HID: fixup quirk for NCR devices

NCR devices are terminally broken by design -- they claim themselves to contain
proper input applications in their HID report descriptor, but behave very badly
if treated in standard way.

According to NCR developers, the devices get confused when queried for reports
in a standard way, rendering them unusable.

NCR is shipping application called "RPSL" that can be used to drive these
devices through hiddev, under the assumption that in-kernel driver doesn't
perform initial report query.
If it does, neither in-kernel nor hiddev-based driver can operate with these
devices any more.

Introduce a quirk that skips the report query for all NCR devices. The previous
NOGET quirk was wrong and had been introduced because I misunderstood the nature
of brokenness of these devices.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This commit is contained in:
Jiri Kosina 2009-11-05 14:08:03 +01:00
parent 73cdcf567a
commit 5b915d9e6d
3 changed files with 4 additions and 2 deletions

View file

@ -996,7 +996,8 @@ static int usbhid_start(struct hid_device *hid)
usbhid->urbctrl->transfer_dma = usbhid->ctrlbuf_dma;
usbhid->urbctrl->transfer_flags |= (URB_NO_TRANSFER_DMA_MAP | URB_NO_SETUP_DMA_MAP);
usbhid_init_reports(hid);
if (!(hid->quirks & HID_QUIRK_NO_INIT_REPORTS))
usbhid_init_reports(hid);
set_bit(HID_STARTED, &usbhid->iofl);

View file

@ -281,7 +281,7 @@ u32 usbhid_lookup_quirk(const u16 idVendor, const u16 idProduct)
if (idVendor == USB_VENDOR_ID_NCR &&
idProduct >= USB_DEVICE_ID_NCR_FIRST &&
idProduct <= USB_DEVICE_ID_NCR_LAST)
return HID_QUIRK_NOGET;
return HID_QUIRK_NO_INIT_REPORTS;
down_read(&dquirks_rwsem);
bl_entry = usbhid_exists_dquirk(idVendor, idProduct);

View file

@ -312,6 +312,7 @@ struct hid_item {
#define HID_QUIRK_MULTI_INPUT 0x00000040
#define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000
#define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000
#define HID_QUIRK_NO_INIT_REPORTS 0x20000000
/*
* This is the global environment of the parser. This information is