* Alan Cox : TCP ack handling is buggy, the DESTROY timer
* was buggy. Put a remove_sock() in the handler
* for memory when we hit 0. Also altered the timer
- * code. The ACK stuff can wait and needs major
+ * code. The ACK stuff can wait and needs major
* TCP layer surgery.
* Alan Cox : Fixed TCP ack bug, removed remove sock
* and fixed timer/inet_bh race.
*/
#include <linux/capability.h>
-#include <linux/config.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/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/xfrm.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-AF_CAN" ,
+ "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
+ "sk_lock-AF_RXRPC" , "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-AF_CAN" ,
+ "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
+ "slock-AF_RXRPC" , "slock-AF_MAX"
+};
+static const char *af_family_clock_key_strings[AF_MAX+1] = {
+ "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
+ "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
+ "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
+ "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" ,
+ "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
+ "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
+ "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
+ "clock-21" , "clock-AF_SNA" , "clock-AF_IRDA" ,
+ "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
+ "clock-27" , "clock-28" , "clock-29" ,
+ "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
+ "clock-AF_RXRPC" , "clock-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)
{
return -EINVAL;
if (copy_from_user(&tv, optval, sizeof(tv)))
return -EFAULT;
-
+ if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
+ return -EDOM;
+
+ if (tv.tv_sec < 0) {
+ static int warned __read_mostly;
+
+ *timeo_p = 0;
+ if (warned < 10 && net_ratelimit())
+ warned++;
+ printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) "
+ "tries to set negative timeout\n",
+ current->comm, task_pid_nr(current));
+ return 0;
+ }
*timeo_p = MAX_SCHEDULE_TIMEOUT;
if (tv.tv_sec == 0 && tv.tv_usec == 0)
return 0;
{
static int warned;
static char warncomm[TASK_COMM_LEN];
- if (strcmp(warncomm, current->comm) && warned < 5) {
- strcpy(warncomm, current->comm);
+ if (strcmp(warncomm, current->comm) && warned < 5) {
+ strcpy(warncomm, current->comm);
printk(KERN_WARNING "process `%s' is using obsolete "
"%s SO_BSDCOMPAT\n", warncomm, name);
warned++;
}
static void sock_disable_timestamp(struct sock *sk)
-{
- if (sock_flag(sk, SOCK_TIMESTAMP)) {
+{
+ if (sock_flag(sk, SOCK_TIMESTAMP)) {
sock_reset_flag(sk, SOCK_TIMESTAMP);
net_disable_timestamp();
}
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);
+ err = sk_filter(sk, skb);
if (err)
goto out;
+ if (!sk_rmem_schedule(sk, skb->truesize)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
skb->dev = NULL;
skb_set_owner_r(skb, sk);
}
EXPORT_SYMBOL(sock_queue_rcv_skb);
-int sk_receive_skb(struct sock *sk, struct sk_buff *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, 0))
+ if (sk_filter(sk, skb))
goto discard_and_relse;
skb->dev = NULL;
- bh_lock_sock(sk);
- if (!sock_owned_by_user(sk))
- rc = sk->sk_backlog_rcv(sk, skb);
+ 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:
}
EXPORT_SYMBOL(sk_dst_check);
+static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
+{
+ int ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+ struct net *net = sk->sk_net;
+ char devname[IFNAMSIZ];
+ int index;
+
+ /* Sorry... */
+ ret = -EPERM;
+ if (!capable(CAP_NET_RAW))
+ goto out;
+
+ ret = -EINVAL;
+ if (optlen < 0)
+ goto out;
+
+ /* Bind this socket to a particular device like "eth0",
+ * as specified in the passed interface name. If the
+ * name is "" or the option length is zero the socket
+ * is not bound.
+ */
+ if (optlen > IFNAMSIZ - 1)
+ optlen = IFNAMSIZ - 1;
+ memset(devname, 0, sizeof(devname));
+
+ ret = -EFAULT;
+ if (copy_from_user(devname, optval, optlen))
+ goto out;
+
+ if (devname[0] == '\0') {
+ index = 0;
+ } else {
+ struct net_device *dev = dev_get_by_name(net, devname);
+
+ ret = -ENODEV;
+ if (!dev)
+ goto out;
+
+ index = dev->ifindex;
+ dev_put(dev);
+ }
+
+ lock_sock(sk);
+ sk->sk_bound_dev_if = index;
+ sk_dst_reset(sk);
+ release_sock(sk);
+
+ ret = 0;
+
+out:
+#endif
+
+ return ret;
+}
+
+static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
+{
+ if (valbool)
+ sock_set_flag(sk, bit);
+ else
+ sock_reset_flag(sk, bit);
+}
+
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
char __user *optval, int optlen)
{
struct sock *sk=sock->sk;
- struct sk_filter *filter;
int val;
int valbool;
struct linger ling;
int ret = 0;
-
+
/*
* Options without arguments
*/
return 0;
}
#endif
-
- if(optlen<sizeof(int))
- return(-EINVAL);
-
+
+ if (optname == SO_BINDTODEVICE)
+ return sock_bindtodevice(sk, optval, optlen);
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
if (get_user(val, (int __user *)optval))
return -EFAULT;
-
- valbool = val?1:0;
+
+ valbool = val?1:0;
lock_sock(sk);
- switch(optname)
- {
- case SO_DEBUG:
- if(val && !capable(CAP_NET_ADMIN))
- {
- ret = -EACCES;
- }
- else if (valbool)
- sock_set_flag(sk, SOCK_DBG);
- else
- sock_reset_flag(sk, SOCK_DBG);
- break;
- case SO_REUSEADDR:
- sk->sk_reuse = valbool;
- break;
- case SO_TYPE:
- case SO_ERROR:
- ret = -ENOPROTOOPT;
- break;
- case SO_DONTROUTE:
- if (valbool)
- sock_set_flag(sk, SOCK_LOCALROUTE);
- else
- sock_reset_flag(sk, SOCK_LOCALROUTE);
- break;
- case SO_BROADCAST:
- sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
- break;
- case SO_SNDBUF:
- /* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_wmem_max)
- val = sysctl_wmem_max;
+ switch(optname) {
+ case SO_DEBUG:
+ if (val && !capable(CAP_NET_ADMIN)) {
+ ret = -EACCES;
+ } else
+ sock_valbool_flag(sk, SOCK_DBG, valbool);
+ break;
+ case SO_REUSEADDR:
+ sk->sk_reuse = valbool;
+ break;
+ case SO_TYPE:
+ case SO_ERROR:
+ ret = -ENOPROTOOPT;
+ break;
+ case SO_DONTROUTE:
+ sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
+ break;
+ case SO_BROADCAST:
+ sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
+ break;
+ case SO_SNDBUF:
+ /* Don't error on this BSD doesn't and if you think
+ about it this is right. Otherwise apps have to
+ play 'guess the biggest size' games. RCVBUF/SNDBUF
+ are treated in BSD as hints */
+
+ 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;
- else
- sk->sk_sndbuf = val * 2;
+ sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+ if ((val * 2) < SOCK_MIN_SNDBUF)
+ sk->sk_sndbuf = SOCK_MIN_SNDBUF;
+ else
+ sk->sk_sndbuf = val * 2;
- /*
- * Wake up sending tasks if we
- * upped the value.
- */
- sk->sk_write_space(sk);
+ /*
+ * Wake up sending tasks if we
+ * upped the value.
+ */
+ sk->sk_write_space(sk);
+ break;
+
+ case SO_SNDBUFFORCE:
+ if (!capable(CAP_NET_ADMIN)) {
+ ret = -EPERM;
break;
+ }
+ goto set_sndbuf;
- case SO_SNDBUFFORCE:
- if (!capable(CAP_NET_ADMIN)) {
- ret = -EPERM;
- break;
- }
- goto set_sndbuf;
-
- case SO_RCVBUF:
- /* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_rmem_max)
- val = sysctl_rmem_max;
+ case SO_RCVBUF:
+ /* Don't error on this BSD doesn't and if you think
+ about it this is right. Otherwise apps have to
+ play 'guess the biggest size' games. RCVBUF/SNDBUF
+ are treated in BSD as hints */
+
+ if (val > sysctl_rmem_max)
+ val = sysctl_rmem_max;
set_rcvbuf:
- sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
- /*
- * 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;
+ sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+ /*
+ * 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_RCVBUFFORCE:
- if (!capable(CAP_NET_ADMIN)) {
- ret = -EPERM;
- break;
- }
- goto set_rcvbuf;
-
- case SO_KEEPALIVE:
+ case SO_KEEPALIVE:
#ifdef CONFIG_INET
- if (sk->sk_protocol == IPPROTO_TCP)
- tcp_set_keepalive(sk, valbool);
+ if (sk->sk_protocol == IPPROTO_TCP)
+ tcp_set_keepalive(sk, valbool);
#endif
- sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
+ sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
+ break;
+
+ case SO_OOBINLINE:
+ sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
+ break;
+
+ case SO_NO_CHECK:
+ sk->sk_no_check = valbool;
+ break;
+
+ case SO_PRIORITY:
+ if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN))
+ sk->sk_priority = val;
+ else
+ ret = -EPERM;
+ break;
+
+ case SO_LINGER:
+ if (optlen < sizeof(ling)) {
+ ret = -EINVAL; /* 1003.1g */
break;
-
- case SO_OOBINLINE:
- sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
- break;
-
- case SO_NO_CHECK:
- sk->sk_no_check = valbool;
- break;
-
- case SO_PRIORITY:
- if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN))
- sk->sk_priority = val;
- else
- ret = -EPERM;
+ }
+ if (copy_from_user(&ling,optval,sizeof(ling))) {
+ ret = -EFAULT;
break;
-
- case SO_LINGER:
- if(optlen<sizeof(ling)) {
- ret = -EINVAL; /* 1003.1g */
- break;
- }
- if (copy_from_user(&ling,optval,sizeof(ling))) {
- ret = -EFAULT;
- break;
- }
- if (!ling.l_onoff)
- sock_reset_flag(sk, SOCK_LINGER);
- else {
+ }
+ if (!ling.l_onoff)
+ sock_reset_flag(sk, SOCK_LINGER);
+ else {
#if (BITS_PER_LONG == 32)
- if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
- sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
- else
+ if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
+ sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
+ else
#endif
- sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
- sock_set_flag(sk, SOCK_LINGER);
- }
- break;
-
- case SO_BSDCOMPAT:
- sock_warn_obsolete_bsdism("setsockopt");
- break;
-
- case SO_PASSCRED:
- if (valbool)
- set_bit(SOCK_PASSCRED, &sock->flags);
+ sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
+ sock_set_flag(sk, SOCK_LINGER);
+ }
+ break;
+
+ case SO_BSDCOMPAT:
+ sock_warn_obsolete_bsdism("setsockopt");
+ break;
+
+ case SO_PASSCRED:
+ if (valbool)
+ set_bit(SOCK_PASSCRED, &sock->flags);
+ else
+ clear_bit(SOCK_PASSCRED, &sock->flags);
+ break;
+
+ case SO_TIMESTAMP:
+ case SO_TIMESTAMPNS:
+ if (valbool) {
+ if (optname == SO_TIMESTAMP)
+ sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
else
- clear_bit(SOCK_PASSCRED, &sock->flags);
- break;
-
- case SO_TIMESTAMP:
- if (valbool) {
- sock_set_flag(sk, SOCK_RCVTSTAMP);
- sock_enable_timestamp(sk);
- } else
- sock_reset_flag(sk, SOCK_RCVTSTAMP);
- break;
+ sock_set_flag(sk, SOCK_RCVTSTAMPNS);
+ sock_set_flag(sk, SOCK_RCVTSTAMP);
+ sock_enable_timestamp(sk);
+ } else {
+ sock_reset_flag(sk, SOCK_RCVTSTAMP);
+ sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
+ }
+ break;
- case SO_RCVLOWAT:
- if (val < 0)
- val = INT_MAX;
- sk->sk_rcvlowat = val ? : 1;
- break;
+ case SO_RCVLOWAT:
+ if (val < 0)
+ val = INT_MAX;
+ sk->sk_rcvlowat = val ? : 1;
+ break;
- case SO_RCVTIMEO:
- ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
- break;
+ case SO_RCVTIMEO:
+ ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
+ break;
- case SO_SNDTIMEO:
- ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
- break;
+ case SO_SNDTIMEO:
+ ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
+ break;
-#ifdef CONFIG_NETDEVICES
- case SO_BINDTODEVICE:
- {
- char devname[IFNAMSIZ];
+ case SO_ATTACH_FILTER:
+ ret = -EINVAL;
+ if (optlen == sizeof(struct sock_fprog)) {
+ struct sock_fprog fprog;
- /* Sorry... */
- if (!capable(CAP_NET_RAW)) {
- ret = -EPERM;
+ ret = -EFAULT;
+ if (copy_from_user(&fprog, optval, sizeof(fprog)))
break;
- }
-
- /* Bind this socket to a particular device like "eth0",
- * as specified in the passed interface name. If the
- * name is "" or the option length is zero the socket
- * is not bound.
- */
-
- if (!valbool) {
- sk->sk_bound_dev_if = 0;
- } else {
- if (optlen > IFNAMSIZ - 1)
- optlen = IFNAMSIZ - 1;
- memset(devname, 0, sizeof(devname));
- if (copy_from_user(devname, optval, optlen)) {
- ret = -EFAULT;
- break;
- }
- /* Remove any cached route for this socket. */
- sk_dst_reset(sk);
-
- if (devname[0] == '\0') {
- sk->sk_bound_dev_if = 0;
- } else {
- struct net_device *dev = dev_get_by_name(devname);
- if (!dev) {
- ret = -ENODEV;
- break;
- }
- sk->sk_bound_dev_if = dev->ifindex;
- dev_put(dev);
- }
- }
- break;
+ ret = sk_attach_filter(&fprog, sk);
}
-#endif
-
-
- case SO_ATTACH_FILTER:
- ret = -EINVAL;
- if (optlen == sizeof(struct sock_fprog)) {
- struct sock_fprog fprog;
-
- ret = -EFAULT;
- if (copy_from_user(&fprog, optval, sizeof(fprog)))
- break;
-
- ret = sk_attach_filter(&fprog, sk);
- }
- break;
-
- case SO_DETACH_FILTER:
- spin_lock_bh(&sk->sk_lock.slock);
- filter = sk->sk_filter;
- if (filter) {
- sk->sk_filter = NULL;
- spin_unlock_bh(&sk->sk_lock.slock);
- sk_filter_release(sk, filter);
- break;
- }
- spin_unlock_bh(&sk->sk_lock.slock);
- ret = -ENONET;
- break;
+ break;
+
+ case SO_DETACH_FILTER:
+ ret = sk_detach_filter(sk);
+ break;
+
+ case SO_PASSSEC:
+ if (valbool)
+ set_bit(SOCK_PASSSEC, &sock->flags);
+ else
+ clear_bit(SOCK_PASSSEC, &sock->flags);
+ break;
+ case SO_MARK:
+ if (!capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ else {
+ sk->sk_mark = val;
+ }
+ break;
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
- default:
- ret = -ENOPROTOOPT;
- break;
- }
+ default:
+ ret = -ENOPROTOOPT;
+ break;
+ }
release_sock(sk);
return ret;
}
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
-
- union
- {
- int val;
- struct linger ling;
+
+ union {
+ int val;
+ struct linger ling;
struct timeval tm;
} v;
-
+
unsigned int lv = sizeof(int);
int len;
-
- if(get_user(len,optlen))
- return -EFAULT;
- if(len < 0)
- return -EINVAL;
-
- switch(optname)
- {
- case SO_DEBUG:
- v.val = sock_flag(sk, SOCK_DBG);
- break;
-
- case SO_DONTROUTE:
- v.val = sock_flag(sk, SOCK_LOCALROUTE);
- break;
-
- case SO_BROADCAST:
- v.val = !!sock_flag(sk, SOCK_BROADCAST);
- break;
-
- case SO_SNDBUF:
- v.val = sk->sk_sndbuf;
- break;
-
- case SO_RCVBUF:
- v.val = sk->sk_rcvbuf;
- break;
-
- case SO_REUSEADDR:
- v.val = sk->sk_reuse;
- break;
-
- case SO_KEEPALIVE:
- v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
- break;
-
- case SO_TYPE:
- v.val = sk->sk_type;
- break;
- case SO_ERROR:
- v.val = -sock_error(sk);
- if(v.val==0)
- v.val = xchg(&sk->sk_err_soft, 0);
- break;
-
- case SO_OOBINLINE:
- v.val = !!sock_flag(sk, SOCK_URGINLINE);
- break;
-
- case SO_NO_CHECK:
- v.val = sk->sk_no_check;
- break;
+ if (get_user(len, optlen))
+ return -EFAULT;
+ if (len < 0)
+ return -EINVAL;
- case SO_PRIORITY:
- v.val = sk->sk_priority;
- break;
-
- case SO_LINGER:
- lv = sizeof(v.ling);
- v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER);
- v.ling.l_linger = sk->sk_lingertime / HZ;
- break;
-
- case SO_BSDCOMPAT:
- sock_warn_obsolete_bsdism("getsockopt");
- break;
+ switch(optname) {
+ case SO_DEBUG:
+ v.val = sock_flag(sk, SOCK_DBG);
+ break;
+
+ case SO_DONTROUTE:
+ v.val = sock_flag(sk, SOCK_LOCALROUTE);
+ break;
+
+ case SO_BROADCAST:
+ v.val = !!sock_flag(sk, SOCK_BROADCAST);
+ break;
+
+ case SO_SNDBUF:
+ v.val = sk->sk_sndbuf;
+ break;
+
+ case SO_RCVBUF:
+ v.val = sk->sk_rcvbuf;
+ break;
+
+ case SO_REUSEADDR:
+ v.val = sk->sk_reuse;
+ break;
+
+ case SO_KEEPALIVE:
+ v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
+ break;
+
+ case SO_TYPE:
+ v.val = sk->sk_type;
+ break;
+
+ case SO_ERROR:
+ v.val = -sock_error(sk);
+ if (v.val==0)
+ v.val = xchg(&sk->sk_err_soft, 0);
+ break;
+
+ case SO_OOBINLINE:
+ v.val = !!sock_flag(sk, SOCK_URGINLINE);
+ break;
+
+ case SO_NO_CHECK:
+ v.val = sk->sk_no_check;
+ break;
+
+ case SO_PRIORITY:
+ v.val = sk->sk_priority;
+ break;
+
+ case SO_LINGER:
+ lv = sizeof(v.ling);
+ v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER);
+ v.ling.l_linger = sk->sk_lingertime / HZ;
+ break;
+
+ case SO_BSDCOMPAT:
+ sock_warn_obsolete_bsdism("getsockopt");
+ break;
+
+ case SO_TIMESTAMP:
+ v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
+ !sock_flag(sk, SOCK_RCVTSTAMPNS);
+ break;
+
+ case SO_TIMESTAMPNS:
+ v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
+ break;
+
+ case SO_RCVTIMEO:
+ lv=sizeof(struct timeval);
+ if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
+ v.tm.tv_sec = 0;
+ v.tm.tv_usec = 0;
+ } else {
+ v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
+ v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
+ }
+ break;
+
+ case SO_SNDTIMEO:
+ lv=sizeof(struct timeval);
+ if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
+ v.tm.tv_sec = 0;
+ v.tm.tv_usec = 0;
+ } else {
+ v.tm.tv_sec = sk->sk_sndtimeo / HZ;
+ v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
+ }
+ break;
- case SO_TIMESTAMP:
- v.val = sock_flag(sk, SOCK_RCVTSTAMP);
- break;
+ case SO_RCVLOWAT:
+ v.val = sk->sk_rcvlowat;
+ break;
- case SO_RCVTIMEO:
- lv=sizeof(struct timeval);
- if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
- v.tm.tv_sec = 0;
- v.tm.tv_usec = 0;
- } else {
- v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
- v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
- }
- break;
+ case SO_SNDLOWAT:
+ v.val=1;
+ break;
- case SO_SNDTIMEO:
- lv=sizeof(struct timeval);
- if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
- v.tm.tv_sec = 0;
- v.tm.tv_usec = 0;
- } else {
- v.tm.tv_sec = sk->sk_sndtimeo / HZ;
- v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
- }
- break;
+ case SO_PASSCRED:
+ v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
+ break;
- case SO_RCVLOWAT:
- v.val = sk->sk_rcvlowat;
- break;
+ case SO_PEERCRED:
+ if (len > sizeof(sk->sk_peercred))
+ len = sizeof(sk->sk_peercred);
+ if (copy_to_user(optval, &sk->sk_peercred, len))
+ return -EFAULT;
+ goto lenout;
- case SO_SNDLOWAT:
- v.val=1;
- break;
+ case SO_PEERNAME:
+ {
+ char address[128];
+
+ if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
+ return -ENOTCONN;
+ if (lv < len)
+ return -EINVAL;
+ if (copy_to_user(optval, address, len))
+ return -EFAULT;
+ goto lenout;
+ }
- case SO_PASSCRED:
- v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
- break;
+ /* Dubious BSD thing... Probably nobody even uses it, but
+ * the UNIX standard wants it for whatever reason... -DaveM
+ */
+ case SO_ACCEPTCONN:
+ v.val = sk->sk_state == TCP_LISTEN;
+ break;
- case SO_PEERCRED:
- if (len > sizeof(sk->sk_peercred))
- len = sizeof(sk->sk_peercred);
- if (copy_to_user(optval, &sk->sk_peercred, len))
- return -EFAULT;
- goto lenout;
-
- case SO_PEERNAME:
- {
- char address[128];
-
- if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
- return -ENOTCONN;
- if (lv < len)
- return -EINVAL;
- if (copy_to_user(optval, address, len))
- return -EFAULT;
- goto lenout;
- }
+ case SO_PASSSEC:
+ v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
+ break;
- /* Dubious BSD thing... Probably nobody even uses it, but
- * the UNIX standard wants it for whatever reason... -DaveM
- */
- case SO_ACCEPTCONN:
- v.val = sk->sk_state == TCP_LISTEN;
- break;
+ case SO_PEERSEC:
+ return security_socket_getpeersec_stream(sock, optval, optlen, len);
- case SO_PEERSEC:
- return security_socket_getpeersec_stream(sock, optval, optlen, len);
+ case SO_MARK:
+ v.val = sk->sk_mark;
+ break;
- default:
- return(-ENOPROTOOPT);
+ default:
+ return -ENOPROTOOPT;
}
+
if (len > lv)
len = lv;
if (copy_to_user(optval, &v, len))
return -EFAULT;
lenout:
- if (put_user(len, optlen))
- return -EFAULT;
- return 0;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ return 0;
}
-/**
- * sk_alloc - All socket objects are allocated here
- * @family: protocol family
- * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
- * @prot: struct proto associated with this new sock instance
- * @zero_it: if we should zero the newly allocated sock
+/*
+ * Initialize an sk_lock.
+ *
+ * (We also register the sk_lock with the lock validator.)
*/
-struct sock *sk_alloc(int family, gfp_t priority,
- struct proto *prot, int zero_it)
+static inline void sock_lock_init(struct sock *sk)
{
- struct sock *sk = NULL;
- kmem_cache_t *slab = prot->slab;
+ 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);
+}
+static void sock_copy(struct sock *nsk, const struct sock *osk)
+{
+#ifdef CONFIG_SECURITY_NETWORK
+ void *sptr = nsk->sk_security;
+#endif
+
+ memcpy(nsk, osk, osk->sk_prot->obj_size);
+#ifdef CONFIG_SECURITY_NETWORK
+ nsk->sk_security = sptr;
+ security_sk_clone(osk, nsk);
+#endif
+}
+
+static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
+ int family)
+{
+ struct sock *sk;
+ struct kmem_cache *slab;
+
+ slab = prot->slab;
if (slab != NULL)
sk = kmem_cache_alloc(slab, priority);
else
sk = kmalloc(prot->obj_size, priority);
- if (sk) {
- if (zero_it) {
- memset(sk, 0, prot->obj_size);
- sk->sk_family = family;
- /*
- * See comment in struct sock definition to understand
- * why we need sk_prot_creator -acme
- */
- sk->sk_prot = sk->sk_prot_creator = prot;
- sock_lock_init(sk);
- }
-
+ if (sk != NULL) {
if (security_sk_alloc(sk, family, priority))
goto out_free;
if (!try_module_get(prot->owner))
- goto out_free;
+ goto out_free_sec;
}
+
return sk;
+out_free_sec:
+ security_sk_free(sk);
out_free:
if (slab != NULL)
kmem_cache_free(slab, sk);
return NULL;
}
+static void sk_prot_free(struct proto *prot, struct sock *sk)
+{
+ struct kmem_cache *slab;
+ struct module *owner;
+
+ owner = prot->owner;
+ slab = prot->slab;
+
+ security_sk_free(sk);
+ if (slab != NULL)
+ kmem_cache_free(slab, sk);
+ else
+ kfree(sk);
+ module_put(owner);
+}
+
+/**
+ * sk_alloc - All socket objects are allocated here
+ * @net: the applicable net namespace
+ * @family: protocol family
+ * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ * @prot: struct proto associated with this new sock instance
+ * @zero_it: if we should zero the newly allocated sock
+ */
+struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
+ struct proto *prot)
+{
+ struct sock *sk;
+
+ sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
+ if (sk) {
+ sk->sk_family = family;
+ /*
+ * See comment in struct sock definition to understand
+ * why we need sk_prot_creator -acme
+ */
+ sk->sk_prot = sk->sk_prot_creator = prot;
+ sock_lock_init(sk);
+ sk->sk_net = get_net(net);
+ }
+
+ return sk;
+}
+
void sk_free(struct sock *sk)
{
struct sk_filter *filter;
- struct module *owner = sk->sk_prot_creator->owner;
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;
+ sk_filter_uncharge(sk, filter);
+ rcu_assign_pointer(sk->sk_filter, NULL);
}
sock_disable_timestamp(sk);
printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
__FUNCTION__, atomic_read(&sk->sk_omem_alloc));
- security_sk_free(sk);
- if (sk->sk_prot_creator->slab != NULL)
- kmem_cache_free(sk->sk_prot_creator->slab, sk);
- else
- kfree(sk);
- module_put(owner);
+ put_net(sk->sk_net);
+ sk_prot_free(sk->sk_prot_creator, sk);
}
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);
+ struct sock *newsk;
+ newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
if (newsk != NULL) {
struct sk_filter *filter;
- memcpy(newsk, sk, sk->sk_prot->obj_size);
+ sock_copy(newsk, sk);
/* SANITY */
+ get_net(newsk->sk_net);
sk_node_init(&newsk->sk_node);
sock_lock_init(newsk);
bh_lock_sock(newsk);
+ newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL;
atomic_set(&newsk->sk_rmem_alloc, 0);
atomic_set(&newsk->sk_wmem_alloc, 0);
rwlock_init(&newsk->sk_dst_lock);
rwlock_init(&newsk->sk_callback_lock);
+ lockdep_set_class_and_name(&newsk->sk_callback_lock,
+ af_callback_keys + newsk->sk_family,
+ af_family_clock_key_strings[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);
EXPORT_SYMBOL_GPL(sk_clone);
+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_SOFTWARE;
+ 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;
+ }
+}
+EXPORT_SYMBOL_GPL(sk_setup_caps);
+
void __init sk_init(void)
{
if (num_physpages <= 4096) {
*/
-/*
- * Write buffer destructor automatically called from kfree_skb.
+/*
+ * Write buffer destructor automatically called from kfree_skb.
*/
void sock_wfree(struct sk_buff *skb)
{
sock_put(sk);
}
-/*
- * Read buffer destructor automatically called from kfree_skb.
+/*
+ * Read buffer destructor automatically called from kfree_skb.
*/
void sock_rfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
+ skb_truesize_check(skb);
atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+ sk_mem_uncharge(skb->sk, skb->truesize);
}
/*
* Allocate a skb from the socket's receive buffer.
- */
+ */
struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority)
{
return NULL;
}
-/*
+/*
* Allocate a memory block from the socket's option memory buffer.
- */
+ */
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) {
void *mem;
/* First do the add, to avoid the race if kmalloc
- * might sleep.
+ * might sleep.
*/
atomic_add(size, &sk->sk_omem_alloc);
mem = kmalloc(size, priority);
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;
return NULL;
}
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
+struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
int noblock, int *errcode)
{
return sock_alloc_send_pskb(sk, size, 0, noblock, errcode);
{
DEFINE_WAIT(wait);
- for(;;) {
+ for (;;) {
prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_bh(&sk->sk_lock.slock);
schedule();
spin_lock_bh(&sk->sk_lock.slock);
- if(!sock_owned_by_user(sk))
+ if (!sock_owned_by_user(sk))
break;
}
finish_wait(&sk->sk_lock.wq, &wait);
} while (skb != NULL);
bh_lock_sock(sk);
- } while((skb = sk->sk_backlog.head) != NULL);
+ } while ((skb = sk->sk_backlog.head) != NULL);
}
/**
EXPORT_SYMBOL(sk_wait_data);
+/**
+ * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated
+ * @sk: socket
+ * @size: memory size to allocate
+ * @kind: allocation type
+ *
+ * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
+ * rmem allocation. This function assumes that protocols which have
+ * memory_pressure use sk_wmem_queued as write buffer accounting.
+ */
+int __sk_mem_schedule(struct sock *sk, int size, int kind)
+{
+ struct proto *prot = sk->sk_prot;
+ int amt = sk_mem_pages(size);
+ int allocated;
+
+ sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+ allocated = atomic_add_return(amt, prot->memory_allocated);
+
+ /* Under limit. */
+ if (allocated <= prot->sysctl_mem[0]) {
+ if (prot->memory_pressure && *prot->memory_pressure)
+ *prot->memory_pressure = 0;
+ return 1;
+ }
+
+ /* Under pressure. */
+ if (allocated > prot->sysctl_mem[1])
+ if (prot->enter_memory_pressure)
+ prot->enter_memory_pressure();
+
+ /* Over hard limit. */
+ if (allocated > prot->sysctl_mem[2])
+ goto suppress_allocation;
+
+ /* guarantee minimum buffer size under pressure */
+ if (kind == SK_MEM_RECV) {
+ if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
+ return 1;
+ } else { /* SK_MEM_SEND */
+ if (sk->sk_type == SOCK_STREAM) {
+ if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
+ return 1;
+ } else if (atomic_read(&sk->sk_wmem_alloc) <
+ prot->sysctl_wmem[0])
+ return 1;
+ }
+
+ if (prot->memory_pressure) {
+ if (!*prot->memory_pressure ||
+ prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) *
+ sk_mem_pages(sk->sk_wmem_queued +
+ atomic_read(&sk->sk_rmem_alloc) +
+ sk->sk_forward_alloc))
+ return 1;
+ }
+
+suppress_allocation:
+
+ if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
+ sk_stream_moderate_sndbuf(sk);
+
+ /* Fail only if socket is _under_ its sndbuf.
+ * In this case we cannot block, so that we have to fail.
+ */
+ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
+ return 1;
+ }
+
+ /* Alas. Undo changes. */
+ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
+ atomic_sub(amt, prot->memory_allocated);
+ return 0;
+}
+
+EXPORT_SYMBOL(__sk_mem_schedule);
+
+/**
+ * __sk_reclaim - reclaim memory_allocated
+ * @sk: socket
+ */
+void __sk_mem_reclaim(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+
+ atomic_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
+ prot->memory_allocated);
+ sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
+
+ if (prot->memory_pressure && *prot->memory_pressure &&
+ (atomic_read(prot->memory_allocated) < prot->sysctl_mem[0]))
+ *prot->memory_pressure = 0;
+}
+
+EXPORT_SYMBOL(__sk_mem_reclaim);
+
+
/*
* Set of default routines for initialising struct proto_ops when
* the protocol does not support a particular function. In certain
return -EOPNOTSUPP;
}
-int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
+int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
int len, int flags)
{
return -EOPNOTSUPP;
return -EOPNOTSUPP;
}
-int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
+int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
int *len, int peer)
{
return -EOPNOTSUPP;
read_lock(&sk->sk_callback_lock);
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep);
- sk_wake_async(sk,0,POLL_ERR);
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
read_unlock(&sk->sk_callback_lock);
}
read_lock(&sk->sk_callback_lock);
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep);
- sk_wake_async(sk,1,POLL_IN);
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
read_unlock(&sk->sk_callback_lock);
}
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
- if((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
+ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
- sk_wake_async(sk, 2, POLL_OUT);
+ sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
read_unlock(&sk->sk_callback_lock);
{
if (sk->sk_socket && sk->sk_socket->file)
if (send_sigurg(&sk->sk_socket->file->f_owner))
- sk_wake_async(sk, 3, POLL_PRI);
+ sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
void sk_reset_timer(struct sock *sk, struct timer_list* timer,
sk->sk_send_head = NULL;
init_timer(&sk->sk_timer);
-
+
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
sock_set_flag(sk, SOCK_ZAPPED);
- if(sock)
- {
+ if (sock) {
sk->sk_type = sock->type;
sk->sk_sleep = &sock->wait;
sock->sk = sk;
rwlock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
+ lockdep_set_class_and_name(&sk->sk_callback_lock,
+ af_callback_keys + sk->sk_family,
+ af_family_clock_key_strings[sk->sk_family]);
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
- sk->sk_stamp.tv_sec = -1L;
- sk->sk_stamp.tv_usec = -1L;
+ sk->sk_stamp = ktime_set(-1L, -1L);
atomic_set(&sk->sk_refcnt, 1);
+ atomic_set(&sk->sk_drops, 0);
}
-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));
- if (sk->sk_lock.owner)
+ spin_lock_bh(&sk->sk_lock.slock);
+ if (sk->sk_lock.owned)
__lock_sock(sk);
- sk->sk_lock.owner = (void *)1;
- spin_unlock_bh(&(sk->sk_lock.slock));
+ sk->sk_lock.owned = 1;
+ 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));
+ sk->sk_lock.owned = 0;
+ if (waitqueue_active(&sk->sk_lock.wq))
+ wake_up(&sk->sk_lock.wq);
+ spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);
int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
-{
+{
+ struct timeval tv;
if (!sock_flag(sk, SOCK_TIMESTAMP))
sock_enable_timestamp(sk);
- if (sk->sk_stamp.tv_sec == -1)
+ tv = ktime_to_timeval(sk->sk_stamp);
+ if (tv.tv_sec == -1)
return -ENOENT;
- if (sk->sk_stamp.tv_sec == 0)
- do_gettimeofday(&sk->sk_stamp);
- return copy_to_user(userstamp, &sk->sk_stamp, sizeof(struct timeval)) ?
- -EFAULT : 0;
-}
+ if (tv.tv_sec == 0) {
+ sk->sk_stamp = ktime_get_real();
+ tv = ktime_to_timeval(sk->sk_stamp);
+ }
+ return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
+}
EXPORT_SYMBOL(sock_get_timestamp);
+int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
+{
+ struct timespec ts;
+ if (!sock_flag(sk, SOCK_TIMESTAMP))
+ sock_enable_timestamp(sk);
+ ts = ktime_to_timespec(sk->sk_stamp);
+ if (ts.tv_sec == -1)
+ return -ENOENT;
+ if (ts.tv_sec == 0) {
+ sk->sk_stamp = ktime_get_real();
+ ts = ktime_to_timespec(sk->sk_stamp);
+ }
+ return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL(sock_get_timestampns);
+
void sock_enable_timestamp(struct sock *sk)
-{
- if (!sock_flag(sk, SOCK_TIMESTAMP)) {
+{
+ if (!sock_flag(sk, SOCK_TIMESTAMP)) {
sock_set_flag(sk, SOCK_TIMESTAMP);
net_enable_timestamp();
}
}
-EXPORT_SYMBOL(sock_enable_timestamp);
/*
* Get a socket option on an socket.
{
struct sock *sk = sock->sk;
- if (sk->sk_prot->compat_setsockopt != NULL)
+ 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);
{
char *request_sock_slab_name = NULL;
char *timewait_sock_slab_name;
- int rc = -ENOBUFS;
+
+ if (sock_prot_inuse_init(prot) != 0) {
+ printk(KERN_CRIT "%s: Can't alloc inuse counters!\n", prot->name);
+ goto out;
+ }
if (alloc_slab) {
prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
+ SLAB_HWCACHE_ALIGN, NULL);
if (prot->slab == NULL) {
printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n",
prot->name);
- goto out;
+ goto out_free_inuse;
}
if (prot->rsk_prot != NULL) {
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);
+ SLAB_HWCACHE_ALIGN, NULL);
if (prot->rsk_prot->slab == NULL) {
printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
kmem_cache_create(timewait_sock_slab_name,
prot->twsk_prot->twsk_obj_size,
0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ NULL);
if (prot->twsk_prot->twsk_slab == NULL)
goto out_free_timewait_sock_slab_name;
}
write_lock(&proto_list_lock);
list_add(&prot->node, &proto_list);
write_unlock(&proto_list_lock);
- rc = 0;
-out:
- return rc;
+ return 0;
+
out_free_timewait_sock_slab_name:
kfree(timewait_sock_slab_name);
out_free_request_sock_slab:
out_free_sock_slab:
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
- goto out;
+out_free_inuse:
+ sock_prot_inuse_free(prot);
+out:
+ return -ENOBUFS;
}
EXPORT_SYMBOL(proto_register);
list_del(&prot->node);
write_unlock(&proto_list_lock);
+ sock_prot_inuse_free(prot);
+
if (prot->slab != NULL) {
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
EXPORT_SYMBOL(proto_unregister);
#ifdef CONFIG_PROC_FS
-static inline struct proto *__proto_head(void)
-{
- return list_entry(proto_list.next, struct proto, node);
-}
-
-static inline struct proto *proto_head(void)
-{
- return list_empty(&proto_list) ? NULL : __proto_head();
-}
-
-static inline struct proto *proto_next(struct proto *proto)
-{
- return proto->node.next == &proto_list ? NULL :
- list_entry(proto->node.next, struct proto, node);
-}
-
-static inline struct proto *proto_get_idx(loff_t pos)
-{
- struct proto *proto;
- loff_t i = 0;
-
- list_for_each_entry(proto, &proto_list, node)
- if (i++ == pos)
- goto out;
-
- proto = NULL;
-out:
- return proto;
-}
-
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(proto_list_lock)
{
read_lock(&proto_list_lock);
- return *pos ? proto_get_idx(*pos - 1) : SEQ_START_TOKEN;
+ return seq_list_start_head(&proto_list, *pos);
}
static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- ++*pos;
- return v == SEQ_START_TOKEN ? proto_head() : proto_next(v);
+ return seq_list_next(v, &proto_list, pos);
}
static void proto_seq_stop(struct seq_file *seq, void *v)
+ __releases(proto_list_lock)
{
read_unlock(&proto_list_lock);
}
static int proto_seq_show(struct seq_file *seq, void *v)
{
- if (v == SEQ_START_TOKEN)
+ if (v == &proto_list)
seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
"protocol",
"size",
"module",
"cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
else
- proto_seq_printf(seq, v);
+ proto_seq_printf(seq, list_entry(v, struct proto, node));
return 0;
}
-static struct seq_operations proto_seq_ops = {
+static const struct seq_operations proto_seq_ops = {
.start = proto_seq_start,
.next = proto_seq_next,
.stop = proto_seq_stop,
return seq_open(file, &proto_seq_ops);
}
-static struct file_operations proto_seq_fops = {
+static const struct file_operations proto_seq_fops = {
.owner = THIS_MODULE,
.open = proto_seq_open,
.read = seq_read,
static int __init proto_init(void)
{
/* register /proc/net/protocols */
- return proc_net_fops_create("protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0;
+ return proc_net_fops_create(&init_net, "protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0;
}
subsys_initcall(proto_init);
EXPORT_SYMBOL(sock_i_uid);
EXPORT_SYMBOL(sock_i_ino);
EXPORT_SYMBOL(sysctl_optmem_max);
-#ifdef CONFIG_SYSCTL
-EXPORT_SYMBOL(sysctl_rmem_max);
-EXPORT_SYMBOL(sysctl_wmem_max);
-#endif