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

Daniel Borkmann says:

====================
pull-request: bpf 2020-02-07

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

We've added 15 non-merge commits during the last 10 day(s) which contain
a total of 12 files changed, 114 insertions(+), 31 deletions(-).

The main changes are:

1) Various BPF sockmap fixes related to RCU handling in the map's tear-
   down code, from Jakub Sitnicki.

2) Fix macro state explosion in BPF sk_storage map when calculating its
   bucket_log on allocation, from Martin KaFai Lau.

3) Fix potential BPF sockmap update race by rechecking socket's established
   state under lock, from Lorenz Bauer.

4) Fix crash in bpftool on missing xlated instructions when kptr_restrict
   sysctl is set, from Toke Høiland-Jørgensen.

5) Fix i40e's XSK wakeup code to return proper error in busy state and
   various misc fixes in xdpsock BPF sample code, from Maciej Fijalkowski.

6) Fix the way modifiers are skipped in BTF in the verifier while walking
   pointers to avoid program rejection, from Alexei Starovoitov.

7) Fix Makefile for runqslower BPF tool to i) rebuild on libbpf changes and
   ii) to fix undefined reference linker errors for older gcc version due to
   order of passed gcc parameters, from Yulia Kartseva and Song Liu.

8) Fix a trampoline_count BPF kselftest warning about missing braces around
   initializer, from Andrii Nakryiko.

9) Fix up redundant "HAVE" prefix from large INSN limit kernel probe in
   bpftool, from Michal Rostecki.
====================

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

2 files changed, 21 insertions, 12 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 458be6b3eda9..3ab23f698221 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -643,9 +643,10 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 	bpf_map_init_from_attr(&smap->map, attr);
 
+	nbuckets = roundup_pow_of_two(num_possible_cpus());
 	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
-	smap->bucket_log = max_t(u32, 1, ilog2(roundup_pow_of_two(num_possible_cpus())));
-	nbuckets = 1U << smap->bucket_log;
+	nbuckets = max_t(u32, 2, nbuckets);
+	smap->bucket_log = ilog2(nbuckets);
 	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
 
 	ret = bpf_map_charge_init(&smap->map.memory, cost);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 8998e356f423..085cef5857bb 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -234,7 +234,6 @@ static void sock_map_free(struct bpf_map *map)
 	int i;
 
 	synchronize_rcu();
-	rcu_read_lock();
 	raw_spin_lock_bh(&stab->lock);
 	for (i = 0; i < stab->map.max_entries; i++) {
 		struct sock **psk = &stab->sks[i];
@@ -243,13 +242,15 @@ static void sock_map_free(struct bpf_map *map)
 		sk = xchg(psk, NULL);
 		if (sk) {
 			lock_sock(sk);
+			rcu_read_lock();
 			sock_map_unref(sk, psk);
+			rcu_read_unlock();
 			release_sock(sk);
 		}
 	}
 	raw_spin_unlock_bh(&stab->lock);
-	rcu_read_unlock();
 
+	/* wait for psock readers accessing its map link */
 	synchronize_rcu();
 
 	bpf_map_area_free(stab->sks);
@@ -416,14 +417,16 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!sock_map_sk_is_suitable(sk) ||
-	    sk->sk_state != TCP_ESTABLISHED) {
+	if (!sock_map_sk_is_suitable(sk)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
 	sock_map_sk_acquire(sk);
-	ret = sock_map_update_common(map, idx, sk, flags);
+	if (sk->sk_state != TCP_ESTABLISHED)
+		ret = -EOPNOTSUPP;
+	else
+		ret = sock_map_update_common(map, idx, sk, flags);
 	sock_map_sk_release(sk);
 out:
 	fput(sock->file);
@@ -739,14 +742,16 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!sock_map_sk_is_suitable(sk) ||
-	    sk->sk_state != TCP_ESTABLISHED) {
+	if (!sock_map_sk_is_suitable(sk)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
 	sock_map_sk_acquire(sk);
-	ret = sock_hash_update_common(map, key, sk, flags);
+	if (sk->sk_state != TCP_ESTABLISHED)
+		ret = -EOPNOTSUPP;
+	else
+		ret = sock_hash_update_common(map, key, sk, flags);
 	sock_map_sk_release(sk);
 out:
 	fput(sock->file);
@@ -859,19 +864,22 @@ static void sock_hash_free(struct bpf_map *map)
 	int i;
 
 	synchronize_rcu();
-	rcu_read_lock();
 	for (i = 0; i < htab->buckets_num; i++) {
 		bucket = sock_hash_select_bucket(htab, i);
 		raw_spin_lock_bh(&bucket->lock);
 		hlist_for_each_entry_safe(elem, node, &bucket->head, node) {
 			hlist_del_rcu(&elem->node);
 			lock_sock(elem->sk);
+			rcu_read_lock();
 			sock_map_unref(elem->sk, elem);
+			rcu_read_unlock();
 			release_sock(elem->sk);
 		}
 		raw_spin_unlock_bh(&bucket->lock);
 	}
-	rcu_read_unlock();
+
+	/* wait for psock readers accessing its map link */
+	synchronize_rcu();
 
 	bpf_map_area_free(htab->buckets);
 	kfree(htab);