diff options
Diffstat (limited to 'net/core/sock.c')
-rw-r--r-- | net/core/sock.c | 1488 |
1 files changed, 984 insertions, 504 deletions
diff --git a/net/core/sock.c b/net/core/sock.c index 8f71684305c3..a3ba0358c77c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -113,6 +113,7 @@ #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/compat.h> #include <linux/uaccess.h> @@ -138,10 +139,15 @@ #include <net/tcp.h> #include <net/busy_poll.h> +#include <linux/ethtool.h> + +#include "dev.h" + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -static void sock_inuse_add(struct net *net, int val); +static void sock_def_write_space_wfree(struct sock *sk); +static void sock_def_write_space(struct sock *sk); /** * sk_ns_capable - General socket capability test @@ -223,6 +229,7 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { @@ -323,14 +330,33 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); - ret = sk->sk_backlog_rcv(sk, skb); + ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv, + tcp_v6_do_rcv, + tcp_v4_do_rcv, + sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +void sk_error_report(struct sock *sk) +{ + sk->sk_error_report(sk); + + switch (sk->sk_family) { + case AF_INET: + fallthrough; + case AF_INET6: + trace_inet_sk_error_report(sk); + break; + default: + break; + } +} +EXPORT_SYMBOL(sk_error_report); + +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -359,36 +385,50 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; - if (copy_from_user(&tv32, optval, sizeof(tv32))) + if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; - if (copy_from_user(&old_tv, optval, sizeof(old_tv))) + if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_user(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; @@ -411,18 +451,6 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool return 0; } -static void sock_warn_obsolete_bsdism(const char *name) -{ - static int warned; - static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", - warncomm, name); - warned++; - } -} - static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -480,17 +508,35 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sock_queue_rcv_skb); -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason) { + enum skb_drop_reason drop_reason; int err; err = sk_filter(sk, skb); - if (err) - return err; - - return __sock_queue_rcv_skb(sk, skb); + if (err) { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + goto out; + } + err = __sock_queue_rcv_skb(sk, skb); + switch (err) { + case -ENOMEM: + drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; + break; + case -ENOBUFS: + drop_reason = SKB_DROP_REASON_PROTO_MEM; + break; + default: + drop_reason = SKB_NOT_DROPPED_YET; + break; + } +out: + if (reason) + *reason = drop_reason; + return err; } -EXPORT_SYMBOL(sock_queue_rcv_skb); +EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) @@ -536,11 +582,17 @@ discard_and_relse: } EXPORT_SYMBOL(__sk_receive_skb); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, + u32)); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (dst && dst->obsolete && + INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, + dst, cookie) == NULL) { sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; RCU_INIT_POINTER(sk->sk_dst_cache, NULL); @@ -556,7 +608,9 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (dst && dst->obsolete && + INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, + dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; @@ -566,7 +620,7 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_setbindtodevice_locked(struct sock *sk, int ifindex) +static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -574,14 +628,16 @@ static int sock_setbindtodevice_locked(struct sock *sk, int ifindex) /* Sorry... */ ret = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_RAW)) + if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; - sk->sk_bound_dev_if = ifindex; + /* Paired with all READ_ONCE() done locklessly. */ + WRITE_ONCE(sk->sk_bound_dev_if, ifindex); + if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); @@ -594,8 +650,21 @@ out: return ret; } -static int sock_setbindtodevice(struct sock *sk, char __user *optval, - int optlen) +int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) +{ + int ret; + + if (lock_sk) + lock_sock(sk); + ret = sock_bindtoindex_locked(sk, ifindex); + if (lock_sk) + release_sock(sk); + + return ret; +} +EXPORT_SYMBOL(sock_bindtoindex); + +static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -617,7 +686,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, memset(devname, 0, sizeof(devname)); ret = -EFAULT; - if (copy_from_user(devname, optval, optlen)) + if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; @@ -634,25 +703,25 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, goto out; } - lock_sock(sk); - ret = sock_setbindtodevice_locked(sk, index); - release_sock(sk); - + sockopt_lock_sock(sk); + ret = sock_bindtoindex_locked(sk, index); + sockopt_release_sock(sk); out: #endif return ret; } -static int sock_getbindtodevice(struct sock *sk, char __user *optval, - int __user *optlen, int len) +static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); struct net *net = sock_net(sk); char devname[IFNAMSIZ]; - if (sk->sk_bound_dev_if == 0) { + if (bound_dev_if == 0) { len = 0; goto zero; } @@ -661,19 +730,19 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval, if (len < IFNAMSIZ) goto out; - ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); + ret = netdev_get_name(net, devname, bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; - if (copy_to_user(optval, devname, len)) + if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; @@ -684,15 +753,6 @@ out: return ret; } -static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, - int valbool) -{ - if (valbool) - sock_set_flag(sk, bit); - else - sock_reset_flag(sk, bit); -} - bool sk_mc_loop(struct sock *sk) { if (dev_recursion_level()) @@ -707,21 +767,322 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); +void sock_set_reuseaddr(struct sock *sk) +{ + lock_sock(sk); + sk->sk_reuse = SK_CAN_REUSE; + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_reuseaddr); + +void sock_set_reuseport(struct sock *sk) +{ + lock_sock(sk); + sk->sk_reuseport = true; + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_reuseport); + +void sock_no_linger(struct sock *sk) +{ + lock_sock(sk); + sk->sk_lingertime = 0; + sock_set_flag(sk, SOCK_LINGER); + release_sock(sk); +} +EXPORT_SYMBOL(sock_no_linger); + +void sock_set_priority(struct sock *sk, u32 priority) +{ + lock_sock(sk); + sk->sk_priority = priority; + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_priority); + +void sock_set_sndtimeo(struct sock *sk, s64 secs) +{ + lock_sock(sk); + if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) + sk->sk_sndtimeo = secs * HZ; + else + sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_sndtimeo); + +static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) +{ + if (val) { + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); + sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns); + sock_set_flag(sk, SOCK_RCVTSTAMP); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); + } else { + sock_reset_flag(sk, SOCK_RCVTSTAMP); + sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + } +} + +void sock_enable_timestamps(struct sock *sk) +{ + lock_sock(sk); + __sock_set_timestamps(sk, true, false, true); + release_sock(sk); +} +EXPORT_SYMBOL(sock_enable_timestamps); + +void sock_set_timestamp(struct sock *sk, int optname, bool valbool) +{ + switch (optname) { + case SO_TIMESTAMP_OLD: + __sock_set_timestamps(sk, valbool, false, false); + break; + case SO_TIMESTAMP_NEW: + __sock_set_timestamps(sk, valbool, true, false); + break; + case SO_TIMESTAMPNS_OLD: + __sock_set_timestamps(sk, valbool, false, true); + break; + case SO_TIMESTAMPNS_NEW: + __sock_set_timestamps(sk, valbool, true, true); + break; + } +} + +static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) +{ + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + bool match = false; + int *vclock_index; + int i, num; + + if (sk->sk_bound_dev_if) + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + + if (!dev) { + pr_err("%s: sock not bind to device\n", __func__); + return -EOPNOTSUPP; + } + + num = ethtool_get_phc_vclocks(dev, &vclock_index); + dev_put(dev); + + for (i = 0; i < num; i++) { + if (*(vclock_index + i) == phc_index) { + match = true; + break; + } + } + + if (num > 0) + kfree(vclock_index); + + if (!match) + return -EINVAL; + + sk->sk_bind_phc = phc_index; + + return 0; +} + +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping) +{ + int val = timestamping.flags; + int ret; + + if (val & ~SOF_TIMESTAMPING_MASK) + return -EINVAL; + + if (val & SOF_TIMESTAMPING_OPT_ID && + !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { + if (sk_is_tcp(sk)) { + if ((1 << sk->sk_state) & + (TCPF_CLOSE | TCPF_LISTEN)) + return -EINVAL; + atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); + } else { + atomic_set(&sk->sk_tskey, 0); + } + } + + if (val & SOF_TIMESTAMPING_OPT_STATS && + !(val & SOF_TIMESTAMPING_OPT_TSONLY)) + return -EINVAL; + + if (val & SOF_TIMESTAMPING_BIND_PHC) { + ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); + if (ret) + return ret; + } + + sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + return 0; +} + +void sock_set_keepalive(struct sock *sk) +{ + lock_sock(sk); + if (sk->sk_prot->keepalive) + sk->sk_prot->keepalive(sk, true); + sock_valbool_flag(sk, SOCK_KEEPOPEN, true); + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_keepalive); + +static void __sock_set_rcvbuf(struct sock *sk, int val) +{ + /* Ensure val * 2 fits into an int, to prevent max_t() from treating it + * as a negative value. + */ + val = min_t(int, val, INT_MAX / 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. + */ + WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); +} + +void sock_set_rcvbuf(struct sock *sk, int val) +{ + lock_sock(sk); + __sock_set_rcvbuf(sk, val); + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_rcvbuf); + +static void __sock_set_mark(struct sock *sk, u32 val) +{ + if (val != sk->sk_mark) { + sk->sk_mark = val; + sk_dst_reset(sk); + } +} + +void sock_set_mark(struct sock *sk, u32 val) +{ + lock_sock(sk); + __sock_set_mark(sk, val); + release_sock(sk); +} +EXPORT_SYMBOL(sock_set_mark); + +static void sock_release_reserved_memory(struct sock *sk, int bytes) +{ + /* Round down bytes to multiple of pages */ + bytes = round_down(bytes, PAGE_SIZE); + + WARN_ON(bytes > sk->sk_reserved_mem); + sk->sk_reserved_mem -= bytes; + sk_mem_reclaim(sk); +} + +static int sock_reserve_memory(struct sock *sk, int bytes) +{ + long allocated; + bool charged; + int pages; + + if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk)) + return -EOPNOTSUPP; + + if (!bytes) + return 0; + + pages = sk_mem_pages(bytes); + + /* pre-charge to memcg */ + charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages, + GFP_KERNEL | __GFP_RETRY_MAYFAIL); + if (!charged) + return -ENOMEM; + + /* pre-charge to forward_alloc */ + sk_memory_allocated_add(sk, pages); + allocated = sk_memory_allocated(sk); + /* If the system goes into memory pressure with this + * precharge, give up and return error. + */ + if (allocated > sk_prot_mem_limits(sk, 1)) { + sk_memory_allocated_sub(sk, pages); + mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); + return -ENOMEM; + } + sk->sk_forward_alloc += pages << PAGE_SHIFT; + + sk->sk_reserved_mem += pages << PAGE_SHIFT; + + return 0; +} + +void sockopt_lock_sock(struct sock *sk) +{ + /* When current->bpf_ctx is set, the setsockopt is called from + * a bpf prog. bpf has ensured the sk lock has been + * acquired before calling setsockopt(). + */ + if (has_current_bpf_ctx()) + return; + + lock_sock(sk); +} +EXPORT_SYMBOL(sockopt_lock_sock); + +void sockopt_release_sock(struct sock *sk) +{ + if (has_current_bpf_ctx()) + return; + + release_sock(sk); +} +EXPORT_SYMBOL(sockopt_release_sock); + +bool sockopt_ns_capable(struct user_namespace *ns, int cap) +{ + return has_current_bpf_ctx() || ns_capable(ns, cap); +} +EXPORT_SYMBOL(sockopt_ns_capable); + +bool sockopt_capable(int cap) +{ + return has_current_bpf_ctx() || capable(cap); +} +EXPORT_SYMBOL(sockopt_capable); + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ -int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, unsigned int optlen) +int sk_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen) { + struct so_timestamping timestamping; + struct socket *sock = sk->sk_socket; struct sock_txtime sk_txtime; - struct sock *sk = sock->sk; int val; int valbool; struct linger ling; @@ -737,16 +1098,16 @@ int sock_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; - lock_sock(sk); + sockopt_lock_sock(sk); switch (optname) { case SO_DEBUG: - if (val && !capable(CAP_NET_ADMIN)) + if (val && !sockopt_capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); @@ -776,7 +1137,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - val = min_t(u32, val, sysctl_wmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. @@ -790,7 +1151,7 @@ set_sndbuf: break; case SO_SNDBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { + if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } @@ -808,34 +1169,11 @@ set_sndbuf: * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - val = min_t(u32, val, sysctl_rmem_max); -set_rcvbuf: - /* Ensure val * 2 fits into an int, to prevent max_t() - * from treating it as a negative value. - */ - val = min_t(int, val, INT_MAX / 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. - */ - WRITE_ONCE(sk->sk_rcvbuf, - max_t(int, val * 2, SOCK_MIN_RCVBUF)); + __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { + if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } @@ -843,9 +1181,8 @@ set_rcvbuf: /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ - if (val < 0) - val = 0; - goto set_rcvbuf; + __sock_set_rcvbuf(sk, max(val, 0)); + break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) @@ -863,7 +1200,8 @@ set_rcvbuf: case SO_PRIORITY: if ((val >= 0 && val <= 6) || - ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; @@ -874,7 +1212,7 @@ set_rcvbuf: ret = -EINVAL; /* 1003.1g */ break; } - if (copy_from_user(&ling, optval, sizeof(ling))) { + if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } @@ -892,7 +1230,6 @@ set_rcvbuf: break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); break; case SO_PASSCRED: @@ -906,72 +1243,28 @@ set_rcvbuf: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - if (valbool) { - if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW) - sock_set_flag(sk, SOCK_TSTAMP_NEW); - else - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - - if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW) - sock_reset_flag(sk, SOCK_RCVTSTAMPNS); - else - sock_set_flag(sk, SOCK_RCVTSTAMPNS); - sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk, SOCK_TIMESTAMP); - } else { - sock_reset_flag(sk, SOCK_RCVTSTAMP); - sock_reset_flag(sk, SOCK_RCVTSTAMPNS); - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - } + sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: - sock_set_flag(sk, SOCK_TSTAMP_NEW); - /* fall through */ case SO_TIMESTAMPING_OLD: - if (val & ~SOF_TIMESTAMPING_MASK) { - ret = -EINVAL; - break; - } - - if (val & SOF_TIMESTAMPING_OPT_ID && - !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) { - if ((1 << sk->sk_state) & - (TCPF_CLOSE | TCPF_LISTEN)) { - ret = -EINVAL; - break; - } - sk->sk_tskey = tcp_sk(sk)->snd_una; - } else { - sk->sk_tskey = 0; + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) { + ret = -EFAULT; + break; } + } else { + memset(×tamping, 0, sizeof(timestamping)); + timestamping.flags = val; } - - if (val & SOF_TIMESTAMPING_OPT_STATS && - !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { - ret = -EINVAL; - break; - } - - sk->sk_tsflags = val; - if (val & SOF_TIMESTAMPING_RX_SOFTWARE) - sock_enable_timestamp(sk, - SOCK_TIMESTAMPING_RX_SOFTWARE); - else { - if (optname == SO_TIMESTAMPING_NEW) - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - - sock_disable_timestamp(sk, - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); - } + ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - if (sock->ops->set_rcvlowat) + if (sock && sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); @@ -979,60 +1272,52 @@ set_rcvbuf: case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, + optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, + optlen, optname == SO_SNDTIMEO_OLD); break; - 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; + case SO_ATTACH_FILTER: { + struct sock_fprog fprog; + ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); + if (!ret) ret = sk_attach_filter(&fprog, sk); - } break; - + } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; - if (copy_from_user(&ufd, optval, sizeof(ufd))) + if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; - case SO_ATTACH_REUSEPORT_CBPF: - ret = -EINVAL; - if (optlen == sizeof(struct sock_fprog)) { - struct sock_fprog fprog; - - ret = -EFAULT; - if (copy_from_user(&fprog, optval, sizeof(fprog))) - break; + case SO_ATTACH_REUSEPORT_CBPF: { + struct sock_fprog fprog; + ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); + if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); - } break; - + } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; - if (copy_from_user(&ufd, optval, sizeof(ufd))) + if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); @@ -1061,12 +1346,22 @@ set_rcvbuf: clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + ret = -EPERM; + break; + } + + __sock_set_mark(sk, val); + break; + case SO_RCVMARK: + if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; - } else if (val != sk->sk_mark) { - sk->sk_mark = val; - sk_dst_reset(sk); + break; } + + sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; case SO_RXQ_OVFL: @@ -1095,24 +1390,40 @@ set_rcvbuf: #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)) + if ((val > sk->sk_ll_usec) && !sockopt_capable(CAP_NET_ADMIN)) ret = -EPERM; else { if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); + } + break; + case SO_PREFER_BUSY_POLL: + if (valbool && !sockopt_capable(CAP_NET_ADMIN)) + ret = -EPERM; + else + WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); + break; + case SO_BUSY_POLL_BUDGET: + if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) { + ret = -EPERM; + } else { + if (val < 0 || val > U16_MAX) + ret = -EINVAL; + else + WRITE_ONCE(sk->sk_busy_poll_budget, val); } break; #endif case SO_MAX_PACING_RATE: { - unsigned long ulval = (val == ~0U) ? ~0UL : val; + unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && - get_user(ulval, (unsigned long __user *)optval)) { + copy_from_sockptr(&ulval, optval, sizeof(ulval))) { ret = -EFAULT; break; } @@ -1135,13 +1446,12 @@ set_rcvbuf: case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { - if (!((sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP) || + if (!(sk_is_tcp(sk) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; } else if (sk->sk_family != PF_RDS) { - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; } if (!ret) { if (val < 0 || val > 1) @@ -1152,38 +1462,98 @@ set_rcvbuf: break; case SO_TXTIME: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { - ret = -EPERM; - } else if (optlen != sizeof(struct sock_txtime)) { + if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; - } else if (copy_from_user(&sk_txtime, optval, + break; + } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; + break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; - } else { - sock_valbool_flag(sk, SOCK_TXTIME, true); - sk->sk_clockid = sk_txtime.clockid; - sk->sk_txtime_deadline_mode = - !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); - sk->sk_txtime_report_errors = - !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); + break; + } + /* CLOCK_MONOTONIC is only used by sch_fq, and this packet + * scheduler has enough safe guards. + */ + if (sk_txtime.clockid != CLOCK_MONOTONIC && + !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + ret = -EPERM; + break; } + sock_valbool_flag(sk, SOCK_TXTIME, true); + sk->sk_clockid = sk_txtime.clockid; + sk->sk_txtime_deadline_mode = + !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); + sk->sk_txtime_report_errors = + !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: - ret = sock_setbindtodevice_locked(sk, val); + ret = sock_bindtoindex_locked(sk, val); + break; + + case SO_BUF_LOCK: + if (val & ~SOCK_BUF_LOCK_MASK) { + ret = -EINVAL; + break; + } + sk->sk_userlocks = val | (sk->sk_userlocks & + ~SOCK_BUF_LOCK_MASK); + break; + + case SO_RESERVE_MEM: + { + int delta; + + if (val < 0) { + ret = -EINVAL; + break; + } + + delta = val - sk->sk_reserved_mem; + if (delta < 0) + sock_release_reserved_memory(sk, -delta); + else + ret = sock_reserve_memory(sk, delta); + break; + } + + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + /* Paired with READ_ONCE() in tcp_rtx_synack() */ + WRITE_ONCE(sk->sk_txrehash, (u8)val); break; default: ret = -ENOPROTOOPT; break; } - release_sock(sk); + sockopt_release_sock(sk); return ret; } + +int sock_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + return sk_setsockopt(sock->sk, level, optname, + optval, optlen); +} EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1198,22 +1568,25 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred, } } -static int groups_to_user(gid_t __user *dst, const struct group_info *src) +static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; - for (i = 0; i < src->ngroups; i++) - if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i)) + for (i = 0; i < src->ngroups; i++) { + gid_t gid = from_kgid_munged(user_ns, src->gid[i]); + + if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; + } return 0; } -int sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +int sk_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen) { - struct sock *sk = sock->sk; + struct socket *sock = sk->sk_socket; union { int val; @@ -1224,12 +1597,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; + struct so_timestamping timestamping; } v; int lv = sizeof(int); int len; - if (get_user(len, optlen)) + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; @@ -1306,7 +1680,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); break; case SO_TIMESTAMP_OLD: @@ -1328,7 +1701,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING_OLD: - v.val = sk->sk_tsflags; + lv = sizeof(v.timestamping); + v.timestamping.flags = sk->sk_tsflags; + v.timestamping.bind_phc = sk->sk_bind_phc; break; case SO_RCVTIMEO_OLD: @@ -1358,28 +1733,35 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); - if (copy_to_user(optval, &peercred, len)) + spin_unlock(&sk->sk_peer_lock); + + if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); - return put_user(len, optlen) ? -EFAULT : -ERANGE; + put_cred(cred); + return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user(optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1394,7 +1776,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return -ENOTCONN; if (lv < len) return -EINVAL; - if (copy_to_user(optval, address, len)) + if (copy_to_sockptr(optval, address, len)) return -EFAULT; goto lenout; } @@ -1411,12 +1793,16 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERSEC: - return security_socket_getpeersec_stream(sock, optval, optlen, len); + return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len); case SO_MARK: v.val = sk->sk_mark; break; + case SO_RCVMARK: + v.val = sock_flag(sk, SOCK_RCVMARK); + break; + case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; @@ -1439,7 +1825,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: - len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + len = sk_get_filter(sk, optval, len); if (len < 0) return len; @@ -1461,6 +1847,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; + case SO_PREFER_BUSY_POLL: + v.val = READ_ONCE(sk->sk_prefer_busy_poll); + break; #endif case SO_MAX_PACING_RATE: @@ -1484,7 +1873,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); - if (copy_to_user(optval, &meminfo, len)) + if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; @@ -1522,7 +1911,26 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BINDTOIFINDEX: - v.val = sk->sk_bound_dev_if; + v.val = READ_ONCE(sk->sk_bound_dev_if); + break; + + case SO_NETNS_COOKIE: + lv = sizeof(u64); + if (len != lv) + return -EINVAL; + v.val64 = sock_net(sk)->net_cookie; + break; + + case SO_BUF_LOCK: + v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; + break; + + case SO_RESERVE_MEM: + v.val = sk->sk_reserved_mem; + break; + + case SO_TXREHASH: + v.val = sk->sk_txrehash; break; default: @@ -1534,14 +1942,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len > lv) len = lv; - if (copy_to_user(optval, &v, len)) + if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } +int sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + return sk_getsockopt(sock->sk, level, optname, + USER_SOCKPTR(optval), + USER_SOCKPTR(optlen)); +} + /* * Initialize an sk_lock. * @@ -1572,13 +1988,24 @@ static inline void sock_lock_init(struct sock *sk) */ static void sock_copy(struct sock *nsk, const struct sock *osk) { + const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif + + /* If we move sk_tx_queue_mapping out of the private section, + * we must check if sk_tx_queue_clear() is called after + * sock_copy() in sk_clone_lock(). + */ + BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < + offsetof(struct sock, sk_dontcopy_begin) || + offsetof(struct sock, sk_tx_queue_mapping) >= + offsetof(struct sock, sk_dontcopy_end)); + 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)); + prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; @@ -1608,7 +2035,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; - sk_tx_queue_clear(sk); } return sk; @@ -1666,7 +2092,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { - get_net(net); + get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } @@ -1677,6 +2103,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); } return sk; @@ -1716,11 +2143,12 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) - put_net(sock_net(sk)); + put_net_track(sock_net(sk), &sk->ns_tracker); sk_prot_free(sk->sk_prot_creator, sk); } @@ -1792,116 +2220,122 @@ static void sk_init_common(struct sock *sk) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { - struct sock *newsk; + struct proto *prot = READ_ONCE(sk->sk_prot); + struct sk_filter *filter; bool is_charged = true; + struct sock *newsk; - newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family); - if (newsk != NULL) { - struct sk_filter *filter; - - sock_copy(newsk, sk); - - newsk->sk_prot_creator = sk->sk_prot; + newsk = sk_prot_alloc(prot, priority, sk->sk_family); + if (!newsk) + goto out; - /* SANITY */ - if (likely(newsk->sk_net_refcnt)) - 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; + sock_copy(newsk, sk); - atomic_set(&newsk->sk_rmem_alloc, 0); - /* - * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) - */ - refcount_set(&newsk->sk_wmem_alloc, 1); - atomic_set(&newsk->sk_omem_alloc, 0); - sk_init_common(newsk); + newsk->sk_prot_creator = prot; - newsk->sk_dst_cache = NULL; - newsk->sk_dst_pending_confirm = 0; - newsk->sk_wmem_queued = 0; - newsk->sk_forward_alloc = 0; - atomic_set(&newsk->sk_drops, 0); - newsk->sk_send_head = NULL; - newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; - atomic_set(&newsk->sk_zckey, 0); + /* SANITY */ + if (likely(newsk->sk_net_refcnt)) { + get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); + sock_inuse_add(sock_net(newsk), 1); + } + 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; - sock_reset_flag(newsk, SOCK_DONE); + atomic_set(&newsk->sk_rmem_alloc, 0); - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; + /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ + refcount_set(&newsk->sk_wmem_alloc, 1); - cgroup_sk_alloc(&newsk->sk_cgrp_data); + atomic_set(&newsk->sk_omem_alloc, 0); + sk_init_common(newsk); - rcu_read_lock(); - filter = rcu_dereference(sk->sk_filter); - if (filter != NULL) - /* though it's an empty new sock, the charging may fail - * if sysctl_optmem_max was changed between creation of - * original socket and cloning - */ - is_charged = sk_filter_charge(newsk, filter); - RCU_INIT_POINTER(newsk->sk_filter, filter); - rcu_read_unlock(); + newsk->sk_dst_cache = NULL; + newsk->sk_dst_pending_confirm = 0; + newsk->sk_wmem_queued = 0; + newsk->sk_forward_alloc = 0; + newsk->sk_reserved_mem = 0; + atomic_set(&newsk->sk_drops, 0); + newsk->sk_send_head = NULL; + newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { - /* We need to make sure that we don't uncharge the new - * socket if we couldn't charge it in the first place - * as otherwise we uncharge the parent's filter. - */ - if (!is_charged) - RCU_INIT_POINTER(newsk->sk_filter, NULL); - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } - RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); + sock_reset_flag(newsk, SOCK_DONE); - if (bpf_sk_storage_clone(sk, newsk)) { - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; - newsk->sk_err = 0; - newsk->sk_err_soft = 0; - newsk->sk_priority = 0; - newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); + cgroup_sk_clone(&newsk->sk_cgrp_data); - /* - * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.txt for details) + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) + /* though it's an empty new sock, the charging may fail + * if sysctl_optmem_max was changed between creation of + * original socket and cloning */ - smp_wmb(); - refcount_set(&newsk->sk_refcnt, 2); + is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); - /* - * Increment the counter in the same struct proto as the master - * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that - * is the same as sk->sk_prot->socks, as this field was copied - * with memcpy). - * - * This _changes_ the previous behaviour, where - * tcp_create_openreq_child always was incrementing the - * equivalent to tcp_prot->socks (inet_sock_nr), so this have - * to be taken into account in all callers. -acme + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. */ - sk_refcnt_debug_inc(newsk); - sk_set_socket(newsk, NULL); - RCU_INIT_POINTER(newsk->sk_wq, NULL); - - if (newsk->sk_prot->sockets_allocated) - sk_sockets_allocated_inc(newsk); + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); - if (sock_needs_netstamp(sk) && - newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); + if (bpf_sk_storage_clone(sk, newsk)) { + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; } + + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + newsk->sk_user_data = NULL; + + newsk->sk_err = 0; + newsk->sk_err_soft = 0; + newsk->sk_priority = 0; + newsk->sk_incoming_cpu = raw_smp_processor_id(); + + /* Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.rst for details) + */ + smp_wmb(); + refcount_set(&newsk->sk_refcnt, 2); + + /* Increment the counter in the same struct proto as the master + * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that + * is the same as sk->sk_prot->socks, as this field was copied + * with memcpy). + * + * This _changes_ the previous behaviour, where + * tcp_create_openreq_child always was incrementing the + * equivalent to tcp_prot->socks (inet_sock_nr), so this have + * to be taken into account in all callers. -acme + */ + sk_refcnt_debug_inc(newsk); + sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); + RCU_INIT_POINTER(newsk->sk_wq, NULL); + + if (newsk->sk_prot->sockets_allocated) + sk_sockets_allocated_inc(newsk); + + if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); out: return newsk; } @@ -1917,22 +2351,42 @@ void sk_free_unlock_clone(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); +static void sk_trim_gso_size(struct sock *sk) +{ + if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE) + return; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6 && + sk_is_tcp(sk) && + !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return; +#endif + sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE; +} + void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk_dst_set(sk, dst); - sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; + sk->sk_route_caps = dst->dev->features; + if (sk_is_tcp(sk)) + sk->sk_route_caps |= NETIF_F_GSO; 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 (unlikely(sk->sk_gso_disabled)) + sk->sk_route_caps &= ~NETIF_F_GSO_MASK; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; - sk->sk_gso_max_size = dst->dev->gso_max_size; - max_segs = max_t(u32, dst->dev->gso_max_segs, 1); + /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ + sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); + sk_trim_gso_size(sk); + sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1); + /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ + max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; @@ -1951,8 +2405,20 @@ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; + bool free; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { + if (sock_flag(sk, SOCK_RCU_FREE) && + sk->sk_write_space == sock_def_write_space) { + rcu_read_lock(); + free = refcount_sub_and_test(len, &sk->sk_wmem_alloc); + sock_def_write_space_wfree(sk); + rcu_read_unlock(); + if (unlikely(free)) + __sk_free(sk); + return; + } + /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call @@ -2027,16 +2493,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) { - struct sock *sk = skb->sk; + if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) + return; - if (refcount_inc_not_zero(&sk->sk_refcnt)) { - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); - skb->destructor = sock_efree; - } - } else { - skb_orphan(skb); - } + skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); @@ -2063,6 +2523,18 @@ void sock_efree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_efree); +/* Buffer destructor for prefetch/receive path where reference count may + * not be held, e.g. for listen sockets. + */ +#ifdef CONFIG_INET +void sock_pfree(struct sk_buff *skb) +{ + if (sk_is_refcounted(skb->sk)) + sock_gen_put(skb->sk); +} +EXPORT_SYMBOL(sock_pfree); +#endif /* CONFIG_INET */ + kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; @@ -2118,7 +2590,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > - sysctl_optmem_max) + READ_ONCE(sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); @@ -2136,8 +2608,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned int)size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + int optmem_max = READ_ONCE(sysctl_optmem_max); + + if ((unsigned int)size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. @@ -2162,7 +2636,7 @@ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, if (WARN_ON_ONCE(!mem)) return; if (nullify) - kzfree(mem); + kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); @@ -2256,13 +2730,6 @@ failure: } 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, 0); -} -EXPORT_SYMBOL(sock_alloc_send_skb); - int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { @@ -2270,7 +2737,8 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, switch (cmsg->cmsg_type) { case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; @@ -2344,8 +2812,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -/* On 32bit arches, an skb frag is limited to 2^15 */ -#define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** @@ -2403,7 +2869,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) } EXPORT_SYMBOL(sk_page_frag_refill); -static void __lock_sock(struct sock *sk) +void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { @@ -2435,7 +2901,7 @@ void __release_sock(struct sock *sk) do { next = skb->next; prefetch(next); - WARN_ON_ONCE(skb_dst_is_noref(skb)); + DEBUG_NET_WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); @@ -2460,6 +2926,7 @@ void __sk_flush_backlog(struct sock *sk) __release_sock(sk); spin_unlock_bh(&sk->sk_lock.slock); } +EXPORT_SYMBOL_GPL(__sk_flush_backlog); /** * sk_wait_data - wait for data to arrive at sk_receive_queue @@ -2497,12 +2964,16 @@ EXPORT_SYMBOL(sk_wait_data); */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { + bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; struct proto *prot = sk->sk_prot; - long allocated = sk_memory_allocated_add(sk, amt); bool charged = true; + long allocated; - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) + sk_memory_allocated_add(sk, amt); + allocated = sk_memory_allocated(sk); + if (memcg_charge && + !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge()))) goto suppress_allocation; /* Under limit. */ @@ -2556,8 +3027,14 @@ suppress_allocation: /* 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) + if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { + /* Force charge with __GFP_NOFAIL */ + if (memcg_charge && !charged) { + mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge() | __GFP_NOFAIL); + } return 1; + } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) @@ -2565,12 +3042,11 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_memcg) + if (memcg_charge && charged) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; } -EXPORT_SYMBOL(__sk_mem_raise_allocated); /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated @@ -2586,10 +3062,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); - sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT; + sk->sk_forward_alloc += amt << PAGE_SHIFT; ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) - sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT; + sk->sk_forward_alloc -= amt << PAGE_SHIFT; return ret; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -2612,17 +3088,16 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } -EXPORT_SYMBOL(__sk_mem_reduce_allocated); /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket - * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) + * @amount: number of bytes (rounded down to a PAGE_SIZE multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { - amount >>= SK_MEM_QUANTUM_SHIFT; - sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + amount >>= PAGE_SHIFT; + sk->sk_forward_alloc -= amount << PAGE_SHIFT; __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -2692,20 +3167,6 @@ int sock_no_shutdown(struct socket *sock, int how) } EXPORT_SYMBOL(sock_no_shutdown); -int sock_no_setsockopt(struct socket *sock, int level, int optname, - 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 socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; @@ -2732,6 +3193,21 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct * } EXPORT_SYMBOL(sock_no_mmap); +/* + * When a file is received (via SCM_RIGHTS, etc), we must bump the + * various sock-based usage counts. + */ +void __receive_sock(struct file *file) +{ + struct socket *sock; + + sock = sock_from_file(file); + if (sock) { + sock_update_netprioidx(&sock->sk->sk_cgrp_data); + sock_update_classid(&sock->sk->sk_cgrp_data); + } +} + ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; @@ -2811,20 +3287,42 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { + if (sock_writeable(sk)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ - if (sock_writeable(sk)) - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } +/* An optimised version of sock_def_write_space(), should only be called + * for SOCK_RCU_FREE sockets under RCU read section and after putting + * ->sk_wmem_alloc. + */ +static void sock_def_write_space_wfree(struct sock *sk) +{ + /* Do not wake up a writer until he can make "significant" + * progress. --DaveM + */ + if (sock_writeable(sk)) { + struct socket_wq *wq = rcu_dereference(sk->sk_wq); + + /* rely on refcount_sub from sock_wfree() */ + smp_mb__after_atomic(); + if (wq && waitqueue_active(&wq->wait)) + wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); + + /* Should agree with poll, otherwise some programs break */ + sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + } +} + static void sock_def_destruct(struct sock *sk) { } @@ -2852,6 +3350,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) } EXPORT_SYMBOL(sk_stop_timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) +{ + if (del_timer_sync(timer)) + __sock_put(sk); +} +EXPORT_SYMBOL(sk_stop_timer_sync); + void sock_init_data(struct socket *sock, struct sock *sk) { sk_init_common(sk); @@ -2860,8 +3365,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; - sk->sk_rcvbuf = sysctl_rmem_default; - sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); @@ -2901,6 +3406,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; @@ -2914,18 +3421,19 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; + sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.txt for details) + * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); @@ -2935,17 +3443,15 @@ EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); + might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (sk->sk_lock.owned) + if (sock_owned_by_user_nocheck(sk)) __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, subclass, 0, _RET_IP_); - local_bh_enable(); + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); @@ -2968,41 +3474,37 @@ void release_sock(struct sock *sk) } 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) +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (!sk->sk_lock.owned) + if (!sock_owned_by_user_nocheck(sk)) { /* - * Note : We must disable BH + * Fast path return with bottom halves disabled and + * sock::sk_lock.slock held. + * + * The 'mutex' is not contended and holding + * sock::sk_lock.slock prevents all other lockers to + * proceed so the corresponding unlock_sock_fast() can + * avoid the slow path of release_sock() completely and + * just release slock. + * + * From a semantical POV this is equivalent to 'acquiring' + * the 'mutex', hence the corresponding lockdep + * mutex_release() has to happen in the fast path of + * unlock_sock_fast(). */ 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(); + __acquire(&sk->sk_lock.slock); + spin_unlock_bh(&sk->sk_lock.slock); return true; } -EXPORT_SYMBOL(lock_sock_fast); +EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) @@ -3108,24 +3610,11 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; - return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); -#ifdef CONFIG_COMPAT -int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - struct sock *sk = sock->sk; - - if (sk->sk_prot->compat_getsockopt != NULL) - return sk->sk_prot->compat_getsockopt(sk, level, optname, - optval, optlen); - return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); -} -EXPORT_SYMBOL(compat_sock_common_getsockopt); -#endif - int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -3133,8 +3622,7 @@ int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int addr_len = 0; int err; - err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, - flags & ~MSG_DONTWAIT, &addr_len); + err = sk->sk_prot->recvmsg(sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; @@ -3145,35 +3633,22 @@ 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, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + return READ_ONCE(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, unsigned int optlen) -{ - struct sock *sk = sock->sk; - - if (sk->sk_prot->compat_setsockopt != NULL) - return sk->sk_prot->compat_setsockopt(sk, level, optname, - optval, optlen); - return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); -} -EXPORT_SYMBOL(compat_sock_common_setsockopt); -#endif - void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* - * Observation: when sock_common_release is called, processes have + * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * @@ -3220,19 +3695,8 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) } #ifdef CONFIG_PROC_FS -#define PROTO_INUSE_NR 64 /* should be enough for the first time */ -struct prot_inuse { - int val[PROTO_INUSE_NR]; -}; - static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); -void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) -{ - __this_cpu_add(net->core.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; @@ -3245,17 +3709,12 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot) } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); -static void sock_inuse_add(struct net *net, int val) -{ - this_cpu_add(*net->core.sock_inuse, val); -} - int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) - res += *per_cpu_ptr(net->core.sock_inuse, cpu); + res += per_cpu_ptr(net->core.prot_inuse, cpu)->all; return res; } @@ -3267,22 +3726,12 @@ static int __net_init sock_inuse_init_net(struct net *net) net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; - - net->core.sock_inuse = alloc_percpu(int); - if (net->core.sock_inuse == NULL) - goto out; - return 0; - -out: - free_percpu(net->core.prot_inuse); - return -ENOMEM; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); - free_percpu(net->core.sock_inuse); } static struct pernet_operations net_inuse_ops = { @@ -3328,10 +3777,43 @@ static inline void release_proto_idx(struct proto *prot) { } -static void sock_inuse_add(struct net *net, int val) +#endif + +static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { + if (!twsk_prot) + return; + kfree(twsk_prot->twsk_slab_name); + twsk_prot->twsk_slab_name = NULL; + kmem_cache_destroy(twsk_prot->twsk_slab); + twsk_prot->twsk_slab = NULL; +} + +static int tw_prot_init(const struct proto *prot) +{ + struct timewait_sock_ops *twsk_prot = prot->twsk_prot; + + if (!twsk_prot) + return 0; + + twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", + prot->name); + if (!twsk_prot->twsk_slab_name) + return -ENOMEM; + + twsk_prot->twsk_slab = + kmem_cache_create(twsk_prot->twsk_slab_name, + twsk_prot->twsk_obj_size, 0, + SLAB_ACCOUNT | prot->slab_flags, + NULL); + if (!twsk_prot->twsk_slab) { + pr_crit("%s: Can't create timewait sock SLAB cache!\n", + prot->name); + return -ENOMEM; + } + + return 0; } -#endif static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { @@ -3372,6 +3854,14 @@ int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; + if (prot->memory_allocated && !prot->sysctl_mem) { + pr_err("%s: missing sysctl_mem\n", prot->name); + return -EINVAL; + } + if (prot->memory_allocated && !prot->per_cpu_fw_alloc) { + pr_err("%s: missing per_cpu_fw_alloc\n", prot->name); + return -EINVAL; + } if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, @@ -3389,37 +3879,23 @@ int proto_register(struct proto *prot, int alloc_slab) if (req_prot_init(prot)) goto out_free_request_sock_slab; - if (prot->twsk_prot != NULL) { - prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); - - if (prot->twsk_prot->twsk_slab_name == NULL) - goto out_free_request_sock_slab; - - prot->twsk_prot->twsk_slab = - kmem_cache_create(prot->twsk_prot->twsk_slab_name, - prot->twsk_prot->twsk_obj_size, - 0, - SLAB_ACCOUNT | - prot->slab_flags, - NULL); - if (prot->twsk_prot->twsk_slab == NULL) - goto out_free_timewait_sock_slab_name; - } + if (tw_prot_init(prot)) + goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); - goto out_free_timewait_sock_slab_name; + goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; -out_free_timewait_sock_slab_name: - if (alloc_slab && prot->twsk_prot) - kfree(prot->twsk_prot->twsk_slab_name); +out_free_timewait_sock_slab: + if (alloc_slab) + tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); @@ -3443,12 +3919,7 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); - - if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) { - kmem_cache_destroy(prot->twsk_prot->twsk_slab); - kfree(prot->twsk_prot->twsk_slab_name); - prot->twsk_prot->twsk_slab = NULL; - } + tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); @@ -3465,6 +3936,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && + protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif @@ -3606,3 +4078,11 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ + +int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) +{ + if (!sk->sk_prot->bind_add) + return -EOPNOTSUPP; + return sk->sk_prot->bind_add(sk, addr, addr_len); +} +EXPORT_SYMBOL(sock_bind_add); |