[PATCH] USB: ehci-hcd updates

This should apply to 2.5.59 too.  It seems to get rid of some pesky
hangs, on at least some hardware, but I won't have time to test it
on either VIA version ... maybe someone else will make the time?  :)

      New QH state prevents a re-activation race
	- nobody can un-halt a qh before its cleanup is done
	- resubmit-from-completion had this race (some usbtest cases)
	  as could some normal submit paths on busy endpoints (storage)
	- faster controllers would trip on this more consistently

      Queues of qtds
	- work harder to avoid ever modifing any qh in software
	- short reads block queue advance much less often
	- be more cautious with large (>~19KB) unaligned buffers

      Unlinking urbs
	- if qtd unlinked is at queue head, use its latest status
	  (main effect is reporting bytes from partial transfers)
	- another new qh state:  defer qh unlink if IAA is busy
	  (eliminates a busy-wait loop in a rare scenario)

      Enable features to improve bus utilization
	- PCI MWI ... can produce better write throughput; and by
	  using right cacheline size, sometimes read throughput too
	- USB NAK throttle ... sometimes reduces PCI access rates

      Other
	- async dump shows more funky qh+qtd states, and NAK count
	- cope with with some of the sprintf wierdness
	- periodic dump is usually smaller (so is that schedule)
      	- minor cleanups

drivers/usb/host/ehci-dbg.c

@@ -277,7 +277,26 @@ static inline void remove_debug_files (struct ehci_hcd *bus) { }
 		default: tmp = '?'; break; \
 		}; tmp; })
 
-static void qh_lines (struct ehci_qh *qh, char **nextp, unsigned *sizep)
+static inline char token_mark (u32 token)
+{
+	token = le32_to_cpu (token);
+	if (token & QTD_STS_ACTIVE)
+		return '*';
+	if (token & QTD_STS_HALT)
+		return '-';
+	if (QTD_PID (token) != 1 /* not IN: OUT or SETUP */
+			|| QTD_LENGTH (token) == 0)
+		return ' ';
+	/* tries to advance through hw_alt_next */
+	return '/';
+}
+
+static void qh_lines (
+	struct ehci_hcd *ehci,
+	struct ehci_qh *qh,
+	char **nextp,
+	unsigned *sizep
+)
 {
 	u32			scratch;
 	u32			hw_curr;
@@ -286,26 +305,49 @@ static void qh_lines (struct ehci_qh *qh, char **nextp, unsigned *sizep)
 	unsigned		temp;
 	unsigned		size = *sizep;
 	char			*next = *nextp;
-
+	char			mark;
+
+	mark = token_mark (qh->hw_token);
+	if (mark == '/') {	/* qh_alt_next controls qh advance? */
+		if ((qh->hw_alt_next & QTD_MASK) == ehci->async->hw_alt_next)
+			mark = '#';	/* blocked */
+		else if (qh->hw_alt_next & cpu_to_le32 (0x01))
+			mark = '.';	/* use hw_qtd_next */
+		/* else alt_next points to some other qtd */
+	}
 	scratch = cpu_to_le32p (&qh->hw_info1);
-	hw_curr = cpu_to_le32p (&qh->hw_current);
+	hw_curr = (mark == '*') ? cpu_to_le32p (&qh->hw_current) : 0;
 	temp = snprintf (next, size,
-			"qh/%p dev%d %cs ep%d %08x %08x (%08x %08x)",
+			"qh/%p dev%d %cs ep%d %08x %08x (%08x%c %s nak%d)",
 			qh, scratch & 0x007f,
 			speed_char (scratch),
 			(scratch >> 8) & 0x000f,
 			scratch, cpu_to_le32p (&qh->hw_info2),
-			hw_curr, cpu_to_le32p (&qh->hw_token));
+			cpu_to_le32p (&qh->hw_token), mark,
+			(cpu_to_le32 (0x8000000) & qh->hw_token)
+				? "data0" : "data1",
+			(cpu_to_le32p (&qh->hw_alt_next) >> 1) & 0x0f);
 	size -= temp;
 	next += temp;
 
+	/* hc may be modifying the list as we read it ... */
 	list_for_each (entry, &qh->qtd_list) {
 		td = list_entry (entry, struct ehci_qtd, qtd_list);
 		scratch = cpu_to_le32p (&td->hw_token);
+		mark = ' ';
+		if (hw_curr == td->qtd_dma)
+			mark = '*';
+		else if (qh->hw_qtd_next == td->qtd_dma)
+			mark = '+';
+		else if (QTD_LENGTH (scratch)) {
+			if (td->hw_alt_next == ehci->async->hw_alt_next)
+				mark = '#';
+			else if (td->hw_alt_next != EHCI_LIST_END)
+				mark = '/';
+		}
 		temp = snprintf (next, size,
-				"\n\t%std/%p %s len=%d %08x urb %p",
-				(hw_curr == td->qtd_dma) ? "*" : "",
-				td, ({ char *tmp;
+				"\n\t%p%c%s len=%d %08x urb %p",
+				td, mark, ({ char *tmp;
 				 switch ((scratch>>8)&0x03) {
 				 case 0: tmp = "out"; break;
 				 case 1: tmp = "in"; break;
@@ -315,13 +357,27 @@ static void qh_lines (struct ehci_qh *qh, char **nextp, unsigned *sizep)
 				(scratch >> 16) & 0x7fff,
 				scratch,
 				td->urb);
+		if (temp < 0)
+			temp = 0;
+		else if (size < temp)
+			temp = size;
 		size -= temp;
 		next += temp;
+		if (temp == size)
+			goto done;
 	}
 
 	temp = snprintf (next, size, "\n");
-	*sizep = size - temp;
-	*nextp = next + temp;
+	if (temp < 0)
+		temp = 0;
+	else if (size < temp)
+		temp = size;
+	size -= temp;
+	next += temp;
+
+done:
+	*sizep = size;
+	*nextp = next;
 }
 
 static ssize_t
@@ -344,14 +400,15 @@ show_async (struct device *dev, char *buf)
 	 * one QH per line, and TDs we know about
 	 */
 	spin_lock_irqsave (&ehci->lock, flags);
-	for (qh = ehci->async->qh_next.qh; qh; qh = qh->qh_next.qh)
-		qh_lines (qh, &next, &size);
-	if (ehci->reclaim) {
+	for (qh = ehci->async->qh_next.qh; size > 0 && qh; qh = qh->qh_next.qh)
+		qh_lines (ehci, qh, &next, &size);
+	if (ehci->reclaim && size > 0) {
 		temp = snprintf (next, size, "\nreclaim =\n");
 		size -= temp;
 		next += temp;
 
-		qh_lines (ehci->reclaim, &next, &size);
+		for (qh = ehci->reclaim; size > 0 && qh; qh = qh->reclaim)
+			qh_lines (ehci, qh, &next, &size);
 	}
 	spin_unlock_irqrestore (&ehci->lock, flags);
 
@@ -421,7 +478,7 @@ show_periodic (struct device *dev, char *buf)
 						scratch & 0x007f,
 						(scratch >> 8) & 0x000f,
 						p.qh->usecs, p.qh->c_usecs,
-						scratch >> 16);
+						0x7ff & (scratch >> 16));
 
 					/* FIXME TD info too */
 
@@ -490,7 +547,8 @@ show_registers (struct device *dev, char *buf)
 
 	/* Capability Registers */
 	i = readw (&ehci->caps->hci_version);
-	temp = snprintf (next, size, "EHCI %x.%02x, hcd state %d\n",
+	temp = snprintf (next, size,
+		"EHCI %x.%02x, hcd state %d (version " DRIVER_VERSION ")\n",
 		i >> 8, i & 0x0ff, ehci->hcd.state);
 	size -= temp;
 	next += temp;

drivers/usb/host/ehci-hcd.c

@@ -94,7 +94,7 @@
  * 2001-June	Works with usb-storage and NEC EHCI on 2.4
  */
 
-#define DRIVER_VERSION "2002-Nov-29"
+#define DRIVER_VERSION "2003-Jan-22"
 #define DRIVER_AUTHOR "David Brownell"
 #define DRIVER_DESC "USB 2.0 'Enhanced' Host Controller (EHCI) Driver"
 
@@ -110,10 +110,11 @@ static const char	hcd_name [] = "ehci-hcd";
 
 /* magic numbers that can affect system performance */
 #define	EHCI_TUNE_CERR		3	/* 0-3 qtd retries; 0 == don't stop */
-#define	EHCI_TUNE_RL_HS		0	/* nak throttle; see 4.9 */
+#define	EHCI_TUNE_RL_HS		4	/* nak throttle; see 4.9 */
 #define	EHCI_TUNE_RL_TT		0
 #define	EHCI_TUNE_MULT_HS	1	/* 1-3 transactions/uframe; 4.10.3 */
 #define	EHCI_TUNE_MULT_TT	1
+#define	EHCI_TUNE_FLS		2	/* (small) 256 frame schedule */
 
 #define EHCI_WATCHDOG_JIFFIES	(HZ/100)	/* arbitrary; ~10 msec */
 #define EHCI_ASYNC_JIFFIES	(HZ/20)		/* async idle timeout */
@@ -416,13 +417,26 @@ static int ehci_start (struct usb_hcd *hcd)
 			ehci_info (ehci, "enabled 64bit PCI DMA\n");
 	}
 
+	/* help hc dma work well with cachelines */
+	pci_set_mwi (ehci->hcd.pdev);
+
 	/* clear interrupt enables, set irq latency */
 	temp = readl (&ehci->regs->command) & 0xff;
 	if (log2_irq_thresh < 0 || log2_irq_thresh > 6)
 		log2_irq_thresh = 0;
 	temp |= 1 << (16 + log2_irq_thresh);
 	// if hc can park (ehci >= 0.96), default is 3 packets per async QH 
-	// keeping default periodic framelist size
+	if (HCC_PGM_FRAMELISTLEN (hcc_params)) {
+		/* periodic schedule size can be smaller than default */
+		temp &= ~(3 << 2);
+		temp |= (EHCI_TUNE_FLS << 2);
+		switch (EHCI_TUNE_FLS) {
+		case 0: ehci->periodic_size = 1024; break;
+		case 1: ehci->periodic_size = 512; break;
+		case 2: ehci->periodic_size = 256; break;
+		default:	BUG ();
+		}
+	}
 	temp &= ~(CMD_IAAD | CMD_ASE | CMD_PSE),
 	// Philips, Intel, and maybe others need CMD_RUN before the
 	// root hub will detect new devices (why?); NEC doesn't
@@ -759,7 +773,6 @@ static int ehci_urb_dequeue (struct usb_hcd *hcd, struct urb *urb)
 	struct ehci_hcd		*ehci = hcd_to_ehci (hcd);
 	struct ehci_qh		*qh;
 	unsigned long		flags;
-	int			maybe_irq = 1;
 
 	spin_lock_irqsave (&ehci->lock, flags);
 	switch (usb_pipetype (urb->pipe)) {
@@ -769,23 +782,23 @@ static int ehci_urb_dequeue (struct usb_hcd *hcd, struct urb *urb)
 		qh = (struct ehci_qh *) urb->hcpriv;
 		if (!qh)
 			break;
-		while (qh->qh_state == QH_STATE_LINKED
+
+		/* if we need to use IAA and it's busy, defer */
+		if (qh->qh_state == QH_STATE_LINKED
 				&& ehci->reclaim
 				&& HCD_IS_RUNNING (ehci->hcd.state)
 				) {
-			spin_unlock_irqrestore (&ehci->lock, flags);
+			struct ehci_qh		*last;
 
-			if (maybe_irq) {
-				if (in_interrupt ())
-					return -EAGAIN;
-				maybe_irq = 0;
-			}
-			/* let pending unlinks complete, so this can start */
-			wait_ms (1);
+			for (last = ehci->reclaim;
+					last->reclaim;
+					last = last->reclaim)
+				continue;
+			qh->qh_state = QH_STATE_UNLINK_WAIT;
+			last->reclaim = qh;
 
-			spin_lock_irqsave (&ehci->lock, flags);
-		}
-		if (!HCD_IS_RUNNING (ehci->hcd.state) && ehci->reclaim)
+		/* bypass IAA if the hc can't care */
+		} else if (!HCD_IS_RUNNING (ehci->hcd.state) && ehci->reclaim)
 			end_unlink_async (ehci, NULL);
 
 		/* something else might have unlinked the qh by now */

drivers/usb/host/ehci-mem.c

@@ -75,8 +75,6 @@ static struct ehci_qtd *ehci_qtd_alloc (struct ehci_hcd *ehci, int flags)
 	qtd = pci_pool_alloc (ehci->qtd_pool, flags, &dma);
 	if (qtd != 0) {
 		ehci_qtd_init (qtd, dma);
-		if (ehci->async)
-			qtd->hw_alt_next = ehci->async->hw_alt_next;
 	}
 	return qtd;
 }

drivers/usb/host/ehci.h

@@ -236,12 +236,12 @@ struct ehci_qtd {
 	/* the rest is HCD-private */
 	dma_addr_t		qtd_dma;		/* qtd address */
 	struct list_head	qtd_list;		/* sw qtd list */
-
-	/* dma same in urb's qtds, except 1st control qtd (setup buffer) */
 	struct urb		*urb;			/* qtd's urb */
 	size_t			length;			/* length of buffer */
 } __attribute__ ((aligned (32)));
 
+#define QTD_MASK cpu_to_le32 (~0x1f)	/* mask NakCnt+T in qh->hw_alt_next */
+
 /*-------------------------------------------------------------------------*/
 
 /* type tag from {qh,itd,sitd,fstn}->hw_next */
@@ -305,6 +305,7 @@ struct ehci_qh {
 	union ehci_shadow	qh_next;	/* ptr to qh; or periodic */
 	struct list_head	qtd_list;	/* sw qtd list */
 	struct ehci_qtd		*dummy;
+	struct ehci_qh		*reclaim;	/* next to reclaim */
 
 	atomic_t		refcount;
 	unsigned		stamp;
@@ -313,6 +314,8 @@ struct ehci_qh {
 #define	QH_STATE_LINKED		1		/* HC sees this */
 #define	QH_STATE_UNLINK		2		/* HC may still see this */
 #define	QH_STATE_IDLE		3		/* HC doesn't see this */
+#define	QH_STATE_UNLINK_WAIT	4		/* LINKED and on reclaim q */
+#define	QH_STATE_COMPLETING	5		/* don't touch token.HALT */
 
 	/* periodic schedule info */
 	u8			usecs;		/* intr bandwidth */