Merge tag 'v5.12-rc8' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 154 insertions, 60 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6c5967e80132..1f79b9aa9a3f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,6 +1184,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
 			return -ENOMEM;
 
 		for_each_netdev(net, d) {
+			struct netdev_name_node *name_node;
+			list_for_each_entry(name_node, &d->name_node->list, list) {
+				if (!sscanf(name_node->name, name, &i))
+					continue;
+				if (i < 0 || i >= max_netdevices)
+					continue;
+
+				/*  avoid cases where sscanf is not exact inverse of printf */
+				snprintf(buf, IFNAMSIZ, name, i);
+				if (!strncmp(buf, name_node->name, IFNAMSIZ))
+					set_bit(i, inuse);
+			}
 			if (!sscanf(d->name, name, &i))
 				continue;
 			if (i < 0 || i >= max_netdevices)
@@ -4294,6 +4306,13 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 		 */
 		thread = READ_ONCE(napi->thread);
 		if (thread) {
+			/* Avoid doing set_bit() if the thread is in
+			 * INTERRUPTIBLE state, cause napi_thread_wait()
+			 * makes sure to proceed with napi polling
+			 * if the thread is explicitly woken from here.
+			 */
+			if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE)
+				set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
 			wake_up_process(thread);
 			return;
 		}
@@ -5905,7 +5924,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	NAPI_GRO_CB(skb)->frag0_len = 0;
 
 	if (!skb_headlen(skb) && pinfo->nr_frags &&
-	    !PageHighMem(skb_frag_page(frag0))) {
+	    !PageHighMem(skb_frag_page(frag0)) &&
+	    (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
 		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
 						    skb_frag_size(frag0),
@@ -6486,6 +6506,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
 		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_SCHED_THREADED |
 			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
@@ -6968,19 +6989,29 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 static int napi_thread_wait(struct napi_struct *napi)
 {
+	bool woken = false;
+
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
-		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+	while (!kthread_should_stop()) {
+		/* Testing SCHED_THREADED bit here to make sure the current
+		 * kthread owns this napi and could poll on this napi.
+		 * Testing SCHED bit is not enough because SCHED bit might be
+		 * set by some other busy poll thread or by napi_disable().
+		 */
+		if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
 			WARN_ON(!list_empty(&napi->poll_list));
 			__set_current_state(TASK_RUNNING);
 			return 0;
 		}
 
 		schedule();
+		/* woken being true indicates this thread owns this napi. */
+		woken = true;
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
+
 	return -1;
 }
 
@@ -11346,7 +11377,7 @@ static void __net_exit default_device_exit(struct net *net)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
-		if (dev->rtnl_link_ops)
+		if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
 			continue;
 
 		/* Push remaining network devices to init_net */
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 571f191c06d9..db65ce62b625 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 	return 0;
 
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&hw_data->send_timer);
+		cancel_work_sync(&hw_data->dm_alert_work);
+		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+			struct devlink_trap_metadata *hw_metadata;
+
+			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+			net_dm_hw_metadata_free(hw_metadata);
+			consume_skb(skb);
+		}
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
@@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
 err_unregister_trace:
 	unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		while ((skb = __skb_dequeue(&data->drop_queue)))
+			consume_skb(skb);
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
diff --git a/net/core/dst.c b/net/core/dst.c
index 0c01bd8d9d81..fb3bcba87744 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-static struct dst_ops md_dst_ops = {
-	.family =		AF_UNSPEC,
-};
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
 
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
-	WARN_ONCE(1, "Attempting to call output on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
 }
 
-static int dst_md_discard(struct sk_buff *skb)
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr)
 {
-	WARN_ONCE(1, "Attempting to call input on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
+static struct dst_ops dst_blackhole_ops = {
+	.family		= AF_UNSPEC,
+	.neigh_lookup	= dst_blackhole_neigh_lookup,
+	.check		= dst_blackhole_check,
+	.cow_metrics	= dst_blackhole_cow_metrics,
+	.update_pmtu	= dst_blackhole_update_pmtu,
+	.redirect	= dst_blackhole_redirect,
+	.mtu		= dst_blackhole_mtu,
+};
 
 static void __metadata_dst_init(struct metadata_dst *md_dst,
 				enum metadata_type type, u8 optslen)
-
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
-	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+	dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
 		 DST_METADATA | DST_NOCOUNT);
-
-	dst->input = dst_md_discard;
-	dst->output = dst_md_discard_out;
-
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
 	md_dst->type = type;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index adfdad234674..9323d34d34cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5658,7 +5658,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
 		return -EINVAL;
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
 		return -EINVAL;
 
 	dev = __dev_via_ifindex(dev, ifindex);
@@ -5668,7 +5668,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	mtu = READ_ONCE(dev->mtu);
 
 	dev_len = mtu + dev->hard_header_len;
-	skb_len = skb->len + len_diff; /* minus result pass check */
+
+	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+	skb_len += len_diff; /* minus result pass check */
 	if (skb_len <= dev_len) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
 		goto out;
@@ -5713,6 +5717,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
+	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	if (*mtu_len)
+		xdp_len = *mtu_len + dev->hard_header_len;
+
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2ef2224b3bff..a96a4f5de0ce 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -176,7 +176,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 	 * avoid confusion with packets without such field
 	 */
 	if (icmp_has_id(ih->type))
-		key_icmp->id = ih->un.echo.id ? : 1;
+		key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
 	else
 		key_icmp->id = 0;
 }
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e2982b3970b8..8379719d1dce 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1379,7 +1379,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 			 * we can reinject the packet there.
 			 */
 			n2 = NULL;
-			if (dst) {
+			if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
 				n2 = dst_neigh_lookup_skb(dst, skb);
 				if (n2)
 					n1 = n2;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0edc0b2baaa4..3485b16a7ff3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2147,7 +2147,7 @@ out:
 out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
-	cb->seq = net->dev_base_seq;
+	cb->seq = tgt_net->dev_base_seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 	if (netnsid >= 0)
 		put_net(tgt_net);
@@ -2863,7 +2863,7 @@ static int do_setlink(const struct sk_buff *skb,
 
 			BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
 
-			err = af_ops->set_link_af(dev, af);
+			err = af_ops->set_link_af(dev, af, extack);
 			if (err < 0) {
 				rcu_read_unlock();
 				goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 420f23c0f81f..4275b88726f4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3660,6 +3660,8 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 	struct ts_state state;
 	unsigned int ret;
 
+	BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb));
+
 	config->get_next_block = skb_ts_get_next_block;
 	config->finish = skb_ts_finish;
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 1261512d6807..5def3a2e85be 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -488,6 +488,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 	if (unlikely(!msg))
 		return -EAGAIN;
 	sk_msg_init(msg);
+	skb_set_owner_r(skb, sk);
 	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
 }
 
@@ -790,7 +791,6 @@ static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
-		skb_set_owner_r(skb, sk);
 		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_PASS:
@@ -808,10 +808,6 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 	rcu_read_lock();
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
-		/* We skip full set_owner_r here because if we do a SK_PASS
-		 * or SK_DROP we can skip skb memory accounting and use the
-		 * TLS context.
-		 */
 		skb->sk = psock->sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
@@ -880,12 +876,13 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		kfree_skb(skb);
 		goto out;
 	}
-	skb_set_owner_r(skb, sk);
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
+		skb->sk = sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
 out:
@@ -956,12 +953,13 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		kfree_skb(skb);
 		goto out;
 	}
-	skb_set_owner_r(skb, sk);
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
+		skb->sk = sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
 out:
diff --git a/net/core/sock.c b/net/core/sock.c
index 0ed98f20448a..5ec90f99e102 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,16 +2132,10 @@ 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 (refcount_inc_not_zero(&sk->sk_refcnt)) {
-			WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
-			skb->destructor = sock_efree;
-		}
-	} else {
+	if (can_skb_orphan_partial(skb))
+		skb_set_owner_sk_safe(skb, skb->sk);
+	else
 		skb_orphan(skb);
-	}
 }
 EXPORT_SYMBOL(skb_orphan_partial);
 
@@ -3440,6 +3434,32 @@ static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
 	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;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3496,22 +3516,8 @@ 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;
-		}
+		if (tw_prot_init(prot))
+			goto out_free_timewait_sock_slab;
 	}
 
 	mutex_lock(&proto_list_mutex);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 05354976c1fc..858276e72c68 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -350,7 +350,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		napi_direct &= !xdp_return_frame_no_direct();
+		if (napi_direct && xdp_return_frame_no_direct())
+			napi_direct = false;
 		page_pool_put_full_page(xa->page_pool, page, napi_direct);
 		rcu_read_unlock();
 		break;