* 2 of the License, or (at your option) any later version.
*/
-#include <linux/config.h>
+#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
+#include <linux/highmem.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
+#include <net/request_sock.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
#include <net/tcp.h>
#endif
+/*
+ * Each address family might have different locking rules, so we have
+ * one slock key per address family:
+ */
+static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_slock_keys[AF_MAX];
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/*
+ * Make lock validator output more readable. (we pre-construct these
+ * strings build-time, so that runtime initialization of socket
+ * locks is fast):
+ */
+static const char *af_family_key_strings[AF_MAX+1] = {
+ "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
+ "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
+ "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
+ "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" ,
+ "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
+ "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
+ "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
+ "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
+ "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
+ "sk_lock-27" , "sk_lock-28" , "sk_lock-29" ,
+ "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-AF_MAX"
+};
+static const char *af_family_slock_key_strings[AF_MAX+1] = {
+ "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
+ "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
+ "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
+ "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" ,
+ "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
+ "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
+ "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
+ "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" ,
+ "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
+ "slock-27" , "slock-28" , "slock-29" ,
+ "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_MAX"
+};
+#endif
+
+/*
+ * sk_callback_lock locking rules are per-address-family,
+ * so split the lock classes by using a per-AF key:
+ */
+static struct lock_class_key af_callback_keys[AF_MAX];
+
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
* platforms. This makes socket queueing behavior and performance
#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
/* Run time adjustable parameters. */
-__u32 sysctl_wmem_max = SK_WMEM_MAX;
-__u32 sysctl_rmem_max = SK_RMEM_MAX;
-__u32 sysctl_wmem_default = SK_WMEM_MAX;
-__u32 sysctl_rmem_default = SK_RMEM_MAX;
+__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
+__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
+__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
+__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
/* Maximal space eaten by iovec or ancilliary data plus some space */
-int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512);
+int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
}
+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;
+ }
+
+ err = sk_filter(sk, skb);
+ 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;
+}
+EXPORT_SYMBOL(sock_queue_rcv_skb);
+
+int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
+{
+ int rc = NET_RX_SUCCESS;
+
+ if (sk_filter(sk, skb))
+ goto discard_and_relse;
+
+ skb->dev = NULL;
+
+ if (nested)
+ bh_lock_sock_nested(sk);
+ else
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk)) {
+ /*
+ * trylock + unlock semantics:
+ */
+ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
+
+ rc = sk->sk_backlog_rcv(sk, skb);
+
+ mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+ } else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
+out:
+ sock_put(sk);
+ return rc;
+discard_and_relse:
+ kfree_skb(skb);
+ goto out;
+}
+EXPORT_SYMBOL(sk_receive_skb);
+
+struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
+{
+ struct dst_entry *dst = sk->sk_dst_cache;
+
+ if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+ sk->sk_dst_cache = NULL;
+ dst_release(dst);
+ return NULL;
+ }
+
+ return dst;
+}
+EXPORT_SYMBOL(__sk_dst_check);
+
+struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
+{
+ 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;
+}
+EXPORT_SYMBOL(sk_dst_check);
+
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
*/
#ifdef SO_DONTLINGER /* Compatibility item... */
- switch (optname) {
- case SO_DONTLINGER:
- sock_reset_flag(sk, SOCK_LINGER);
- return 0;
+ if (optname == SO_DONTLINGER) {
+ lock_sock(sk);
+ sock_reset_flag(sk, SOCK_LINGER);
+ release_sock(sk);
+ return 0;
}
-#endif
-
+#endif
+
if(optlen<sizeof(int))
return(-EINVAL);
if (val > sysctl_wmem_max)
val = sysctl_wmem_max;
-
+set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
if ((val * 2) < SOCK_MIN_SNDBUF)
sk->sk_sndbuf = SOCK_MIN_SNDBUF;
sk->sk_write_space(sk);
break;
+ case SO_SNDBUFFORCE:
+ if (!capable(CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ break;
+ }
+ goto set_sndbuf;
+
+ case SO_SETXID:
+ if (current->xid) {
+ ret = -EPERM;
+ break;
+ }
+ if (val < 0 || val > MAX_S_CONTEXT) {
+ ret = -EINVAL;
+ break;
+ }
+ sk->sk_xid = val;
+ break;
+
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
about it this is right. Otherwise apps have to
if (val > sysctl_rmem_max)
val = sysctl_rmem_max;
-
+set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
- /* FIXME: is this lower bound the right one? */
+ /*
+ * We double it on the way in to account for
+ * "struct sk_buff" etc. overhead. Applications
+ * assume that the SO_RCVBUF setting they make will
+ * allow that much actual data to be received on that
+ * socket.
+ *
+ * Applications are unaware that "struct sk_buff" and
+ * other overheads allocate from the receive buffer
+ * during socket buffer allocation.
+ *
+ * And after considering the possible alternatives,
+ * returning the value we actually used in getsockopt
+ * is the most desirable behavior.
+ */
if ((val * 2) < SOCK_MIN_RCVBUF)
sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
else
sk->sk_rcvbuf = val * 2;
break;
+ case SO_RCVBUFFORCE:
+ if (!capable(CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ break;
+ }
+ goto set_rcvbuf;
+
case SO_KEEPALIVE:
#ifdef CONFIG_INET
if (sk->sk_protocol == IPPROTO_TCP)
sock_reset_flag(sk, SOCK_LINGER);
else {
#if (BITS_PER_LONG == 32)
- if (ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
+ if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
else
#endif
- sk->sk_lingertime = ling.l_linger * HZ;
+ sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
sock_set_flag(sk, SOCK_LINGER);
}
break;
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
-#if defined(CONFIG_VNET) || defined(CONFIG_VNET_MODULE)
- case SO_SETXID:
- if (current->xid) {
- ret = -EPERM;
- break;
- }
- if (val < 0 || val > MAX_S_CONTEXT) {
- ret = -EINVAL;
- break;
- }
- sk->sk_xid = val;
- break;
-#endif
-
case SO_TIMESTAMP:
if (valbool) {
sock_set_flag(sk, SOCK_RCVTSTAMP);
char devname[IFNAMSIZ];
/* Sorry... */
- if (!capable(CAP_NET_RAW)) {
+ if (!nx_capable(CAP_NET_RAW, NXC_RAW_SOCKET)) {
ret = -EPERM;
break;
}
if (!valbool) {
sk->sk_bound_dev_if = 0;
} else {
- if (optlen > IFNAMSIZ)
- optlen = IFNAMSIZ;
+ if (optlen > IFNAMSIZ - 1)
+ optlen = IFNAMSIZ - 1;
+ memset(devname, 0, sizeof(devname));
if (copy_from_user(devname, optval, optlen)) {
ret = -EFAULT;
break;
break;
case SO_DETACH_FILTER:
- spin_lock_bh(&sk->sk_lock.slock);
- filter = sk->sk_filter;
+ rcu_read_lock_bh();
+ filter = rcu_dereference(sk->sk_filter);
if (filter) {
- sk->sk_filter = NULL;
- spin_unlock_bh(&sk->sk_lock.slock);
+ rcu_assign_pointer(sk->sk_filter, NULL);
sk_filter_release(sk, filter);
+ rcu_read_unlock_bh();
break;
}
- spin_unlock_bh(&sk->sk_lock.slock);
+ rcu_read_unlock_bh();
ret = -ENONET;
break;
+ case SO_PASSSEC:
+ if (valbool)
+ set_bit(SOCK_PASSSEC, &sock->flags);
+ else
+ clear_bit(SOCK_PASSSEC, &sock->flags);
+ break;
+
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
default:
len = sizeof(sk->sk_peercred);
if (copy_to_user(optval, &sk->sk_peercred, len))
return -EFAULT;
+
goto lenout;
case SO_PEERNAME:
v.val = sk->sk_state == TCP_LISTEN;
break;
+ case SO_PASSSEC:
+ v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
+ break;
+
case SO_PEERSEC:
- return security_socket_getpeersec(sock, optval, optlen, len);
+ return security_socket_getpeersec_stream(sock, optval, optlen, len);
default:
return(-ENOPROTOOPT);
return 0;
}
+/*
+ * Initialize an sk_lock.
+ *
+ * (We also register the sk_lock with the lock validator.)
+ */
+static void inline sock_lock_init(struct sock *sk)
+{
+ sock_lock_init_class_and_name(sk,
+ af_family_slock_key_strings[sk->sk_family],
+ af_family_slock_keys + sk->sk_family,
+ af_family_key_strings[sk->sk_family],
+ af_family_keys + sk->sk_family);
+}
+
/**
* sk_alloc - All socket objects are allocated here
* @family: protocol family
* @prot: struct proto associated with this new sock instance
* @zero_it: if we should zero the newly allocated sock
*/
-struct sock *sk_alloc(int family, int priority, struct proto *prot, int zero_it)
+struct sock *sk_alloc(int family, gfp_t priority,
+ struct proto *prot, int zero_it)
{
struct sock *sk = NULL;
- kmem_cache_t *slab = prot->slab;
+ struct kmem_cache *slab = prot->slab;
if (slab != NULL)
sk = kmem_cache_alloc(slab, priority);
sock_vx_init(sk);
sock_nx_init(sk);
- if (security_sk_alloc(sk, family, priority)) {
- if (slab != NULL)
- kmem_cache_free(slab, sk);
- else
- kfree(sk);
- sk = NULL;
- } else
- __module_get(prot->owner);
+ if (security_sk_alloc(sk, family, priority))
+ goto out_free;
+
+ if (!try_module_get(prot->owner))
+ goto out_free;
}
return sk;
+
+out_free:
+ if (slab != NULL)
+ kmem_cache_free(slab, sk);
+ else
+ kfree(sk);
+ return NULL;
}
void sk_free(struct sock *sk)
if (sk->sk_destruct)
sk->sk_destruct(sk);
- filter = sk->sk_filter;
+ filter = rcu_dereference(sk->sk_filter);
if (filter) {
sk_filter_release(sk, filter);
- sk->sk_filter = NULL;
+ rcu_assign_pointer(sk->sk_filter, NULL);
}
sock_disable_timestamp(sk);
module_put(owner);
}
+struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
+{
+ struct sock *newsk = sk_alloc(sk->sk_family, priority, sk->sk_prot, 0);
+
+ if (newsk != NULL) {
+ struct sk_filter *filter;
+
+ sock_copy(newsk, sk);
+
+ /* SANITY */
+ sock_vx_init(newsk);
+ sock_nx_init(newsk);
+ sk_node_init(&newsk->sk_node);
+ sock_lock_init(newsk);
+ bh_lock_sock(newsk);
+
+ atomic_set(&newsk->sk_rmem_alloc, 0);
+ atomic_set(&newsk->sk_wmem_alloc, 0);
+ atomic_set(&newsk->sk_omem_alloc, 0);
+ skb_queue_head_init(&newsk->sk_receive_queue);
+ skb_queue_head_init(&newsk->sk_write_queue);
+#ifdef CONFIG_NET_DMA
+ skb_queue_head_init(&newsk->sk_async_wait_queue);
+#endif
+
+ rwlock_init(&newsk->sk_dst_lock);
+ rwlock_init(&newsk->sk_callback_lock);
+ lockdep_set_class(&newsk->sk_callback_lock,
+ af_callback_keys + newsk->sk_family);
+
+ newsk->sk_dst_cache = NULL;
+ newsk->sk_wmem_queued = 0;
+ newsk->sk_forward_alloc = 0;
+ newsk->sk_send_head = NULL;
+ newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL;
+ newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
+
+ sock_reset_flag(newsk, SOCK_DONE);
+ skb_queue_head_init(&newsk->sk_error_queue);
+
+ filter = newsk->sk_filter;
+ if (filter != NULL)
+ sk_filter_charge(newsk, filter);
+
+ if (unlikely(xfrm_sk_clone_policy(newsk))) {
+ /* It is still raw copy of parent, so invalidate
+ * destructor and make plain sk_free() */
+ newsk->sk_destruct = NULL;
+ sk_free(newsk);
+ newsk = NULL;
+ goto out;
+ }
+
+ newsk->sk_err = 0;
+ newsk->sk_priority = 0;
+ atomic_set(&newsk->sk_refcnt, 2);
+
+ set_vx_info(&newsk->sk_vx_info, sk->sk_vx_info);
+ newsk->sk_xid = sk->sk_xid;
+ vx_sock_inc(newsk);
+ set_nx_info(&newsk->sk_nx_info, sk->sk_nx_info);
+ newsk->sk_nid = sk->sk_nid;
+
+ /*
+ * Increment the counter in the same struct proto as the master
+ * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
+ * is the same as sk->sk_prot->socks, as this field was copied
+ * with memcpy).
+ *
+ * This _changes_ the previous behaviour, where
+ * tcp_create_openreq_child always was incrementing the
+ * equivalent to tcp_prot->socks (inet_sock_nr), so this have
+ * to be taken into account in all callers. -acme
+ */
+ sk_refcnt_debug_inc(newsk);
+ newsk->sk_socket = NULL;
+ newsk->sk_sleep = NULL;
+
+ if (newsk->sk_prot->sockets_allocated)
+ atomic_inc(newsk->sk_prot->sockets_allocated);
+ }
+out:
+ return newsk;
+}
+
+EXPORT_SYMBOL_GPL(sk_clone);
+
void __init sk_init(void)
{
if (num_physpages <= 4096) {
/*
* Allocate a skb from the socket's send buffer.
*/
-struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, int priority)
+struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
+ gfp_t priority)
{
if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
struct sk_buff * skb = alloc_skb(size, priority);
/*
* Allocate a skb from the socket's receive buffer.
*/
-struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, int priority)
+struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
+ gfp_t priority)
{
if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
struct sk_buff *skb = alloc_skb(size, priority);
/*
* Allocate a memory block from the socket's option memory buffer.
*/
-void *sock_kmalloc(struct sock *sk, int size, int priority)
+void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
if ((unsigned)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
int noblock, int *errcode)
{
struct sk_buff *skb;
- unsigned int gfp_mask;
+ gfp_t gfp_mask;
long timeo;
int err;
goto failure;
if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
- skb = alloc_skb(header_len, sk->sk_allocation);
+ skb = alloc_skb(header_len, gfp_mask);
if (skb) {
int npages;
int i;
static void sock_def_destruct(struct sock *sk)
{
- if (sk->sk_protinfo)
- kfree(sk->sk_protinfo);
+ kfree(sk->sk_protinfo);
}
void sk_send_sigurg(struct sock *sk)
skb_queue_head_init(&sk->sk_receive_queue);
skb_queue_head_init(&sk->sk_write_queue);
skb_queue_head_init(&sk->sk_error_queue);
+#ifdef CONFIG_NET_DMA
+ skb_queue_head_init(&sk->sk_async_wait_queue);
+#endif
sk->sk_send_head = NULL;
rwlock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
+ lockdep_set_class(&sk->sk_callback_lock,
+ af_callback_keys + sk->sk_family);
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
atomic_set(&sk->sk_refcnt, 1);
}
-void fastcall lock_sock(struct sock *sk)
+void fastcall lock_sock_nested(struct sock *sk, int subclass)
{
might_sleep();
- spin_lock_bh(&(sk->sk_lock.slock));
+ spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_lock.owner)
__lock_sock(sk);
sk->sk_lock.owner = (void *)1;
- spin_unlock_bh(&(sk->sk_lock.slock));
+ spin_unlock(&sk->sk_lock.slock);
+ /*
+ * The sk_lock has mutex_lock() semantics here:
+ */
+ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
+ local_bh_enable();
}
-EXPORT_SYMBOL(lock_sock);
+EXPORT_SYMBOL(lock_sock_nested);
void fastcall release_sock(struct sock *sk)
{
- spin_lock_bh(&(sk->sk_lock.slock));
+ /*
+ * The sk_lock has mutex_unlock() semantics:
+ */
+ mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+
+ spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_backlog.tail)
__release_sock(sk);
sk->sk_lock.owner = NULL;
- if (waitqueue_active(&(sk->sk_lock.wq)))
- wake_up(&(sk->sk_lock.wq));
- spin_unlock_bh(&(sk->sk_lock.slock));
+ if (waitqueue_active(&sk->sk_lock.wq))
+ wake_up(&sk->sk_lock.wq);
+ spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);
EXPORT_SYMBOL(sock_common_getsockopt);
+#ifdef CONFIG_COMPAT
+int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+
+ if (sk->sk_prot->compat_getsockopt != NULL)
+ return sk->sk_prot->compat_getsockopt(sk, level, optname,
+ optval, optlen);
+ return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
+}
+EXPORT_SYMBOL(compat_sock_common_getsockopt);
+#endif
+
int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
{
EXPORT_SYMBOL(sock_common_setsockopt);
+#ifdef CONFIG_COMPAT
+int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int optlen)
+{
+ struct sock *sk = sock->sk;
+
+ if (sk->sk_prot->compat_setsockopt != NULL)
+ return sk->sk_prot->compat_setsockopt(sk, level, optname,
+ optval, optlen);
+ return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
+}
+EXPORT_SYMBOL(compat_sock_common_setsockopt);
+#endif
+
void sk_common_release(struct sock *sk)
{
if (sk->sk_prot->destroy)
xfrm_sk_free_policy(sk);
-#ifdef INET_REFCNT_DEBUG
- if (atomic_read(&sk->sk_refcnt) != 1)
- printk(KERN_DEBUG "Destruction of the socket %p delayed, c=%d\n",
- sk, atomic_read(&sk->sk_refcnt));
-#endif
+ sk_refcnt_debug_release(sk);
sock_put(sk);
}
int proto_register(struct proto *prot, int alloc_slab)
{
+ char *request_sock_slab_name = NULL;
+ char *timewait_sock_slab_name;
int rc = -ENOBUFS;
if (alloc_slab) {
prot->name);
goto out;
}
+
+ if (prot->rsk_prot != NULL) {
+ static const char mask[] = "request_sock_%s";
+
+ request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);
+ if (request_sock_slab_name == NULL)
+ goto out_free_sock_slab;
+
+ sprintf(request_sock_slab_name, mask, prot->name);
+ prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name,
+ prot->rsk_prot->obj_size, 0,
+ SLAB_HWCACHE_ALIGN, NULL, NULL);
+
+ if (prot->rsk_prot->slab == NULL) {
+ printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
+ prot->name);
+ goto out_free_request_sock_slab_name;
+ }
+ }
+
+ if (prot->twsk_prot != NULL) {
+ static const char mask[] = "tw_sock_%s";
+
+ timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);
+
+ if (timewait_sock_slab_name == NULL)
+ goto out_free_request_sock_slab;
+
+ sprintf(timewait_sock_slab_name, mask, prot->name);
+ prot->twsk_prot->twsk_slab =
+ kmem_cache_create(timewait_sock_slab_name,
+ prot->twsk_prot->twsk_obj_size,
+ 0, SLAB_HWCACHE_ALIGN,
+ NULL, NULL);
+ if (prot->twsk_prot->twsk_slab == NULL)
+ goto out_free_timewait_sock_slab_name;
+ }
}
write_lock(&proto_list_lock);
rc = 0;
out:
return rc;
+out_free_timewait_sock_slab_name:
+ kfree(timewait_sock_slab_name);
+out_free_request_sock_slab:
+ if (prot->rsk_prot && prot->rsk_prot->slab) {
+ kmem_cache_destroy(prot->rsk_prot->slab);
+ prot->rsk_prot->slab = NULL;
+ }
+out_free_request_sock_slab_name:
+ kfree(request_sock_slab_name);
+out_free_sock_slab:
+ kmem_cache_destroy(prot->slab);
+ prot->slab = NULL;
+ goto out;
}
EXPORT_SYMBOL(proto_register);
void proto_unregister(struct proto *prot)
{
write_lock(&proto_list_lock);
+ list_del(&prot->node);
+ write_unlock(&proto_list_lock);
if (prot->slab != NULL) {
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
}
- list_del(&prot->node);
- write_unlock(&proto_list_lock);
+ if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
+ const char *name = kmem_cache_name(prot->rsk_prot->slab);
+
+ kmem_cache_destroy(prot->rsk_prot->slab);
+ kfree(name);
+ prot->rsk_prot->slab = NULL;
+ }
+
+ if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
+ const char *name = kmem_cache_name(prot->twsk_prot->twsk_slab);
+
+ kmem_cache_destroy(prot->twsk_prot->twsk_slab);
+ kfree(name);
+ prot->twsk_prot->twsk_slab = NULL;
+ }
}
EXPORT_SYMBOL(proto_unregister);
EXPORT_SYMBOL(sock_wmalloc);
EXPORT_SYMBOL(sock_i_uid);
EXPORT_SYMBOL(sock_i_ino);
-#ifdef CONFIG_SYSCTL
EXPORT_SYMBOL(sysctl_optmem_max);
+#ifdef CONFIG_SYSCTL
EXPORT_SYMBOL(sysctl_rmem_max);
EXPORT_SYMBOL(sysctl_wmem_max);
#endif
git://git.onelab.eu / linux-2.6.git / blobdiff