Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 49 insertions, 29 deletions

diff --git a/net/socket.c b/net/socket.c
index 38eec1583f6d..16449d6daeca 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -103,13 +103,6 @@
 #include <net/busy_poll.h>
 #include <linux/errqueue.h>
 
-/* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */
-#if IS_ENABLED(CONFIG_INET)
-#define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
-#else
-#define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__)
-#endif
-
 #ifdef CONFIG_NET_RX_BUSY_POLL
 unsigned int sysctl_net_busy_read __read_mostly;
 unsigned int sysctl_net_busy_poll __read_mostly;
@@ -241,20 +234,13 @@ static struct kmem_cache *sock_inode_cachep __ro_after_init;
 static struct inode *sock_alloc_inode(struct super_block *sb)
 {
 	struct socket_alloc *ei;
-	struct socket_wq *wq;
 
 	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
-	wq = kmalloc(sizeof(*wq), GFP_KERNEL);
-	if (!wq) {
-		kmem_cache_free(sock_inode_cachep, ei);
-		return NULL;
-	}
-	init_waitqueue_head(&wq->wait);
-	wq->fasync_list = NULL;
-	wq->flags = 0;
-	ei->socket.wq = wq;
+	init_waitqueue_head(&ei->socket.wq.wait);
+	ei->socket.wq.fasync_list = NULL;
+	ei->socket.wq.flags = 0;
 
 	ei->socket.state = SS_UNCONNECTED;
 	ei->socket.flags = 0;
@@ -265,12 +251,11 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void sock_destroy_inode(struct inode *inode)
+static void sock_free_inode(struct inode *inode)
 {
 	struct socket_alloc *ei;
 
 	ei = container_of(inode, struct socket_alloc, vfs_inode);
-	kfree_rcu(ei->socket.wq, rcu);
 	kmem_cache_free(sock_inode_cachep, ei);
 }
 
@@ -295,7 +280,7 @@ static void init_inodecache(void)
 
 static const struct super_operations sockfs_ops = {
 	.alloc_inode	= sock_alloc_inode,
-	.destroy_inode	= sock_destroy_inode,
+	.free_inode	= sock_free_inode,
 	.statfs		= simple_statfs,
 };
 
@@ -429,7 +414,7 @@ static int sock_map_fd(struct socket *sock, int flags)
 	}
 
 	newfile = sock_alloc_file(sock, flags, NULL);
-	if (likely(!IS_ERR(newfile))) {
+	if (!IS_ERR(newfile)) {
 		fd_install(fd, newfile);
 		return fd;
 	}
@@ -606,7 +591,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		module_put(owner);
 	}
 
-	if (sock->wq->fasync_list)
+	if (sock->wq.fasync_list)
 		pr_err("%s: fasync list not empty!\n", __func__);
 
 	if (!sock->file) {
@@ -641,10 +626,13 @@ EXPORT_SYMBOL(__sock_tx_timestamp);
 
 INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *,
 					   size_t));
+INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *,
+					    size_t));
 static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
 {
-	int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock,
-				      msg, msg_data_left(msg));
+	int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg,
+				     inet_sendmsg, sock, msg,
+				     msg_data_left(msg));
 	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
@@ -870,12 +858,15 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 
 INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *,
-					   size_t , int ));
+					   size_t, int));
+INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *,
+					    size_t, int));
 static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 				     int flags)
 {
-	return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg,
-				   msg_data_left(msg), flags);
+	return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg,
+				  inet_recvmsg, sock, msg, msg_data_left(msg),
+				  flags);
 }
 
 /**
@@ -1289,13 +1280,12 @@ static int sock_fasync(int fd, struct file *filp, int on)
 {
 	struct socket *sock = filp->private_data;
 	struct sock *sk = sock->sk;
-	struct socket_wq *wq;
+	struct socket_wq *wq = &sock->wq;
 
 	if (sk == NULL)
 		return -EINVAL;
 
 	lock_sock(sk);
-	wq = sock->wq;
 	fasync_helper(fd, filp, on, &wq->fasync_list);
 
 	if (!wq->fasync_list)
@@ -2051,6 +2041,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
 static int __sys_setsockopt(int fd, int level, int optname,
 			    char __user *optval, int optlen)
 {
+	mm_segment_t oldfs = get_fs();
+	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
 
@@ -2063,6 +2055,22 @@ static int __sys_setsockopt(int fd, int level, int optname,
 		if (err)
 			goto out_put;
 
+		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level,
+						     &optname, optval, &optlen,
+						     &kernel_optval);
+
+		if (err < 0) {
+			goto out_put;
+		} else if (err > 0) {
+			err = 0;
+			goto out_put;
+		}
+
+		if (kernel_optval) {
+			set_fs(KERNEL_DS);
+			optval = (char __user __force *)kernel_optval;
+		}
+
 		if (level == SOL_SOCKET)
 			err =
 			    sock_setsockopt(sock, level, optname, optval,
@@ -2071,6 +2079,11 @@ static int __sys_setsockopt(int fd, int level, int optname,
 			err =
 			    sock->ops->setsockopt(sock, level, optname, optval,
 						  optlen);
+
+		if (kernel_optval) {
+			set_fs(oldfs);
+			kfree(kernel_optval);
+		}
 out_put:
 		fput_light(sock->file, fput_needed);
 	}
@@ -2093,6 +2106,7 @@ static int __sys_getsockopt(int fd, int level, int optname,
 {
 	int err, fput_needed;
 	struct socket *sock;
+	int max_optlen;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
@@ -2100,6 +2114,8 @@ static int __sys_getsockopt(int fd, int level, int optname,
 		if (err)
 			goto out_put;
 
+		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
+
 		if (level == SOL_SOCKET)
 			err =
 			    sock_getsockopt(sock, level, optname, optval,
@@ -2108,6 +2124,10 @@ static int __sys_getsockopt(int fd, int level, int optname,
 			err =
 			    sock->ops->getsockopt(sock, level, optname, optval,
 						  optlen);
+
+		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
+						     optval, optlen,
+						     max_optlen, err);
 out_put:
 		fput_light(sock->file, fput_needed);
 	}