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 <[email protected]>

Documentation/bpf/bpf_devel_QA.rst

@@ -20,11 +20,11 @@ Reporting bugs
 Q: How do I report bugs for BPF kernel code?
 --------------------------------------------
 A: Since all BPF kernel development as well as bpftool and iproute2 BPF
-loader development happens through the netdev kernel mailing list,
+loader development happens through the bpf kernel mailing list,
 please report any found issues around BPF to the following mailing
 list:
 
- netdev@vger.kernel.org
+ bpf@vger.kernel.org
 
 This may also include issues related to XDP, BPF tracing, etc.
 
@@ -46,17 +46,12 @@ Submitting patches
 
 Q: To which mailing list do I need to submit my BPF patches?
 ------------------------------------------------------------
-A: Please submit your BPF patches to the netdev kernel mailing list:
+A: Please submit your BPF patches to the bpf kernel mailing list:
 
- [email protected]
-
-Historically, BPF came out of networking and has always been maintained
-by the kernel networking community. Although these days BPF touches
-many other subsystems as well, the patches are still routed mainly
-through the networking community.
+ [email protected]
 
 In case your patch has changes in various different subsystems (e.g.
-tracing, security, etc), make sure to Cc the related kernel mailing
+networking, tracing, security, etc), make sure to Cc the related kernel mailing
 lists and maintainers from there as well, so they are able to review
 the changes and provide their Acked-by's to the patches.
 
@@ -168,7 +163,7 @@ a BPF point of view.
 Be aware that this is not a final verdict that the patch will
 automatically get accepted into net or net-next trees eventually:
 
-On the netdev kernel mailing list reviews can come in at any point
+On the bpf kernel mailing list reviews can come in at any point
 in time. If discussions around a patch conclude that they cannot
 get included as-is, we will either apply a follow-up fix or drop
 them from the trees entirely. Therefore, we also reserve to rebase
@@ -494,15 +489,15 @@ A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have
 that set up, proceed with building the latest LLVM and clang version
 from the git repositories::
 
-     $ git clone http://llvm.org/git/llvm.git
-     $ cd llvm/tools
-     $ git clone --depth 1 http://llvm.org/git/clang.git
-     $ cd ..; mkdir build; cd build
-     $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
+     $ git clone https://github.com/llvm/llvm-project.git
+     $ mkdir -p llvm-project/llvm/build/install
+     $ cd llvm-project/llvm/build
+     $ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
+                -DLLVM_ENABLE_PROJECTS="clang"    \
                 -DBUILD_SHARED_LIBS=OFF           \
                 -DCMAKE_BUILD_TYPE=Release        \
                 -DLLVM_BUILD_RUNTIME=OFF
-     $ make -j $(getconf _NPROCESSORS_ONLN)
+     $ ninja
 
 The built binaries can then be found in the build/bin/ directory, where
 you can point the PATH variable to.

include/linux/skmsg.h

@@ -352,29 +352,15 @@ static inline void sk_psock_update_proto(struct sock *sk,
 	psock->saved_write_space = sk->sk_write_space;
 
 	psock->sk_proto = sk->sk_prot;
-	sk->sk_prot = ops;
+	/* Pairs with lockless read in sk_clone_lock() */
+	WRITE_ONCE(sk->sk_prot, ops);
 }
 
 static inline void sk_psock_restore_proto(struct sock *sk,
 					  struct sk_psock *psock)
 {
 	sk->sk_prot->unhash = psock->saved_unhash;
-
-	if (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,
-				       psock->saved_write_space);
-		} else {
-			sk->sk_prot = psock->sk_proto;
-			sk->sk_write_space = psock->saved_write_space;
-		}
-		psock->sk_proto = NULL;
-	} else {
-		sk->sk_write_space = psock->saved_write_space;
-	}
+	tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 }
 
 static inline void sk_psock_set_state(struct sk_psock *psock,

include/net/sock.h

@@ -527,10 +527,43 @@ enum sk_pacing {
 	SK_PACING_FQ		= 2,
 };
 
+/* Pointer stored in sk_user_data might not be suitable for copying
+ * when cloning the socket. For instance, it can point to a reference
+ * counted object. sk_user_data bottom bit is set if pointer must not
+ * be copied.
+ */
+#define SK_USER_DATA_NOCOPY	1UL
+#define SK_USER_DATA_PTRMASK	~(SK_USER_DATA_NOCOPY)
+
+/**
+ * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
+ * @sk: socket
+ */
+static inline bool sk_user_data_is_nocopy(const struct sock *sk)
+{
+	return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY);
+}
+
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
-#define rcu_dereference_sk_user_data(sk)	rcu_dereference(__sk_user_data((sk)))
-#define rcu_assign_sk_user_data(sk, ptr)	rcu_assign_pointer(__sk_user_data((sk)), ptr)
+#define rcu_dereference_sk_user_data(sk)				\
+({									\
+	void *__tmp = rcu_dereference(__sk_user_data((sk)));		\
+	(void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK);		\
+})
+#define rcu_assign_sk_user_data(sk, ptr)				\
+({									\
+	uintptr_t __tmp = (uintptr_t)(ptr);				\
+	WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK);			\
+	rcu_assign_pointer(__sk_user_data((sk)), __tmp);		\
+})
+#define rcu_assign_sk_user_data_nocopy(sk, ptr)				\
+({									\
+	uintptr_t __tmp = (uintptr_t)(ptr);				\
+	WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK);			\
+	rcu_assign_pointer(__sk_user_data((sk)),			\
+			   __tmp | SK_USER_DATA_NOCOPY);		\
+})
 
 /*
  * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK

include/net/sock_reuseport.h

@@ -55,6 +55,4 @@ static inline bool reuseport_has_conns(struct sock *sk, bool set)
 	return ret;
 }
 
-int reuseport_get_id(struct sock_reuseport *reuse);
-
 #endif  /* _SOCK_REUSEPORT_H */

include/net/tcp.h

@@ -2203,6 +2203,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len);
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 		      struct msghdr *msg, int len, int flags);
+#ifdef CONFIG_NET_SOCK_MSG
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#else
+static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+}
+#endif
 
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF

include/uapi/linux/bpf.h

@@ -2890,6 +2890,25 @@ union bpf_attr {
  *		Obtain the 64bit jiffies
  *	Return
  *		The 64 bit jiffies
+ *
+ * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ *	Description
+ *		For an eBPF program attached to a perf event, retrieve the
+ *		branch records (struct perf_branch_entry) associated to *ctx*
+ *		and store it in	the buffer pointed by *buf* up to size
+ *		*size* bytes.
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
+ *		instead	return the number of bytes required to store all the
+ *		branch entries. If this flag is set, *buf* may be NULL.
+ *
+ *		**-EINVAL** if arguments invalid or **size** not a multiple
+ *		of sizeof(struct perf_branch_entry).
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3010,7 +3029,8 @@ union bpf_attr {
 	FN(probe_read_kernel_str),	\
 	FN(tcp_send_ack),		\
 	FN(send_signal_thread),		\
-	FN(jiffies64),
+	FN(jiffies64),			\
+	FN(read_branch_records),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3089,6 +3109,9 @@ enum bpf_func_id {
 /* BPF_FUNC_sk_storage_get flags */
 #define BPF_SK_STORAGE_GET_F_CREATE	(1ULL << 0)
 
+/* BPF_FUNC_read_branch_records flags. */
+#define BPF_F_GET_BRANCH_RECORDS_SIZE	(1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,

kernel/bpf/reuseport_array.c

@@ -305,11 +305,6 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	if (err)
 		goto put_file_unlock;
 
-	/* Ensure reuse->reuseport_id is set */
-	err = reuseport_get_id(reuse);
-	if (err < 0)
-		goto put_file_unlock;
-
 	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
 	rcu_assign_pointer(array->ptrs[index], nsk);
 	free_osk = osk;

kernel/bpf/verifier.c

@@ -3693,14 +3693,16 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_sk_redirect_map &&
 		    func_id != BPF_FUNC_sock_map_update &&
 		    func_id != BPF_FUNC_map_delete_elem &&
-		    func_id != BPF_FUNC_msg_redirect_map)
+		    func_id != BPF_FUNC_msg_redirect_map &&
+		    func_id != BPF_FUNC_sk_select_reuseport)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_SOCKHASH:
 		if (func_id != BPF_FUNC_sk_redirect_hash &&
 		    func_id != BPF_FUNC_sock_hash_update &&
 		    func_id != BPF_FUNC_map_delete_elem &&
-		    func_id != BPF_FUNC_msg_redirect_hash)
+		    func_id != BPF_FUNC_msg_redirect_hash &&
+		    func_id != BPF_FUNC_sk_select_reuseport)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
@@ -3774,7 +3776,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 			goto error;
 		break;
 	case BPF_FUNC_sk_select_reuseport:
-		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
+		    map->map_type != BPF_MAP_TYPE_SOCKMAP &&
+		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
 	case BPF_FUNC_map_peek_elem:

kernel/trace/bpf_trace.c

@@ -843,6 +843,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_send_signal_proto;
 	case BPF_FUNC_send_signal_thread:
 		return &bpf_send_signal_thread_proto;
+	case BPF_FUNC_perf_event_read_value:
+		return &bpf_perf_event_read_value_proto;
 	default:
 		return NULL;
 	}
@@ -858,8 +860,6 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_get_stack:
 		return &bpf_get_stack_proto;
-	case BPF_FUNC_perf_event_read_value:
-		return &bpf_perf_event_read_value_proto;
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;
@@ -1028,6 +1028,45 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
          .arg3_type      = ARG_CONST_SIZE,
 };
 
+BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
+	   void *, buf, u32, size, u64, flags)
+{
+#ifndef CONFIG_X86
+	return -ENOENT;
+#else
+	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
+	struct perf_branch_stack *br_stack = ctx->data->br_stack;
+	u32 to_copy;
+
+	if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
+		return -EINVAL;
+
+	if (unlikely(!br_stack))
+		return -EINVAL;
+
+	if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
+		return br_stack->nr * br_entry_size;
+
+	if (!buf || (size % br_entry_size != 0))
+		return -EINVAL;
+
+	to_copy = min_t(u32, br_stack->nr * br_entry_size, size);
+	memcpy(buf, br_stack->entries, to_copy);
+
+	return to_copy;
+#endif
+}
+
+static const struct bpf_func_proto bpf_read_branch_records_proto = {
+	.func           = bpf_read_branch_records,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type      = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1040,6 +1079,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_stack_proto_tp;
 	case BPF_FUNC_perf_prog_read_value:
 		return &bpf_perf_prog_read_value_proto;
+	case BPF_FUNC_read_branch_records:
+		return &bpf_read_branch_records_proto;
 	default:
 		return tracing_func_proto(func_id, prog);
 	}

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)

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;