v6_daddr __sk_common.skc_v6_daddr
+#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr
+
socket_lock_t sk_lock;
struct sk_buff_head sk_receive_queue;
/*
@@ -304,6 +345,10 @@ struct sock {
#ifdef CONFIG_RPS
__u32 sk_rxhash;
#endif
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ unsigned int sk_napi_id;
+ unsigned int sk_ll_usec;
+#endif
atomic_t sk_drops;
int sk_rcvbuf;
@@ -319,7 +364,7 @@ struct sock {
#endif
unsigned long sk_flags;
struct dst_entry *sk_rx_dst;
- struct dst_entry *sk_dst_cache;
+ struct dst_entry __rcu *sk_dst_cache;
spinlock_t sk_dst_lock;
atomic_t sk_wmem_alloc;
atomic_t sk_omem_alloc;
@@ -327,13 +372,16 @@ struct sock {
struct sk_buff_head sk_write_queue;
kmemcheck_bitfield_begin(flags);
unsigned int sk_shutdown : 2,
- sk_no_check : 2,
+ sk_no_check_tx : 1,
+ sk_no_check_rx : 1,
sk_userlocks : 4,
sk_protocol : 8,
sk_type : 16;
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
+ u32 sk_pacing_rate; /* bytes per second */
+ u32 sk_max_pacing_rate;
netdev_features_t sk_route_caps;
netdev_features_t sk_route_nocaps;
int sk_gso_type;
@@ -349,7 +397,7 @@ struct sock {
unsigned short sk_ack_backlog;
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
-#ifdef CONFIG_CGROUPS
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
__u32 sk_cgrp_prioidx;
#endif
struct pid *sk_peer_pid;
@@ -372,7 +420,7 @@ struct sock {
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_data_ready)(struct sock *sk);
void (*sk_write_space)(struct sock *sk);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk,
@@ -380,6 +428,11 @@ struct sock {
void (*sk_destruct)(struct sock *sk);
};
+#define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
+
+#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk)))
+#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr)
+
/*
* SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
* or not whether his port will be reused by someone else. SK_FORCE_REUSE
@@ -585,24 +638,23 @@ static inline void sk_add_bind_node(struct sock *sk,
hlist_add_head(&sk->sk_bind_node, list);
}
-#define sk_for_each(__sk, node, list) \
- hlist_for_each_entry(__sk, node, list, sk_node)
-#define sk_for_each_rcu(__sk, node, list) \
- hlist_for_each_entry_rcu(__sk, node, list, sk_node)
+#define sk_for_each(__sk, list) \
+ hlist_for_each_entry(__sk, list, sk_node)
+#define sk_for_each_rcu(__sk, list) \
+ hlist_for_each_entry_rcu(__sk, list, sk_node)
#define sk_nulls_for_each(__sk, node, list) \
hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
#define sk_nulls_for_each_rcu(__sk, node, list) \
hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
-#define sk_for_each_from(__sk, node) \
- if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
- hlist_for_each_entry_from(__sk, node, sk_node)
+#define sk_for_each_from(__sk) \
+ hlist_for_each_entry_from(__sk, sk_node)
#define sk_nulls_for_each_from(__sk, node) \
if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
-#define sk_for_each_safe(__sk, node, tmp, list) \
- hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
-#define sk_for_each_bound(__sk, node, list) \
- hlist_for_each_entry(__sk, node, list, sk_bind_node)
+#define sk_for_each_safe(__sk, tmp, list) \
+ hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
+#define sk_for_each_bound(__sk, list) \
+ hlist_for_each_entry(__sk, list, sk_bind_node)
static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
@@ -646,6 +698,8 @@ enum sock_flags {
* Will use last 4 bytes of packet sent from
* user-space instead.
*/
+ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
+ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
};
static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
@@ -716,12 +770,7 @@ static inline int sk_stream_wspace(const struct sock *sk)
return sk->sk_sndbuf - sk->sk_wmem_queued;
}
-extern void sk_stream_write_space(struct sock *sk);
-
-static inline bool sk_stream_memory_free(const struct sock *sk)
-{
- return sk->sk_wmem_queued < sk->sk_sndbuf;
-}
+void sk_stream_write_space(struct sock *sk);
/* OOB backlog add */
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
@@ -763,7 +812,7 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
return 0;
}
-extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
@@ -773,37 +822,51 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
return sk->sk_backlog_rcv(sk, skb);
}
-static inline void sock_rps_record_flow(const struct sock *sk)
+static inline void sock_rps_record_flow_hash(__u32 hash)
{
#ifdef CONFIG_RPS
struct rps_sock_flow_table *sock_flow_table;
rcu_read_lock();
sock_flow_table = rcu_dereference(rps_sock_flow_table);
- rps_record_sock_flow(sock_flow_table, sk->sk_rxhash);
+ rps_record_sock_flow(sock_flow_table, hash);
rcu_read_unlock();
#endif
}
-static inline void sock_rps_reset_flow(const struct sock *sk)
+static inline void sock_rps_reset_flow_hash(__u32 hash)
{
#ifdef CONFIG_RPS
struct rps_sock_flow_table *sock_flow_table;
rcu_read_lock();
sock_flow_table = rcu_dereference(rps_sock_flow_table);
- rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash);
+ rps_reset_sock_flow(sock_flow_table, hash);
rcu_read_unlock();
#endif
}
+static inline void sock_rps_record_flow(const struct sock *sk)
+{
+#ifdef CONFIG_RPS
+ sock_rps_record_flow_hash(sk->sk_rxhash);
+#endif
+}
+
+static inline void sock_rps_reset_flow(const struct sock *sk)
+{
+#ifdef CONFIG_RPS
+ sock_rps_reset_flow_hash(sk->sk_rxhash);
+#endif
+}
+
static inline void sock_rps_save_rxhash(struct sock *sk,
const struct sk_buff *skb)
{
#ifdef CONFIG_RPS
- if (unlikely(sk->sk_rxhash != skb->rxhash)) {
+ if (unlikely(sk->sk_rxhash != skb->hash)) {
sock_rps_reset_flow(sk);
- sk->sk_rxhash = skb->rxhash;
+ sk->sk_rxhash = skb->hash;
}
#endif
}
@@ -828,15 +891,15 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
__rc; \
})
-extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
-extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
-extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
-extern int sk_stream_error(struct sock *sk, int flags, int err);
-extern void sk_stream_kill_queues(struct sock *sk);
-extern void sk_set_memalloc(struct sock *sk);
-extern void sk_clear_memalloc(struct sock *sk);
+int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
+int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
+void sk_stream_wait_close(struct sock *sk, long timeo_p);
+int sk_stream_error(struct sock *sk, int flags, int err);
+void sk_stream_kill_queues(struct sock *sk);
+void sk_set_memalloc(struct sock *sk);
+void sk_clear_memalloc(struct sock *sk);
-extern int sk_wait_data(struct sock *sk, long *timeo);
+int sk_wait_data(struct sock *sk, long *timeo);
struct request_sock_ops;
struct timewait_sock_ops;
@@ -844,6 +907,18 @@ struct inet_hashinfo;
struct raw_hashinfo;
struct module;
+/*
+ * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
+ * un-modified. Special care is taken when initializing object to zero.
+ */
+static inline void sk_prot_clear_nulls(struct sock *sk, int size)
+{
+ if (offsetof(struct sock, sk_node.next) != 0)
+ memset(sk, 0, offsetof(struct sock, sk_node.next));
+ memset(&sk->sk_node.pprev, 0,
+ size - offsetof(struct sock, sk_node.pprev));
+}
+
/* Networking protocol blocks we attach to sockets.
* socket layer -> transport layer interface
* transport -> network interface is defined by struct inet_proto
@@ -910,6 +985,7 @@ struct proto {
unsigned int inuse_idx;
#endif
+ bool (*stream_memory_free)(const struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
atomic_long_t *memory_allocated; /* Current allocated memory. */
@@ -975,11 +1051,10 @@ enum cg_proto_flags {
};
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;
+ struct res_counter memory_allocated; /* Current allocated memory. */
+ struct percpu_counter sockets_allocated; /* Current number of sockets. */
+ int memory_pressure;
+ long sysctl_mem[3];
unsigned long flags;
/*
* memcg field is used to find which memcg we belong directly
@@ -993,8 +1068,8 @@ struct cg_proto {
struct mem_cgroup *memcg;
};
-extern int proto_register(struct proto *prot, int alloc_slab);
-extern void proto_unregister(struct proto *prot);
+int proto_register(struct proto *prot, int alloc_slab);
+void proto_unregister(struct proto *prot);
static inline bool memcg_proto_active(struct cg_proto *cg_proto)
{
@@ -1019,7 +1094,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk)
sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}
-inline void sk_refcnt_debug_release(const struct sock *sk)
+static 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",
@@ -1048,6 +1123,21 @@ static inline struct cg_proto *parent_cg_proto(struct proto *proto,
}
#endif
+static inline bool sk_stream_memory_free(const struct sock *sk)
+{
+ if (sk->sk_wmem_queued >= sk->sk_sndbuf)
+ return false;
+
+ return sk->sk_prot->stream_memory_free ?
+ sk->sk_prot->stream_memory_free(sk) : true;
+}
+
+static inline bool sk_stream_is_writeable(const struct sock *sk)
+{
+ return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
+ sk_stream_memory_free(sk);
+}
+
static inline bool sk_has_memory_pressure(const struct sock *sk)
{
@@ -1060,7 +1150,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
return false;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
- return !!*sk->sk_cgrp->memory_pressure;
+ return !!sk->sk_cgrp->memory_pressure;
return !!*sk->sk_prot->memory_pressure;
}
@@ -1080,8 +1170,7 @@ static inline void sk_leave_memory_pressure(struct sock *sk)
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;
+ cg_proto->memory_pressure = 0;
}
}
@@ -1096,7 +1185,7 @@ static inline void sk_enter_memory_pressure(struct sock *sk)
struct proto *prot = sk->sk_prot;
for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
- cg_proto->enter_memory_pressure(sk);
+ cg_proto->memory_pressure = 1;
}
sk->sk_prot->enter_memory_pressure(sk);
@@ -1117,7 +1206,7 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
struct res_counter *fail;
int ret;
- ret = res_counter_charge_nofail(prot->memory_allocated,
+ ret = res_counter_charge_nofail(&prot->memory_allocated,
amt << PAGE_SHIFT, &fail);
if (ret < 0)
*parent_status = OVER_LIMIT;
@@ -1126,13 +1215,13 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
unsigned long amt)
{
- res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+ 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);
+ ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
return ret >> PAGE_SHIFT;
}
@@ -1180,7 +1269,7 @@ static inline void sk_sockets_allocated_dec(struct sock *sk)
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(&cg_proto->sockets_allocated);
}
percpu_counter_dec(prot->sockets_allocated);
@@ -1194,7 +1283,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk)
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(&cg_proto->sockets_allocated);
}
percpu_counter_inc(prot->sockets_allocated);
@@ -1206,7 +1295,7 @@ 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_read_positive(sk->sk_cgrp->sockets_allocated);
+ return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated);
return percpu_counter_read_positive(prot->sockets_allocated);
}
@@ -1234,8 +1323,8 @@ proto_memory_pressure(struct proto *prot)
#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
-extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
-extern int sock_prot_inuse_get(struct net *net, struct proto *proto);
+void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
+int sock_prot_inuse_get(struct net *net, struct proto *proto);
#else
static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
int inc)
@@ -1311,8 +1400,8 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
/*
* Functions for memory accounting
*/
-extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
-extern void __sk_mem_reclaim(struct sock *sk);
+int __sk_mem_schedule(struct sock *sk, int size, int kind);
+void __sk_mem_reclaim(struct sock *sk);
#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
@@ -1401,6 +1490,11 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
*/
#define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
+static inline void sock_release_ownership(struct sock *sk)
+{
+ sk->sk_lock.owned = 0;
+}
+
/*
* Macro so as to not evaluate some arguments when
* lockdep is not enabled.
@@ -1420,14 +1514,14 @@ do { \
lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
} while (0)
-extern void lock_sock_nested(struct sock *sk, int subclass);
+void lock_sock_nested(struct sock *sk, int subclass);
static inline void lock_sock(struct sock *sk)
{
lock_sock_nested(sk, 0);
}
-extern void release_sock(struct sock *sk);
+void release_sock(struct sock *sk);
/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock))
@@ -1436,7 +1530,7 @@ extern void release_sock(struct sock *sk);
SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
-extern bool lock_sock_fast(struct sock *sk);
+bool lock_sock_fast(struct sock *sk);
/**
* unlock_sock_fast - complement of lock_sock_fast
* @sk: socket
@@ -1454,133 +1548,80 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
}
-extern struct sock *sk_alloc(struct net *net, int family,
- gfp_t priority,
- struct proto *prot);
-extern void sk_free(struct sock *sk);
-extern void sk_release_kernel(struct sock *sk);
-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,
- gfp_t priority);
-extern struct sk_buff *sock_rmalloc(struct sock *sk,
- unsigned long size, int force,
- gfp_t priority);
-extern void sock_wfree(struct sk_buff *skb);
-extern void sock_rfree(struct sk_buff *skb);
-extern void sock_edemux(struct sk_buff *skb);
-
-extern int sock_setsockopt(struct socket *sock, int level,
- int op, char __user *optval,
- unsigned int optlen);
-
-extern int sock_getsockopt(struct socket *sock, int level,
- int op, char __user *optval,
- int __user *optlen);
-extern struct sk_buff *sock_alloc_send_skb(struct sock *sk,
- unsigned long size,
- int noblock,
- int *errcode);
-extern struct sk_buff *sock_alloc_send_pskb(struct sock *sk,
- unsigned long header_len,
- unsigned long data_len,
- int noblock,
- int *errcode);
-extern void *sock_kmalloc(struct sock *sk, int size,
- gfp_t priority);
-extern void sock_kfree_s(struct sock *sk, void *mem, int size);
-extern void sk_send_sigurg(struct sock *sk);
+struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
+ struct proto *prot);
+void sk_free(struct sock *sk);
+void sk_release_kernel(struct sock *sk);
+struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
+
+struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
+ gfp_t priority);
+void sock_wfree(struct sk_buff *skb);
+void skb_orphan_partial(struct sk_buff *skb);
+void sock_rfree(struct sk_buff *skb);
+void sock_edemux(struct sk_buff *skb);
+
+int sock_setsockopt(struct socket *sock, int level, int op,
+ char __user *optval, unsigned int optlen);
+
+int sock_getsockopt(struct socket *sock, int level, int op,
+ char __user *optval, int __user *optlen);
+struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
+ int noblock, int *errcode);
+struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
+ unsigned long data_len, int noblock,
+ int *errcode, int max_page_order);
+void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
+void sock_kfree_s(struct sock *sk, void *mem, int size);
+void sk_send_sigurg(struct sock *sk);
/*
* Functions to fill in entries in struct proto_ops when a protocol
* does not implement a particular function.
*/
-extern int sock_no_bind(struct socket *,
- struct sockaddr *, int);
-extern int sock_no_connect(struct socket *,
- struct sockaddr *, int, int);
-extern int sock_no_socketpair(struct socket *,
- struct socket *);
-extern int sock_no_accept(struct socket *,
- struct socket *, int);
-extern int sock_no_getname(struct socket *,
- struct sockaddr *, int *, int);
-extern unsigned int sock_no_poll(struct file *, struct socket *,
- struct poll_table_struct *);
-extern int sock_no_ioctl(struct socket *, unsigned int,
- unsigned long);
-extern int sock_no_listen(struct socket *, int);
-extern int sock_no_shutdown(struct socket *, int);
-extern int sock_no_getsockopt(struct socket *, int , int,
- char __user *, int __user *);
-extern int sock_no_setsockopt(struct socket *, int, int,
- char __user *, unsigned int);
-extern int sock_no_sendmsg(struct kiocb *, struct socket *,
- struct msghdr *, size_t);
-extern int sock_no_recvmsg(struct kiocb *, struct socket *,
- struct msghdr *, size_t, int);
-extern int sock_no_mmap(struct file *file,
- struct socket *sock,
- struct vm_area_struct *vma);
-extern ssize_t sock_no_sendpage(struct socket *sock,
- struct page *page,
- int offset, size_t size,
- int flags);
+int sock_no_bind(struct socket *, struct sockaddr *, int);
+int sock_no_connect(struct socket *, struct sockaddr *, int, int);
+int sock_no_socketpair(struct socket *, struct socket *);
+int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
+unsigned int sock_no_poll(struct file *, struct socket *,
+ struct poll_table_struct *);
+int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
+int sock_no_listen(struct socket *, int);
+int sock_no_shutdown(struct socket *, int);
+int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
+int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
+int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t);
+int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
+ int);
+int sock_no_mmap(struct file *file, struct socket *sock,
+ struct vm_area_struct *vma);
+ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
+ size_t size, int flags);
/*
* Functions to fill in entries in struct proto_ops when a protocol
* uses the inet style.
*/
-extern int sock_common_getsockopt(struct socket *sock, int level, int optname,
+int sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen);
-extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
+int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags);
-extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
+int sock_common_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen);
-extern int compat_sock_common_getsockopt(struct socket *sock, int level,
+int compat_sock_common_getsockopt(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
-extern int compat_sock_common_setsockopt(struct socket *sock, int level,
+int compat_sock_common_setsockopt(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
-extern void sk_common_release(struct sock *sk);
+void sk_common_release(struct sock *sk);
/*
* Default socket callbacks and setup code
*/
/* Initialise core socket variables */
-extern void sock_init_data(struct socket *sock, struct sock *sk);
-
-extern void sk_filter_release_rcu(struct rcu_head *rcu);
-
-/**
- * sk_filter_release - release a socket filter
- * @fp: filter to remove
- *
- * Remove a filter from a socket and release its resources.
- */
-
-static inline void sk_filter_release(struct sk_filter *fp)
-{
- if (atomic_dec_and_test(&fp->refcnt))
- call_rcu(&fp->rcu, sk_filter_release_rcu);
-}
-
-static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
-{
- unsigned int size = sk_filter_len(fp);
-
- atomic_sub(size, &sk->sk_omem_alloc);
- sk_filter_release(fp);
-}
-
-static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
- atomic_inc(&fp->refcnt);
- atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
-}
+void sock_init_data(struct socket *sock, struct sock *sk);
/*
* Socket reference counting postulates.
@@ -1613,9 +1654,12 @@ static inline void sock_put(struct sock *sk)
if (atomic_dec_and_test(&sk->sk_refcnt))
sk_free(sk);
}
+/* Generic version of sock_put(), dealing with all sockets
+ * (TCP_TIMEWAIT, ESTABLISHED...)
+ */
+void sock_gen_put(struct sock *sk);
-extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
- const int nested);
+int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
{
@@ -1669,8 +1713,8 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
write_unlock_bh(&sk->sk_callback_lock);
}
-extern kuid_t sock_i_uid(struct sock *sk);
-extern unsigned long sock_i_ino(struct sock *sk);
+kuid_t sock_i_uid(struct sock *sk);
+unsigned long sock_i_ino(struct sock *sk);
static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
@@ -1686,14 +1730,12 @@ sk_dst_get(struct sock *sk)
rcu_read_lock();
dst = rcu_dereference(sk->sk_dst_cache);
- if (dst)
- dst_hold(dst);
+ if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+ dst = NULL;
rcu_read_unlock();
return dst;
}
-extern void sk_reset_txq(struct sock *sk);
-
static inline void dst_negative_advice(struct sock *sk)
{
struct dst_entry *ndst, *dst = __sk_dst_get(sk);
@@ -1703,7 +1745,7 @@ static inline void dst_negative_advice(struct sock *sk)
if (ndst != dst) {
rcu_assign_pointer(sk->sk_dst_cache, ndst);
- sk_reset_txq(sk);
+ sk_tx_queue_clear(sk);
}
}
}
@@ -1726,9 +1768,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_set(sk, dst);
- spin_unlock(&sk->sk_dst_lock);
+ struct dst_entry *old_dst;
+
+ sk_tx_queue_clear(sk);
+ old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+ dst_release(old_dst);
}
static inline void
@@ -1740,21 +1784,19 @@ __sk_dst_reset(struct sock *sk)
static inline void
sk_dst_reset(struct sock *sk)
{
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_reset(sk);
- spin_unlock(&sk->sk_dst_lock);
+ sk_dst_set(sk, NULL);
}
-extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
+struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
-extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
+struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
static inline bool sk_can_gso(const struct sock *sk)
{
return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}
-extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
+void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
{
@@ -1967,14 +2009,14 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
sk_mem_charge(sk, skb->truesize);
}
-extern void sk_reset_timer(struct sock *sk, struct timer_list *timer,
- unsigned long expires);
+void sk_reset_timer(struct sock *sk, struct timer_list *timer,
+ unsigned long expires);
-extern void sk_stop_timer(struct sock *sk, struct timer_list *timer);
+void sk_stop_timer(struct sock *sk, struct timer_list *timer);
-extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-extern int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
+int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
/*
* Recover an error report and clear atomically
@@ -2007,18 +2049,21 @@ static inline void sk_wake_async(struct sock *sk, int how, int band)
sock_wake_async(sk->sk_socket, how, band);
}
-#define SOCK_MIN_SNDBUF 2048
-/*
- * Since sk_rmem_alloc sums skb->truesize, even a small frame might need
- * sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak
+/* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
+ * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak.
+ * Note: for send buffers, TCP works better if we can build two skbs at
+ * minimum.
*/
-#define SOCK_MIN_RCVBUF (2048 + sizeof(struct sk_buff))
+#define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff)))
+
+#define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2)
+#define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE
static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
- sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
+ sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF);
}
}
@@ -2039,7 +2084,7 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
return &sk->sk_frag;
}
-extern bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
+bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
/*
* Default write policy as shown to user space via poll/select/SIGIO
@@ -2077,10 +2122,10 @@ static inline int sock_intr_errno(long timeo)
return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}
-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);
+void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb);
+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)
@@ -2113,15 +2158,14 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
__sock_recv_wifi_status(msg, sk, skb);
}
-extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb);
+void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb);
static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
(1UL << SOCK_RCVTSTAMP) | \
- (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
(1UL << SOCK_TIMESTAMPING_SOFTWARE) | \
(1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \
(1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
@@ -2137,10 +2181,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
* @sk: socket sending this packet
* @tx_flags: filled with instructions for time stamping
*
- * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if
- * parameters are invalid.
+ * Currently only depends on SOCK_TIMESTAMPING* flags.
*/
-extern int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
+void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
/**
* sk_eat_skb - Release a skb if it is no longer needed
@@ -2188,8 +2231,12 @@ void sock_net_set(struct sock *sk, struct net *net)
*/
static inline void sk_change_net(struct sock *sk, struct net *net)
{
- put_net(sock_net(sk));
- sock_net_set(sk, hold_net(net));
+ struct net *current_net = sock_net(sk);
+
+ if (!net_eq(current_net, net)) {
+ put_net(current_net);
+ sock_net_set(sk, hold_net(net));
+ }
}
static inline struct sock *skb_steal_sock(struct sk_buff *skb)
@@ -2204,9 +2251,16 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb)
return NULL;
}
-extern void sock_enable_timestamp(struct sock *sk, int flag);
-extern int sock_get_timestamp(struct sock *, struct timeval __user *);
-extern int sock_get_timestampns(struct sock *, struct timespec __user *);
+void sock_enable_timestamp(struct sock *sk, int flag);
+int sock_get_timestamp(struct sock *, struct timeval __user *);
+int sock_get_timestampns(struct sock *, struct timespec __user *);
+int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
+ int type);
+
+bool sk_ns_capable(const struct sock *sk,
+ struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
/*
* Enable debug/info messages
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 19:14:22 +0000