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

Alexei Starovoitov says:

====================
pull-request: bpf 2019-07-25

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

The main changes are:

1) fix segfault in libbpf, from Andrii.

2) fix gso_segs access, from Eric.

3) tls/sockmap fixes, from Jakub and John.
====================

Signed-off-by: David S. Miller <[email protected]>

Documentation/networking/tls-offload.rst

@@ -513,3 +513,9 @@ Redirects leak clear text
 
 In the RX direction, if segment has already been decrypted by the device
 and it gets redirected or mirrored - clear text will be transmitted out.
+
+shutdown() doesn't clear TLS state
+----------------------------------
+
+shutdown() system call allows for a TLS socket to be reused as a different
+connection. Offload doesn't currently handle that.

include/linux/filter.h

@@ -24,6 +24,7 @@
 
 #include <net/sch_generic.h>
 
+#include <asm/byteorder.h>
 #include <uapi/linux/filter.h>
 #include <uapi/linux/bpf.h>
 
@@ -747,6 +748,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 	return size <= size_default && (size & (size - 1)) == 0;
 }
 
+static inline u8
+bpf_ctx_narrow_load_shift(u32 off, u32 size, u32 size_default)
+{
+	u8 load_off = off & (size_default - 1);
+
+#ifdef __LITTLE_ENDIAN
+	return load_off * 8;
+#else
+	return (size_default - (load_off + size)) * 8;
+#endif
+}
+
 #define bpf_ctx_wide_access_ok(off, size, type, field)			\
 	(size == sizeof(__u64) &&					\
 	off >= offsetof(type, field) &&					\

include/linux/skmsg.h

@@ -354,7 +354,13 @@ static inline void sk_psock_restore_proto(struct sock *sk,
 	sk->sk_write_space = psock->saved_write_space;
 
 	if (psock->sk_proto) {
-		sk->sk_prot = psock->sk_proto;
+		struct inet_connection_sock *icsk = inet_csk(sk);
+		bool has_ulp = !!icsk->icsk_ulp_data;
+
+		if (has_ulp)
+			tcp_update_ulp(sk, psock->sk_proto);
+		else
+			sk->sk_prot = psock->sk_proto;
 		psock->sk_proto = NULL;
 	}
 }

include/net/tcp.h

@@ -2108,6 +2108,8 @@ struct tcp_ulp_ops {
 
 	/* initialize ulp */
 	int (*init)(struct sock *sk);
+	/* update ulp */
+	void (*update)(struct sock *sk, struct proto *p);
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 
@@ -2119,6 +2121,7 @@ void tcp_unregister_ulp(struct tcp_ulp_ops *type);
 int tcp_set_ulp(struct sock *sk, const char *name);
 void tcp_get_available_ulp(char *buf, size_t len);
 void tcp_cleanup_ulp(struct sock *sk);
+void tcp_update_ulp(struct sock *sk, struct proto *p);
 
 #define MODULE_ALIAS_TCP_ULP(name)				\
 	__MODULE_INFO(alias, alias_userspace, name);		\

include/net/tls.h

@@ -107,9 +107,7 @@ struct tls_device {
 enum {
 	TLS_BASE,
 	TLS_SW,
-#ifdef CONFIG_TLS_DEVICE
 	TLS_HW,
-#endif
 	TLS_HW_RECORD,
 	TLS_NUM_CONFIG,
 };
@@ -162,6 +160,7 @@ struct tls_sw_context_tx {
 	int async_capable;
 
 #define BIT_TX_SCHEDULED	0
+#define BIT_TX_CLOSING		1
 	unsigned long tx_bitmask;
 };
 
@@ -272,6 +271,8 @@ struct tls_context {
 	unsigned long flags;
 
 	/* cache cold stuff */
+	struct proto *sk_proto;
+
 	void (*sk_destruct)(struct sock *sk);
 	void (*sk_proto_close)(struct sock *sk, long timeout);
 
@@ -289,6 +290,8 @@ struct tls_context {
 
 	struct list_head list;
 	refcount_t refcount;
+
+	struct work_struct gc;
 };
 
 enum tls_offload_ctx_dir {
@@ -355,13 +358,17 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
 		  unsigned int optlen);
 
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
+void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
+void tls_sw_strparser_done(struct tls_context *tls_ctx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags);
-void tls_sw_close(struct sock *sk, long timeout);
-void tls_sw_free_resources_tx(struct sock *sk);
+void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
+void tls_sw_release_resources_tx(struct sock *sk);
+void tls_sw_free_ctx_tx(struct tls_context *tls_ctx);
 void tls_sw_free_resources_rx(struct sock *sk);
 void tls_sw_release_resources_rx(struct sock *sk);
+void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
 bool tls_sw_stream_read(const struct sock *sk);

kernel/bpf/verifier.c

@@ -8616,8 +8616,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 
 		if (is_narrower_load && size < target_size) {
-			u8 shift = (off & (size_default - 1)) * 8;
-
+			u8 shift = bpf_ctx_narrow_load_shift(off, size,
+							     size_default);
 			if (ctx_field_size <= 4) {
 				if (shift)
 					insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,

net/core/filter.c

@@ -7455,12 +7455,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct __sk_buff, gso_segs):
 		/* si->dst_reg = skb_shinfo(SKB); */
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct sk_buff, head));
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
 				      BPF_REG_AX, si->src_reg,
 				      offsetof(struct sk_buff, end));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_buff, head));
 		*insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
 #else
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),

net/core/skmsg.c

@@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy);
 
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
-	rcu_assign_sk_user_data(sk, NULL);
 	sk_psock_cork_free(psock);
 	sk_psock_zap_ingress(psock);
-	sk_psock_restore_proto(sk, psock);
 
 	write_lock_bh(&sk->sk_callback_lock);
+	sk_psock_restore_proto(sk, psock);
+	rcu_assign_sk_user_data(sk, NULL);
 	if (psock->progs.skb_parser)
 		sk_psock_stop_strp(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);

net/core/sock_map.c

@@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map)
 	raw_spin_unlock_bh(&stab->lock);
 	rcu_read_unlock();
 
+	synchronize_rcu();
+
 	bpf_map_area_free(stab->sks);
 	kfree(stab);
 }
@@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 			     struct sock **psk)
 {
 	struct sock *sk;
+	int err = 0;
 
 	raw_spin_lock_bh(&stab->lock);
 	sk = *psk;
 	if (!sk_test || sk_test == sk)
-		*psk = NULL;
+		sk = xchg(psk, NULL);
+
+	if (likely(sk))
+		sock_map_unref(sk, psk);
+	else
+		err = -EINVAL;
+
 	raw_spin_unlock_bh(&stab->lock);
-	if (unlikely(!sk))
-		return -EINVAL;
-	sock_map_unref(sk, psk);
-	return 0;
+	return err;
 }
 
 static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk,
@@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 				  struct sock *sk, u64 flags)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sk_psock_link *link;
 	struct sk_psock *psock;
 	struct sock *osk;
@@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 		return -EINVAL;
 	if (unlikely(idx >= map->max_entries))
 		return -E2BIG;
+	if (unlikely(icsk->icsk_ulp_data))
+		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)

net/ipv4/tcp_ulp.c

@@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
 	rcu_read_unlock();
 }
 
+void tcp_update_ulp(struct sock *sk, struct proto *proto)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (!icsk->icsk_ulp_ops) {
+		sk->sk_prot = proto;
+		return;
+	}
+
+	if (icsk->icsk_ulp_ops->update)
+		icsk->icsk_ulp_ops->update(sk, proto);
+}
+
 void tcp_cleanup_ulp(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);