UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

staging: dwc2: always release host channel after dequeueing 

Previously, when an active urb was dequeued, its host channel would
not always be released. There is some special handling for this in
dwc2_hc_chhltd_intr_dma, but when it was the last urb/qtd in its qh, a
safeguard in dwc2_hc_n_intr would short-circuit and prevent the regular
interrupt handlers from running, without releasing the channel.

This is easily triggered when using a 3G modem using the option driver.
Opening and closing any ttyUSBx device will eat up a host channel that
is forever unusable from that point on.

Signed-off-by: Matthijs Kooijman <matthijs@stdin.nl>
[paulz@synopsys.com: fixed comment style and added a couple of NULL checks]
Signed-off-by: Paul Zimmerman <paulz@synopsys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Matthijs Kooijman 2013-03-25 12:00:25 -07:00 committed by Greg Kroah-Hartman
parent 257f658015
commit 8509f2f43a
1 changed files with 29 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
drivers/staging/dwc2/hcd_intr.c
View File

@ -708,7 +708,7 @@ static void dwc2_release_channel(struct dwc2_hsotg *hsotg,
free_qtd = 1;
break;
case DWC2_HC_XFER_XACT_ERR:
if (qtd->error_count >= 3) {
if (qtd && qtd->error_count >= 3) {
dev_vdbg(hsotg->dev,
" Complete URB with transaction error\n");
free_qtd = 1;
@ -729,7 +729,7 @@ static void dwc2_release_channel(struct dwc2_hsotg *hsotg,
case DWC2_HC_XFER_PERIODIC_INCOMPLETE:
dev_vdbg(hsotg->dev, " Complete URB with I/O error\n");
free_qtd = 1;
if (qtd->urb) {
if (qtd && qtd->urb) {
qtd->urb->status = -EIO;
dwc2_host_complete(hsotg, qtd->urb->priv, qtd->urb,
-EIO);
@ -1708,8 +1708,9 @@ static bool dwc2_halt_status_ok(struct dwc2_hsotg *hsotg,
dev_dbg(hsotg->dev,
"hcint 0x%08x, hcintmsk 0x%08x, hcsplt 0x%08x,\n",
chan->hcint, hcintmsk, hcsplt);
dev_dbg(hsotg->dev, "qtd->complete_split %d\n",
qtd->complete_split);
if (qtd)
dev_dbg(hsotg->dev, "qtd->complete_split %d\n",
qtd->complete_split);
dev_warn(hsotg->dev,
"%s: no halt status, channel %d, ignoring interrupt\n",
__func__, chnum);
@ -1937,7 +1938,31 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
chan->hcint = hcint;
hcint &= hcintmsk;
/*
* If the channel was halted due to a dequeue, the qtd list might
* be empty or at least the first entry will not be the active qtd.
* In this case, take a shortcut and just release the channel.
*/
if (chan->halt_status == DWC2_HC_XFER_URB_DEQUEUE) {
/*
* If the channel was halted, this should be the only
* interrupt unmasked
*/
WARN_ON(hcint != HCINTMSK_CHHLTD);
if (hsotg->core_params->dma_desc_enable > 0)
dwc2_hcd_complete_xfer_ddma(hsotg, chan, chnum,
chan->halt_status);
else
dwc2_release_channel(hsotg, chan, NULL,
chan->halt_status);
return;
}
if (list_empty(&chan->qh->qtd_list)) {
/*
* TODO: Will this ever happen with the
* DWC2_HC_XFER_URB_DEQUEUE handling above?
*/
dev_dbg(hsotg->dev, "## no QTD queued for channel %d ##\n",
chnum);
dev_dbg(hsotg->dev,