Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/testing/selftests/net/forwarding/Makefile
  f62c5acc800e ("selftests/net/forwarding: add missing tests to Makefile")
  50fe062c806e ("selftests: forwarding: new test, verify host mdb entries")
https://lore.kernel.org/all/20220502111539.0b7e4621@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 87 insertions, 67 deletions

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 11a65a9d3906..35a1ae61744c 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1187,6 +1187,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 
 	lock_sock(sk);
 
+	if (so->bound) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	/* do not register frame reception for functional addressing */
 	if (so->opt.flags & CAN_ISOTP_SF_BROADCAST)
 		do_rx_reg = 0;
@@ -1197,10 +1202,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 		goto out;
 	}
 
-	if (so->bound && addr->can_ifindex == so->ifindex &&
-	    rx_id == so->rxid && tx_id == so->txid)
-		goto out;
-
 	dev = dev_get_by_index(net, addr->can_ifindex);
 	if (!dev) {
 		err = -ENODEV;
@@ -1235,22 +1236,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 
 	dev_put(dev);
 
-	if (so->bound && do_rx_reg) {
-		/* unregister old filter */
-		if (so->ifindex) {
-			dev = dev_get_by_index(net, so->ifindex);
-			if (dev) {
-				can_rx_unregister(net, dev, so->rxid,
-						  SINGLE_MASK(so->rxid),
-						  isotp_rcv, sk);
-				can_rx_unregister(net, dev, so->txid,
-						  SINGLE_MASK(so->txid),
-						  isotp_rcv_echo, sk);
-				dev_put(dev);
-			}
-		}
-	}
-
 	/* switch to new settings */
 	so->ifindex = ifindex;
 	so->rxid = rx_id;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 1c5815530e0d..83eb97c94e83 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2385,7 +2385,11 @@ again:
 		if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) {
 			err = -ENOSPC;
 		} else {
-			pr_warn_ratelimited("FULL or reached pool quota\n");
+			if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL))
+				pr_warn_ratelimited("cluster is full (osdmap FULL)\n");
+			else
+				pr_warn_ratelimited("pool %lld is full or reached quota\n",
+						    req->r_t.base_oloc.pool);
 			req->r_t.paused = true;
 			maybe_request_map(osdc);
 		}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 9b8443774449..5f85e01d4093 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -22,6 +22,8 @@
 static siphash_aligned_key_t net_secret;
 static siphash_aligned_key_t ts_secret;
 
+#define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ)
+
 static __always_inline void net_secret_init(void)
 {
 	net_get_random_once(&net_secret, sizeof(net_secret));
@@ -94,17 +96,19 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
 }
 EXPORT_SYMBOL(secure_tcpv6_seq);
 
-u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
 {
 	const struct {
 		struct in6_addr saddr;
 		struct in6_addr daddr;
+		unsigned int timeseed;
 		__be16 dport;
 	} __aligned(SIPHASH_ALIGNMENT) combined = {
 		.saddr = *(struct in6_addr *)saddr,
 		.daddr = *(struct in6_addr *)daddr,
-		.dport = dport
+		.timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD,
+		.dport = dport,
 	};
 	net_secret_init();
 	return siphash(&combined, offsetofend(typeof(combined), dport),
@@ -142,11 +146,13 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
 }
 EXPORT_SYMBOL_GPL(secure_tcp_seq);
 
-u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
+u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
 	net_secret_init();
-	return siphash_3u32((__force u32)saddr, (__force u32)daddr,
-			    (__force u16)dport, &net_secret);
+	return siphash_4u32((__force u32)saddr, (__force u32)daddr,
+			    (__force u16)dport,
+			    jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD,
+			    &net_secret);
 }
 EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 #endif
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1ba8ebc439f3..b65d074d9620 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 			/* decrease mem now to avoid the memleak warning */
 			atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 				   &sk->sk_omem_alloc);
-			kfree_rcu(psl, rcu);
 		}
 		rcu_assign_pointer(pmc->sflist, newpsl);
+		if (psl)
+			kfree_rcu(psl, rcu);
 		psl = newpsl;
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
@@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 			   &sk->sk_omem_alloc);
-		kfree_rcu(psl, rcu);
-	} else
+	} else {
 		(void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode,
 			0, NULL, 0);
+	}
 	rcu_assign_pointer(pmc->sflist, newpsl);
+	if (psl)
+		kfree_rcu(psl, rcu);
 	pmc->sfmode = msf->imsf_fmode;
 	err = 0;
 done:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 17440840a791..a5d57fa679ca 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -504,7 +504,7 @@ not_unique:
 	return -EADDRNOTAVAIL;
 }
 
-static u32 inet_sk_port_offset(const struct sock *sk)
+static u64 inet_sk_port_offset(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 
@@ -726,15 +726,17 @@ EXPORT_SYMBOL_GPL(inet_unhash);
  * Note that we use 32bit integers (vs RFC 'short integers')
  * because 2^16 is not a multiple of num_ephemeral and this
  * property might be used by clever attacker.
- * RFC claims using TABLE_LENGTH=10 buckets gives an improvement,
- * we use 256 instead to really give more isolation and
- * privacy, this only consumes 1 KB of kernel memory.
+ * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
+ * attacks were since demonstrated, thus we use 65536 instead to really
+ * give more isolation and privacy, at the expense of 256kB of kernel
+ * memory.
  */
-#define INET_TABLE_PERTURB_SHIFT 8
-static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT];
+#define INET_TABLE_PERTURB_SHIFT 16
+#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+static u32 *table_perturb;
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
-		struct sock *sk, u32 port_offset,
+		struct sock *sk, u64 port_offset,
 		int (*check_established)(struct inet_timewait_death_row *,
 			struct sock *, __u16, struct inet_timewait_sock **))
 {
@@ -774,10 +776,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	if (likely(remaining > 1))
 		remaining &= ~1U;
 
-	net_get_random_once(table_perturb, sizeof(table_perturb));
-	index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT);
+	net_get_random_once(table_perturb,
+			    INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+	index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
+
+	offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
+	offset %= remaining;
 
-	offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining;
 	/* In first pass we try ports of @low parity.
 	 * inet_csk_get_port() does the opposite choice.
 	 */
@@ -831,11 +836,12 @@ next_port:
 	return -EADDRNOTAVAIL;
 
 ok:
-	/* If our first attempt found a candidate, skip next candidate
-	 * in 1/16 of cases to add some noise.
+	/* Here we want to add a little bit of randomness to the next source
+	 * port that will be chosen. We use a max() with a random here so that
+	 * on low contention the randomness is maximal and on high contention
+	 * it may be inexistent.
 	 */
-	if (!i && !(prandom_u32() % 16))
-		i = 2;
+	i = max_t(int, i, (prandom_u32() & 7) * 2);
 	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
 
 	/* Head lock still held and bh's disabled */
@@ -859,7 +865,7 @@ ok:
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk)
 {
-	u32 port_offset = 0;
+	u64 port_offset = 0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet_sk_port_offset(sk);
@@ -909,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 					    low_limit,
 					    high_limit);
 	init_hashinfo_lhash2(h);
+
+	/* this one is used for source ports of outgoing connections */
+	table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE,
+				      sizeof(*table_perturb), GFP_KERNEL);
+	if (!table_perturb)
+		panic("TCP: failed to alloc table_perturb");
 }
 
 int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 4740afecf7c6..32ccac10bd62 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -308,7 +308,7 @@ not_unique:
 	return -EADDRNOTAVAIL;
 }
 
-static u32 inet6_sk_port_offset(const struct sock *sk)
+static u64 inet6_sk_port_offset(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 
@@ -320,7 +320,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk)
 int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 		       struct sock *sk)
 {
-	u32 port_offset = 0;
+	u64 port_offset = 0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet6_sk_port_offset(sk);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 909f937befd7..7f695c39d9a8 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -460,10 +460,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 				newpsl->sl_addr[i] = psl->sl_addr[i];
 			atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 				   &sk->sk_omem_alloc);
-			kfree_rcu(psl, rcu);
 		}
+		rcu_assign_pointer(pmc->sflist, newpsl);
+		kfree_rcu(psl, rcu);
 		psl = newpsl;
-		rcu_assign_pointer(pmc->sflist, psl);
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
 	for (i = 0; i < psl->sl_count; i++) {
@@ -565,12 +565,12 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf,
 			       psl->sl_count, psl->sl_addr, 0);
 		atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
 			   &sk->sk_omem_alloc);
-		kfree_rcu(psl, rcu);
 	} else {
 		ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0);
 	}
-	mutex_unlock(&idev->mc_lock);
 	rcu_assign_pointer(pmc->sflist, newpsl);
+	mutex_unlock(&idev->mc_lock);
+	kfree_rcu(psl, rcu);
 	pmc->sfmode = gsf->gf_fmode;
 	err = 0;
 done:
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 67524982b89b..6ff3e10ff8e3 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -38,7 +38,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -94,7 +94,7 @@ int nfc_dev_up(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -142,7 +142,7 @@ int nfc_dev_down(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -207,7 +207,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -246,7 +246,7 @@ int nfc_stop_poll(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -291,7 +291,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -335,7 +335,7 @@ int nfc_dep_link_down(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -401,7 +401,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -448,7 +448,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -495,7 +495,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb,
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		kfree_skb(skb);
 		goto error;
@@ -552,7 +552,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -601,7 +601,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx)
 
 	device_lock(&dev->dev);
 
-	if (!device_is_registered(&dev->dev)) {
+	if (dev->shutting_down) {
 		rc = -ENODEV;
 		goto error;
 	}
@@ -1134,6 +1134,7 @@ int nfc_register_device(struct nfc_dev *dev)
 			dev->rfkill = NULL;
 		}
 	}
+	dev->shutting_down = false;
 	device_unlock(&dev->dev);
 
 	rc = nfc_genl_device_added(dev);
@@ -1167,12 +1168,10 @@ void nfc_unregister_device(struct nfc_dev *dev)
 		rfkill_destroy(dev->rfkill);
 		dev->rfkill = NULL;
 	}
+	dev->shutting_down = true;
 	device_unlock(&dev->dev);
 
 	if (dev->ops->check_presence) {
-		device_lock(&dev->dev);
-		dev->shutting_down = true;
-		device_unlock(&dev->dev);
 		del_timer_sync(&dev->check_pres_timer);
 		cancel_work_sync(&dev->check_pres_work);
 	}
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index f184b0db79d4..7c62417ccfd7 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1244,7 +1244,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
 	struct sk_buff *msg;
 	void *hdr;
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
 	if (!msg)
 		return -ENOMEM;
 
@@ -1260,7 +1260,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC);
 
 	return 0;
 
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 5327d130c4b5..2f638f8b7b1e 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -495,6 +495,14 @@ void rds_tcp_tune(struct socket *sock)
 
 	tcp_sock_set_nodelay(sock->sk);
 	lock_sock(sk);
+	/* TCP timer functions might access net namespace even after
+	 * a process which created this net namespace terminated.
+	 */
+	if (!sk->sk_net_refcnt) {
+		sk->sk_net_refcnt = 1;
+		get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+		sock_inuse_add(net, 1);
+	}
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index a4111408ffd0..6a1611b0e303 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -117,6 +117,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 	       local, srx->transport_type, srx->transport.family);
 
 	udp_conf.family = srx->transport.family;
+	udp_conf.use_udp_checksums = true;
 	if (udp_conf.family == AF_INET) {
 		udp_conf.local_ip = srx->transport.sin.sin_addr;
 		udp_conf.local_udp_port = srx->transport.sin.sin_port;
@@ -124,6 +125,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 	} else {
 		udp_conf.local_ip6 = srx->transport.sin6.sin6_addr;
 		udp_conf.local_udp_port = srx->transport.sin6.sin6_port;
+		udp_conf.use_udp6_tx_checksums = true;
+		udp_conf.use_udp6_rx_checksums = true;
 #endif
 	}
 	ret = udp_sock_create(net, &udp_conf, &local->socket);