diff options
Diffstat (limited to 'net/core/sock.c')
| -rw-r--r-- | net/core/sock.c | 1649 |
1 files changed, 1236 insertions, 413 deletions
diff --git a/net/core/sock.c b/net/core/sock.c index 2654c147c00..026e01f7027 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -7,8 +7,6 @@ * handler for protocols to use and generic option handler. * * - * Version: $Id: sock.c,v 1.117 2002/02/01 22:01:03 davem Exp $ - * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> @@ -91,8 +89,11 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/errno.h> +#include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> @@ -112,9 +113,12 @@ #include <linux/tcp.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/user_namespace.h> +#include <linux/static_key.h> +#include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/netdevice.h> #include <net/protocol.h> @@ -122,15 +126,111 @@ #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> +#include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> +#include <net/cls_cgroup.h> +#include <net/netprio_cgroup.h> #include <linux/filter.h> +#include <trace/events/sock.h> + #ifdef CONFIG_INET #include <net/tcp.h> #endif +#include <net/busy_poll.h> + +static DEFINE_MUTEX(proto_list_mutex); +static LIST_HEAD(proto_list); + +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + +#ifdef CONFIG_MEMCG_KMEM +int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) +{ + struct proto *proto; + int ret = 0; + + mutex_lock(&proto_list_mutex); + list_for_each_entry(proto, &proto_list, node) { + if (proto->init_cgroup) { + ret = proto->init_cgroup(memcg, ss); + if (ret) + goto out; + } + } + + mutex_unlock(&proto_list_mutex); + return ret; +out: + list_for_each_entry_continue_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); + return ret; +} + +void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) +{ + struct proto *proto; + + mutex_lock(&proto_list_mutex); + list_for_each_entry_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); +} +#endif + /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -138,13 +238,17 @@ 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 +#if defined(CONFIG_MEMCG_KMEM) +struct static_key memcg_socket_limit_enabled; +EXPORT_SYMBOL(memcg_socket_limit_enabled); +#endif + /* * 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] = { +static const char *const 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" , @@ -152,13 +256,15 @@ static const char *af_family_key_strings[AF_MAX+1] = { "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_RDS" , "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" + "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , + "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , + "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX" }; -static const char *af_family_slock_key_strings[AF_MAX+1] = { +static const char *const 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" , @@ -166,13 +272,15 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "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_RDS" , "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" + "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , + "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , + "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX" }; -static const char *af_family_clock_key_strings[AF_MAX+1] = { +static const char *const 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" , @@ -180,13 +288,14 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = { "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_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-29" , + "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , - "clock-AF_RXRPC" , "clock-AF_MAX" + "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , + "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , + "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX" }; -#endif /* * sk_callback_lock locking rules are per-address-family, @@ -200,18 +309,76 @@ static struct lock_class_key af_callback_keys[AF_MAX]; * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 -#define _SK_MEM_OVERHEAD (sizeof(struct sk_buff) + 256) +#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +EXPORT_SYMBOL(sysctl_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 */ +/* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); +EXPORT_SYMBOL(sysctl_optmem_max); + +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -228,11 +395,11 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) static int warned __read_mostly; *timeo_p = 0; - if (warned < 10 && net_ratelimit()) + 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)); + pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", + __func__, current->comm, task_pid_nr(current)); + } return 0; } *timeo_p = MAX_SCHEDULE_TIMEOUT; @@ -249,42 +416,44 @@ static void sock_warn_obsolete_bsdism(const char *name) static char warncomm[TASK_COMM_LEN]; 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); + pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", + warncomm, name); warned++; } } -static void sock_disable_timestamp(struct sock *sk) +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + +static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { - if (sock_flag(sk, SOCK_TIMESTAMP)) { - sock_reset_flag(sk, SOCK_TIMESTAMP); - net_disable_timestamp(); + if (sk->sk_flags & flags) { + sk->sk_flags &= ~flags; + if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP)) + net_disable_timestamp(); } } int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int err = 0; + int err; int skb_len; + unsigned long flags; + struct sk_buff_head *list = &sk->sk_receive_queue; - /* 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; + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + atomic_inc(&sk->sk_drops); + trace_sock_rcvqueue_full(sk, skb); + return -ENOMEM; } err = sk_filter(sk, skb); if (err) - goto out; + return err; - if (!sk_rmem_schedule(sk, skb->truesize)) { - err = -ENOBUFS; - goto out; + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { + atomic_inc(&sk->sk_drops); + return -ENOBUFS; } skb->dev = NULL; @@ -297,12 +466,19 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ skb_len = skb->len; - skb_queue_tail(&sk->sk_receive_queue, skb); + /* we escape from rcu protected region, make sure we dont leak + * a norefcounted dst + */ + skb_dst_force(skb); + + spin_lock_irqsave(&list->lock, flags); + skb->dropcount = atomic_read(&sk->sk_drops); + __skb_queue_tail(list, skb); + spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); -out: - return err; + sk->sk_data_ready(sk); + return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -315,6 +491,10 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } if (nested) bh_lock_sock_nested(sk); else @@ -325,11 +505,15 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); - rc = sk->sk_backlog_rcv(sk, skb); + rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else - sk_add_backlog(sk, skb); + } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + bh_unlock_sock(sk); + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } + bh_unlock_sock(sk); out: sock_put(sk); @@ -342,10 +526,11 @@ EXPORT_SYMBOL(sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst = sk->sk_dst_cache; + struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - sk->sk_dst_cache = NULL; + sk_tx_queue_clear(sk); + RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -368,17 +553,18 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; /* Sorry... */ ret = -EPERM; - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; @@ -398,17 +584,18 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) 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); + index = 0; + if (devname[0] != '\0') { + struct net_device *dev; + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, devname); + if (dev) + index = dev->ifindex; + rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; - - index = dev->ifindex; - dev_put(dev); } lock_sock(sk); @@ -424,6 +611,46 @@ out: return ret; } +static int sock_getbindtodevice(struct sock *sk, char __user *optval, + int __user *optlen, int len) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + + if (sk->sk_bound_dev_if == 0) { + len = 0; + goto zero; + } + + ret = -EINVAL; + if (len < IFNAMSIZ) + goto out; + + ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); + if (ret) + goto out; + + len = strlen(devname) + 1; + + ret = -EFAULT; + if (copy_to_user(optval, devname, len)) + goto out; + +zero: + ret = -EFAULT; + if (put_user(len, optlen)) + goto out; + + ret = 0; + +out: +#endif + + return ret; +} + static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) { if (valbool) @@ -438,9 +665,9 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) */ int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { - struct sock *sk=sock->sk; + struct sock *sk = sock->sk; int val; int valbool; struct linger ling; @@ -450,17 +677,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname, * Options without arguments */ -#ifdef SO_DONTLINGER /* Compatibility item... */ - if (optname == SO_DONTLINGER) { - lock_sock(sk); - sock_reset_flag(sk, SOCK_LINGER); - release_sock(sk); - return 0; - } -#endif - if (optname == SO_BINDTODEVICE) - return sock_bindtodevice(sk, optval, optlen); + return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; @@ -468,21 +686,26 @@ int sock_setsockopt(struct socket *sock, int level, int optname, if (get_user(val, (int __user *)optval)) return -EFAULT; - valbool = val?1:0; + valbool = val ? 1 : 0; lock_sock(sk); - switch(optname) { + switch (optname) { case SO_DEBUG: - if (val && !capable(CAP_NET_ADMIN)) { + if (val && !capable(CAP_NET_ADMIN)) ret = -EACCES; - } else + else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: - sk->sk_reuse = valbool; + sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; break; case SO_TYPE: + case SO_PROTOCOL: + case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; break; @@ -494,23 +717,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname, 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; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, 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; - - /* - * Wake up sending tasks if we - * upped the value. - */ + sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -523,12 +738,11 @@ 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; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_rmem_max); set_rcvbuf: sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* @@ -546,10 +760,7 @@ set_rcvbuf: * 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_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: @@ -561,7 +772,8 @@ set_rcvbuf: case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) tcp_set_keepalive(sk, valbool); #endif sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); @@ -572,11 +784,12 @@ set_rcvbuf: break; case SO_NO_CHECK: - sk->sk_no_check = valbool; + sk->sk_no_check_tx = valbool; break; case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) + if ((val >= 0 && val <= 6) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; @@ -587,7 +800,7 @@ set_rcvbuf: ret = -EINVAL; /* 1003.1g */ break; } - if (copy_from_user(&ling,optval,sizeof(ling))) { + if (copy_from_user(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } @@ -623,13 +836,38 @@ set_rcvbuf: else sock_set_flag(sk, SOCK_RCVTSTAMPNS); sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } break; + case SO_TIMESTAMPING: + if (val & ~SOF_TIMESTAMPING_MASK) { + ret = -EINVAL; + break; + } + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, + val & SOF_TIMESTAMPING_TX_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE, + val & SOF_TIMESTAMPING_TX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE, + val & SOF_TIMESTAMPING_RX_HARDWARE); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, + val & SOF_TIMESTAMPING_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, + val & SOF_TIMESTAMPING_SYS_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE, + val & SOF_TIMESTAMPING_RAW_HARDWARE); + break; + case SO_RCVLOWAT: if (val < 0) val = INT_MAX; @@ -661,6 +899,13 @@ set_rcvbuf: ret = sk_detach_filter(sk); break; + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); @@ -668,15 +913,57 @@ set_rcvbuf: clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) ret = -EPERM; - else { + else sk->sk_mark = val; - } break; /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ + case SO_RXQ_OVFL: + sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); + break; + + case SO_WIFI_STATUS: + sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); + break; + + case SO_PEEK_OFF: + if (sock->ops->set_peek_off) + ret = sock->ops->set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + break; + + case SO_NOFCS: + sock_valbool_flag(sk, SOCK_NOFCS, valbool); + break; + + case SO_SELECT_ERR_QUEUE: + sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); + break; + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + /* allow unprivileged users to decrease the value */ + if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else { + if (val < 0) + ret = -EINVAL; + else + sk->sk_ll_usec = val; + } + break; +#endif + + case SO_MAX_PACING_RATE: + sk->sk_max_pacing_rate = val; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, + sk->sk_max_pacing_rate); + break; + default: ret = -ENOPROTOOPT; break; @@ -684,7 +971,21 @@ set_rcvbuf: release_sock(sk); return ret; } +EXPORT_SYMBOL(sock_setsockopt); + +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) +{ + ucred->pid = pid_vnr(pid); + ucred->uid = ucred->gid = -1; + if (cred) { + struct user_namespace *current_ns = current_user_ns(); + + ucred->uid = from_kuid_munged(current_ns, cred->euid); + ucred->gid = from_kgid_munged(current_ns, cred->egid); + } +} int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) @@ -697,7 +998,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct timeval tm; } v; - unsigned int lv = sizeof(int); + int lv = sizeof(int); int len; if (get_user(len, optlen)) @@ -705,7 +1006,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len < 0) return -EINVAL; - switch(optname) { + memset(&v, 0, sizeof(v)); + + switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; @@ -715,7 +1018,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); + v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: @@ -730,26 +1033,38 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reuse; break; + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); + v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; + case SO_PROTOCOL: + v.val = sk->sk_protocol; + break; + + case SO_DOMAIN: + v.val = sk->sk_family; + break; + case SO_ERROR: v.val = -sock_error(sk); - if (v.val==0) + if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); + v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: - v.val = sk->sk_no_check; + v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: @@ -758,7 +1073,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_LINGER: lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); + v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = sk->sk_lingertime / HZ; break; @@ -775,8 +1090,26 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); break; + case SO_TIMESTAMPING: + v.val = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_TX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_TX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_RX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)) + v.val |= SOF_TIMESTAMPING_SYS_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RAW_HARDWARE; + break; + case SO_RCVTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -787,7 +1120,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -802,19 +1135,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDLOWAT: - v.val=1; + v.val = 1; break; case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) + { + struct ucred peercred; + if (len > sizeof(peercred)) + len = sizeof(peercred); + cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; + } case SO_PEERNAME: { @@ -837,7 +1174,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PASSSEC: - v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: @@ -847,6 +1184,56 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_mark; break; + case SO_RXQ_OVFL: + v.val = sock_flag(sk, SOCK_RXQ_OVFL); + break; + + case SO_WIFI_STATUS: + v.val = sock_flag(sk, SOCK_WIFI_STATUS); + break; + + case SO_PEEK_OFF: + if (!sock->ops->set_peek_off) + return -EOPNOTSUPP; + + v.val = sk->sk_peek_off; + break; + case SO_NOFCS: + v.val = sock_flag(sk, SOCK_NOFCS); + break; + + case SO_BINDTODEVICE: + return sock_getbindtodevice(sk, optval, optlen, len); + + case SO_GET_FILTER: + len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + if (len < 0) + return len; + + goto lenout; + + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + + case SO_SELECT_ERR_QUEUE: + v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); + break; + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + v.val = sk->sk_ll_usec; + break; +#endif + + case SO_MAX_PACING_RATE: + v.val = sk->sk_max_pacing_rate; + break; + default: return -ENOPROTOOPT; } @@ -875,19 +1262,45 @@ static inline void sock_lock_init(struct sock *sk) af_family_keys + sk->sk_family); } +/* + * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, + * even temporarly, because of RCU lookups. sk_node should also be left as is. + * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end + */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); + + memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); - memcpy(nsk, osk, osk->sk_prot->obj_size); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) +{ + unsigned long nulls1, nulls2; + + nulls1 = offsetof(struct sock, __sk_common.skc_node.next); + nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); + if (nulls1 > nulls2) + swap(nulls1, nulls2); + + if (nulls1 != 0) + memset((char *)sk, 0, nulls1); + memset((char *)sk + nulls1 + sizeof(void *), 0, + nulls2 - nulls1 - sizeof(void *)); + memset((char *)sk + nulls2 + sizeof(void *), 0, + size - nulls2 - sizeof(void *)); +} +EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); + static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { @@ -895,17 +1308,28 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, struct kmem_cache *slab; slab = prot->slab; - if (slab != NULL) - sk = kmem_cache_alloc(slab, priority); - else + if (slab != NULL) { + sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); + if (!sk) + return sk; + if (priority & __GFP_ZERO) { + if (prot->clear_sk) + prot->clear_sk(sk, prot->obj_size); + else + sk_prot_clear_nulls(sk, prot->obj_size); + } + } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { + kmemcheck_annotate_bitfield(sk, flags); + if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) goto out_free_sec; + sk_tx_queue_clear(sk); } return sk; @@ -936,13 +1360,23 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +void sock_update_netprioidx(struct sock *sk) +{ + if (in_interrupt()) + return; + + sk->sk_cgrp_prioidx = task_netprioidx(current); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); +#endif + /** * 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) @@ -958,36 +1392,90 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, */ sk->sk_prot = sk->sk_prot_creator = prot; sock_lock_init(sk); - sk->sk_net = get_net(net); + sock_net_set(sk, get_net(net)); + atomic_set(&sk->sk_wmem_alloc, 1); + + sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; } +EXPORT_SYMBOL(sk_alloc); -void sk_free(struct sock *sk) +static void __sk_free(struct sock *sk) { struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); - filter = rcu_dereference(sk->sk_filter); + filter = rcu_dereference_check(sk->sk_filter, + atomic_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); - rcu_assign_pointer(sk->sk_filter, NULL); + RCU_INIT_POINTER(sk->sk_filter, NULL); } - sock_disable_timestamp(sk); + sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); if (atomic_read(&sk->sk_omem_alloc)) - printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", - __FUNCTION__, atomic_read(&sk->sk_omem_alloc)); + pr_debug("%s: optmem leakage (%d bytes) detected\n", + __func__, atomic_read(&sk->sk_omem_alloc)); - put_net(sk->sk_net); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + put_pid(sk->sk_peer_pid); + put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +void sk_free(struct sock *sk) +{ + /* + * We subtract one from sk_wmem_alloc and can know if + * some packets are still in some tx queue. + * If not null, sock_wfree() will call __sk_free(sk) later + */ + if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + __sk_free(sk); +} +EXPORT_SYMBOL(sk_free); + +/* + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace + * is not an option. + * Take reference to a socket to remove it from hash _alive_ and after that + * destroy it in the context of init_net. + */ +void sk_release_kernel(struct sock *sk) +{ + if (sk == NULL || sk->sk_socket == NULL) + return; + + sock_hold(sk); + sock_release(sk->sk_socket); + release_net(sock_net(sk)); + sock_net_set(sk, get_net(&init_net)); + sock_put(sk); +} +EXPORT_SYMBOL(sk_release_kernel); + +static void sk_update_clone(const struct sock *sk, struct sock *newsk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_update_memcg(newsk); +} + +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; @@ -998,14 +1486,18 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); /* SANITY */ - get_net(newsk->sk_net); + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; + newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); - atomic_set(&newsk->sk_wmem_alloc, 0); + /* + * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) + */ + atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); skb_queue_head_init(&newsk->sk_receive_queue); skb_queue_head_init(&newsk->sk_write_queue); @@ -1013,7 +1505,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) skb_queue_head_init(&newsk->sk_async_wait_queue); #endif - rwlock_init(&newsk->sk_dst_lock); + spin_lock_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, @@ -1028,7 +1520,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sock_reset_flag(newsk, SOCK_DONE); skb_queue_head_init(&newsk->sk_error_queue); - filter = newsk->sk_filter; + filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) sk_filter_charge(newsk, filter); @@ -1036,6 +1528,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; @@ -1043,6 +1536,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_err = 0; newsk->sk_priority = 0; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&newsk->sk_refcnt, 2); /* @@ -1057,17 +1555,21 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) * to be taken into account in all callers. -acme */ sk_refcnt_debug_inc(newsk); - newsk->sk_socket = NULL; - newsk->sk_sleep = NULL; + sk_set_socket(newsk, NULL); + newsk->sk_wq = NULL; + + sk_update_clone(sk, newsk); if (newsk->sk_prot->sockets_allocated) - atomic_inc(newsk->sk_prot->sockets_allocated); + sk_sockets_allocated_inc(newsk); + + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); } out: return newsk; } - -EXPORT_SYMBOL_GPL(sk_clone); +EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { @@ -1075,28 +1577,19 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; + sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { - if (dst->header_len) + if (dst->header_len) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - else + } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; + sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; + } } } EXPORT_SYMBOL_GPL(sk_setup_caps); -void __init sk_init(void) -{ - if (num_physpages <= 4096) { - sysctl_wmem_max = 32767; - sysctl_rmem_max = 32767; - sysctl_wmem_default = 32767; - sysctl_rmem_default = 32767; - } else if (num_physpages >= 131072) { - sysctl_wmem_max = 131071; - sysctl_rmem_max = 131071; - } -} - /* * Simple resource managers for sockets. */ @@ -1108,13 +1601,44 @@ void __init sk_init(void) void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + unsigned int len = skb->truesize; - /* In case it might be waiting for more memory. */ - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); - if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) + if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { + /* + * Keep a reference on sk_wmem_alloc, this will be released + * after sk_write_space() call + */ + atomic_sub(len - 1, &sk->sk_wmem_alloc); sk->sk_write_space(sk); - sock_put(sk); + len = 1; + } + /* + * if sk_wmem_alloc reaches 0, we must finish what sk_free() + * could not do because of in-flight packets + */ + if (atomic_sub_and_test(len, &sk->sk_wmem_alloc)) + __sk_free(sk); } +EXPORT_SYMBOL(sock_wfree); + +void skb_orphan_partial(struct sk_buff *skb) +{ + /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, + * so we do not completely orphan skb, but transfert all + * accounted bytes but one, to avoid unexpected reorders. + */ + if (skb->destructor == sock_wfree +#ifdef CONFIG_INET + || skb->destructor == tcp_wfree +#endif + ) { + atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); + skb->truesize = 1; + } else { + skb_orphan(skb); + } +} +EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. @@ -1122,32 +1646,47 @@ void sock_wfree(struct sk_buff *skb) void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + unsigned int len = skb->truesize; - skb_truesize_check(skb); - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - sk_mem_uncharge(skb->sk, skb->truesize); + atomic_sub(len, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, len); } +EXPORT_SYMBOL(sock_rfree); + +void sock_edemux(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; +#ifdef CONFIG_INET + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else +#endif + sock_put(sk); +} +EXPORT_SYMBOL(sock_edemux); -int sock_i_uid(struct sock *sk) +kuid_t sock_i_uid(struct sock *sk) { - int uid; + kuid_t uid; - read_lock(&sk->sk_callback_lock); - uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); + uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; + read_unlock_bh(&sk->sk_callback_lock); return uid; } +EXPORT_SYMBOL(sock_i_uid); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } +EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. @@ -1156,37 +1695,22 @@ 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); - if (skb) { - skb_set_owner_w(skb, sk); - return skb; - } - } - return NULL; -} - -/* - * 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) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { - skb_set_owner_r(skb, sk); + skb_set_owner_w(skb, sk); return skb; } } return NULL; } +EXPORT_SYMBOL(sock_wmalloc); /* * 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 && + if ((unsigned int)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 @@ -1200,6 +1724,7 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } return NULL; } +EXPORT_SYMBOL(sock_kmalloc); /* * Free an option memory block. @@ -1209,11 +1734,12 @@ void sock_kfree_s(struct sock *sk, void *mem, int size) kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } +EXPORT_SYMBOL(sock_kfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ -static long sock_wait_for_wmem(struct sock * sk, long timeo) +static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); @@ -1224,7 +1750,7 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) @@ -1233,7 +1759,7 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) break; timeo = schedule_timeout(timeo); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } @@ -1242,22 +1768,25 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) * Generic send/receive buffer handlers */ -static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, - unsigned long header_len, - unsigned long data_len, - int noblock, int *errcode) +struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, + unsigned long data_len, int noblock, + int *errcode, int max_page_order) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned long chunk; gfp_t gfp_mask; long timeo; int err; + int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; + struct page *page; + int i; - gfp_mask = sk->sk_allocation; - if (gfp_mask & __GFP_WAIT) - gfp_mask |= __GFP_REPEAT; + err = -EMSGSIZE; + if (npages > MAX_SKB_FRAGS) + goto failure; timeo = sock_sndtimeo(sk, noblock); - while (1) { + while (!skb) { err = sock_error(sk); if (err != 0) goto failure; @@ -1266,54 +1795,54 @@ static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - skb = alloc_skb(header_len, gfp_mask); - if (skb) { - int npages; - int i; - - /* No pages, we're done... */ - if (!data_len) - break; - - npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; - skb->truesize += data_len; - skb_shinfo(skb)->nr_frags = npages; - for (i = 0; i < npages; i++) { - struct page *page; - skb_frag_t *frag; - - page = alloc_pages(sk->sk_allocation, 0); - if (!page) { - err = -ENOBUFS; - skb_shinfo(skb)->nr_frags = i; - kfree_skb(skb); - goto failure; - } - - frag = &skb_shinfo(skb)->frags[i]; - frag->page = page; - frag->page_offset = 0; - frag->size = (data_len >= PAGE_SIZE ? - PAGE_SIZE : - data_len); - data_len -= PAGE_SIZE; - } + if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) { + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = -EAGAIN; + if (!timeo) + goto failure; + if (signal_pending(current)) + goto interrupted; + timeo = sock_wait_for_wmem(sk, timeo); + continue; + } - /* Full success... */ - break; - } - err = -ENOBUFS; + err = -ENOBUFS; + gfp_mask = sk->sk_allocation; + if (gfp_mask & __GFP_WAIT) + gfp_mask |= __GFP_REPEAT; + + skb = alloc_skb(header_len, gfp_mask); + if (!skb) goto failure; + + skb->truesize += data_len; + + for (i = 0; npages > 0; i++) { + int order = max_page_order; + + while (order) { + if (npages >= 1 << order) { + page = alloc_pages(sk->sk_allocation | + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, + order); + if (page) + goto fill_page; + } + order--; + } + page = alloc_page(sk->sk_allocation); + if (!page) + goto failure; +fill_page: + chunk = min_t(unsigned long, data_len, + PAGE_SIZE << order); + skb_fill_page_desc(skb, i, page, 0, chunk); + data_len -= chunk; + npages -= 1 << order; } - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - err = -EAGAIN; - if (!timeo) - goto failure; - if (signal_pending(current)) - goto interrupted; - timeo = sock_wait_for_wmem(sk, timeo); } skb_set_owner_w(skb, sk); @@ -1322,17 +1851,78 @@ static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, interrupted: err = sock_intr_errno(timeo); failure: + kfree_skb(skb); *errcode = err; return NULL; } +EXPORT_SYMBOL(sock_alloc_send_pskb); 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); + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } +EXPORT_SYMBOL(sock_alloc_send_skb); + +/* On 32bit arches, an skb frag is limited to 2^15 */ +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +/** + * skb_page_frag_refill - check that a page_frag contains enough room + * @sz: minimum size of the fragment we want to get + * @pfrag: pointer to page_frag + * @prio: priority for memory allocation + * + * Note: While this allocator tries to use high order pages, there is + * no guarantee that allocations succeed. Therefore, @sz MUST be + * less or equal than PAGE_SIZE. + */ +bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) +{ + int order; + + if (pfrag->page) { + if (atomic_read(&pfrag->page->_count) == 1) { + pfrag->offset = 0; + return true; + } + if (pfrag->offset + sz <= pfrag->size) + return true; + put_page(pfrag->page); + } + + order = SKB_FRAG_PAGE_ORDER; + do { + gfp_t gfp = prio; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + pfrag->page = alloc_pages(gfp, order); + if (likely(pfrag->page)) { + pfrag->offset = 0; + pfrag->size = PAGE_SIZE << order; + return true; + } + } while (--order >= 0); + + return false; +} +EXPORT_SYMBOL(skb_page_frag_refill); + +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) +{ + if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) + return true; + + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; +} +EXPORT_SYMBOL(sk_page_frag_refill); static void __lock_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); @@ -1349,6 +1939,8 @@ static void __lock_sock(struct sock *sk) } static void __release_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { struct sk_buff *skb = sk->sk_backlog.head; @@ -1359,8 +1951,10 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + prefetch(next); + WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; - sk->sk_backlog_rcv(sk, skb); + sk_backlog_rcv(sk, skb); /* * We are in process context here with softirqs @@ -1375,6 +1969,12 @@ static void __release_sock(struct sock *sk) bh_lock_sock(sk); } while ((skb = sk->sk_backlog.head) != NULL); + + /* + * Doing the zeroing here guarantee we can not loop forever + * while a wild producer attempts to flood us. + */ + sk->sk_backlog.len = 0; } /** @@ -1392,14 +1992,13 @@ int sk_wait_data(struct sock *sk, long *timeo) int rc; DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } - EXPORT_SYMBOL(sk_wait_data); /** @@ -1416,31 +2015,35 @@ 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; + long allocated; + int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = atomic_add_return(amt, prot->memory_allocated); + + allocated = sk_memory_allocated_add(sk, amt, &parent_status); /* Under limit. */ - if (allocated <= prot->sysctl_mem[0]) { - if (prot->memory_pressure && *prot->memory_pressure) - *prot->memory_pressure = 0; + if (parent_status == UNDER_LIMIT && + allocated <= sk_prot_mem_limits(sk, 0)) { + sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. */ - if (allocated > prot->sysctl_mem[1]) - if (prot->enter_memory_pressure) - prot->enter_memory_pressure(); + /* Under pressure. (we or our parents) */ + if ((parent_status > SOFT_LIMIT) || + allocated > sk_prot_mem_limits(sk, 1)) + sk_enter_memory_pressure(sk); - /* Over hard limit. */ - if (allocated > prot->sysctl_mem[2]) + /* Over hard limit (we or our parents) */ + if ((parent_status == OVER_LIMIT) || + (allocated > sk_prot_mem_limits(sk, 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]) @@ -1450,9 +2053,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) return 1; } - if (prot->memory_pressure) { - if (!*prot->memory_pressure || - prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) * + if (sk_has_memory_pressure(sk)) { + int alloc; + + if (!sk_under_memory_pressure(sk)) + return 1; + alloc = sk_sockets_allocated_read_positive(sk); + if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) @@ -1471,12 +2078,15 @@ suppress_allocation: return 1; } + trace_sock_exceed_buf_limit(sk, prot, allocated); + /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - atomic_sub(amt, prot->memory_allocated); + + sk_memory_allocated_sub(sk, amt); + return 0; } - EXPORT_SYMBOL(__sk_mem_schedule); /** @@ -1485,17 +2095,14 @@ EXPORT_SYMBOL(__sk_mem_schedule); */ 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_memory_allocated_sub(sk, + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); 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; + if (sk_under_memory_pressure(sk) && + (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) + sk_leave_memory_pressure(sk); } - EXPORT_SYMBOL(__sk_mem_reclaim); @@ -1510,78 +2117,92 @@ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int *len, int peer) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getname); -unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt) +unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) { return 0; } +EXPORT_SYMBOL(sock_no_poll); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_setsockopt); int sock_no_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getsockopt); int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } +EXPORT_SYMBOL(sock_no_mmap); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1595,6 +2216,7 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz kunmap(page); return res; } +EXPORT_SYMBOL(sock_no_sendpage); /* * Default Socket Callbacks @@ -1602,47 +2224,61 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz static void sock_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_all(sk->sk_sleep); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk, int len) +static void sock_def_readable(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | + POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_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 (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | + POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) @@ -1656,6 +2292,7 @@ void sk_send_sigurg(struct sock *sk) if (send_sigurg(&sk->sk_socket->file->f_owner)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } +EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) @@ -1663,15 +2300,13 @@ void sk_reset_timer(struct sock *sk, struct timer_list* timer, if (!mod_timer(timer, expires)) sock_hold(sk); } - EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) __sock_put(sk); } - EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) @@ -1691,18 +2326,18 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_rcvbuf = sysctl_rmem_default; sk->sk_sndbuf = sysctl_wmem_default; sk->sk_state = TCP_CLOSE; - sk->sk_socket = sock; + sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; - sk->sk_sleep = &sock->wait; + sk->sk_wq = sock->wq; sock->sk = sk; } else - sk->sk_sleep = NULL; + sk->sk_wq = NULL; - rwlock_init(&sk->sk_dst_lock); + spin_lock_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, @@ -1714,22 +2349,35 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + sk->sk_peek_off = -1; - sk->sk_peercred.pid = 0; - sk->sk_peercred.uid = -1; - sk->sk_peercred.gid = -1; + sk->sk_peer_pid = NULL; + sk->sk_peer_cred = NULL; sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; - sk->sk_stamp = ktime_set(-1L, -1L); + sk->sk_stamp = ktime_set(-1L, 0); + +#ifdef CONFIG_NET_RX_BUSY_POLL + sk->sk_napi_id = 0; + sk->sk_ll_usec = sysctl_net_busy_read; +#endif + sk->sk_max_pacing_rate = ~0U; + sk->sk_pacing_rate = ~0U; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { @@ -1745,7 +2393,6 @@ void lock_sock_nested(struct sock *sk, int subclass) mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); } - EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) @@ -1758,18 +2405,58 @@ void release_sock(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); - sk->sk_lock.owned = 0; + + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken + * sk_lock.slock locked, owned = 0, BH disabled + * return true if slow path is taken + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +bool lock_sock_fast(struct sock *sk) +{ + might_sleep(); + spin_lock_bh(&sk->sk_lock.slock); + + if (!sk->sk_lock.owned) + /* + * Note : We must disable BH + */ + return false; + + __lock_sock(sk); + 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, 0, 0, _RET_IP_); + local_bh_enable(); + return true; +} +EXPORT_SYMBOL(lock_sock_fast); + int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); tv = ktime_to_timeval(sk->sk_stamp); if (tv.tv_sec == -1) return -ENOENT; @@ -1785,7 +2472,7 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) { struct timespec ts; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec(sk->sk_stamp); if (ts.tv_sec == -1) return -ENOENT; @@ -1797,14 +2484,68 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) } EXPORT_SYMBOL(sock_get_timestampns); -void sock_enable_timestamp(struct sock *sk) +void sock_enable_timestamp(struct sock *sk, int flag) { - if (!sock_flag(sk, SOCK_TIMESTAMP)) { - sock_set_flag(sk, SOCK_TIMESTAMP); - net_enable_timestamp(); + if (!sock_flag(sk, flag)) { + unsigned long previous_flags = sk->sk_flags; + + sock_set_flag(sk, flag); + /* + * we just set one of the two flags which require net + * time stamping, but time stamping might have been on + * already because of the other one + */ + if (!(previous_flags & SK_FLAGS_TIMESTAMP)) + net_enable_timestamp(); } } +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type) +{ + struct sock_exterr_skb *serr; + struct sk_buff *skb, *skb2; + int copied, err; + + err = -EAGAIN; + skb = skb_dequeue(&sk->sk_error_queue); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + serr = SKB_EXT_ERR(skb); + put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + + msg->msg_flags |= MSG_ERRQUEUE; + err = copied; + + /* Reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else + spin_unlock_bh(&sk->sk_error_queue.lock); + +out_free_skb: + kfree_skb(skb); +out: + return err; +} +EXPORT_SYMBOL(sock_recv_errqueue); + /* * Get a socket option on an socket. * @@ -1819,7 +2560,6 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_getsockopt); #ifdef CONFIG_COMPAT @@ -1849,25 +2589,23 @@ int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = addr_len; return err; } - EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); } - 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) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -1911,104 +2649,194 @@ void sk_common_release(struct sock *sk) xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + sock_put(sk); } - EXPORT_SYMBOL(sk_common_release); -static DEFINE_RWLOCK(proto_list_lock); -static LIST_HEAD(proto_list); +#ifdef CONFIG_PROC_FS +#define PROTO_INUSE_NR 64 /* should be enough for the first time */ +struct prot_inuse { + int val[PROTO_INUSE_NR]; +}; -int proto_register(struct proto *prot, int alloc_slab) +static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); + +#ifdef CONFIG_NET_NS +void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { - char *request_sock_slab_name = NULL; - char *timewait_sock_slab_name; + __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val); +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_add); - if (sock_prot_inuse_init(prot) != 0) { - printk(KERN_CRIT "%s: Can't alloc inuse counters!\n", prot->name); - goto out; +int sock_prot_inuse_get(struct net *net, struct proto *prot) +{ + int cpu, idx = prot->inuse_idx; + int res = 0; + + for_each_possible_cpu(cpu) + res += per_cpu_ptr(net->core.inuse, cpu)->val[idx]; + + return res >= 0 ? res : 0; +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_get); + +static int __net_init sock_inuse_init_net(struct net *net) +{ + net->core.inuse = alloc_percpu(struct prot_inuse); + return net->core.inuse ? 0 : -ENOMEM; +} + +static void __net_exit sock_inuse_exit_net(struct net *net) +{ + free_percpu(net->core.inuse); +} + +static struct pernet_operations net_inuse_ops = { + .init = sock_inuse_init_net, + .exit = sock_inuse_exit_net, +}; + +static __init int net_inuse_init(void) +{ + if (register_pernet_subsys(&net_inuse_ops)) + panic("Cannot initialize net inuse counters"); + + return 0; +} + +core_initcall(net_inuse_init); +#else +static DEFINE_PER_CPU(struct prot_inuse, prot_inuse); + +void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) +{ + __this_cpu_add(prot_inuse.val[prot->inuse_idx], val); +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_add); + +int sock_prot_inuse_get(struct net *net, struct proto *prot) +{ + int cpu, idx = prot->inuse_idx; + int res = 0; + + for_each_possible_cpu(cpu) + res += per_cpu(prot_inuse, cpu).val[idx]; + + return res >= 0 ? res : 0; +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_get); +#endif + +static void assign_proto_idx(struct proto *prot) +{ + prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); + + if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { + pr_err("PROTO_INUSE_NR exhausted\n"); + return; } + set_bit(prot->inuse_idx, proto_inuse_idx); +} + +static void release_proto_idx(struct proto *prot) +{ + if (prot->inuse_idx != PROTO_INUSE_NR - 1) + clear_bit(prot->inuse_idx, proto_inuse_idx); +} +#else +static inline void assign_proto_idx(struct proto *prot) +{ +} + +static inline void release_proto_idx(struct proto *prot) +{ +} +#endif + +int proto_register(struct proto *prot, int alloc_slab) +{ if (alloc_slab) { prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0, - SLAB_HWCACHE_ALIGN, NULL); + SLAB_HWCACHE_ALIGN | prot->slab_flags, + NULL); if (prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", - prot->name); - goto out_free_inuse; + pr_crit("%s: Can't create sock SLAB cache!\n", + 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) + prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); + if (prot->rsk_prot->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->slab = kmem_cache_create(prot->rsk_prot->slab_name, prot->rsk_prot->obj_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (prot->rsk_prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", - prot->name); + pr_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"; + prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); - timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL); - - if (timewait_sock_slab_name == NULL) + if (prot->twsk_prot->twsk_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, + kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, - 0, SLAB_HWCACHE_ALIGN, + 0, + SLAB_HWCACHE_ALIGN | + prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) goto out_free_timewait_sock_slab_name; } } - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_add(&prot->node, &proto_list); - write_unlock(&proto_list_lock); + assign_proto_idx(prot); + mutex_unlock(&proto_list_mutex); return 0; out_free_timewait_sock_slab_name: - kfree(timewait_sock_slab_name); + kfree(prot->twsk_prot->twsk_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); + if (prot->rsk_prot) + kfree(prot->rsk_prot->slab_name); out_free_sock_slab: kmem_cache_destroy(prot->slab); prot->slab = NULL; -out_free_inuse: - sock_prot_inuse_free(prot); out: return -ENOBUFS; } - EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); + release_proto_idx(prot); list_del(&prot->node); - write_unlock(&proto_list_lock); - - sock_prot_inuse_free(prot); + mutex_unlock(&proto_list_mutex); if (prot->slab != NULL) { kmem_cache_destroy(prot->slab); @@ -2016,29 +2844,24 @@ void proto_unregister(struct proto *prot) } 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); + kfree(prot->rsk_prot->slab_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); + kfree(prot->twsk_prot->twsk_slab_name); prot->twsk_prot->twsk_slab = NULL; } } - EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(proto_list_lock) + __acquires(proto_list_mutex) { - read_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } @@ -2048,25 +2871,36 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void proto_seq_stop(struct seq_file *seq, void *v) - __releases(proto_list_lock) + __releases(proto_list_mutex) { - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } +static long sock_prot_memory_allocated(struct proto *proto) +{ + return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; +} + +static char *sock_prot_memory_pressure(struct proto *proto) +{ + return proto->memory_pressure != NULL ? + proto_memory_pressure(proto) ? "yes" : "no" : "NI"; +} static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { - seq_printf(seq, "%-9s %4u %6d %6d %-3s %6u %-3s %-10s " + + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, - proto->sockets_allocated != NULL ? atomic_read(proto->sockets_allocated) : -1, - proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1, - proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", + sock_prot_inuse_get(seq_file_net(seq), proto), + sock_prot_memory_allocated(proto), + sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), @@ -2118,7 +2952,8 @@ static const struct seq_operations proto_seq_ops = { static int proto_seq_open(struct inode *inode, struct file *file) { - return seq_open(file, &proto_seq_ops); + return seq_open_net(inode, file, &proto_seq_ops, + sizeof(struct seq_net_private)); } static const struct file_operations proto_seq_fops = { @@ -2126,45 +2961,33 @@ static const struct file_operations proto_seq_fops = { .open = proto_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, +}; + +static __net_init int proto_init_net(struct net *net) +{ + if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops)) + return -ENOMEM; + + return 0; +} + +static __net_exit void proto_exit_net(struct net *net) +{ + remove_proc_entry("protocols", net->proc_net); +} + + +static __net_initdata struct pernet_operations proto_net_ops = { + .init = proto_init_net, + .exit = proto_exit_net, }; static int __init proto_init(void) { - /* register /proc/net/protocols */ - return proc_net_fops_create(&init_net, "protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0; + return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ - -EXPORT_SYMBOL(sk_alloc); -EXPORT_SYMBOL(sk_free); -EXPORT_SYMBOL(sk_send_sigurg); -EXPORT_SYMBOL(sock_alloc_send_skb); -EXPORT_SYMBOL(sock_init_data); -EXPORT_SYMBOL(sock_kfree_s); -EXPORT_SYMBOL(sock_kmalloc); -EXPORT_SYMBOL(sock_no_accept); -EXPORT_SYMBOL(sock_no_bind); -EXPORT_SYMBOL(sock_no_connect); -EXPORT_SYMBOL(sock_no_getname); -EXPORT_SYMBOL(sock_no_getsockopt); -EXPORT_SYMBOL(sock_no_ioctl); -EXPORT_SYMBOL(sock_no_listen); -EXPORT_SYMBOL(sock_no_mmap); -EXPORT_SYMBOL(sock_no_poll); -EXPORT_SYMBOL(sock_no_recvmsg); -EXPORT_SYMBOL(sock_no_sendmsg); -EXPORT_SYMBOL(sock_no_sendpage); -EXPORT_SYMBOL(sock_no_setsockopt); -EXPORT_SYMBOL(sock_no_shutdown); -EXPORT_SYMBOL(sock_no_socketpair); -EXPORT_SYMBOL(sock_rfree); -EXPORT_SYMBOL(sock_setsockopt); -EXPORT_SYMBOL(sock_wfree); -EXPORT_SYMBOL(sock_wmalloc); -EXPORT_SYMBOL(sock_i_uid); -EXPORT_SYMBOL(sock_i_ino); -EXPORT_SYMBOL(sysctl_optmem_max); |