From fa38dfcc56b5f6cce787f9aaa5d1830509213802 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 20 May 2008 16:59:33 -0400 Subject: [PATCH] USB: EHCI: fix performance regression This patch (as1099) fixes a performance regression in ehci-hcd. The fundamental problem is that queue headers get removed from the schedule too quickly, since the code checks for a counter advancing rather than making an actual time-based check. The latency involved in removing the queue header and then relinking it can severely degrade certain kinds of workloads. The patch replaces a simple counter with a timestamp derived from the controller's uframe value. In addition, the delay for unlinking an idle queue header is increased from 5 ms to 10 ms; since some controllers (nVidia) have a latency of up to 1 ms for unlinking, this reduces the relative impact from 20% to 10%. Finally, a logical error left over from the IAA watchdog-timer conversion is corrected. Now the driver will always either unlink an idle queue header or set up a timer to unlink it later. The old code would sometimes fail to do either. Signed-off-by: Alan Stern Cc: David Brownell Cc: Leonid Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-hcd.c | 3 ++- drivers/usb/host/ehci-q.c | 15 ++++++++------- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 369a8a5ea7bb..3e3c5d3ea0ad 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -84,7 +84,8 @@ static const char hcd_name [] = "ehci_hcd"; #define EHCI_IAA_MSECS 10 /* arbitrary */ #define EHCI_IO_JIFFIES (HZ/10) /* io watchdog > irq_thresh */ #define EHCI_ASYNC_JIFFIES (HZ/20) /* async idle timeout */ -#define EHCI_SHRINK_JIFFIES (HZ/200) /* async qh unlink delay */ +#define EHCI_SHRINK_JIFFIES (HZ/100) /* async qh unlink delay */ +#define EHCI_SHRINK_UFRAMES (10*8) /* same value in uframes */ /* Initial IRQ latency: faster than hw default */ static int log2_irq_thresh = 0; // 0 to 6 diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index b85b54160cda..5200481deb27 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -1116,8 +1116,7 @@ static void scan_async (struct ehci_hcd *ehci) struct ehci_qh *qh; enum ehci_timer_action action = TIMER_IO_WATCHDOG; - if (!++(ehci->stamp)) - ehci->stamp++; + ehci->stamp = ehci_readl(ehci, &ehci->regs->frame_index); timer_action_done (ehci, TIMER_ASYNC_SHRINK); rescan: qh = ehci->async->qh_next.qh; @@ -1148,12 +1147,14 @@ rescan: * doesn't stay idle for long. * (plus, avoids some kind of re-activation race.) */ - if (list_empty (&qh->qtd_list)) { - if (qh->stamp == ehci->stamp) + if (list_empty(&qh->qtd_list) && + qh->qh_state == QH_STATE_LINKED) { + if (!ehci->reclaim && + ((ehci->stamp - qh->stamp) & 8191) >= + EHCI_SHRINK_UFRAMES) + start_unlink_async(ehci, qh); + else action = TIMER_ASYNC_SHRINK; - else if (!ehci->reclaim - && qh->qh_state == QH_STATE_LINKED) - start_unlink_async (ehci, qh); } qh = qh->qh_next.qh; -- 2.20.1