[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180308095739.okdn7ghvlpy4oiy5@linutronix.de>
Date: Thu, 8 Mar 2018 10:57:39 +0100
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To: Mauro Carvalho Chehab <mchehab@...pensource.com>
Cc: Frederic Weisbecker <frederic@...nel.org>,
LKML <linux-kernel@...r.kernel.org>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Alan Stern <stern@...land.harvard.edu>,
linux-usb@...r.kernel.org
Subject: Re: [RFC PATCH] usb: hcd: complete URBs in threaded-IRQ context
instead of tasklet
On 2018-02-27 14:39:34 [-0300], Mauro Carvalho Chehab wrote:
> Hi Sebastian,
Hi Mauro,
> Sorry for taking some time to test it, has been busy those days...
:)
> Anyway, I tested it today. Didn't work. It keep losing data.
Okay, this was unexpected. What I learned from the thread is that you
use the dwc2 controller and once upgrade to a kernel which completes the
URBs in BH context then you starting losing data from your DVB-s USB
device. And it was assumed that this is because BH/ksoftirq is getting
"paused" if it is running for too long. If that is the case then a
revert of "let us complete the URB in BH context" should get it working
again. Is that so?
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -4287,7 +4287,9 @@ void dwc2_host_complete(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd,
kfree(qtd->urb);
qtd->urb = NULL;
+ spin_unlock(&hsotg->lock);
usb_hcd_giveback_urb(dwc2_hsotg_to_hcd(hsotg), urb, status);
+ spin_lock(&hsotg->lock);
}
/*
@@ -4968,7 +4970,7 @@ static struct hc_driver dwc2_hc_driver = {
.hcd_priv_size = sizeof(struct wrapper_priv_data),
.irq = _dwc2_hcd_irq,
- .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
+ .flags = HCD_MEMORY | HCD_USB2,
.start = _dwc2_hcd_start,
.stop = _dwc2_hcd_stop,
--
2.16.2
> Regards,
Sebastian
Powered by blists - more mailing lists