summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2020-02-21 15:22:45 -0800
committerDavid S. Miller <davem@davemloft.net>2020-02-21 15:22:45 -0800
commitb105e8e281ac2dbea4229982ad57fbefab05963d (patch)
tree58ea551205dd646d809c789fccb2381b60b00d9e /net
parente65ee2fb54d4745d7b7d9061d7fe33c5c5bf3b06 (diff)
parenteb1e1478b6f4e70d99fee3f49bb7f7143c8c871d (diff)
downloadlinux-b105e8e281ac2dbea4229982ad57fbefab05963d.tar.gz
linux-b105e8e281ac2dbea4229982ad57fbefab05963d.tar.bz2
linux-b105e8e281ac2dbea4229982ad57fbefab05963d.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2020-02-21 The following pull-request contains BPF updates for your *net-next* tree. We've added 25 non-merge commits during the last 4 day(s) which contain a total of 33 files changed, 2433 insertions(+), 161 deletions(-). The main changes are: 1) Allow for adding TCP listen sockets into sock_map/hash so they can be used with reuseport BPF programs, from Jakub Sitnicki. 2) Add a new bpf_program__set_attach_target() helper for adding libbpf support to specify the tracepoint/function dynamically, from Eelco Chaudron. 3) Add bpf_read_branch_records() BPF helper which helps use cases like profile guided optimizations, from Daniel Xu. 4) Enable bpf_perf_event_read_value() in all tracing programs, from Song Liu. 5) Relax BTF mandatory check if only used for libbpf itself e.g. to process BTF defined maps, from Andrii Nakryiko. 6) Move BPF selftests -mcpu compilation attribute from 'probe' to 'v3' as it has been observed that former fails in envs with low memlock, from Yonghong Song. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/core/filter.c27
-rw-r--r--net/core/skmsg.c2
-rw-r--r--net/core/sock.c14
-rw-r--r--net/core/sock_map.c167
-rw-r--r--net/core/sock_reuseport.c50
-rw-r--r--net/ipv4/tcp_bpf.c18
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_ulp.c3
-rw-r--r--net/tls/tls_main.c3
9 files changed, 211 insertions, 75 deletions
diff --git a/net/core/filter.c b/net/core/filter.c
index c180871e606d..925b23de218b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8620,6 +8620,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
struct bpf_map *, map, void *, key, u32, flags)
{
+ bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
struct sock_reuseport *reuse;
struct sock *selected_sk;
@@ -8628,26 +8629,20 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
return -ENOENT;
reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
- if (!reuse)
- /* selected_sk is unhashed (e.g. by close()) after the
- * above map_lookup_elem(). Treat selected_sk has already
- * been removed from the map.
+ if (!reuse) {
+ /* 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.
+ *
+ * Other maps (e.g. sock_map) do not provide this guarantee and
+ * the sk may never be in the reuseport group to begin with.
*/
- return -ENOENT;
+ return is_sockarray ? -ENOENT : -EINVAL;
+ }
if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) {
- struct sock *sk;
-
- if (unlikely(!reuse_kern->reuseport_id))
- /* There is a small race between adding the
- * sk to the map and setting the
- * reuse_kern->reuseport_id.
- * Treat it as the sk has not been added to
- * the bpf map yet.
- */
- return -ENOENT;
+ struct sock *sk = reuse_kern->sk;
- sk = reuse_kern->sk;
if (sk->sk_protocol != selected_sk->sk_protocol)
return -EPROTOTYPE;
else if (sk->sk_family != selected_sk->sk_family)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ded2d5227678..eeb28cb85664 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -512,7 +512,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
refcount_set(&psock->refcnt, 1);
- rcu_assign_sk_user_data(sk, psock);
+ rcu_assign_sk_user_data_nocopy(sk, psock);
sock_hold(sk);
return psock;
diff --git a/net/core/sock.c b/net/core/sock.c
index a4c8fac781ff..e4af4dbc1c9e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1572,13 +1572,14 @@ static inline void sock_lock_init(struct sock *sk)
*/
static void sock_copy(struct sock *nsk, const struct sock *osk)
{
+ const struct proto *prot = READ_ONCE(osk->sk_prot);
#ifdef CONFIG_SECURITY_NETWORK
void *sptr = nsk->sk_security;
#endif
memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));
memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
- osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
+ prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
#ifdef CONFIG_SECURITY_NETWORK
nsk->sk_security = sptr;
@@ -1792,16 +1793,17 @@ static void sk_init_common(struct sock *sk)
*/
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
{
+ struct proto *prot = READ_ONCE(sk->sk_prot);
struct sock *newsk;
bool is_charged = true;
- newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
+ newsk = sk_prot_alloc(prot, priority, sk->sk_family);
if (newsk != NULL) {
struct sk_filter *filter;
sock_copy(newsk, sk);
- newsk->sk_prot_creator = sk->sk_prot;
+ newsk->sk_prot_creator = prot;
/* SANITY */
if (likely(newsk->sk_net_refcnt))
@@ -1863,6 +1865,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
goto out;
}
+ /* Clear sk_user_data if parent had the pointer tagged
+ * as not suitable for copying when cloning.
+ */
+ if (sk_user_data_is_nocopy(newsk))
+ RCU_INIT_POINTER(newsk->sk_user_data, NULL);
+
newsk->sk_err = 0;
newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 3a7a96ab088a..2e0f465295c3 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -10,6 +10,7 @@
#include <linux/skmsg.h>
#include <linux/list.h>
#include <linux/jhash.h>
+#include <linux/sock_diag.h>
struct bpf_stab {
struct bpf_map map;
@@ -31,7 +32,8 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
return ERR_PTR(-EPERM);
if (attr->max_entries == 0 ||
attr->key_size != 4 ||
- attr->value_size != 4 ||
+ (attr->value_size != sizeof(u32) &&
+ attr->value_size != sizeof(u64)) ||
attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
@@ -228,6 +230,30 @@ out:
return ret;
}
+static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk)
+{
+ struct sk_psock *psock;
+ int ret;
+
+ psock = sk_psock_get_checked(sk);
+ if (IS_ERR(psock))
+ return PTR_ERR(psock);
+
+ if (psock) {
+ tcp_bpf_reinit(sk);
+ return 0;
+ }
+
+ psock = sk_psock_init(sk, map->numa_node);
+ if (!psock)
+ return -ENOMEM;
+
+ ret = tcp_bpf_init(sk);
+ if (ret < 0)
+ sk_psock_put(sk, psock);
+ return ret;
+}
+
static void sock_map_free(struct bpf_map *map)
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
@@ -275,7 +301,22 @@ 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 ERR_PTR(-EOPNOTSUPP);
+ return __sock_map_lookup_elem(map, *(u32 *)key);
+}
+
+static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
+{
+ struct sock *sk;
+
+ if (map->value_size != sizeof(u64))
+ return ERR_PTR(-ENOSPC);
+
+ sk = __sock_map_lookup_elem(map, *(u32 *)key);
+ if (!sk)
+ return ERR_PTR(-ENOENT);
+
+ sock_gen_cookie(sk);
+ return &sk->sk_cookie;
}
static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
@@ -334,6 +375,11 @@ static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next)
return 0;
}
+static bool sock_map_redirect_allowed(const struct sock *sk)
+{
+ return sk->sk_state != TCP_LISTEN;
+}
+
static int sock_map_update_common(struct bpf_map *map, u32 idx,
struct sock *sk, u64 flags)
{
@@ -356,7 +402,14 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
if (!link)
return -ENOMEM;
- ret = sock_map_link(map, &stab->progs, sk);
+ /* Only sockets we can redirect into/from in BPF need to hold
+ * refs to parser/verdict progs and have their sk_data_ready
+ * and sk_write_space callbacks overridden.
+ */
+ if (sock_map_redirect_allowed(sk))
+ ret = sock_map_link(map, &stab->progs, sk);
+ else
+ ret = sock_map_link_no_progs(map, sk);
if (ret < 0)
goto out_free;
@@ -391,7 +444,8 @@ out_free:
static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops)
{
return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
- ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+ ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB ||
+ ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;
}
static bool sock_map_sk_is_suitable(const struct sock *sk)
@@ -400,14 +454,26 @@ static bool sock_map_sk_is_suitable(const struct sock *sk)
sk->sk_protocol == IPPROTO_TCP;
}
+static bool sock_map_sk_state_allowed(const struct sock *sk)
+{
+ return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+}
+
static int sock_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 flags)
{
- u32 ufd = *(u32 *)value;
u32 idx = *(u32 *)key;
struct socket *sock;
struct sock *sk;
int ret;
+ u64 ufd;
+
+ if (map->value_size == sizeof(u64))
+ ufd = *(u64 *)value;
+ else
+ ufd = *(u32 *)value;
+ if (ufd > S32_MAX)
+ return -EINVAL;
sock = sockfd_lookup(ufd, &ret);
if (!sock)
@@ -423,7 +489,7 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
}
sock_map_sk_acquire(sk);
- if (sk->sk_state != TCP_ESTABLISHED)
+ if (!sock_map_sk_state_allowed(sk))
ret = -EOPNOTSUPP;
else
ret = sock_map_update_common(map, idx, sk, flags);
@@ -460,13 +526,17 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
struct bpf_map *, map, u32, key, u64, flags)
{
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- tcb->bpf.flags = flags;
- tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key);
- if (!tcb->bpf.sk_redir)
+
+ sk = __sock_map_lookup_elem(map, key);
+ if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+
+ tcb->bpf.flags = flags;
+ tcb->bpf.sk_redir = sk;
return SK_PASS;
}
@@ -483,12 +553,17 @@ const struct bpf_func_proto bpf_sk_redirect_map_proto = {
BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg,
struct bpf_map *, map, u32, key, u64, flags)
{
+ struct sock *sk;
+
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- msg->flags = flags;
- msg->sk_redir = __sock_map_lookup_elem(map, key);
- if (!msg->sk_redir)
+
+ sk = __sock_map_lookup_elem(map, key);
+ if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+
+ msg->flags = flags;
+ msg->sk_redir = sk;
return SK_PASS;
}
@@ -506,6 +581,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_alloc = sock_map_alloc,
.map_free = sock_map_free,
.map_get_next_key = sock_map_get_next_key,
+ .map_lookup_elem_sys_only = sock_map_lookup_sys,
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
.map_lookup_elem = sock_map_lookup,
@@ -680,7 +756,14 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
if (!link)
return -ENOMEM;
- ret = sock_map_link(map, &htab->progs, sk);
+ /* Only sockets we can redirect into/from in BPF need to hold
+ * refs to parser/verdict progs and have their sk_data_ready
+ * and sk_write_space callbacks overridden.
+ */
+ if (sock_map_redirect_allowed(sk))
+ ret = sock_map_link(map, &htab->progs, sk);
+ else
+ ret = sock_map_link_no_progs(map, sk);
if (ret < 0)
goto out_free;
@@ -729,10 +812,17 @@ out_free:
static int sock_hash_update_elem(struct bpf_map *map, void *key,
void *value, u64 flags)
{
- u32 ufd = *(u32 *)value;
struct socket *sock;
struct sock *sk;
int ret;
+ u64 ufd;
+
+ if (map->value_size == sizeof(u64))
+ ufd = *(u64 *)value;
+ else
+ ufd = *(u32 *)value;
+ if (ufd > S32_MAX)
+ return -EINVAL;
sock = sockfd_lookup(ufd, &ret);
if (!sock)
@@ -748,7 +838,7 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key,
}
sock_map_sk_acquire(sk);
- if (sk->sk_state != TCP_ESTABLISHED)
+ if (!sock_map_sk_state_allowed(sk))
ret = -EOPNOTSUPP;
else
ret = sock_hash_update_common(map, key, sk, flags);
@@ -808,7 +898,8 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
return ERR_PTR(-EPERM);
if (attr->max_entries == 0 ||
attr->key_size == 0 ||
- attr->value_size != 4 ||
+ (attr->value_size != sizeof(u32) &&
+ attr->value_size != sizeof(u64)) ||
attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
if (attr->key_size > MAX_BPF_STACK)
@@ -885,6 +976,26 @@ static void sock_hash_free(struct bpf_map *map)
kfree(htab);
}
+static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
+{
+ struct sock *sk;
+
+ if (map->value_size != sizeof(u64))
+ return ERR_PTR(-ENOSPC);
+
+ sk = __sock_hash_lookup_elem(map, key);
+ if (!sk)
+ return ERR_PTR(-ENOENT);
+
+ sock_gen_cookie(sk);
+ return &sk->sk_cookie;
+}
+
+static void *sock_hash_lookup(struct bpf_map *map, void *key)
+{
+ return __sock_hash_lookup_elem(map, key);
+}
+
static void sock_hash_release_progs(struct bpf_map *map)
{
psock_progs_drop(&container_of(map, struct bpf_htab, map)->progs);
@@ -916,13 +1027,17 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
struct bpf_map *, map, void *, key, u64, flags)
{
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- tcb->bpf.flags = flags;
- tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key);
- if (!tcb->bpf.sk_redir)
+
+ sk = __sock_hash_lookup_elem(map, key);
+ if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+
+ tcb->bpf.flags = flags;
+ tcb->bpf.sk_redir = sk;
return SK_PASS;
}
@@ -939,12 +1054,17 @@ const struct bpf_func_proto bpf_sk_redirect_hash_proto = {
BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg,
struct bpf_map *, map, void *, key, u64, flags)
{
+ struct sock *sk;
+
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- msg->flags = flags;
- msg->sk_redir = __sock_hash_lookup_elem(map, key);
- if (!msg->sk_redir)
+
+ sk = __sock_hash_lookup_elem(map, key);
+ if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+
+ msg->flags = flags;
+ msg->sk_redir = sk;
return SK_PASS;
}
@@ -964,7 +1084,8 @@ const struct bpf_map_ops sock_hash_ops = {
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
- .map_lookup_elem = sock_map_lookup,
+ .map_lookup_elem = sock_hash_lookup,
+ .map_lookup_elem_sys_only = sock_hash_lookup_sys,
.map_release_uref = sock_hash_release_progs,
.map_check_btf = map_check_no_btf,
};
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 91e9f2223c39..adcb3aea576d 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -16,27 +16,8 @@
DEFINE_SPINLOCK(reuseport_lock);
-#define REUSEPORT_MIN_ID 1
static DEFINE_IDA(reuseport_ida);
-int reuseport_get_id(struct sock_reuseport *reuse)
-{
- int id;
-
- if (reuse->reuseport_id)
- return reuse->reuseport_id;
-
- id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0,
- /* Called under reuseport_lock */
- GFP_ATOMIC);
- if (id < 0)
- return id;
-
- reuse->reuseport_id = id;
-
- return reuse->reuseport_id;
-}
-
static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
{
unsigned int size = sizeof(struct sock_reuseport) +
@@ -55,6 +36,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
int reuseport_alloc(struct sock *sk, bool bind_inany)
{
struct sock_reuseport *reuse;
+ int id, ret = 0;
/* bh lock used since this function call may precede hlist lock in
* soft irq of receive path or setsockopt from process context
@@ -78,10 +60,18 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
reuse = __reuseport_alloc(INIT_SOCKS);
if (!reuse) {
- spin_unlock_bh(&reuseport_lock);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
+ id = ida_alloc(&reuseport_ida, GFP_ATOMIC);
+ if (id < 0) {
+ kfree(reuse);
+ ret = id;
+ goto out;
+ }
+
+ reuse->reuseport_id = id;
reuse->socks[0] = sk;
reuse->num_socks = 1;
reuse->bind_inany = bind_inany;
@@ -90,7 +80,7 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
out:
spin_unlock_bh(&reuseport_lock);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(reuseport_alloc);
@@ -134,8 +124,7 @@ static void reuseport_free_rcu(struct rcu_head *head)
reuse = container_of(head, struct sock_reuseport, rcu);
sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1));
- if (reuse->reuseport_id)
- ida_simple_remove(&reuseport_ida, reuse->reuseport_id);
+ ida_free(&reuseport_ida, reuse->reuseport_id);
kfree(reuse);
}
@@ -199,12 +188,15 @@ void reuseport_detach_sock(struct sock *sk)
reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
lockdep_is_held(&reuseport_lock));
- /* At least one of the sk in this reuseport group is added to
- * a bpf map. Notify the bpf side. The bpf map logic will
- * remove the sk if it is indeed added to a bpf map.
+ /* Notify the bpf side. The sk may be added to a sockarray
+ * map. If so, sockarray logic will remove it from the map.
+ *
+ * Other bpf map types that work with reuseport, like sockmap,
+ * don't need an explicit callback from here. They override sk
+ * unhash/close ops to remove the sk from the map before we
+ * get to this point.
*/
- if (reuse->reuseport_id)
- bpf_sk_reuseport_detach(sk);
+ bpf_sk_reuseport_detach(sk);
rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 8a01428f80c1..7d6e1b75d4d4 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -645,8 +645,10 @@ static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock)
/* Reinit occurs when program types change e.g. TCP_BPF_TX is removed
* or added requiring sk_prot hook updates. We keep original saved
* hooks in this case.
+ *
+ * Pairs with lockless read in sk_clone_lock().
*/
- sk->sk_prot = &tcp_bpf_prots[family][config];
+ WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
}
static int tcp_bpf_assert_proto_ops(struct proto *ops)
@@ -691,3 +693,17 @@ int tcp_bpf_init(struct sock *sk)
rcu_read_unlock();
return 0;
}
+
+/* If a child got cloned from a listening socket that had tcp_bpf
+ * protocol callbacks installed, we need to restore the callbacks to
+ * the default ones because the child does not inherit the psock state
+ * that tcp_bpf callbacks expect.
+ */
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+ int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
+ struct proto *prot = newsk->sk_prot;
+
+ if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
+ newsk->sk_prot = sk->sk_prot_creator;
+}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ad3b56d9fa71..c8274371c3d0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,6 +548,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->fastopen_req = NULL;
RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
+ tcp_bpf_clone(sk, newsk);
+
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
return newsk;
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 38d3ad141161..6c43fa189195 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -106,7 +106,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto,
if (!icsk->icsk_ulp_ops) {
sk->sk_write_space = write_space;
- sk->sk_prot = proto;
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, proto);
return;
}
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 94774c0e5ff3..82225bcc1117 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -742,7 +742,8 @@ static void tls_update(struct sock *sk, struct proto *p,
ctx->sk_write_space = write_space;
ctx->sk_proto = p;
} else {
- sk->sk_prot = p;
+ /* Pairs with lockless read in sk_clone_lock(). */
+ WRITE_ONCE(sk->sk_prot, p);
sk->sk_write_space = write_space;
}
}