[PATCH 3/3] usb: octeon-hcd: sleep on an hrtimer for far-off periodic transfers

[Orgad Shaneh]

cvmx_usb_schedule() enables the SOF interrupt whenever any pipe has
next_tx_frame in the future, and leaves it enabled until the transfer
is due. An interrupt endpoint keeps such a deadline pending
permanently, so a single attached hub (status pipe polled every 256ms)
costs an interrupt on every SOF - 8000/s in high-speed mode, forever.
On a 500MHz CN5020 that is measurably ~20% of one core spent counting
frames.

The frame counter is resynchronized from HFNUM at the top of every
poll, so the driver does not actually need to see every SOF to know
when a deadline arrives. Sleep on an hrtimer when the nearest deadline
is more than a few frames away (one high-speed frame is 125us) and
keep SOF interrupts only for deadlines that are imminent - or far
enough away to risk the 16383-frame HFNUM wrap, where the interrupt
path still tracks the counter extension.

Measured on a CN5020 board with one 4-port hub attached and idle:
8200 -> 4 USB interrupts/s, with no change in enumeration or transfer
behavior.

Signed-off-by: Orgad Shaneh <orgads@xxxxxxxxx>
---

diff --git a/drivers/usb/host/octeon-hcd.c b/drivers/usb/host/octeon-hcd.c
--- a/drivers/usb/host/octeon-hcd.c
+++ b/drivers/usb/host/octeon-hcd.c
@@ -378,8 +378,22 @@
 	struct cvmx_usb_transaction *active_split;
 	struct cvmx_usb_tx_fifo periodic;
 	struct cvmx_usb_tx_fifo nonperiodic;
+	struct hrtimer sof_timer;
 };
 
+static int cvmx_usb_poll(struct octeon_hcd *usb);
+
+static enum hrtimer_restart octeon_usb_sof_timer(struct hrtimer *t)
+{
+	struct octeon_hcd *usb = container_of(t, struct octeon_hcd, sof_timer);
+	unsigned long flags;
+
+	spin_lock_irqsave(&usb->lock, flags);
+	cvmx_usb_poll(usb);
+	spin_unlock_irqrestore(&usb->lock, flags);
+	return HRTIMER_NORESTART;
+}
+
 /*
  * This macro logically sets a single field in a CSR. It does the sequence
  * read, modify, and write
@@ -1908,6 +1922,7 @@
 	int channel;
 	struct cvmx_usb_pipe *pipe;
 	int need_sof;
+	u64 min_due;
 	enum cvmx_usb_transfer ttype;
 
 	if (usb->init_flags & CVMX_USB_INITIALIZE_FLAGS_NO_DMA) {
@@ -1948,15 +1963,33 @@
 	 * future that might need to be scheduled
 	 */
 	need_sof = 0;
+	min_due = ~0ull;
 	for (ttype = CVMX_USB_TRANSFER_CONTROL;
 	     ttype <= CVMX_USB_TRANSFER_INTERRUPT; ttype++) {
 		list_for_each_entry(pipe, &usb->active_pipes[ttype], node) {
-			if (pipe->next_tx_frame > usb->frame_number) {
-				need_sof = 1;
-				break;
-			}
+			if (pipe->next_tx_frame > usb->frame_number &&
+			    pipe->next_tx_frame < min_due)
+				min_due = pipe->next_tx_frame;
 		}
 	}
+	if (min_due != ~0ull) {
+		u64 delta = min_due - usb->frame_number;
+
+		/*
+		 * frame_number is resynced from HFNUM on every poll, so a
+		 * deadline that is many frames away does not need an
+		 * interrupt on every SOF to count them down - sleep on the
+		 * timer instead and keep SOF interrupts for deadlines within
+		 * a few frames. Stay well below the 16383-frame wrap of
+		 * HFNUM. One (micro)frame is 125us in high-speed mode.
+		 */
+		if (delta <= 4 || delta > 8000)
+			need_sof = 1;
+		else
+			hrtimer_start(&usb->sof_timer,
+				      ns_to_ktime((delta - 2) * 125000),
+				      HRTIMER_MODE_REL);
+	}
 	USB_SET_FIELD32(CVMX_USBCX_GINTMSK(usb->index),
 			cvmx_usbcx_gintmsk, sofmsk, need_sof);
 }
@@ -3646,6 +3679,8 @@
 	usb = (struct octeon_hcd *)hcd->hcd_priv;
 
 	spin_lock_init(&usb->lock);
+	hrtimer_setup(&usb->sof_timer, octeon_usb_sof_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	usb->init_flags = initialize_flags;
 
@@ -3696,6 +3731,7 @@
 	unsigned long flags;
 
 	usb_remove_hcd(hcd);
+	hrtimer_cancel(&usb->sof_timer);
 	spin_lock_irqsave(&usb->lock, flags);
 	status = cvmx_usb_shutdown(usb);
 	spin_unlock_irqrestore(&usb->lock, flags);
-- 
2.47.0