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

Pull networking fixes from David Miller:1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 2) Fix TCP retransmission timestamps on passive Fast Open, from Yuchung
    Cheng.

 3) Orphan NFC, we'll take the patches directly into my tree. From
    Johannes Berg.

 4) We can't recycle cloned TCP skbs, from Eric Dumazet.

 5) Some flow dissector bpf test fixes, from Stanislav Fomichev.

 6) Fix RCU marking and warnings in rhashtable, from Herbert Xu.

 7) Fix some potential fib6 leaks, from Eric Dumazet.

 8) Fix a _decode_session4 uninitialized memory read bug fix that got
    lost in a merge. From Florian Westphal.

 9) Fix ipv6 source address routing wrt. exception route entries, from
    Wei Wang.

10) The netdev_xmit_more() conversion was not done %100 properly in mlx5
    driver, fix from Tariq Toukan.

11) Clean up botched merge on netfilter kselftest, from Florian
    Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (74 commits)
  of_net: fix of_get_mac_address retval if compiled without CONFIG_OF
  net: fix kernel-doc warnings for socket.c
  net: Treat sock->sk_drops as an unsigned int when printing
  kselftests: netfilter: fix leftover net/net-next merge conflict
  mlxsw: core: Prevent reading unsupported slave address from SFP EEPROM
  mlxsw: core: Prevent QSFP module initialization for old hardware
  vsock/virtio: Initialize core virtio vsock before registering the driver
  net/mlx5e: Fix possible modify header actions memory leak
  net/mlx5e: Fix no rewrite fields with the same match
  net/mlx5e: Additional check for flow destination comparison
  net/mlx5e: Add missing ethtool driver info for representors
  net/mlx5e: Fix number of vports for ingress ACL configuration
  net/mlx5e: Fix ethtool rxfh commands when CONFIG_MLX5_EN_RXNFC is disabled
  net/mlx5e: Fix wrong xmit_more application
  net/mlx5: Fix peer pf disable hca command
  net/mlx5: E-Switch, Correct type to u16 for vport_num and int for vport_index
  net/mlx5: Add meaningful return codes to status_to_err function
  net/mlx5: Imply MLXFW in mlx5_core
  Revert "tipc: fix modprobe tipc failed after switch order of device registration"
  vsock/virtio: free packets during the socket release
  ...

5 files changed, 29 insertions, 9 deletions

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 191b79948424..1e525d70f833 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -164,6 +164,9 @@ static void dev_map_free(struct bpf_map *map)
 	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
+	/* Make sure prior __dev_map_entry_free() have completed. */
+	rcu_barrier();
+
 	/* To ensure all pending flush operations have completed wait for flush
 	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
 	 * Because the above synchronize_rcu() ensures the map is disconnected
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 192d32e77db3..0f2708fde5f7 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -527,18 +527,30 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	return insn - insn_buf;
 }
 
-static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
+static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map,
+							void *key, const bool mark)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
 
 	if (l) {
-		bpf_lru_node_set_ref(&l->lru_node);
+		if (mark)
+			bpf_lru_node_set_ref(&l->lru_node);
 		return l->key + round_up(map->key_size, 8);
 	}
 
 	return NULL;
 }
 
+static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return __htab_lru_map_lookup_elem(map, key, true);
+}
+
+static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key)
+{
+	return __htab_lru_map_lookup_elem(map, key, false);
+}
+
 static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
@@ -1250,6 +1262,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_lru_map_lookup_elem,
+	.map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,
 	.map_update_elem = htab_lru_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_gen_lookup = htab_lru_map_gen_lookup,
@@ -1281,7 +1294,6 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 {
-	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l;
 	void __percpu *pptr;
 	int ret = -ENOENT;
@@ -1297,8 +1309,9 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 	l = __htab_map_lookup_elem(map, key);
 	if (!l)
 		goto out;
-	if (htab_is_lru(htab))
-		bpf_lru_node_set_ref(&l->lru_node);
+	/* We do not mark LRU map element here in order to not mess up
+	 * eviction heuristics when user space does a map walk.
+	 */
 	pptr = htab_elem_get_ptr(l, map->key_size);
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(value + off,
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index bc53e5b20ddc..84a80b02db99 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -518,7 +518,7 @@ out:
 static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
 {
 	struct bpf_prog *prog;
-	int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
+	int ret = inode_permission(inode, MAY_READ);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ad3ccf82f31d..cb5440b02e82 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -808,7 +808,10 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = map->ops->map_peek_elem(map, value);
 	} else {
 		rcu_read_lock();
-		ptr = map->ops->map_lookup_elem(map, key);
+		if (map->ops->map_lookup_elem_sys_only)
+			ptr = map->ops->map_lookup_elem_sys_only(map, key);
+		else
+			ptr = map->ops->map_lookup_elem(map, key);
 		if (IS_ERR(ptr)) {
 			err = PTR_ERR(ptr);
 		} else if (!ptr) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b496ffdf5f36..f92d6ad5e080 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1297,7 +1297,8 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 }
 
 #ifdef CONFIG_MODULES
-int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module)
+static int bpf_event_notify(struct notifier_block *nb, unsigned long op,
+			    void *module)
 {
 	struct bpf_trace_module *btm, *tmp;
 	struct module *mod = module;
@@ -1336,7 +1337,7 @@ static struct notifier_block bpf_module_nb = {
 	.notifier_call = bpf_event_notify,
 };
 
-int __init bpf_event_init(void)
+static int __init bpf_event_init(void)
 {
 	register_module_notifier(&bpf_module_nb);
 	return 0;