summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorRobert Schedel <r.schedel@yahoo.de>2009-06-23 11:26:48 +0200
committerJiri Kosina <jkosina@suse.cz>2009-07-23 01:27:59 +0200
commit0810b51170570ed21cae56b8131db6a5e3efa584 (patch)
treeaca5fd5ad71897582c01527ddf57db0aa498d4e1 /arch
parent3c3301083e3bea4d14c597106c7b20b4b85fc03d (diff)
HID: Support new variants of Samsung USB IR receiver (0419:0001)
This patch extends the existing Samsung IrDA (0419:0001) quirk file with newly reported variants: * New device variants with 203 byte and 135 byte report descriptors were reported to be recognized incorrectly. This patch adds an autodetection for those two, using report descriptor size to enable new quirks. * Any other unknown 0419:0001 variants will now be treated without any quirk flags (i.e. IGNORE_HIDINPUT/HIDDEV_FORCE will not be set by default anymore). More details: 1. Descriptor size 184 bytes ("Satelco bundled remote") Already supported since kernel 2.6.25 (my old patch). 2. Descriptor size 203 bytes ("Optronix remote") This receiver mostly works with the regular HID input driver. Only when some keys are released, another spurious key press event is interpreted due to incorrect array ranges. According to HID 1.11, section 6.2.2.5, arrays should return a 0 value when no control is asserted, and ranges should go from 1 to the number of elements. The patch clips the value with a logical range from 1..15 (instead of originally 0..18). Ticket with more information available at https://bugs.launchpad.net/bugs/326986 3. Descriptor size 135 bytes ("Gotview remote") This receiver has a similar issue than the previous one, i.e. it mostly works with regular HID input, except some key press events get stuck on key release. The patch clips the array value from 1..14 (instead of originally 0..17). Ticket with more information available at http://bugs.archlinux.org/task/15216 4. Other unknown variants (found one report with 218 bytes, but no further information about issues) For such unknown variants we should refrain from changing any device flags. Currently, HIDINPUT is suppressed and HIDDEV is enforced (because in 2.6.25 the quirk table did not yet allow differentiating variants and we did not expect variants either). Now we should be as strict as possible and enable it only for the first variant above. Signed-off-by: Robert Schedel <r.schedel@yahoo.de> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Diffstat (limited to 'arch')
0 files changed, 0 insertions, 0 deletions