tgupdate: merge t/DO-NOT-MERGE-mptcp-enabled-by-default into t/upstream base

Author: matttbe

net/mptcp/bpf.c

@@ -224,15 +224,26 @@ struct bpf_iter_mptcp_subflow_kern {
 __bpf_kfunc_start_defs();
 
 __bpf_kfunc static struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx(const struct sock *sk)
+bpf_mptcp_subflow_ctx(const struct sock *sk__ign)
 {
+	const struct sock *sk = sk__ign;
+
 	if (sk && sk_fullsock(sk) &&
 	    sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
 		return mptcp_subflow_ctx(sk);
 
 	return NULL;
 }
 
+__bpf_kfunc static struct sock *
+bpf_mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
+{
+	if (!subflow)
+		return NULL;
+
+	return mptcp_subflow_tcp_sock(subflow);
+}
+
 __bpf_kfunc static int
 bpf_iter_mptcp_subflow_new(struct bpf_iter_mptcp_subflow *it,
 			   struct sock *sk)
@@ -277,47 +288,42 @@ bpf_iter_mptcp_subflow_destroy(struct bpf_iter_mptcp_subflow *it)
 {
 }
 
-__bpf_kfunc struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos)
+__bpf_kfunc static bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
 {
-	if (pos >= MPTCP_SUBFLOWS_MAX)
-		return NULL;
-	return data->contexts[pos];
+	return tcp_rtx_queue_empty(sk);
 }
 
-__bpf_kfunc static bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
+__bpf_kfunc static bool bpf_sk_stream_memory_free(const struct sock *sk__ign)
 {
-	return tcp_rtx_queue_empty(sk);
+	const struct sock *sk = sk__ign;
+
+	if (sk && sk_fullsock(sk) &&
+	    sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
+		return sk_stream_memory_free(sk);
+
+	return NULL;
 }
 
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(bpf_mptcp_common_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_mptcp_subflow_tcp_sock, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_destroy, KF_ITER_DESTROY)
-BTF_KFUNCS_END(bpf_mptcp_common_kfunc_ids)
-
-static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
-	.owner	= THIS_MODULE,
-	.set	= &bpf_mptcp_common_kfunc_ids,
-};
-
-BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)
 BTF_ID_FLAGS(func, mptcp_subflow_set_scheduled)
-BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx_by_pos)
 BTF_ID_FLAGS(func, mptcp_subflow_active)
 BTF_ID_FLAGS(func, mptcp_set_timeout)
 BTF_ID_FLAGS(func, mptcp_wnd_end)
-BTF_ID_FLAGS(func, tcp_stream_memory_free)
+BTF_ID_FLAGS(func, bpf_sk_stream_memory_free, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_mptcp_subflow_queues_empty)
 BTF_ID_FLAGS(func, mptcp_pm_subflow_chk_stale, KF_SLEEPABLE)
-BTF_KFUNCS_END(bpf_mptcp_sched_kfunc_ids)
+BTF_KFUNCS_END(bpf_mptcp_common_kfunc_ids)
 
-static const struct btf_kfunc_id_set bpf_mptcp_sched_kfunc_set = {
+static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
 	.owner	= THIS_MODULE,
-	.set	= &bpf_mptcp_sched_kfunc_ids,
+	.set	= &bpf_mptcp_common_kfunc_ids,
 };
 
 static int __init bpf_mptcp_kfunc_init(void)
@@ -328,7 +334,7 @@ static int __init bpf_mptcp_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCKOPT,
 					       &bpf_mptcp_common_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
-					       &bpf_mptcp_sched_kfunc_set);
+					       &bpf_mptcp_common_kfunc_set);
 #ifdef CONFIG_BPF_JIT
 	ret = ret ?: register_bpf_struct_ops(&bpf_mptcp_sched_ops, mptcp_sched_ops);
 #endif

net/mptcp/protocol.h

@@ -718,8 +718,6 @@ void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
 u64 mptcp_wnd_end(const struct mptcp_sock *msk);
 void mptcp_set_timeout(struct sock *sk);
-struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos);
 struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);

net/mptcp/sched.c

@@ -157,21 +157,6 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 static void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
 					  struct mptcp_sched_data *data)
 {
-	struct mptcp_subflow_context *subflow;
-	int i = 0;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (i == MPTCP_SUBFLOWS_MAX) {
-			pr_warn_once("too many subflows");
-			break;
-		}
-		mptcp_subflow_set_scheduled(subflow, false);
-		data->contexts[i++] = subflow;
-	}
-	data->subflows = i;
-
-	for (; i < MPTCP_SUBFLOWS_MAX; i++)
-		data->contexts[i] = NULL;
 }
 
 int mptcp_sched_get_send(struct mptcp_sock *msk)

tools/testing/selftests/bpf/progs/mptcp_bpf.h

@@ -45,11 +45,10 @@ mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
 /* ksym */
 extern struct mptcp_subflow_context *
 bpf_mptcp_subflow_ctx(const struct sock *sk) __ksym;
+extern struct sock *
+bpf_mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) __ksym;
 
 extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 					bool scheduled) __ksym;
 
-extern struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos) __ksym;
-
 #endif

tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c

@@ -20,26 +20,16 @@ SEC("struct_ops")
 int BPF_PROG(bpf_bkup_get_send, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	int nr = -1;
-
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		struct mptcp_subflow_context *subflow;
-
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
+	struct mptcp_subflow_context *subflow;
 
+	bpf_for_each(mptcp_subflow, subflow, (struct sock *)msk) {
 		if (!BPF_CORE_READ_BITFIELD_PROBED(subflow, backup) ||
 		    !BPF_CORE_READ_BITFIELD_PROBED(subflow, request_bkup)) {
-			nr = i;
+			mptcp_subflow_set_scheduled(subflow, true);
 			break;
 		}
 	}
 
-	if (nr != -1) {
-		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, nr), true);
-		return -1;
-	}
 	return 0;
 }
 

tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c

@@ -11,15 +11,10 @@ char _license[] SEC("license") = "GPL";
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
-struct bpf_subflow_send_info {
-	__u8 subflow_id;
-	__u64 linger_time;
-};
-
 extern bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) __ksym;
 extern void mptcp_set_timeout(struct sock *sk) __ksym;
 extern __u64 mptcp_wnd_end(const struct mptcp_sock *msk) __ksym;
-extern bool tcp_stream_memory_free(const struct sock *sk, int wake) __ksym;
+extern bool bpf_sk_stream_memory_free(const struct sock *sk) __ksym;
 extern bool bpf_mptcp_subflow_queues_empty(struct sock *sk) __ksym;
 extern void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) __ksym;
 
@@ -44,19 +39,6 @@ static __always_inline bool tcp_rtx_and_write_queues_empty(struct sock *sk)
 	return bpf_mptcp_subflow_queues_empty(sk) && tcp_write_queue_empty(sk);
 }
 
-static __always_inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
-{
-	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
-		return false;
-
-	return tcp_stream_memory_free(sk, wake);
-}
-
-static __always_inline bool sk_stream_memory_free(const struct sock *sk)
-{
-	return __sk_stream_memory_free(sk, 0);
-}
-
 SEC("struct_ops")
 void BPF_PROG(mptcp_sched_burst_init, struct mptcp_sock *msk)
 {
@@ -71,7 +53,7 @@ SEC("struct_ops")
 int BPF_PROG(bpf_burst_get_send, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	struct bpf_subflow_send_info send_info[SSK_MODE_MAX];
+	struct subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
 	__u32 pace, burst, wmem;
@@ -81,18 +63,12 @@ int BPF_PROG(bpf_burst_get_send, struct mptcp_sock *msk,
 
 	/* pick the subflow with the lower wmem/wspace ratio */
 	for (i = 0; i < SSK_MODE_MAX; ++i) {
-		send_info[i].subflow_id = MPTCP_SUBFLOWS_MAX;
+		send_info[i].ssk = NULL;
 		send_info[i].linger_time = -1;
 	}
 
-	for (i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		bool backup;
-
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
-
-		backup = subflow->backup || subflow->request_bkup;
+	bpf_for_each(mptcp_subflow, subflow, sk) {
+		bool backup = subflow->backup || subflow->request_bkup;
 
 		ssk = mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
@@ -110,24 +86,26 @@ int BPF_PROG(bpf_burst_get_send, struct mptcp_sock *msk,
 
 		linger_time = div_u64((__u64)ssk->sk_wmem_queued << 32, pace);
 		if (linger_time < send_info[backup].linger_time) {
-			send_info[backup].subflow_id = i;
+			send_info[backup].ssk = ssk;
 			send_info[backup].linger_time = linger_time;
 		}
 	}
 	mptcp_set_timeout(sk);
 
 	/* pick the best backup if no other subflow is active */
 	if (!nr_active)
-		send_info[SSK_MODE_ACTIVE].subflow_id = send_info[SSK_MODE_BACKUP].subflow_id;
+		send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk;
 
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, send_info[SSK_MODE_ACTIVE].subflow_id);
-	if (!subflow)
+	ssk = send_info[SSK_MODE_ACTIVE].ssk;
+	if (!ssk || !bpf_sk_stream_memory_free(ssk))
 		return -1;
-	ssk = mptcp_subflow_tcp_sock(subflow);
-	if (!ssk || !sk_stream_memory_free(ssk))
+
+	subflow = bpf_mptcp_subflow_ctx(ssk);
+	if (!subflow)
 		return -1;
 
 	burst = min(MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
+	ssk = bpf_core_cast(ssk, struct sock);
 	wmem = ssk->sk_wmem_queued;
 	if (!burst)
 		goto out;
@@ -146,20 +124,16 @@ SEC("struct_ops")
 int BPF_PROG(bpf_burst_get_retrans, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	int backup = MPTCP_SUBFLOWS_MAX, pick = MPTCP_SUBFLOWS_MAX, subflow_id;
+	struct sock *backup = NULL, *pick = NULL;
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
-	struct sock *ssk;
 
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
+	bpf_for_each(mptcp_subflow, subflow, (struct sock *)msk) {
+		struct sock *ssk = bpf_mptcp_subflow_tcp_sock(subflow);
 
-		if (!mptcp_subflow_active(subflow))
+		if (!ssk || !mptcp_subflow_active(subflow))
 			continue;
 
-		ssk = mptcp_subflow_tcp_sock(subflow);
 		/* still data outstanding at TCP level? skip this */
 		if (!tcp_rtx_and_write_queues_empty(ssk)) {
 			mptcp_pm_subflow_chk_stale(msk, ssk);
@@ -168,23 +142,23 @@ int BPF_PROG(bpf_burst_get_retrans, struct mptcp_sock *msk,
 		}
 
 		if (subflow->backup || subflow->request_bkup) {
-			if (backup == MPTCP_SUBFLOWS_MAX)
-				backup = i;
+			if (!backup)
+				backup = ssk;
 			continue;
 		}
 
-		if (pick == MPTCP_SUBFLOWS_MAX)
-			pick = i;
+		if (!pick)
+			pick = ssk;
 	}
 
-	if (pick < MPTCP_SUBFLOWS_MAX) {
-		subflow_id = pick;
+	if (pick)
 		goto out;
-	}
-	subflow_id = min_stale_count > 1 ? backup : MPTCP_SUBFLOWS_MAX;
+	pick = min_stale_count > 1 ? backup : NULL;
 
 out:
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, subflow_id);
+	if (!pick)
+		return -1;
+	subflow = bpf_mptcp_subflow_ctx(pick);
 	if (!subflow)
 		return -1;
 	mptcp_subflow_set_scheduled(subflow, true);

tools/testing/selftests/bpf/progs/mptcp_bpf_first.c

@@ -20,7 +20,13 @@ SEC("struct_ops")
 int BPF_PROG(bpf_first_get_send, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, 0), true);
+	struct mptcp_subflow_context *subflow;
+
+	subflow = bpf_mptcp_subflow_ctx(msk->first);
+	if (!subflow)
+		return -1;
+
+	mptcp_subflow_set_scheduled(subflow, true);
 	return 0;
 }
 

tools/testing/selftests/bpf/progs/mptcp_bpf_red.c

@@ -20,12 +20,10 @@ SEC("struct_ops")
 int BPF_PROG(bpf_red_get_send, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		if (!bpf_mptcp_subflow_ctx_by_pos(data, i))
-			break;
+	struct mptcp_subflow_context *subflow;
 
-		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, i), true);
-	}
+	bpf_for_each(mptcp_subflow, subflow, (struct sock *)msk)
+		mptcp_subflow_set_scheduled(subflow, true);
 
 	return 0;
 }