#ifndef _SOCK_H
#define _SOCK_H
-#include <linux/config.h>
+#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/module.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
+ * to the lock validator by explicitly managing
+ * the slock as a lock variant (in addition to
+ * the slock itself):
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
} socket_lock_t;
-#define sock_lock_init(__sk) \
-do { spin_lock_init(&((__sk)->sk_lock.slock)); \
- (__sk)->sk_lock.owner = NULL; \
- init_waitqueue_head(&((__sk)->sk_lock.wq)); \
-} while(0)
-
struct sock;
+struct proto;
/**
* struct sock_common - minimal network layer representation of sockets
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @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 tcp_tw_bucket.
- */
+ * for struct sock and struct inet_timewait_sock.
+ */
struct sock_common {
unsigned short skc_family;
volatile unsigned char skc_state;
struct hlist_node skc_node;
struct hlist_node skc_bind_node;
atomic_t skc_refcnt;
+ unsigned int skc_hash;
+ struct proto *skc_prot;
+ struct net *skc_net;
};
/**
* struct sock - network layer representation of sockets
- * @__sk_common: shared layout with tcp_tw_bucket
+ * @__sk_common: shared layout with inet_timewait_sock
* @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
* @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
* @sk_lock: synchronizer
* @sk_receive_queue: incoming packets
* @sk_wmem_alloc: transmit queue bytes committed
* @sk_write_queue: Packet sending queue
+ * @sk_async_wait_queue: DMA copied packets
* @sk_omem_alloc: "o" is "option" or "other"
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, %SO_OOBINLINE settings
* @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
+ * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_lingertime: %SO_LINGER l_linger setting
- * @sk_hashent: hash entry in several tables (e.g. tcp_ehash)
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
* @sk_error_queue: rarely used
- * @sk_prot: protocol handlers inside a network family
* @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance)
* @sk_err: last error
* @sk_err_soft: errors that don't cause failure but are the cause of a persistent failure not just 'timed out'
*/
struct sock {
/*
- * Now struct tcp_tw_bucket also uses sock_common, so please just
+ * Now struct inet_timewait_sock also uses sock_common, so please just
* don't add nothing before this first member (__sk_common) --acme
*/
struct sock_common __sk_common;
#define sk_node __sk_common.skc_node
#define sk_bind_node __sk_common.skc_bind_node
#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;
- unsigned int sk_allocation;
- int sk_sndbuf;
+ gfp_t sk_allocation;
int sk_route_caps;
- int sk_hashent;
+ 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;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
int sk_err,
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
struct ucred sk_peercred;
- int sk_rcvlowat;
long sk_rcvtimeo;
long sk_sndtimeo;
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;
/*
* Hashed lists helper routines
*/
-static inline struct sock *__sk_head(struct hlist_head *head)
+static inline struct sock *__sk_head(const struct hlist_head *head)
{
return hlist_entry(head->first, struct sock, sk_node);
}
-static inline struct sock *sk_head(struct hlist_head *head)
+static inline struct sock *sk_head(const struct hlist_head *head)
{
return hlist_empty(head) ? NULL : __sk_head(head);
}
-static inline struct sock *sk_next(struct sock *sk)
+static inline struct sock *sk_next(const struct sock *sk)
{
return sk->sk_node.next ?
hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}
-static inline int sk_unhashed(struct sock *sk)
+static inline int sk_unhashed(const struct sock *sk)
{
return hlist_unhashed(&sk->sk_node);
}
-static inline int sk_hashed(struct sock *sk)
+static inline int sk_hashed(const struct sock *sk)
{
- return sk->sk_node.pprev != NULL;
+ return !sk_unhashed(sk);
}
static __inline__ void sk_node_init(struct hlist_node *node)
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_NO_LARGESEND, /* whether to sent large segments or not */
+ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
};
static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb)
{
+ skb_truesize_check(skb);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
sk->sk_wmem_queued -= skb->truesize;
sk->sk_forward_alloc += skb->truesize;
}
/* The per-socket spinlock must be held here. */
-#define sk_add_backlog(__sk, __skb) \
-do { if (!(__sk)->sk_backlog.tail) { \
- (__sk)->sk_backlog.head = \
- (__sk)->sk_backlog.tail = (__skb); \
- } else { \
- ((__sk)->sk_backlog.tail)->next = (__skb); \
- (__sk)->sk_backlog.tail = (__skb); \
- } \
- (__skb)->next = NULL; \
-} while(0)
-
-#define sk_wait_event(__sk, __timeo, __condition) \
-({ int rc; \
- release_sock(__sk); \
- rc = __condition; \
- if (!rc) { \
- *(__timeo) = schedule_timeout(*(__timeo)); \
- rc = __condition; \
- } \
- lock_sock(__sk); \
- rc; \
-})
+static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
+{
+ if (!sk->sk_backlog.tail) {
+ sk->sk_backlog.head = sk->sk_backlog.tail = skb;
+ } else {
+ sk->sk_backlog.tail->next = skb;
+ sk->sk_backlog.tail = skb;
+ }
+ 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; \
+ })
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 int sk_wait_data(struct sock *sk, long *timeo);
struct request_sock_ops;
-
-/* Here is the right place to enable sock refcounting debugging */
-#define SOCK_REFCNT_DEBUG
+struct timewait_sock_ops;
/* Networking protocol blocks we attach to sockets.
* socket layer -> transport layer interface
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *option);
+ int (*compat_setsockopt)(struct sock *sk,
+ int level,
+ int optname, char __user *optval,
+ int optlen);
+ int (*compat_getsockopt)(struct sock *sk,
+ int level,
+ int optname, char __user *optval,
+ int __user *option);
int (*sendmsg)(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len);
int (*recvmsg)(struct kiocb *iocb, struct sock *sk,
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;
+
struct request_sock_ops *rsk_prot;
+ struct timewait_sock_ops *twsk_prot;
struct module *owner;
#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 ||
sk_stream_mem_schedule(sk, skb->truesize, 1);
}
+static inline int sk_stream_wmem_schedule(struct sock *sk, int size)
+{
+ return size <= sk->sk_forward_alloc ||
+ sk_stream_mem_schedule(sk, size, 0);
+}
+
/* Used by processes to "lock" a socket state, so that
* interrupts and bottom half handlers won't change it
* from under us. It essentially blocks any incoming
* 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. */
#define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock))
+#define bh_lock_sock_nested(__sk) \
+ spin_lock_nested(&((__sk)->sk_lock.slock), \
+ SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
-extern struct sock *sk_alloc(int family,
- unsigned int __nocast priority,
- struct proto *prot, int zero_it);
+extern struct sock *sk_alloc(struct net *net, int family,
+ gfp_t priority,
+ struct proto *prot);
extern void sk_free(struct sock *sk);
+extern struct sock *sk_clone(const struct sock *sk,
+ const gfp_t priority);
extern struct sk_buff *sock_wmalloc(struct sock *sk,
unsigned long size, int force,
- unsigned int __nocast priority);
+ gfp_t priority);
extern struct sk_buff *sock_rmalloc(struct sock *sk,
unsigned long size, int force,
- unsigned int __nocast priority);
+ gfp_t priority);
extern void sock_wfree(struct sk_buff *skb);
extern void sock_rfree(struct sk_buff *skb);
int noblock,
int *errcode);
extern void *sock_kmalloc(struct sock *sk, int size,
- unsigned int __nocast priority);
+ gfp_t priority);
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);
struct msghdr *msg, size_t size, int flags);
extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, int optlen);
+extern 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 optname, char __user *optval, int optlen);
extern void sk_common_release(struct sock *sk);
*
*/
-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) {
- int pkt_len = sk_run_filter(skb, filter->insns,
- filter->len);
- if (!pkt_len)
- err = -EPERM;
- else
- skb_trim(skb, pkt_len);
- }
-
- 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,
+ const int nested);
+
/* Detach socket from process context.
* Announce socket dead, detach it from wait queue and inode.
* Note that parent inode held reference count on this struct sock,
sk->sk_sleep = &parent->wait;
parent->sk = sk;
sk->sk_socket = parent;
+ security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
write_unlock(&sk->sk_dst_lock);
}
-static inline struct dst_entry *
-__sk_dst_check(struct sock *sk, u32 cookie)
-{
- struct dst_entry *dst = sk->sk_dst_cache;
+extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
- if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
- sk->sk_dst_cache = NULL;
- dst_release(dst);
- return NULL;
- }
+extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
- return dst;
-}
-
-static inline struct dst_entry *
-sk_dst_check(struct sock *sk, u32 cookie)
+static inline int sk_can_gso(const struct sock *sk)
{
- struct dst_entry *dst = sk_dst_get(sk);
-
- if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
- sk_dst_reset(sk);
- dst_release(dst);
- return NULL;
- }
-
- return dst;
+ return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}
+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)
{
sk->sk_wmem_queued += skb->truesize;
{
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)
extern void sk_stop_timer(struct sock *sk, struct timer_list* timer);
-static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
-{
- int err = 0;
- int skb_len;
-
- /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
- number of warnings when compiling with -W --ANK
- */
- if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned)sk->sk_rcvbuf) {
- err = -ENOMEM;
- goto out;
- }
-
- /* It would be deadlock, if sock_queue_rcv_skb is used
- with socket lock! We assume that users of this
- function are lock free.
- */
- err = sk_filter(sk, skb, 1);
- if (err)
- goto out;
-
- skb->dev = NULL;
- skb_set_owner_r(skb, sk);
-
- /* Cache the SKB length before we tack it onto the receive
- * queue. Once it is added it no longer belongs to us and
- * may be freed by other threads of control pulling packets
- * from the queue.
- */
- skb_len = skb->len;
-
- skb_queue_tail(&sk->sk_receive_queue, skb);
-
- if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_data_ready(sk, skb_len);
-out:
- return err;
-}
+extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
static inline int sock_error(struct sock *sk)
{
- int err = xchg(&sk->sk_err, 0);
+ int err;
+ if (likely(!sk->sk_err))
+ return 0;
+ err = xchg(&sk->sk_err, 0);
return -err;
}
static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
int size, int mem,
- unsigned int __nocast gfp)
+ gfp_t gfp)
{
struct sk_buff *skb;
int hdr_len;
hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
- skb = alloc_skb(size + hdr_len, gfp);
+ skb = alloc_skb_fclone(size + hdr_len, gfp);
if (skb) {
skb->truesize += mem;
- if (sk->sk_forward_alloc >= (int)skb->truesize ||
- sk_stream_mem_schedule(sk, skb->truesize, 0)) {
+ if (sk_stream_wmem_schedule(sk, skb->truesize)) {
skb_reserve(skb, hdr_len);
return skb;
}
static inline struct sk_buff *sk_stream_alloc_skb(struct sock *sk,
int size,
- unsigned int __nocast gfp)
+ gfp_t gfp)
{
return sk_stream_alloc_pskb(sk, size, 0, gfp);
}
{
struct page *page = NULL;
- if (sk->sk_forward_alloc >= (int)PAGE_SIZE ||
- sk_stream_mem_schedule(sk, PAGE_SIZE, 0))
- page = alloc_pages(sk->sk_allocation, 0);
- else {
+ page = alloc_pages(sk->sk_allocation, 0);
+ if (!page) {
sk->sk_prot->enter_memory_pressure();
sk_stream_moderate_sndbuf(sk);
}
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)
-
/*
* Default write policy as shown to user space via poll/select/SIGIO
*/
return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf / 2);
}
-static inline unsigned int __nocast gfp_any(void)
+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 = &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);
- put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval),
- stamp);
- } else
- sk->sk_stamp = *stamp;
+ ktime_t kt = skb->tstamp;
+
+ if (sock_flag(sk, SOCK_RCVTSTAMP))
+ __sock_recv_timestamp(msg, sk, skb);
+ else
+ sk->sk_stamp = kt;
}
/**
* sk_eat_skb - Release a skb if it is no longer needed
* @sk: socket to eat this skb from
* @skb: socket buffer to eat
+ * @copied_early: flag indicating whether DMA operations copied this data early
*
* This routine must be called with interrupts disabled or with the socket
* locked so that the sk_buff queue operation is ok.
*/
-static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
+#ifdef CONFIG_NET_DMA
+static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
+{
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ if (!copied_early)
+ __kfree_skb(skb);
+ else
+ __skb_queue_tail(&sk->sk_async_wait_queue, skb);
+}
+#else
+static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
__skb_unlink(skb, &sk->sk_receive_queue);
__kfree_skb(skb);
}
+#endif
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)
-#if 0
-#define NETDEBUG(x) do { } while (0)
-#define LIMIT_NETDEBUG(x) do {} while(0)
-#else
-#define NETDEBUG(x) do { x; } while (0)
-#define LIMIT_NETDEBUG(x) do { if (net_ratelimit()) { x; } } 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;
-}
+extern void sk_init(void);
+
+#ifdef CONFIG_SYSCTL
+extern struct ctl_table core_table[];
#endif
+extern int sysctl_optmem_max;
+
+extern __u32 sysctl_wmem_default;
+extern __u32 sysctl_rmem_default;
+
#endif /* _SOCK_H */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff