diff mbox series

[net-next,1/5] mptcp: really share subflow snd_wnd

Message ID 20220504215408.349318-2-mathew.j.martineau@linux.intel.com (mailing list archive)
State Accepted
Commit b713d0067574e15cddd08ee7f25acd535b7437cf
Delegated to: Netdev Maintainers
Headers show
Series mptcp: Improve MPTCP-level window tracking | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 3 this patch: 3
netdev/cc_maintainers success CCed 8 of 8 maintainers
netdev/build_clang success Errors and warnings before: 9 this patch: 9
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 3 this patch: 3
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Mat Martineau May 4, 2022, 9:54 p.m. UTC 
From: Paolo Abeni <pabeni@redhat.com>

As per RFC, mptcp subflows use a "shared" snd_wnd: the effective
window is the maximum among the current values received on all
subflows. Without such feature a data transfer using multiple
subflows could block.

Window sharing is currently implemented in the RX side:
__tcp_select_window uses the mptcp-level receive buffer to compute
the announced window.

That is not enough: the TCP stack will stick to the window size
received on the given subflow; we need to propagate the msk window
value on each subflow at xmit time.

Change the packet scheduler to ignore the subflow level window
and use instead the msk level one

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
---
 net/mptcp/protocol.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)
diff mbox series

Patch

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 52ed2c0ac901..97a375eabd34 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1141,19 +1141,20 @@  struct mptcp_sendmsg_info {
 	bool data_lock_held;
 };
 
-static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
-				    int avail_size)
+static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk,
+				    u64 data_seq, int avail_size)
 {
 	u64 window_end = mptcp_wnd_end(msk);
+	u64 mptcp_snd_wnd;
 
 	if (__mptcp_check_fallback(msk))
 		return avail_size;
 
-	if (!before64(data_seq + avail_size, window_end)) {
-		u64 allowed_size = window_end - data_seq;
+	mptcp_snd_wnd = window_end - data_seq;
+	avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size);
 
-		return min_t(unsigned int, allowed_size, avail_size);
-	}
+	if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd))
+		tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd);
 
 	return avail_size;
 }
@@ -1305,7 +1306,7 @@  static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	}
 
 	/* Zero window and all data acked? Probe. */
-	copy = mptcp_check_allowed_size(msk, data_seq, copy);
+	copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy);
 	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
@@ -1498,11 +1499,16 @@  static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	 * to check that subflow has a non empty cwin.
 	 */
 	ssk = send_info[SSK_MODE_ACTIVE].ssk;
-	if (!ssk || !sk_stream_memory_free(ssk) || !tcp_sk(ssk)->snd_wnd)
+	if (!ssk || !sk_stream_memory_free(ssk))
 		return NULL;
 
-	burst = min_t(int, MPTCP_SEND_BURST_SIZE, tcp_sk(ssk)->snd_wnd);
+	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
 	wmem = READ_ONCE(ssk->sk_wmem_queued);
+	if (!burst) {
+		msk->last_snd = NULL;
+		return ssk;
+	}
+
 	subflow = mptcp_subflow_ctx(ssk);
 	subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
 					   READ_ONCE(ssk->sk_pacing_rate) * burst,