Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 98 insertions, 94 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5d1192ceb139..23c92ad15c61 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -262,6 +262,14 @@ static void __unix_insert_socket(struct hlist_head *list, struct sock *sk)
 	sk_add_node(sk, list);
 }
 
+static void __unix_set_addr(struct sock *sk, struct unix_address *addr,
+			    unsigned hash)
+{
+	__unix_remove_socket(sk);
+	smp_store_release(&unix_sk(sk)->addr, addr);
+	__unix_insert_socket(&unix_socket_table[hash], sk);
+}
+
 static inline void unix_remove_socket(struct sock *sk)
 {
 	spin_lock(&unix_table_lock);
@@ -278,11 +286,11 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
 
 static struct sock *__unix_find_socket_byname(struct net *net,
 					      struct sockaddr_un *sunname,
-					      int len, int type, unsigned int hash)
+					      int len, unsigned int hash)
 {
 	struct sock *s;
 
-	sk_for_each(s, &unix_socket_table[hash ^ type]) {
+	sk_for_each(s, &unix_socket_table[hash]) {
 		struct unix_sock *u = unix_sk(s);
 
 		if (!net_eq(sock_net(s), net))
@@ -297,13 +305,12 @@ static struct sock *__unix_find_socket_byname(struct net *net,
 
 static inline struct sock *unix_find_socket_byname(struct net *net,
 						   struct sockaddr_un *sunname,
-						   int len, int type,
-						   unsigned int hash)
+						   int len, unsigned int hash)
 {
 	struct sock *s;
 
 	spin_lock(&unix_table_lock);
-	s = __unix_find_socket_byname(net, sunname, len, type, hash);
+	s = __unix_find_socket_byname(net, sunname, len, hash);
 	if (s)
 		sock_hold(s);
 	spin_unlock(&unix_table_lock);
@@ -484,7 +491,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
 		 */
 		if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) {
 			other->sk_err = ECONNRESET;
-			other->sk_error_report(other);
+			sk_error_report(other);
 		}
 	}
 }
@@ -891,12 +898,12 @@ static int unix_autobind(struct socket *sock)
 retry:
 	addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short);
 	addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0));
+	addr->hash ^= sk->sk_type;
 
 	spin_lock(&unix_table_lock);
 	ordernum = (ordernum+1)&0xFFFFF;
 
-	if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
-				      addr->hash)) {
+	if (__unix_find_socket_byname(net, addr->name, addr->len, addr->hash)) {
 		spin_unlock(&unix_table_lock);
 		/*
 		 * __unix_find_socket_byname() may take long time if many names
@@ -911,11 +918,8 @@ retry:
 		}
 		goto retry;
 	}
-	addr->hash ^= sk->sk_type;
 
-	__unix_remove_socket(sk);
-	smp_store_release(&u->addr, addr);
-	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
+	__unix_set_addr(sk, addr, addr->hash);
 	spin_unlock(&unix_table_lock);
 	err = 0;
 
@@ -960,7 +964,7 @@ static struct sock *unix_find_other(struct net *net,
 		}
 	} else {
 		err = -ECONNREFUSED;
-		u = unix_find_socket_byname(net, sunname, len, type, hash);
+		u = unix_find_socket_byname(net, sunname, len, type ^ hash);
 		if (u) {
 			struct dentry *dentry;
 			dentry = unix_sk(u)->path.dentry;
@@ -978,125 +982,125 @@ fail:
 	return NULL;
 }
 
-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 {
+	struct unix_sock *u = unix_sk(sk);
+	umode_t mode = S_IFSOCK |
+	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
+	struct user_namespace *ns; // barf...
+	struct path parent;
 	struct dentry *dentry;
-	struct path path;
-	int err = 0;
+	unsigned int hash;
+	int err;
+
 	/*
 	 * Get the parent directory, calculate the hash for last
 	 * component.
 	 */
-	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-	err = PTR_ERR(dentry);
+	dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0);
 	if (IS_ERR(dentry))
-		return err;
+		return PTR_ERR(dentry);
+	ns = mnt_user_ns(parent.mnt);
 
 	/*
 	 * All right, let's create it.
 	 */
-	err = security_path_mknod(&path, dentry, mode, 0);
-	if (!err) {
-		err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry),
-				dentry, mode, 0);
-		if (!err) {
-			res->mnt = mntget(path.mnt);
-			res->dentry = dget(dentry);
-		}
-	}
-	done_path_create(&path, dentry);
+	err = security_path_mknod(&parent, dentry, mode, 0);
+	if (!err)
+		err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0);
+	if (err)
+		goto out;
+	err = mutex_lock_interruptible(&u->bindlock);
+	if (err)
+		goto out_unlink;
+	if (u->addr)
+		goto out_unlock;
+
+	addr->hash = UNIX_HASH_SIZE;
+	hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+	spin_lock(&unix_table_lock);
+	u->path.mnt = mntget(parent.mnt);
+	u->path.dentry = dget(dentry);
+	__unix_set_addr(sk, addr, hash);
+	spin_unlock(&unix_table_lock);
+	mutex_unlock(&u->bindlock);
+	done_path_create(&parent, dentry);
+	return 0;
+
+out_unlock:
+	mutex_unlock(&u->bindlock);
+	err = -EINVAL;
+out_unlink:
+	/* failed after successful mknod?  unlink what we'd created... */
+	vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL);
+out:
+	done_path_create(&parent, dentry);
 	return err;
 }
 
+static int unix_bind_abstract(struct sock *sk, struct unix_address *addr)
+{
+	struct unix_sock *u = unix_sk(sk);
+	int err;
+
+	err = mutex_lock_interruptible(&u->bindlock);
+	if (err)
+		return err;
+
+	if (u->addr) {
+		mutex_unlock(&u->bindlock);
+		return -EINVAL;
+	}
+
+	spin_lock(&unix_table_lock);
+	if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
+				      addr->hash)) {
+		spin_unlock(&unix_table_lock);
+		mutex_unlock(&u->bindlock);
+		return -EADDRINUSE;
+	}
+	__unix_set_addr(sk, addr, addr->hash);
+	spin_unlock(&unix_table_lock);
+	mutex_unlock(&u->bindlock);
+	return 0;
+}
+
 static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sock *sk = sock->sk;
-	struct net *net = sock_net(sk);
-	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
 	int err;
 	unsigned int hash;
 	struct unix_address *addr;
-	struct hlist_head *list;
-	struct path path = { };
 
-	err = -EINVAL;
 	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
 	    sunaddr->sun_family != AF_UNIX)
-		goto out;
+		return -EINVAL;
 
-	if (addr_len == sizeof(short)) {
-		err = unix_autobind(sock);
-		goto out;
-	}
+	if (addr_len == sizeof(short))
+		return unix_autobind(sock);
 
 	err = unix_mkname(sunaddr, addr_len, &hash);
 	if (err < 0)
-		goto out;
+		return err;
 	addr_len = err;
-
-	if (sun_path[0]) {
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			goto out;
-		}
-	}
-
-	err = mutex_lock_interruptible(&u->bindlock);
-	if (err)
-		goto out_put;
-
-	err = -EINVAL;
-	if (u->addr)
-		goto out_up;
-
-	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
-		goto out_up;
+		return -ENOMEM;
 
 	memcpy(addr->name, sunaddr, addr_len);
 	addr->len = addr_len;
 	addr->hash = hash ^ sk->sk_type;
 	refcount_set(&addr->refcnt, 1);
 
-	if (sun_path[0]) {
-		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
-		spin_lock(&unix_table_lock);
-		u->path = path;
-		list = &unix_socket_table[hash];
-	} else {
-		spin_lock(&unix_table_lock);
-		err = -EADDRINUSE;
-		if (__unix_find_socket_byname(net, sunaddr, addr_len,
-					      sk->sk_type, hash)) {
-			unix_release_addr(addr);
-			goto out_unlock;
-		}
-
-		list = &unix_socket_table[addr->hash];
-	}
-
-	err = 0;
-	__unix_remove_socket(sk);
-	smp_store_release(&u->addr, addr);
-	__unix_insert_socket(list, sk);
-
-out_unlock:
-	spin_unlock(&unix_table_lock);
-out_up:
-	mutex_unlock(&u->bindlock);
-out_put:
+	if (sun_path[0])
+		err = unix_bind_bsd(sk, addr);
+	else
+		err = unix_bind_abstract(sk, addr);
 	if (err)
-		path_put(&path);
-out:
-	return err;
+		unix_release_addr(addr);
+	return err == -EEXIST ? -EADDRINUSE : err;
 }
 
 static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
@@ -1393,7 +1397,7 @@ restart:
 
 	unix_state_unlock(sk);
 
-	/* take ten and and send info to listening sock */
+	/* take ten and send info to listening sock */
 	spin_lock(&other->sk_receive_queue.lock);
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);