Please update the commit log:
'''
This patch defines two new wrappers mptcp_sched_get_send() and
mptcp_sched_get_retrans(), invoke get_subflow() of msk->sched in them.
Use them instead of using mptcp_subflow_get_send() or
mptcp_subflow_get_retrans() directly.
Set the subflow pointers array in struct mptcp_sched_data before invoking
get_subflow(), then it can be used in get_subflow() in the BPF contexts.
Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler.
Move sock_owned_by_me() and the fallback check code from
mptcp_subflow_get_send/retrans() into the wrappers.
Redundant subflows are not supported in __mptcp_subflow_push_pending()
yet. This patch adds a placeholder in mptcp_sched_get_send() to pick the
first subflow for the redundant subflows case.
'''
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 12 +++++----
net/mptcp/protocol.h | 4 +--
net/mptcp/sched.c | 63 ++++++++++++++++++++++++++------------------
3 files changed, 47 insertions(+), 32 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b1fae2f747c9..15472d0af508 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1532,7 +1532,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
int ret = 0;
prev_ssk = ssk;
- ssk = mptcp_sched_get_send(msk);
+ ssk = mptcp_subflow_get_send(msk);
/* First check. If the ssk has changed since
* the last round, release prev_ssk
@@ -1593,13 +1593,13 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
info.limit = dfrag->data_len;
len = dfrag->data_len - dfrag->already_sent;
while (len > 0) {
- int ret = 0;
+ int ret = 0, err = 0;
/* the caller already invoked the packet scheduler,
* check for a different subflow usage only after
* spooling the first chunk of data
*/
- xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk));
+ xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk), &err);
if (!xmit_ssk)
goto out;
if (xmit_ssk != ssk) {
@@ -2408,7 +2408,7 @@ static void __mptcp_retrans(struct sock *sk)
mptcp_clean_una_wakeup(sk);
/* first check ssk: need to kick "stale" logic */
- ssk = mptcp_sched_get_retrans(msk);
+ ssk = mptcp_subflow_get_retrans(msk);
dfrag = mptcp_rtx_head(sk);
if (!dfrag) {
if (mptcp_data_fin_enabled(msk)) {
@@ -3090,11 +3090,13 @@ void __mptcp_data_acked(struct sock *sk)
void __mptcp_check_push(struct sock *sk, struct sock *ssk)
{
+ int err = 0;
+
if (!mptcp_send_head(sk))
return;
if (!sock_owned_by_user(sk)) {
- struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk));
+ struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk), &err);
if (xmit_ssk == ssk)
__mptcp_subflow_push_pending(sk, ssk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 95c9ace1437b..406e1bb4fff4 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -635,8 +635,8 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
bool scheduled);
struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk);
-struct sock *mptcp_sched_get_send(struct mptcp_sock *msk);
-struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk);
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err);
+int mptcp_sched_get_retrans(struct mptcp_sock *msk);
static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
{
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 8858e1fc8b74..6d7cc4cba2be 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -114,34 +114,51 @@ static int mptcp_sched_data_init(struct mptcp_sock *msk, bool reinject,
for (; i < MPTCP_SUBFLOWS_MAX; i++)
data->contexts[i] = NULL;
+ msk->snd_burst = 0;
+
return 0;
}
-struct sock *mptcp_sched_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err)
{
+ struct mptcp_subflow_context *subflow;
struct mptcp_sched_data data;
struct sock *ssk = NULL;
- int i;
+ *err = -EINVAL;
sock_owned_by_me((struct sock *)msk);
/* the following check is moved out of mptcp_subflow_get_send */
if (__mptcp_check_fallback(msk)) {
- if (!msk->first)
- return NULL;
- return sk_stream_memory_free(msk->first) ? msk->first : NULL;
+ if (msk->first && sk_stream_memory_free(msk->first)) {
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
+ *err = 0;
+ return msk->first;
+ }
+ return NULL;
}
- if (!msk->sched)
- return mptcp_subflow_get_send(msk);
+ if (!msk->sched) {
+ ssk = mptcp_subflow_get_send(msk);
+ if (!ssk)
+ return NULL;
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+ *err = 0;
+ return ssk;
+ }
mptcp_sched_data_init(msk, false, &data);
msk->sched->get_subflow(msk, &data);
- for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
- if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
- ssk = data.contexts[i]->tcp_sock;
- msk->last_snd = ssk;
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ /* TODO: Redundant subflows are not supported in
+ * __mptcp_subflow_push_pending() yet. Here's a
+ * placeholder to pick the first subflow for the
+ * redundant subflows case.
+ */
+ ssk = subflow->tcp_sock;
+ *err = 0;
break;
}
}
@@ -149,31 +166,27 @@ struct sock *mptcp_sched_get_send(struct mptcp_sock *msk)
return ssk;
}
-struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk)
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
{
struct mptcp_sched_data data;
struct sock *ssk = NULL;
- int i;
sock_owned_by_me((const struct sock *)msk);
/* the following check is moved out of mptcp_subflow_get_retrans */
if (__mptcp_check_fallback(msk))
- return NULL;
+ return -EINVAL;
- if (!msk->sched)
- return mptcp_subflow_get_retrans(msk);
+ if (!msk->sched) {
+ ssk = mptcp_subflow_get_retrans(msk);
+ if (!ssk)
+ return -EINVAL;
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+ return 0;
+ }
mptcp_sched_data_init(msk, true, &data);
msk->sched->get_subflow(msk, &data);
- for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
- if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
- ssk = data.contexts[i]->tcp_sock;
- msk->last_snd = ssk;
- break;
- }
- }
-
- return ssk;
+ return 0;
}
--
2.35.3