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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-01 (v2)

The following pull-request contains BPF updates for your *net-next* tree.

We've added 61 non-merge commits during the last 6 day(s) which contain
a total of 153 files changed, 6739 insertions(+), 3367 deletions(-).

The main changes are:

1) pulled work.sysctl from vfs tree with sysctl bpf changes.

2) bpf_link observability, from Andrii.

3) BTF-defined map in map, from Andrii.

4) asan fixes for selftests, from Andrii.

5) Allow bpf_map_lookup_elem for SOCKMAP and SOCKHASH, from Jakub.

6) production cloudflare classifier as a selftes, from Lorenz.

7) bpf_ktime_get_*_ns() helper improvements, from Maciej.

8) unprivileged bpftool feature probe, from Quentin.

9) BPF_ENABLE_STATS command, from Song.

10) enable bpf_[gs]etsockopt() helpers for sock_ops progs, from Stanislav.

11) enable a bunch of common helpers for cg-device, sysctl, sockopt progs,
 from Stanislav.
====================

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

4 files changed, 140 insertions, 133 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 7d6ceaa54d21..dfaf5df13722 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -256,17 +256,6 @@ BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
 					  offset);
 }
 
-BPF_CALL_0(bpf_get_raw_cpu_id)
-{
-	return raw_smp_processor_id();
-}
-
-static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
-	.func		= bpf_get_raw_cpu_id,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-};
-
 static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 			      struct bpf_insn *insn_buf)
 {
@@ -4205,36 +4194,19 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags,
-	   void *, data, u64, size)
-{
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
-
-	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
-}
+#define SOCKOPT_CC_REINIT (1 << 0)
 
-static const struct bpf_func_proto bpf_event_output_data_proto =  {
-	.func		= bpf_event_output_data,
-	.gpl_only       = true,
-	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_CTX,
-	.arg2_type      = ARG_CONST_MAP_PTR,
-	.arg3_type      = ARG_ANYTHING,
-	.arg4_type      = ARG_PTR_TO_MEM,
-	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
-};
-
-BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
-	   int, level, int, optname, char *, optval, int, optlen)
+static int _bpf_setsockopt(struct sock *sk, int level, int optname,
+			   char *optval, int optlen, u32 flags)
 {
-	struct sock *sk = bpf_sock->sk;
 	int ret = 0;
 	int val;
 
 	if (!sk_fullsock(sk))
 		return -EINVAL;
 
+	sock_owned_by_me(sk);
+
 	if (level == SOL_SOCKET) {
 		if (optlen != sizeof(int))
 			return -EINVAL;
@@ -4329,7 +4301,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
-			bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN;
+			bool reinit = flags & SOCKOPT_CC_REINIT;
 
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
@@ -4376,24 +4348,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_setsockopt_proto = {
-	.func		= bpf_setsockopt,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_ANYTHING,
-	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
-};
-
-BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
-	   int, level, int, optname, char *, optval, int, optlen)
+static int _bpf_getsockopt(struct sock *sk, int level, int optname,
+			   char *optval, int optlen)
 {
-	struct sock *sk = bpf_sock->sk;
-
 	if (!sk_fullsock(sk))
 		goto err_clear;
+
+	sock_owned_by_me(sk);
+
 #ifdef CONFIG_INET
 	if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
 		struct inet_connection_sock *icsk;
@@ -4459,8 +4421,71 @@ err_clear:
 	return -EINVAL;
 }
 
-static const struct bpf_func_proto bpf_getsockopt_proto = {
-	.func		= bpf_getsockopt,
+BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	u32 flags = 0;
+	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen,
+			       flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = {
+	.func		= bpf_sock_addr_setsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
+	.func		= bpf_sock_addr_getsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	u32 flags = 0;
+	if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
+		flags |= SOCKOPT_CC_REINIT;
+	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen,
+			       flags);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
+	.func		= bpf_sock_ops_setsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = {
+	.func		= bpf_sock_ops_getsockopt,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
@@ -5983,52 +6008,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	return false;
 }
 
-const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
-{
-	switch (func_id) {
-	case BPF_FUNC_map_lookup_elem:
-		return &bpf_map_lookup_elem_proto;
-	case BPF_FUNC_map_update_elem:
-		return &bpf_map_update_elem_proto;
-	case BPF_FUNC_map_delete_elem:
-		return &bpf_map_delete_elem_proto;
-	case BPF_FUNC_map_push_elem:
-		return &bpf_map_push_elem_proto;
-	case BPF_FUNC_map_pop_elem:
-		return &bpf_map_pop_elem_proto;
-	case BPF_FUNC_map_peek_elem:
-		return &bpf_map_peek_elem_proto;
-	case BPF_FUNC_get_prandom_u32:
-		return &bpf_get_prandom_u32_proto;
-	case BPF_FUNC_get_smp_processor_id:
-		return &bpf_get_raw_smp_processor_id_proto;
-	case BPF_FUNC_get_numa_node_id:
-		return &bpf_get_numa_node_id_proto;
-	case BPF_FUNC_tail_call:
-		return &bpf_tail_call_proto;
-	case BPF_FUNC_ktime_get_ns:
-		return &bpf_ktime_get_ns_proto;
-	default:
-		break;
-	}
-
-	if (!capable(CAP_SYS_ADMIN))
-		return NULL;
-
-	switch (func_id) {
-	case BPF_FUNC_spin_lock:
-		return &bpf_spin_lock_proto;
-	case BPF_FUNC_spin_unlock:
-		return &bpf_spin_unlock_proto;
-	case BPF_FUNC_trace_printk:
-		return bpf_get_trace_printk_proto();
-	case BPF_FUNC_jiffies64:
-		return &bpf_jiffies64_proto;
-	default:
-		return NULL;
-	}
-}
+const struct bpf_func_proto bpf_event_output_data_proto __weak;
 
 static const struct bpf_func_proto *
 sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
@@ -6119,6 +6099,22 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_setsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
+			return &bpf_sock_addr_setsockopt_proto;
+		default:
+			return NULL;
+		}
+	case BPF_FUNC_getsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
+			return &bpf_sock_addr_getsockopt_proto;
+		default:
+			return NULL;
+		}
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6213,6 +6209,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_adjust_room_proto;
 	case BPF_FUNC_skb_change_tail:
 		return &bpf_skb_change_tail_proto;
+	case BPF_FUNC_skb_change_head:
+		return &bpf_skb_change_head_proto;
 	case BPF_FUNC_skb_get_tunnel_key:
 		return &bpf_skb_get_tunnel_key_proto;
 	case BPF_FUNC_skb_set_tunnel_key:
@@ -6335,9 +6333,9 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_setsockopt:
-		return &bpf_setsockopt_proto;
+		return &bpf_sock_ops_setsockopt_proto;
 	case BPF_FUNC_getsockopt:
-		return &bpf_getsockopt_proto;
+		return &bpf_sock_ops_getsockopt_proto;
 	case BPF_FUNC_sock_ops_cb_flags_set:
 		return &bpf_sock_ops_cb_flags_set_proto;
 	case BPF_FUNC_sock_map_update:
@@ -8786,6 +8784,10 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 
 	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
 	if (!reuse) {
+		/* Lookup in sock_map can return TCP ESTABLISHED sockets. */
+		if (sk_is_refcounted(selected_sk))
+			sock_put(selected_sk);
+
 		/* reuseport_array has only sk with non NULL sk_reuseport_cb.
 		 * The only (!reuse) case here is - the sk has already been
 		 * unhashed (e.g. by close()), so treat it as -ENOENT.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 39d37d0ef575..3f2263e79e4b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3379,7 +3379,7 @@ EXPORT_SYMBOL(neigh_app_ns);
 static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
 
 static int proc_unres_qlen(struct ctl_table *ctl, int write,
-			   void __user *buffer, size_t *lenp, loff_t *ppos)
+			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int size, ret;
 	struct ctl_table tmp = *ctl;
@@ -3443,8 +3443,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 }
 
 static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
-					   void __user *buffer,
-					   size_t *lenp, loff_t *ppos)
+					   void *buffer, size_t *lenp,
+					   loff_t *ppos)
 {
 	struct ctl_table tmp = *ctl;
 	int ret;
@@ -3457,8 +3457,8 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-int neigh_proc_dointvec(struct ctl_table *ctl, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer,
+			size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
 
@@ -3467,8 +3467,7 @@ int neigh_proc_dointvec(struct ctl_table *ctl, int write,
 }
 EXPORT_SYMBOL(neigh_proc_dointvec);
 
-int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
-				void __user *buffer,
+int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer,
 				size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3479,8 +3478,8 @@ int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
 EXPORT_SYMBOL(neigh_proc_dointvec_jiffies);
 
 static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
-					      void __user *buffer,
-					      size_t *lenp, loff_t *ppos)
+					      void *buffer, size_t *lenp,
+					      loff_t *ppos)
 {
 	int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos);
 
@@ -3489,8 +3488,7 @@ static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
 }
 
 int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
-				   void __user *buffer,
-				   size_t *lenp, loff_t *ppos)
+				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
 
@@ -3500,8 +3498,8 @@ int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
 EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies);
 
 static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
-					  void __user *buffer,
-					  size_t *lenp, loff_t *ppos)
+					  void *buffer, size_t *lenp,
+					  loff_t *ppos)
 {
 	int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos);
 
@@ -3510,8 +3508,8 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
 }
 
 static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
-					  void __user *buffer,
-					  size_t *lenp, loff_t *ppos)
+					  void *buffer, size_t *lenp,
+					  loff_t *ppos)
 {
 	struct neigh_parms *p = ctl->extra2;
 	int ret;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index b08dfae10f88..00a26cf2cfe9 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -343,7 +343,14 @@ static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 
 static void *sock_map_lookup(struct bpf_map *map, void *key)
 {
-	return __sock_map_lookup_elem(map, *(u32 *)key);
+	struct sock *sk;
+
+	sk = __sock_map_lookup_elem(map, *(u32 *)key);
+	if (!sk || !sk_fullsock(sk))
+		return NULL;
+	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
+		return NULL;
+	return sk;
 }
 
 static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
@@ -1051,7 +1058,14 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
 
 static void *sock_hash_lookup(struct bpf_map *map, void *key)
 {
-	return __sock_hash_lookup_elem(map, key);
+	struct sock *sk;
+
+	sk = __sock_hash_lookup_elem(map, key);
+	if (!sk || !sk_fullsock(sk))
+		return NULL;
+	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
+		return NULL;
+	return sk;
 }
 
 static void sock_hash_release_progs(struct bpf_map *map)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 9f9e00ba3ad7..0ddb13a6282b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL(sysctl_devconf_inherit_init_net);
 
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int orig_size, size;
 	int ret, i;
@@ -115,8 +115,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 static DEFINE_MUTEX(flow_limit_update_mutex);
 
 static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos)
+				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct sd_flow_limit *cur;
 	struct softnet_data *sd;
@@ -180,10 +179,7 @@ write_unlock:
 		}
 		if (len < *lenp)
 			kbuf[len++] = '\n';
-		if (copy_to_user(buffer, kbuf, len)) {
-			ret = -EFAULT;
-			goto done;
-		}
+		memcpy(buffer, kbuf, len);
 		*lenp = len;
 		*ppos += len;
 	}
@@ -194,8 +190,7 @@ done:
 }
 
 static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
-				       void __user *buffer, size_t *lenp,
-				       loff_t *ppos)
+				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int old, *ptr;
 	int ret;
@@ -217,7 +212,7 @@ static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
 
 #ifdef CONFIG_NET_SCHED
 static int set_default_qdisc(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp, loff_t *ppos)
+			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char id[IFNAMSIZ];
 	struct ctl_table tbl = {
@@ -236,7 +231,7 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 #endif
 
 static int proc_do_dev_weight(struct ctl_table *table, int write,
-			   void __user *buffer, size_t *lenp, loff_t *ppos)
+			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
@@ -251,7 +246,7 @@ static int proc_do_dev_weight(struct ctl_table *table, int write,
 }
 
 static int proc_do_rss_key(struct ctl_table *table, int write,
-			   void __user *buffer, size_t *lenp, loff_t *ppos)
+			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table fake_table;
 	char buf[NETDEV_RSS_KEY_LEN * 3];
@@ -264,7 +259,7 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
 
 #ifdef CONFIG_BPF_JIT
 static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
-					   void __user *buffer, size_t *lenp,
+					   void *buffer, size_t *lenp,
 					   loff_t *ppos)
 {
 	int ret, jit_enable = *(int *)table->data;
@@ -291,8 +286,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 # ifdef CONFIG_HAVE_EBPF_JIT
 static int
 proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
-				    void __user *buffer, size_t *lenp,
-				    loff_t *ppos)
+				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -303,8 +297,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
 
 static int
 proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
-				     void __user *buffer, size_t *lenp,
-				     loff_t *ppos)
+				     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;