[PATCH net-next v9 13/15] net: homa: create homa_timer.c

[John Ousterhout <ouster@cs.stanford.edu>]

This file contains code that wakes up periodically to check for
missing data, initiate retransmissions, and declare peer nodes
"dead".

Signed-off-by: John Ousterhout <ouster@cs.stanford.edu>

---
Changes for v9:
* Reflect changes in socket and peer management
* Minor name changes for clarity

Changes for v7:
* Interface changes to homa_sock_start_scan etc.
* Remove locker argument from locking functions
* Use u64 and __u64 properly
---
 net/homa/homa_impl.h  |   3 +
 net/homa/homa_timer.c | 158 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 161 insertions(+)
 create mode 100644 net/homa/homa_timer.c

diff --git a/net/homa/homa_impl.h b/net/homa/homa_impl.h
index 4f9fd9997d28..b3243b4b3669 100644
--- a/net/homa/homa_impl.h
+++ b/net/homa/homa_impl.h
@@ -409,6 +409,9 @@ void     homa_resend_pkt(struct sk_buff *skb, struct homa_rpc *rpc,
 			 struct homa_sock *hsk);
 void     homa_rpc_handoff(struct homa_rpc *rpc);
 void     homa_spin(int ns);
+void     homa_timer(struct homa *homa);
+void     homa_timer_check_rpc(struct homa_rpc *rpc);
+int      homa_timer_main(void *transport);
 struct sk_buff *homa_tx_data_pkt_alloc(struct homa_rpc *rpc,
 				       struct iov_iter *iter, int offset,
 				       int length, int max_seg_data);
diff --git a/net/homa/homa_timer.c b/net/homa/homa_timer.c
new file mode 100644
index 000000000000..e05dba14bc30
--- /dev/null
+++ b/net/homa/homa_timer.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: BSD-2-Clause
+
+/* This file handles timing-related functions for Homa, such as retries
+ * and timeouts.
+ */
+
+#include "homa_impl.h"
+#include "homa_peer.h"
+#include "homa_rpc.h"
+#include "homa_stub.h"
+
+/**
+ * homa_timer_check_rpc() -  Invoked for each RPC during each timer pass; does
+ * most of the work of checking for time-related actions such as sending
+ * resends, aborting RPCs for which there is no response, and sending
+ * requests for acks. It is separate from homa_timer because homa_timer
+ * got too long and deeply indented.
+ * @rpc:     RPC to check; must be locked by the caller.
+ */
+void homa_timer_check_rpc(struct homa_rpc *rpc)
+	__must_hold(&rpc->bucket->lock)
+{
+	struct homa *homa = rpc->hsk->homa;
+	struct homa_resend_hdr resend;
+
+	/* See if we need to request an ack for this RPC. */
+	if (!homa_is_client(rpc->id) && rpc->state == RPC_OUTGOING &&
+	    rpc->msgout.next_xmit_offset >= rpc->msgout.length) {
+		if (rpc->done_timer_ticks == 0) {
+			rpc->done_timer_ticks = homa->timer_ticks;
+		} else {
+			/* >= comparison that handles tick wrap-around. */
+			if ((rpc->done_timer_ticks + homa->request_ack_ticks
+					- 1 - homa->timer_ticks) & 1 << 31) {
+				struct homa_need_ack_hdr h;
+
+				homa_xmit_control(NEED_ACK, &h, sizeof(h), rpc);
+			}
+		}
+	}
+
+	if (rpc->state == RPC_INCOMING) {
+		if (rpc->msgin.num_bpages == 0) {
+			/* Waiting for buffer space, so no problem. */
+			rpc->silent_ticks = 0;
+			return;
+		}
+	} else if (!homa_is_client(rpc->id)) {
+		/* We're the server and we've received the input message;
+		 * no need to worry about retries.
+		 */
+		rpc->silent_ticks = 0;
+		return;
+	}
+
+	if (rpc->state == RPC_OUTGOING) {
+		if (rpc->msgout.next_xmit_offset < rpc->msgout.length) {
+			/* There are granted bytes that we haven't transmitted,
+			 * so no need to be concerned; the ball is in our court.
+			 */
+			rpc->silent_ticks = 0;
+			return;
+		}
+	}
+
+	if (rpc->silent_ticks < homa->resend_ticks)
+		return;
+	if (rpc->silent_ticks >= homa->timeout_ticks) {
+		homa_rpc_abort(rpc, -ETIMEDOUT);
+		return;
+	}
+	if (((rpc->silent_ticks - homa->resend_ticks) % homa->resend_interval)
+			!= 0)
+		return;
+
+	/* Issue a resend for the bytes just after the last ones received
+	 * (gaps in the middle were already handled by homa_gap_retry above).
+	 */
+	if (rpc->msgin.length < 0) {
+		/* Haven't received any data for this message; request
+		 * retransmission of just the first packet (the sender
+		 * will send at least one full packet, regardless of
+		 * the length below).
+		 */
+		resend.offset = htonl(0);
+		resend.length = htonl(100);
+	} else {
+		homa_gap_retry(rpc);
+		resend.offset = htonl(rpc->msgin.recv_end);
+		resend.length = htonl(rpc->msgin.length - rpc->msgin.recv_end);
+		if (resend.length == 0)
+			return;
+	}
+	homa_xmit_control(RESEND, &resend, sizeof(resend), rpc);
+}
+
+/**
+ * homa_timer() - This function is invoked at regular intervals ("ticks")
+ * to implement retries and aborts for Homa.
+ * @homa:    Overall data about the Homa protocol implementation.
+ */
+void homa_timer(struct homa *homa)
+{
+	struct homa_socktab_scan scan;
+	struct homa_sock *hsk;
+	struct homa_rpc *rpc;
+	int total_rpcs = 0;
+	int rpc_count = 0;
+
+	homa->timer_ticks++;
+
+	/* Scan all existing RPCs in all sockets. */
+	for (hsk = homa_socktab_start_scan(homa->socktab, &scan);
+			hsk; hsk = homa_socktab_next(&scan)) {
+		while (hsk->dead_skbs >= homa->dead_buffs_limit)
+			/* If we get here, it means that Homa isn't keeping
+			 * up with RPC reaping, so we'll help out.  See
+			 * "RPC Reaping Strategy" in homa_rpc_reap code for
+			 * details.
+			 */
+			if (homa_rpc_reap(hsk, false) == 0)
+				break;
+
+		if (list_empty(&hsk->active_rpcs) || hsk->shutdown)
+			continue;
+
+		if (!homa_protect_rpcs(hsk))
+			continue;
+		rcu_read_lock();
+		list_for_each_entry_rcu(rpc, &hsk->active_rpcs, active_links) {
+			total_rpcs++;
+			homa_rpc_lock(rpc);
+			if (rpc->state == RPC_IN_SERVICE) {
+				rpc->silent_ticks = 0;
+				homa_rpc_unlock(rpc);
+				continue;
+			}
+			rpc->silent_ticks++;
+			homa_timer_check_rpc(rpc);
+			homa_rpc_unlock(rpc);
+			rpc_count++;
+			if (rpc_count >= 10) {
+				/* Give other kernel threads a chance to run
+				 * on this core.
+				 */
+				rcu_read_unlock();
+				schedule();
+				rcu_read_lock();
+				rpc_count = 0;
+			}
+		}
+		rcu_read_unlock();
+		homa_unprotect_rpcs(hsk);
+	}
+	homa_socktab_end_scan(&scan);
+	homa_skb_release_pages(homa);
+	homa_peer_gc(homa->peertab);
+}
-- 
2.43.0