#ifndef _SOCK_H
#define _SOCK_H
+#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h> /* struct sk_buff */
+#include <linux/mm.h>
#include <linux/security.h>
#include <linux/filter.h>
#include <asm/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>
+#include <net/net_namespace.h>
/*
* This structure really needs to be cleaned up.
* between user contexts and software interrupt processing, whereas the
* mini-semaphore synchronizes multiple users amongst themselves.
*/
-struct sock_iocb;
typedef struct {
spinlock_t slock;
- struct sock_iocb *owner;
+ int owned;
wait_queue_head_t wq;
/*
* We express the mutex-alike socket_lock semantics
* @skc_refcnt: reference count
* @skc_hash: hash value used with various protocol lookup tables
* @skc_prot: protocol handlers inside a network family
+ * @skc_net: reference to the network namespace of this socket
*
* This is the minimal network layer representation of sockets, the header
* for struct sock and struct inet_timewait_sock.
atomic_t skc_refcnt;
unsigned int skc_hash;
struct proto *skc_prot;
+ struct net *skc_net;
};
/**
#define sk_refcnt __sk_common.skc_refcnt
#define sk_hash __sk_common.skc_hash
#define sk_prot __sk_common.skc_prot
+#define sk_net __sk_common.skc_net
unsigned char sk_shutdown : 2,
sk_no_check : 2,
sk_userlocks : 4;
unsigned short sk_type;
int sk_rcvbuf;
socket_lock_t sk_lock;
+ /*
+ * The backlog queue is special, it is always used with
+ * the per-socket spinlock held and requires low latency
+ * access. Therefore we special case it's implementation.
+ */
+ struct {
+ struct sk_buff *head;
+ struct sk_buff *tail;
+ } sk_backlog;
wait_queue_head_t *sk_sleep;
struct dst_entry *sk_dst_cache;
struct xfrm_policy *sk_policy[2];
atomic_t sk_rmem_alloc;
atomic_t sk_wmem_alloc;
atomic_t sk_omem_alloc;
+ int sk_sndbuf;
struct sk_buff_head sk_receive_queue;
struct sk_buff_head sk_write_queue;
struct sk_buff_head sk_async_wait_queue;
int sk_wmem_queued;
int sk_forward_alloc;
gfp_t sk_allocation;
- int sk_sndbuf;
int sk_route_caps;
int sk_gso_type;
int sk_rcvlowat;
unsigned long sk_flags;
unsigned long sk_lingertime;
- /*
- * The backlog queue is special, it is always used with
- * the per-socket spinlock held and requires low latency
- * access. Therefore we special case it's implementation.
- */
- struct {
- struct sk_buff *head;
- struct sk_buff *tail;
- } sk_backlog;
struct sk_buff_head sk_error_queue;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
struct sk_filter *sk_filter;
void *sk_protinfo;
struct timer_list sk_timer;
- struct timeval sk_stamp;
+ ktime_t sk_stamp;
struct socket *sk_socket;
void *sk_user_data;
struct page *sk_sndmsg_page;
SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
SOCK_DBG, /* %SO_DEBUG setting */
SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
+ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
};
skb->next = NULL;
}
-#define sk_wait_event(__sk, __timeo, __condition) \
-({ int rc; \
- release_sock(__sk); \
- rc = __condition; \
- if (!rc) { \
- *(__timeo) = schedule_timeout(*(__timeo)); \
- } \
- lock_sock(__sk); \
- rc = __condition; \
- rc; \
-})
+#define sk_wait_event(__sk, __timeo, __condition) \
+ ({ int __rc; \
+ release_sock(__sk); \
+ __rc = __condition; \
+ if (!__rc) { \
+ *(__timeo) = schedule_timeout(*(__timeo)); \
+ } \
+ lock_sock(__sk); \
+ __rc = __condition; \
+ __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);
void (*unhash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
+#ifdef CONFIG_SMP
+ /* Keeping track of sockets in use */
+ void (*inuse_add)(struct proto *prot, int inc);
+ int (*inuse_getval)(const struct proto *prot);
+ int *inuse_ptr;
+#else
+ int inuse;
+#endif
/* Memory pressure */
void (*enter_memory_pressure)(void);
atomic_t *memory_allocated; /* Current allocated memory. */
int *sysctl_rmem;
int max_header;
- kmem_cache_t *slab;
+ struct kmem_cache *slab;
unsigned int obj_size;
atomic_t *orphan_count;
#ifdef SOCK_REFCNT_DEBUG
atomic_t socks;
#endif
- struct {
- int inuse;
- u8 __pad[SMP_CACHE_BYTES - sizeof(int)];
- } stats[NR_CPUS];
};
+/*
+ * Special macros to let protos use a fast version of inuse{get|add}
+ * using a static percpu variable per proto instead of an allocated one,
+ * saving one dereference.
+ * This might be changed if/when dynamic percpu vars become fast.
+ */
+#ifdef CONFIG_SMP
+# define DEFINE_PROTO_INUSE(NAME) \
+static DEFINE_PER_CPU(int, NAME##_inuse); \
+static void NAME##_inuse_add(struct proto *prot, int inc) \
+{ \
+ __get_cpu_var(NAME##_inuse) += inc; \
+} \
+ \
+static int NAME##_inuse_getval(const struct proto *prot)\
+{ \
+ int res = 0, cpu; \
+ \
+ for_each_possible_cpu(cpu) \
+ res += per_cpu(NAME##_inuse, cpu); \
+ return res; \
+}
+# define REF_PROTO_INUSE(NAME) \
+ .inuse_add = NAME##_inuse_add, \
+ .inuse_getval = NAME##_inuse_getval,
+#else
+# define DEFINE_PROTO_INUSE(NAME)
+# define REF_PROTO_INUSE(NAME)
+#endif
+
extern int proto_register(struct proto *prot, int alloc_slab);
extern void proto_unregister(struct proto *prot);
/* Called with local bh disabled */
static __inline__ void sock_prot_inc_use(struct proto *prot)
{
- prot->stats[smp_processor_id()].inuse++;
+#ifdef CONFIG_SMP
+ prot->inuse_add(prot, 1);
+#else
+ prot->inuse++;
+#endif
}
static __inline__ void sock_prot_dec_use(struct proto *prot)
{
- prot->stats[smp_processor_id()].inuse--;
+#ifdef CONFIG_SMP
+ prot->inuse_add(prot, -1);
+#else
+ prot->inuse--;
+#endif
+}
+
+static __inline__ int sock_prot_inuse(struct proto *proto)
+{
+#ifdef CONFIG_SMP
+ return proto->inuse_getval(proto);
+#else
+ return proto->inuse;
+#endif
}
/* With per-bucket locks this operation is not-atomic, so that
struct sock *sk;
struct scm_cookie *scm;
struct msghdr *msg, async_msg;
- struct iovec async_iov;
struct kiocb *kiocb;
};
static inline int sk_stream_pages(int amt)
{
- return (amt + SK_STREAM_MEM_QUANTUM - 1) / SK_STREAM_MEM_QUANTUM;
+ return DIV_ROUND_UP(amt, SK_STREAM_MEM_QUANTUM);
}
static inline void sk_stream_mem_reclaim(struct sock *sk)
__sk_stream_mem_reclaim(sk);
}
-static inline void sk_stream_writequeue_purge(struct sock *sk)
-{
- struct sk_buff *skb;
-
- while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
- sk_stream_free_skb(sk, skb);
- sk_stream_mem_reclaim(sk);
-}
-
static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
return (int)skb->truesize <= sk->sk_forward_alloc ||
* Since ~2.3.5 it is also exclusive sleep lock serializing
* accesses from user process context.
*/
-#define sock_owned_by_user(sk) ((sk)->sk_lock.owner)
+#define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
+
+/*
+ * Macro so as to not evaluate some arguments when
+ * lockdep is not enabled.
+ *
+ * Mark both the sk_lock and the sk_lock.slock as a
+ * per-address-family lock class.
+ */
+#define sock_lock_init_class_and_name(sk, sname, skey, name, key) \
+do { \
+ sk->sk_lock.owned = 0; \
+ init_waitqueue_head(&sk->sk_lock.wq); \
+ spin_lock_init(&(sk)->sk_lock.slock); \
+ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \
+ sizeof((sk)->sk_lock)); \
+ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \
+ (skey), (sname)); \
+ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
+} while (0)
+
+extern void FASTCALL(lock_sock_nested(struct sock *sk, int subclass));
+
+static inline void lock_sock(struct sock *sk)
+{
+ lock_sock_nested(sk, 0);
+}
-extern void FASTCALL(lock_sock(struct sock *sk));
extern void FASTCALL(release_sock(struct sock *sk));
/* BH context may only use the following locking interface. */
SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
-extern struct sock *sk_alloc(int family,
+extern struct sock *sk_alloc(struct net *net, int family,
gfp_t priority,
- struct proto *prot, int zero_it);
+ struct proto *prot);
extern void sk_free(struct sock *sk);
extern struct sock *sk_clone(const struct sock *sk,
const gfp_t priority);
*
*/
-static inline int sk_filter(struct sock *sk, struct sk_buff *skb, int needlock)
+static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
{
int err;
+ struct sk_filter *filter;
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
- if (sk->sk_filter) {
- struct sk_filter *filter;
-
- if (needlock)
- bh_lock_sock(sk);
-
- filter = sk->sk_filter;
- if (filter) {
- unsigned int pkt_len = sk_run_filter(skb, filter->insns,
- filter->len);
- err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
- }
-
- if (needlock)
- bh_unlock_sock(sk);
+ rcu_read_lock_bh();
+ filter = sk->sk_filter;
+ if (filter) {
+ unsigned int pkt_len = sk_run_filter(skb, filter->insns,
+ filter->len);
+ err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
+ rcu_read_unlock_bh();
+
return err;
}
*
* Remove a filter from a socket and release its resources.
*/
-
-static inline void sk_filter_release(struct sock *sk, struct sk_filter *fp)
+
+static inline void sk_filter_release(struct sk_filter *fp)
+{
+ if (atomic_dec_and_test(&fp->refcnt))
+ kfree(fp);
+}
+
+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);
-
- if (atomic_dec_and_test(&fp->refcnt))
- kfree(fp);
+ sk_filter_release(fp);
}
static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
sk_free(sk);
}
-extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb);
+extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
+ const int nested);
/* Detach socket from process context.
* Announce socket dead, detach it from wait queue and inode.
sk->sk_sleep = &parent->wait;
parent->sk = sk;
sk->sk_socket = parent;
+ security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}
-static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
-{
- __sk_dst_set(sk, dst);
- sk->sk_route_caps = dst->dev->features;
- if (sk->sk_route_caps & NETIF_F_GSO)
- sk->sk_route_caps |= NETIF_F_GSO_MASK;
- if (sk_can_gso(sk)) {
- if (dst->header_len)
- sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
- else
- sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
- }
-}
+extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb)
{
{
if (skb->ip_summed == CHECKSUM_NONE) {
int err = 0;
- unsigned int csum = csum_and_copy_from_user(from,
+ __wsum csum = csum_and_copy_from_user(from,
page_address(page) + off,
copy, 0, &err);
if (err)
return page;
}
-#define sk_stream_for_retrans_queue(skb, sk) \
- for (skb = (sk)->sk_write_queue.next; \
- (skb != (sk)->sk_send_head) && \
- (skb != (struct sk_buff *)&(sk)->sk_write_queue); \
- skb = skb->next)
-
-/*from STCP for fast SACK Process*/
-#define sk_stream_for_retrans_queue_from(skb, sk) \
- for (; (skb != (sk)->sk_send_head) && \
- (skb != (struct sk_buff *)&(sk)->sk_write_queue); \
- skb = skb->next)
-
/*
* Default write policy as shown to user space via poll/select/SIGIO
*/
static inline gfp_t gfp_any(void)
{
- return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
+ return in_atomic() ? GFP_ATOMIC : GFP_KERNEL;
}
static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}
+extern void __sock_recv_timestamp(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)
{
- struct timeval stamp;
+ ktime_t kt = skb->tstamp;
- skb_get_timestamp(skb, &stamp);
- if (sock_flag(sk, SOCK_RCVTSTAMP)) {
- /* Race occurred between timestamp enabling and packet
- receiving. Fill in the current time for now. */
- if (stamp.tv_sec == 0)
- do_gettimeofday(&stamp);
- skb_set_timestamp(skb, &stamp);
- put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval),
- &stamp);
- } else
- sk->sk_stamp = stamp;
+ if (sock_flag(sk, SOCK_RCVTSTAMP))
+ __sock_recv_timestamp(msg, sk, skb);
+ else
+ sk->sk_stamp = kt;
}
/**
extern void sock_enable_timestamp(struct sock *sk);
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
+extern int sock_get_timestampns(struct sock *, struct timespec __user *);
/*
* Enable debug/info messages
*/
+extern int net_msg_warn;
+#define NETDEBUG(fmt, args...) \
+ do { if (net_msg_warn) printk(fmt,##args); } while (0)
-#ifdef CONFIG_NETDEBUG
-#define NETDEBUG(fmt, args...) printk(fmt,##args)
-#define LIMIT_NETDEBUG(fmt, args...) do { if (net_ratelimit()) printk(fmt,##args); } while(0)
-#else
-#define NETDEBUG(fmt, args...) do { } while (0)
-#define LIMIT_NETDEBUG(fmt, args...) do { } while(0)
-#endif
+#define LIMIT_NETDEBUG(fmt, args...) \
+ do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)
/*
* Macros for sleeping on a socket. Use them like this:
extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;
-#ifdef CONFIG_NET
-int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
-#else
-static inline int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
- return -ENODEV;
-}
-#endif
-
extern void sk_init(void);
#ifdef CONFIG_SYSCTL
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff