IB/hfi1: Serve the most starved iowait entry first

When an egress resource(SDMA descriptors, pio credits) is not available,
a sending thread will be put on the resource's wait queue. When the
resource becomes available again, up to a fixed number of sending threads
can be awakened sequentially and removed from the wait queue, depending
on the number of waiting threads and the number of free resources. Since
each awakened sending thread will send as many packets as possible, it
is highly likely that the first sending thread will consume all the
egress resources. Subsequently, it will be put back to the end of the wait
queue. Depending on the timing when the later sending threads wake up,
they may not be able to send any packet and be again put back to the end
of the wait queue sequentially, right behind the first sending thread.
This starvation cycle continues until some sending threads exceed their
retry limit and consequently fail.

This patch fixes the issue by two simple approaches:
(1) Any starved sending thread will be put to the head of the wait queue
while a served sending thread will be put to the tail;
(2) The most starved sending thread will be served first.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 68 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h
index d9740ddea6f1..591697d85eed 100644
--- a/drivers/infiniband/hw/hfi1/iowait.h
+++ b/drivers/infiniband/hw/hfi1/iowait.h
@@ -106,7 +106,9 @@ struct iowait {
 		struct sdma_engine *sde,
 		struct iowait *wait,
 		struct sdma_txreq *tx,
-		unsigned seq);
+		uint seq,
+		bool pkts_sent
+		);
 	void (*wakeup)(struct iowait *wait, int reason);
 	void (*sdma_drained)(struct iowait *wait);
 	seqlock_t *lock;
@@ -118,6 +120,7 @@ struct iowait {
 	u32 count;
 	u32 tx_limit;
 	u32 tx_count;
+	u8 starved_cnt;
 };
 
 #define SDMA_AVAIL_REASON 0
@@ -143,7 +146,8 @@ static inline void iowait_init(
 		struct sdma_engine *sde,
 		struct iowait *wait,
 		struct sdma_txreq *tx,
-		unsigned seq),
+		uint seq,
+		bool pkts_sent),
 	void (*wakeup)(struct iowait *wait, int reason),
 	void (*sdma_drained)(struct iowait *wait))
 {
@@ -305,4 +309,66 @@ static inline struct sdma_txreq *iowait_get_txhead(struct iowait *wait)
 	return tx;
 }
 
+/**
+ * iowait_queue - Put the iowait on a wait queue
+ * @pkts_sent: have some packets been sent before queuing?
+ * @w: the iowait struct
+ * @wait_head: the wait queue
+ *
+ * This function is called to insert an iowait struct into a
+ * wait queue after a resource (eg, sdma decriptor or pio
+ * buffer) is run out.
+ */
+static inline void iowait_queue(bool pkts_sent, struct iowait *w,
+				struct list_head *wait_head)
+{
+	/*
+	 * To play fair, insert the iowait at the tail of the wait queue if it
+	 * has already sent some packets; Otherwise, put it at the head.
+	 */
+	if (pkts_sent) {
+		list_add_tail(&w->list, wait_head);
+		w->starved_cnt = 0;
+	} else {
+		list_add(&w->list, wait_head);
+		w->starved_cnt++;
+	}
+}
+
+/**
+ * iowait_starve_clear - clear the wait queue's starve count
+ * @pkts_sent: have some packets been sent?
+ * @w: the iowait struct
+ *
+ * This function is called to clear the starve count. If no
+ * packets have been sent, the starve count will not be cleared.
+ */
+static inline void iowait_starve_clear(bool pkts_sent, struct iowait *w)
+{
+	if (pkts_sent)
+		w->starved_cnt = 0;
+}
+
+/**
+ * iowait_starve_find_max - Find the maximum of the starve count
+ * @w: the iowait struct
+ * @max: a variable containing the max starve count
+ * @idx: the index of the current iowait in an array
+ * @max_idx: a variable containing the array index for the
+ *         iowait entry that has the max starve count
+ *
+ * This function is called to compare the starve count of a
+ * given iowait with the given max starve count. The max starve
+ * count and the index will be updated if the iowait's start
+ * count is larger.
+ */
+static inline void iowait_starve_find_max(struct iowait *w, u8 *max,
+					  uint idx, uint *max_idx)
+{
+	if (w->starved_cnt > *max) {
+		*max = w->starved_cnt;
+		*max_idx = idx;
+	}
+}
+
 #endif