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

There were quite a few overlapping sets of changes here.

Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.

Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly.  If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.

In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().

Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.

The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 63 insertions, 32 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index cf5894f0e6eb..24ac9083bc13 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1149,9 +1149,8 @@ static int dev_alloc_name_ns(struct net *net,
         return ret;
 }
 
-static int dev_get_valid_name(struct net *net,
-                              struct net_device *dev,
-                              const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+                       const char *name)
 {
         BUG_ON(!net);
 
@@ -1167,6 +1166,7 @@ static int dev_get_valid_name(struct net *net,
 
         return 0;
 }
+EXPORT_SYMBOL(dev_get_valid_name);
 
 /**
  *      dev_change_name - change name of a device
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 709a4e6fb447..f9c7a88cd981 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -303,7 +303,18 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
         case SIOCSIFTXQLEN:
                 if (ifr->ifr_qlen < 0)
                         return -EINVAL;
-                dev->tx_queue_len = ifr->ifr_qlen;
+                if (dev->tx_queue_len ^ ifr->ifr_qlen) {
+                        unsigned int orig_len = dev->tx_queue_len;
+
+                        dev->tx_queue_len = ifr->ifr_qlen;
+                        err = call_netdevice_notifiers(
+                                        NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+                        err = notifier_to_errno(err);
+                        if (err) {
+                                dev->tx_queue_len = orig_len;
+                                return err;
+                        }
+                }
                 return 0;
 
         case SIOCSIFNAME:
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 0c406306792a..f8fcf450a36e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -452,7 +452,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32);
 
 /* return false if legacy contained non-0 deprecated fields
- * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated
+ * maxtxpkt/maxrxpkt. rest of ksettings always updated
  */
 static bool
 convert_legacy_settings_to_link_ksettings(
@@ -467,8 +467,7 @@ convert_legacy_settings_to_link_ksettings(
          * deprecated legacy fields, and they should not use
          * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS
          */
-        if (legacy_settings->transceiver ||
-            legacy_settings->maxtxpkt ||
+        if (legacy_settings->maxtxpkt ||
             legacy_settings->maxrxpkt)
                 retval = false;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index ccf62f44140a..b79c44cc8145 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1840,31 +1840,31 @@ static const struct bpf_func_proto bpf_redirect_proto = {
         .arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
+           struct bpf_map *, map, u32, key, u64, flags)
 {
-        struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+        struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
         if (unlikely(flags))
                 return SK_ABORTED;
 
-        ri->ifindex = key;
-        ri->flags = flags;
-        ri->map = map;
+        tcb->bpf.key = key;
+        tcb->bpf.flags = flags;
+        tcb->bpf.map = map;
 
         return SK_REDIRECT;
 }
 
-struct sock *do_sk_redirect_map(void)
+struct sock *do_sk_redirect_map(struct sk_buff *skb)
 {
-        struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+        struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
         struct sock *sk = NULL;
 
-        if (ri->map) {
-                sk = __sock_map_lookup_elem(ri->map, ri->ifindex);
+        if (tcb->bpf.map) {
+                sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
 
-                ri->ifindex = 0;
-                ri->map = NULL;
-                /* we do not clear flags for future lookup */
+                tcb->bpf.key = 0;
+                tcb->bpf.map = NULL;
         }
 
         return sk;
@@ -1874,9 +1874,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
         .func           = bpf_sk_redirect_map,
         .gpl_only       = false,
         .ret_type       = RET_INTEGER,
-        .arg1_type      = ARG_CONST_MAP_PTR,
-        .arg2_type      = ARG_ANYTHING,
+        .arg1_type      = ARG_PTR_TO_CTX,
+        .arg2_type      = ARG_CONST_MAP_PTR,
         .arg3_type      = ARG_ANYTHING,
+        .arg4_type      = ARG_ANYTHING,
 };
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -3902,7 +3903,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 
         if (type == BPF_WRITE) {
                 switch (off) {
-                case bpf_ctx_range(struct __sk_buff, mark):
                 case bpf_ctx_range(struct __sk_buff, tc_index):
                 case bpf_ctx_range(struct __sk_buff, priority):
                         break;
@@ -3912,6 +3912,8 @@ static bool sk_skb_is_valid_access(int off, int size,
         }
 
         switch (off) {
+        case bpf_ctx_range(struct __sk_buff, mark):
+                return false;
         case bpf_ctx_range(struct __sk_buff, data):
                 info->reg_type = PTR_TO_PACKET;
                 break;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 20b550d07fe3..04680a53c8dd 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1551,7 +1551,10 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
         [IFLA_LINKINFO]         = { .type = NLA_NESTED },
         [IFLA_NET_NS_PID]       = { .type = NLA_U32 },
         [IFLA_NET_NS_FD]        = { .type = NLA_U32 },
-        [IFLA_IFALIAS]          = { .type = NLA_STRING, .len = IFALIASZ-1 },
+        /* IFLA_IFALIAS is a string, but policy is set to NLA_BINARY to
+         * allow 0-length string (needed to remove an alias).
+         */
+        [IFLA_IFALIAS]          = { .type = NLA_BINARY, .len = IFALIASZ - 1 },
         [IFLA_VFINFO_LIST]      = {. type = NLA_NESTED },
         [IFLA_VF_PORTS]         = { .type = NLA_NESTED },
         [IFLA_PORT_SELF]        = { .type = NLA_NESTED },
@@ -2172,7 +2175,7 @@ static int do_setlink(const struct sk_buff *skb,
                                 dev->tx_queue_len = orig_len;
                                 goto errout;
                         }
-                        status |= DO_SETLINK_NOTIFY;
+                        status |= DO_SETLINK_MODIFIED;
                 }
         }
 
@@ -2332,7 +2335,7 @@ static int do_setlink(const struct sk_buff *skb,
 
 errout:
         if (status & DO_SETLINK_MODIFIED) {
-                if (status & DO_SETLINK_NOTIFY)
+                if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
                         netdev_state_change(dev);
 
                 if (err < 0)
@@ -4373,13 +4376,17 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 
         switch (event) {
         case NETDEV_REBOOT:
+        case NETDEV_CHANGEMTU:
         case NETDEV_CHANGEADDR:
         case NETDEV_CHANGENAME:
         case NETDEV_FEAT_CHANGE:
         case NETDEV_BONDING_FAILOVER:
+        case NETDEV_POST_TYPE_CHANGE:
         case NETDEV_NOTIFY_PEERS:
+        case NETDEV_CHANGEUPPER:
         case NETDEV_RESEND_IGMP:
         case NETDEV_CHANGEINFODATA:
+        case NETDEV_CHANGE_TX_QUEUE_LEN:
                 rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
                                    GFP_KERNEL, NULL);
                 break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 40717501cbdd..97e604d55d55 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1124,9 +1124,13 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 
         err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len);
         if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
+                struct sock *save_sk = skb->sk;
+
                 /* Streams do not free skb on error. Reset to prev state. */
                 msg->msg_iter = orig_iter;
+                skb->sk = sk;
                 ___pskb_trim(skb, orig_len);
+                skb->sk = save_sk;
                 return err;
         }
 
@@ -1895,7 +1899,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
         }
 
         /* If we need update frag list, we are in troubles.
-         * Certainly, it possible to add an offset to skb data,
+         * Certainly, it is possible to add an offset to skb data,
          * but taking into account that pulling is expected to
          * be very rare operation, it is worth to fight against
          * further bloating skb head and crucify ourselves here instead.
diff --git a/net/core/sock.c b/net/core/sock.c
index 35656a9e4e44..759400053110 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1677,12 +1677,17 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                 newsk->sk_dst_pending_confirm = 0;
                 newsk->sk_wmem_queued   = 0;
                 newsk->sk_forward_alloc = 0;
+
+                /* sk->sk_memcg will be populated at accept() time */
+                newsk->sk_memcg = NULL;
+
                 atomic_set(&newsk->sk_drops, 0);
                 newsk->sk_send_head     = NULL;
                 newsk->sk_userlocks     = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
                 atomic_set(&newsk->sk_zckey, 0);
 
                 sock_reset_flag(newsk, SOCK_DONE);
+                cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
                 rcu_read_lock();
                 filter = rcu_dereference(sk->sk_filter);
@@ -1714,9 +1719,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                 newsk->sk_incoming_cpu = raw_smp_processor_id();
                 atomic64_set(&newsk->sk_cookie, 0);
 
-                mem_cgroup_sk_alloc(newsk);
-                cgroup_sk_alloc(&newsk->sk_cgrp_data);
-
                 /*
                  * Before updating sk_refcnt, we must commit prior changes to memory
                  * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index eed1ebf7f29d..b1e0dbea1e8c 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk)
          * soft irq of receive path or setsockopt from process context
          */
         spin_lock_bh(&reuseport_lock);
-        WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-                                            lockdep_is_held(&reuseport_lock)),
-                  "multiple allocations for the same socket");
+
+        /* Allocation attempts can occur concurrently via the setsockopt path
+         * and the bind/hash path.  Nothing to do when we lose the race.
+         */
+        if (rcu_dereference_protected(sk->sk_reuseport_cb,
+                                      lockdep_is_held(&reuseport_lock)))
+                goto out;
+
         reuse = __reuseport_alloc(INIT_SOCKS);
         if (!reuse) {
                 spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk)
         reuse->num_socks = 1;
         rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
+out:
         spin_unlock_bh(&reuseport_lock);
 
         return 0;