1 files changed, 63 insertions, 88 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 1e4dd54bfb5a..6c1c8bc93412 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -134,6 +134,7 @@
 #include <linux/sock_diag.h>
 
 #include <linux/filter.h>
+#include <net/sock_reuseport.h>
 
 #include <trace/events/sock.h>
 
@@ -194,44 +195,6 @@ bool sk_net_capable(const struct sock *sk, int 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:
@@ -239,11 +202,6 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
-#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
@@ -433,8 +391,6 @@ static bool sock_needs_netstamp(const 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 (sk->sk_flags & flags) {
@@ -874,7 +830,8 @@ set_rcvbuf:
 
 		if (val & SOF_TIMESTAMPING_OPT_ID &&
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-			if (sk->sk_protocol == IPPROTO_TCP) {
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_type == SOCK_STREAM) {
 				if (sk->sk_state != TCP_ESTABLISHED) {
 					ret = -EINVAL;
 					break;
@@ -933,6 +890,32 @@ set_rcvbuf:
 		}
 		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;
+
+			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)))
+				break;
+
+			ret = sk_reuseport_attach_bpf(ufd, sk);
+		}
+		break;
+
 	case SO_DETACH_FILTER:
 		ret = sk_detach_filter(sk);
 		break;
@@ -1363,6 +1346,7 @@ 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);
+		cgroup_sk_alloc(&sk->sk_cgrp_data);
 	}
 
 	return sk;
@@ -1385,6 +1369,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	owner = prot->owner;
 	slab = prot->slab;
 
+	cgroup_sk_free(&sk->sk_cgrp_data);
 	security_sk_free(sk);
 	if (slab != NULL)
 		kmem_cache_free(slab, sk);
@@ -1393,17 +1378,6 @@ 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
@@ -1432,8 +1406,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		sock_net_set(sk, net);
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
-		sock_update_classid(sk);
-		sock_update_netprioidx(sk);
+		sock_update_classid(&sk->sk_cgrp_data);
+		sock_update_netprioidx(&sk->sk_cgrp_data);
 	}
 
 	return sk;
@@ -1453,6 +1427,8 @@ void sk_destruct(struct sock *sk)
 		sk_filter_uncharge(sk, filter);
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
+	if (rcu_access_pointer(sk->sk_reuseport_cb))
+		reuseport_detach_sock(sk);
 
 	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
@@ -1488,12 +1464,6 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
-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
@@ -1530,7 +1500,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		skb_queue_head_init(&newsk->sk_receive_queue);
 		skb_queue_head_init(&newsk->sk_write_queue);
 
-		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,
@@ -1553,7 +1522,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			 */
 			is_charged = sk_filter_charge(newsk, filter);
 
-		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) {
+		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
@@ -1589,7 +1558,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		sk_set_socket(newsk, NULL);
 		newsk->sk_wq = NULL;
 
-		sk_update_clone(sk, newsk);
+		if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+			sock_update_memcg(newsk);
 
 		if (newsk->sk_prot->sockets_allocated)
 			sk_sockets_allocated_inc(newsk);
@@ -1607,7 +1577,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
 
-	__sk_dst_set(sk, dst);
+	sk_dst_set(sk, dst);
 	sk->sk_route_caps = dst->dev->features;
 	if (sk->sk_route_caps & NETIF_F_GSO)
 		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -1815,7 +1785,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 {
 	DEFINE_WAIT(wait);
 
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 	for (;;) {
 		if (!timeo)
 			break;
@@ -1861,7 +1831,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
 			break;
 
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		err = -EAGAIN;
 		if (!timeo)
@@ -2048,9 +2018,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	finish_wait(sk_sleep(sk), &wait);
 	return rc;
 }
@@ -2071,27 +2041,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	struct proto *prot = sk->sk_prot;
 	int amt = sk_mem_pages(size);
 	long allocated;
-	int parent_status = UNDER_LIMIT;
 
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
 
-	allocated = sk_memory_allocated_add(sk, amt, &parent_status);
+	allocated = sk_memory_allocated_add(sk, amt);
+
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
+	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
+		goto suppress_allocation;
 
 	/* Under limit. */
-	if (parent_status == UNDER_LIMIT &&
-			allocated <= sk_prot_mem_limits(sk, 0)) {
+	if (allocated <= sk_prot_mem_limits(sk, 0)) {
 		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
-	/* Under pressure. (we or our parents) */
-	if ((parent_status > SOFT_LIMIT) ||
-			allocated > sk_prot_mem_limits(sk, 1))
+	/* Under pressure. */
+	if (allocated > sk_prot_mem_limits(sk, 1))
 		sk_enter_memory_pressure(sk);
 
-	/* Over hard limit (we or our parents) */
-	if ((parent_status == OVER_LIMIT) ||
-			(allocated > sk_prot_mem_limits(sk, 2)))
+	/* Over hard limit. */
+	if (allocated > sk_prot_mem_limits(sk, 2))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */
@@ -2140,6 +2110,9 @@ suppress_allocation:
 
 	sk_memory_allocated_sub(sk, amt);
 
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);
+
 	return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -2155,6 +2128,9 @@ void __sk_mem_reclaim(struct sock *sk, int amount)
 	sk_memory_allocated_sub(sk, amount);
 	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
 
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
+
 	if (sk_under_memory_pressure(sk) &&
 	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
 		sk_leave_memory_pressure(sk);
@@ -2283,7 +2259,7 @@ static void sock_def_wakeup(struct sock *sk)
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_all(&wq->wait);
 	rcu_read_unlock();
 }
@@ -2294,7 +2270,7 @@ static void sock_def_error_report(struct sock *sk)
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_poll(&wq->wait, POLLERR);
 	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
 	rcu_read_unlock();
@@ -2306,7 +2282,7 @@ static void sock_def_readable(struct sock *sk)
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
 						POLLRDNORM | POLLRDBAND);
 	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -2324,7 +2300,7 @@ static void sock_def_write_space(struct sock *sk)
 	 */
 	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
 		wq = rcu_dereference(sk->sk_wq);
-		if (wq_has_sleeper(wq))
+		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 
@@ -2388,7 +2364,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	} else
 		sk->sk_wq	=	NULL;
 
-	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,